This rewrites pretty much from scratch the handling of MMIO and PIO
space allocations on powerpc64. The main goals are:
- Get rid of imalloc and use more common code where possible
- Simplify the current mess so that PIO space is allocated and
mapped in a single place for PCI bridges
- Handle allocation constraints of PIO for all bridges including
hot plugged ones within the 2GB space reserved for IO ports,
so that devices on hotplugged busses will now work with drivers
that assume IO ports fit in an int.
- Cleanup and separate tracking of the ISA space in the reserved
low 64K of IO space. No ISA -> Nothing mapped there.
I booted a cell blade with IDE on PIO and MMIO and a dual G5 so
far, that's it :-)
With this patch, all allocations are done using the code in
mm/vmalloc.c, though we use the low level __get_vm_area with
explicit start/stop constraints in order to manage separate
areas for vmalloc/vmap, ioremap, and PCI IOs.
This greatly simplifies a lot of things, as you can see in the
diffstat of that patch :-)
A new pair of functions pcibios_map/unmap_io_space() now replace
all of the previous code that used to manipulate PCI IOs space.
The allocation is done at mapping time, which is now called from
scan_phb's, just before the devices are probed (instead of after,
which is by itself a bug fix). The only other caller is the PCI
hotplug code for hot adding PCI-PCI bridges (slots).
imalloc is gone, as is the "sub-allocation" thing, but I do beleive
that hotplug should still work in the sense that the space allocation
is always done by the PHB, but if you unmap a child bus of this PHB
(which seems to be possible), then the code should properly tear
down all the HPTE mappings for that area of the PHB allocated IO space.
I now always reserve the first 64K of IO space for the bridge with
the ISA bus on it. I have moved the code for tracking ISA in a separate
file which should also make it smarter if we ever are capable of
hot unplugging or re-plugging an ISA bridge.
This should have a side effect on platforms like powermac where VGA IOs
will no longer work. This is done on purpose though as they would have
worked semi-randomly before. The idea at this point is to isolate drivers
that might need to access those and fix them by providing a proper
function to obtain an offset to the legacy IOs of a given bus.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This makes unmap_vm_area static and a wrapper around a new
exported unmap_kernel_range that takes an explicit range instead
of a vm_area struct.
This makes it more versatile for code that wants to play with kernel
page tables outside of the standard vmalloc area.
(One example is some rework of the PowerPC PCI IO space mapping
code that depends on that patch and removes some code duplication
and horrible abuse of forged struct vm_struct).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Mark pte_alloc_one_kernel as __init_refok to fix the following warning:
WARNING: arch/powerpc/mm/built-in.o(.text+0x1068): Section mismatch: reference to .init.text:early_get_page (between 'pte_alloc_one_kernel' and 'steal_context')
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Some missing fixup for the removal of 4 level fixup header.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix up comment on two #endifs to match their #ifs.
Signed-off-by: Jon Tollefson <kniht@linux.vnet.ibm.com>
----
hash_utils_64.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
Signed-off-by: Paul Mackerras <paulus@samba.org>
request_phb_iospace() can be called from different CPUs at init
time (at least with my next patch) and thus needs a spinlock.
As for the next patch, this is a temporary workaround for 2.6.22
issues until my rewrite of IO mappings is ready (for 2.6.23)
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
We get the following warnings in various ARCH=powerpc builds:
WARNING: "ee_restarts" [arch/powerpc/kernel/built-in] is COMMON symbol
WARNING: "fee_restarts" [arch/powerpc/kernel/built-in] is COMMON symbol
WARNING: "htab_hash_searches" [arch/powerpc/mm/built-in] is COMMON symbol
WARNING: "next_slot" [arch/powerpc/mm/built-in] is COMMON symbol
WARNING: "mmu_hash_lock" [arch/powerpc/mm/built-in] is COMMON symbol
WARNING: "primary_pteg_full" [arch/powerpc/mm/built-in] is COMMON symbol
WARNING: "global_dbcr0" [arch/powerpc/kernel/built-in] is COMMON symbol
Switch to moving local symbols (except mmu_hash_lock which is global) and
space directive instead.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
This case will never be hit, but it should be corrected anyway.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds the necessary support to hpte_decode() to handle 1TB
segments and 16GB pages, and removes an uninitialized value
warning on avpn.
We don't have any code to generate HPTEs for 1TB segments or 16GB
pages yet, so this is mostly for completeness, and to fix the
warning.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc:
[POWERPC] Further fixes for the removal of 4level-fixup hack from ppc32
[POWERPC] EEH: log all PCI-X and PCI-E AER registers
[POWERPC] EEH: capture and log pci state on error
[POWERPC] EEH: Split up long error msg
[POWERPC] EEH: log error only after driver notification.
[POWERPC] fsl_soc: Make mac_addr const in fs_enet_of_init().
[POWERPC] Don't use SLAB/SLUB for PTE pages
[POWERPC] Spufs support for 64K LS mappings on 4K kernels
[POWERPC] Add ability to 4K kernel to hash in 64K pages
[POWERPC] Introduce address space "slices"
[POWERPC] Small fixes & cleanups in segment page size demotion
[POWERPC] iSeries: Make HVC_ISERIES the default
[POWERPC] iSeries: suppress build warning in lparmap.c
[POWERPC] Mark pages that don't exist as nosave
[POWERPC] swsusp: Introduce register_nosave_region_late
Since nonboot CPUs are now disabled after tasks and devices have been
frozen and the CPU hotplug infrastructure is used for this purpose, we need
special CPU hotplug notifications that will help the CPU-hotplug-aware
subsystems distinguish normal CPU hotplug events from CPU hotplug events
related to a system-wide suspend or resume operation in progress. This
patch introduces such notifications and causes them to be used during
suspend and resume transitions. It also changes all of the
CPU-hotplug-aware subsystems to take these notifications into consideration
(for now they are handled in the same way as the corresponding "normal"
ones).
[oleg@tv-sign.ru: cleanups]
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Gautham R Shenoy <ego@in.ibm.com>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit d1953c8888 removed the use of
4level-fixup.h for 32-bit systems under arch/powerpc. However, I
missed a few things activated on some configurations, resulting in
some warnings (at least with STRICT_MM_TYPECHECKS enabled) and build
errors in some circumstances. This fixes it.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The SLUB allocator relies on struct page fields first_page and slab,
overwritten by ptl when SPLIT_PTLOCK: so the SLUB allocator cannot then
be used for the lowest level of pagetable pages. This was obstructing
SLUB on PowerPC, which uses kmem_caches for its pagetables. So convert
its pte level to use normal gfp pages (whereas pmd, pud and 64k-page pgd
want partpages, so continue to use kmem_caches for pmd, pud and pgd).
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds the ability for a kernel compiled with 4K page size
to have special slices containing 64K pages and hash the right type
of hash PTEs.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The basic issue is to be able to do what hugetlbfs does but with
different page sizes for some other special filesystems; more
specifically, my need is:
- Huge pages
- SPE local store mappings using 64K pages on a 4K base page size
kernel on Cell
- Some special 4K segments in 64K-page kernels for mapping a dodgy
type of powerpc-specific infiniband hardware that requires 4K MMU
mappings for various reasons I won't explain here.
The main issues are:
- To maintain/keep track of the page size per "segment" (as we can
only have one page size per segment on powerpc, which are 256MB
divisions of the address space).
- To make sure special mappings stay within their allotted
"segments" (including MAP_FIXED crap)
- To make sure everybody else doesn't mmap/brk/grow_stack into a
"segment" that is used for a special mapping
Some of the necessary mechanisms to handle that were present in the
hugetlbfs code, but mostly in ways not suitable for anything else.
The patch relies on some changes to the generic get_unmapped_area()
that just got merged. It still hijacks hugetlb callbacks here or
there as the generic code hasn't been entirely cleaned up yet but
that shouldn't be a problem.
So what is a slice ? Well, I re-used the mechanism used formerly by our
hugetlbfs implementation which divides the address space in
"meta-segments" which I called "slices". The division is done using
256MB slices below 4G, and 1T slices above. Thus the address space is
divided currently into 16 "low" slices and 16 "high" slices. (Special
case: high slice 0 is the area between 4G and 1T).
Doing so simplifies significantly the tracking of segments and avoids
having to keep track of all the 256MB segments in the address space.
While I used the "concepts" of hugetlbfs, I mostly re-implemented
everything in a more generic way and "ported" hugetlbfs to it.
Slices can have an associated page size, which is encoded in the mmu
context and used by the SLB miss handler to set the segment sizes. The
hash code currently doesn't care, it has a specific check for hugepages,
though I might add a mechanism to provide per-slice hash mapping
functions in the future.
The slice code provide a pair of "generic" get_unmapped_area() (bottomup
and topdown) functions that should work with any slice size. There is
some trickiness here so I would appreciate people to have a look at the
implementation of these and let me know if I got something wrong.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The code for demoting segments to 4K had some issues, like for example,
when using _PAGE_4K_PFN flag, the first CPU to hit it would do the
demotion, but other CPUs hitting the same page wouldn't properly flush
their SLBs if mmu_ci_restriction isn't set. There are also potential
issues with hash_preload not handling _PAGE_4K_PFN. All of these are
non issues on current hardware but might bite us in the future.
This patch thus fixes it by:
- Taking the test comparing the mm and current CPU context page
sizes to decide to flush SLBs out of the mmu_ci_restrictions test
since that can also be triggered by _PAGE_4K_PFN pages
- Due to the above being done all the time, demote_segment_4k
doesn't need update the context and flush the SLB
- demote_segment_4k can be static and doesn't need an EXPORT_SYMBOL
- Making hash_preload ignore anything that has either _PAGE_4K_PFN
or _PAGE_NO_CACHE set, thus avoiding duplication of the complicated
logic in hash_page() (and possibly making hash_preload a little bit
faster for the normal case).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
On some powerpc architectures (notably 64-bit powermac) there is a memory
hole, for example on powermacs between 2G and 4G. Since we use the flat
memory model regardless, these pages must be marked as nosave (for suspend
to disk.)
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.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>
This patch moves the die notifier handling to common code. Previous
various architectures had exactly the same code for it. Note that the new
code is compiled unconditionally, this should be understood as an appel to
the other architecture maintainer to implement support for it aswell (aka
sprinkling a notify_die or two in the proper place)
arm had a notifiy_die that did something totally different, I renamed it to
arm_notify_die as part of the patch and made it static to the file it's
declared and used at. avr32 used to pass slightly less information through
this interface and I brought it into line with the other architectures.
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix vmalloc_sync_all bustage]
[bryan.wu@analog.com: fix vmalloc_sync_all in nommu]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: <linux-arch@vger.kernel.org>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Bryan Wu <bryan.wu@analog.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use SLAB_PANIC and delete duplicated panic().
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Ian Molton <spyro@f2s.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For 32-bit systems, powerpc still relies on the 4level-fixup.h hack,
to pretend that the generic pagetable handling stuff is 3-levels
rather than 4. This patch removes this, instead using the newer
pgtable-nopmd.h to handle the elision of both the pud and pmd
pagetable levels (ppc32 pagetables are actually 2 levels).
This removes a little extraneous code, and makes it more easily
compared to the 64-bit pagetable code.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
reserve_mem() and stabs_alloc() are both called only from other __init
routines, so can be marked __init.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The current get_unmapped_area code calls the f_ops->get_unmapped_area or the
arch one (via the mm) only when MAP_FIXED is not passed. That makes it
impossible for archs to impose proper constraints on regions of the virtual
address space. To work around that, get_unmapped_area() then calls some
hugetlbfs specific hacks.
This cause several problems, among others:
- It makes it impossible for a driver or filesystem to do the same thing
that hugetlbfs does (for example, to allow a driver to use larger page sizes
to map external hardware) if that requires applying a constraint on the
addresses (constraining that mapping in certain regions and other mappings
out of those regions).
- Some archs like arm, mips, sparc, sparc64, sh and sh64 already want
MAP_FIXED to be passed down in order to deal with aliasing issues. The code
is there to handle it... but is never called.
This series of patches moves the logic to handle MAP_FIXED down to the various
arch/driver get_unmapped_area() implementations, and then changes the generic
code to always call them. The hugetlbfs hacks then disappear from the generic
code.
Since I need to do some special 64K pages mappings for SPEs on cell, I need to
work around the first problem at least. I have further patches thus
implementing a "slices" layer that handles multiple page sizes through slices
of the address space for use by hugetlbfs, the SPE code, and possibly others,
but it requires that serie of patches first/
There is still a potential (but not practical) issue due to the fact that
filesystems/drivers implemeting g_u_a will effectively bypass all arch checks.
This is not an issue in practice as the only filesystems/drivers using that
hook are doing so for arch specific purposes in the first place.
There is also a problem with mremap that will completely bypass all arch
checks. I'll try to address that separately, I'm not 100% certain yet how,
possibly by making it not work when the vma has a file whose f_ops has a
get_unmapped_area callback, and by making it use is_hugepage_only_range()
before expanding into a new area.
Also, I want to turn is_hugepage_only_range() into a more generic
is_normal_page_range() as that's really what it will end up meaning when used
in stack grow, brk grow and mremap.
None of the above "issues" however are introduced by this patch, they are
already there, so I think the patch can go ini for 2.6.22.
This patch:
Handle MAP_FIXED in powerpc's arch_get_unmapped_area() in all 3
implementations of it.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: William Irwin <bill.irwin@oracle.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: Matthew Wilcox <willy@debian.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Adam Litke <agl@us.ibm.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It is not necessary to tell the slab allocators to align to a cacheline
if an explicit alignment was already specified. It is rather confusing
to specify multiple alignments.
Make sure that the call sites only use one form of alignment.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch was recently posted to lkml and acked by Pekka.
The flag SLAB_MUST_HWCACHE_ALIGN is
1. Never checked by SLAB at all.
2. A duplicate of SLAB_HWCACHE_ALIGN for SLUB
3. Fulfills the role of SLAB_HWCACHE_ALIGN for SLOB.
The only remaining use is in sparc64 and ppc64 and their use there
reflects some earlier role that the slab flag once may have had. If
its specified then SLAB_HWCACHE_ALIGN is also specified.
The flag is confusing, inconsistent and has no purpose.
Remove it.
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes a couple of kexec problems related to 64K page
support in the kernel. kexec issues a tlbie for each pte. The
parameters for the tlbie are the page size and the virtual address.
Support was missing for the computation of these two parameters
for 64K pages. This adds that support.
Signed-off-by: Luke Browning <lukebrowning@us.ibm.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Call the kprobes pagefault handler directly instead of going through
the complex notifier chain.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch takes the definitions for the PPC44x MMU (a software loaded
TLB) from asm-ppc/mmu.h, cleans them up of things no longer necessary
in arch/powerpc and puts them in a new asm-powerpc/mmu_44x.h file. It
also substantially simplifies arch/powerpc/mm/44x_mmu.c and makes a
couple of small fixes necessary for the 44x MMU code to build and work
properly in arch/powerpc.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
arch/powerpc/mm/mem.c exports page_is_ram, which is not used anywhere
that could be modular.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
32-bit powerpc systems define a macro, PHYS_FMT, giving a printf
format string fragment for displaying physical addresses, since most
32-bit powerpc platforms use 32-bit physical addresses but a few use
64-bit physical addresses.
This macro is used in exactly one place, a rare error message, where
we can solve the problem more simply by just unconditionally casting
the address up to 64-bit quantity before formatting it.
This patch does so, meaning that as we bring MMU definitions from
asm-ppc over to asm-powerpc, cleaning them up in the process, we don't
need to implement this ugly macro (which additionally has a very bad
name for something global).
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
BenH's commit a741e67969 in powerpc.git,
although (AFAICT) only intended to affect ppc64, also has side-effects
which break 44x. I think 40x, 8xx and Freescale Book E are also
affected, though I haven't tested them.
The problem lies in unconditionally removing flush_tlb_pending() from
the versions of flush_tlb_mm(), flush_tlb_range() and
flush_tlb_kernel_range() used on ppc64 - which are also used the
embedded platforms mentioned above.
The patch below cleans up the convoluted #ifdef logic in tlbflush.h,
in the process restoring the necessary flushes for the software TLB
platforms. There are three sets of definitions for the flushing
hooks: the software TLB versions (revised to avoid using names which
appear to related to TLB batching), the 32-bit hash based versions
(external functions) amd the 64-bit hash based versions (which
implement batching).
It also moves the declaration of update_mmu_cache() to always be in
tlbflush.h (previously it was in tlbflush.h except for PPC64, where it
was in pgtable.h).
Booted on Ebony (440GP) and compiled for 64-bit and 32-bit
multiplatform.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Here's an implementation of DEBUG_PAGEALLOC for 64 bits powerpc.
It applies on top of the 32 bits patch.
Unlike Anton's previous attempt, I'm not using updatepp. I'm removing
the hash entries from the bolted mapping (using a map in RAM of all the
slots). Expensive but it doesn't really matter, does it ? :-)
Memory hot-added doesn't benefit from this unless it's added at an
address that is below end_of_DRAM() as calculated at boot time.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
arch/powerpc/Kconfig.debug | 2
arch/powerpc/mm/hash_utils_64.c | 84 ++++++++++++++++++++++++++++++++++++++--
2 files changed, 82 insertions(+), 4 deletions(-)
Signed-off-by: Paul Mackerras <paulus@samba.org>
Here's an implementation of DEBUG_PAGEALLOC for ppc32. It disables BAT
mapping and is only tested with Hash table based processor though it
shouldn't be too hard to adapt it to others.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
arch/powerpc/Kconfig.debug | 9 ++++++
arch/powerpc/mm/init_32.c | 4 +++
arch/powerpc/mm/pgtable_32.c | 52 +++++++++++++++++++++++++++++++++++++++
arch/powerpc/mm/ppc_mmu_32.c | 4 ++-
include/asm-powerpc/cacheflush.h | 6 ++++
5 files changed, 74 insertions(+), 1 deletion(-)
Signed-off-by: Paul Mackerras <paulus@samba.org>
On hash table based 32 bits powerpc's, the hash management code runs with
a big spinlock. It's thus important that it never causes itself a hash
fault. That code is generally safe (it does memory accesses in real mode
among other things) with the exception of the actual access to the code
itself. That is, the kernel text needs to be accessible without taking
a hash miss exceptions.
This is currently guaranteed by having a BAT register mapping part of the
linear mapping permanently, which includes the kernel text. But this is
not true if using the "nobats" kernel command line option (which can be
useful for debugging) and will not be true when using DEBUG_PAGEALLOC
implemented in a subsequent patch.
This patch fixes this by pre-faulting in the hash table pages that hit
the kernel text, and making sure we never evict such a page under hash
pressure.
Signed-off-by: Benjamin Herrenchmidt <benh@kernel.crashing.org>
arch/powerpc/mm/hash_low_32.S | 22 ++++++++++++++++++++--
arch/powerpc/mm/mem.c | 3 ---
arch/powerpc/mm/mmu_decl.h | 4 ++++
arch/powerpc/mm/pgtable_32.c | 11 +++++++----
4 files changed, 31 insertions(+), 9 deletions(-)
Signed-off-by: Paul Mackerras <paulus@samba.org>
The 32 bits map_page() function is used internally by the mm code
for early mmu mappings and for ioremap. It should never be called
for an address that already has a valid PTE or hash entry, so we
add a BUG_ON for that and remove the useless flush_HPTE call.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
arch/powerpc/mm/pgtable_32.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
Signed-off-by: Paul Mackerras <paulus@samba.org>
The current tlb flush code on powerpc 64 bits has a subtle race since we
lost the page table lock due to the possible faulting in of new PTEs
after a previous one has been removed but before the corresponding hash
entry has been evicted, which can leads to all sort of fatal problems.
This patch reworks the batch code completely. It doesn't use the mmu_gather
stuff anymore. Instead, we use the lazy mmu hooks that were added by the
paravirt code. They have the nice property that the enter/leave lazy mmu
mode pair is always fully contained by the PTE lock for a given range
of PTEs. Thus we can guarantee that all batches are flushed on a given
CPU before it drops that lock.
We also generalize batching for any PTE update that require a flush.
Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and
disabled by arch_leave_lazy_mmu_mode(). The code epects that this is
always contained within a PTE lock section so no preemption can happen
and no PTE insertion in that range from another CPU. When batching
is enabled on a CPU, every PTE updates that need a hash flush will
use the batch for that flush.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Some drivers have resources that they want to be able to map into
userspace that are 4k in size. On a kernel configured with 64k pages
we currently end up mapping the 4k we want plus another 60k of
physical address space, which could contain anything. This can
introduce security problems, for example in the case of an infiniband
adaptor where the other 60k could contain registers that some other
program is using for its communications.
This patch adds a new function, remap_4k_pfn, which drivers can use to
map a single 4k page to userspace regardless of whether the kernel is
using a 4k or a 64k page size. Like remap_pfn_range, it would
typically be called in a driver's mmap function. It only maps a
single 4k page, which on a 64k page kernel appears replicated 16 times
throughout a 64k page. On a 4k page kernel it reduces to a call to
remap_pfn_range.
The way this works on a 64k kernel is that a new bit, _PAGE_4K_PFN,
gets set on the linux PTE. This alters the way that __hash_page_4K
computes the real address to put in the HPTE. The RPN field of the
linux PTE becomes the 4k RPN directly rather than being interpreted as
a 64k RPN. Since the RPN field is 32 bits, this means that physical
addresses being mapped with remap_4k_pfn have to be below 2^44,
i.e. 0x100000000000.
The patch also factors out the code in arch/powerpc/mm/hash_utils_64.c
that deals with demoting a process to use 4k pages into one function
that gets called in the various different places where we need to do
that. There were some discrepancies between exactly what was done in
the various places, such as a call to spu_flush_all_slbs in one case
but not in others.
Signed-off-by: Paul Mackerras <paulus@samba.org>
This is more consistent and gets us closer to the Sparc code.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This is more consistent and gets us closer to the Sparc code.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The SPU code doesn't properly invalidate SPUs SLBs when necessary,
for example when changing a segment size from the hugetlbfs code. In
addition, it saves and restores the SLB content on context switches
which makes it harder to properly handle those invalidations.
This patch removes the saving & restoring for now, something more
efficient might be found later on. It also adds a spu_flush_all_slbs(mm)
that can be used by the core mm code to flush the SLBs of all SPEs that
are running a given mm at the time of the flush.
In order to do that, it adds a spinlock to the list of all SPEs and move
some bits & pieces from spufs to spu_base.c
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
At present calling lmb_reserve() (and hence lmb_add_region()) twice
for exactly the same memory region will cause strange behaviour.
This makes life difficult when booting from a flat device tree with
memory reserve map. Which regions are automatically reserved by the
kernel has changed over time, so it's quite possible a newer kernel
could attempt to auto-reserve a region which is also explicitly listed
in the device tree's reserve map, leading to trouble.
This patch avoids the problem by making lmb_reserve() ignore a call to
reserve a previously reserved region. It also removes a now redundant
test designed to avoid one specific case of the problem noted above.
At present, this patch deals only with duplicate reservations of an
identical region. Attempting to reserve two different, but
overlapping regions will still cause problems. I might post another
patch later dealing with this case, but I'm avoiding it now since it
is substantially more complicated to deal with, less likely to occur
and more likely to indicate a genuine bug elsewhere if it does occur.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/bunk/trivial: (25 commits)
Documentation/kernel-docs.txt update.
arch/cris: typo in KERN_INFO
Storage class should be before const qualifier
kernel/printk.c: comment fix
update I/O sched Kconfig help texts - CFQ is now default, not AS.
Remove duplicate listing of Cris arch from README
kbuild: more doc. cleanups
doc: make doc. for maxcpus= more visible
drivers/net/eexpress.c: remove duplicate comment
add a help text for BLK_DEV_GENERIC
correct a dead URL in the IP_MULTICAST help text
fix the BAYCOM_SER_HDX help text
fix SCSI_SCAN_ASYNC help text
trivial documentation patch for platform.txt
Fix typos concerning hierarchy
Fix comment typo "spin_lock_irqrestore".
Fix misspellings of "agressive".
drivers/scsi/a100u2w.c: trivial typo patch
Correct trivial typo in log2.h.
Remove useless FIND_FIRST_BIT() macro from cardbus.c.
...