Processors that support the mips64r2 ISA can in four instructions
convert a shifted PGD pointer stored in the upper bits of c0_context
into a usable pointer. By doing this we save a memory load and
associated potential cache miss in the TLB exception handlers.
Since the upper bits of c0_context were holding the CPU number, we
move this to the upper bits of c0_xcontext which doesn't have enough
bits to hold the PGD pointer, but has plenty for the CPU number.
Signed-off-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
On an SMP system with cache aliases, the following sequence of events may
happen:
1) copy_user_highpage() runs on CPU0, invoking kmap_coherent() to create a
temporary mapping in the fixmap region
2) copy_page() starts on CPU0
3) CPU1 sends CPU0 an IPI asking CPU0 to run local_r4k_flush_cache_page()
4) CPU0 takes the interrupt, interrupting copy_page()
5) local_r4k_flush_cache_page() on CPU0 calls kmap_coherent() again
6) The second invocation of kmap_coherent() on CPU0 tries to use the
same fixmap virtual address that was being used by copy_user_highpage()
7) CPU0 throws a machine check exception for the TLB address conflict
Fixed by creating an extra set of fixmap entries for use in interrupt
handlers. This prevents fixmap VA conflicts between copy_user_highpage()
running in user context, and local_r4k_flush_cache_page() invoked from an
SMP IPI.
Signed-off-by: Kevin Cernekee <cernekee@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.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>
For /proc/kcore, vmalloc areas are registered per arch. But, all of them
registers same range of [VMALLOC_START...VMALLOC_END) This patch unifies
them. By this. archs which have no kclist_add() hooks can see vmalloc
area correctly.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Presently, kclist_add() only eats start address and size as its arguments.
Considering to make kclist dynamically reconfigulable, it's necessary to
know which kclists are for System RAM and which are not.
This patch add kclist types as
KCORE_RAM
KCORE_VMALLOC
KCORE_TEXT
KCORE_OTHER
This "type" is used in a patch following this for detecting KCORE_RAM.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 9617729941 ("Drop free_pages()")
modified nr_free_pages() to return 'unsigned long' instead of 'unsigned
int'. This made the casts to 'unsigned long' in most callers superfluous,
so remove them.
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Acked-by: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Chris Zankel <zankel@tensilica.com>
Cc: Michal Simek <monstr@monstr.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
By combining swapper_pg_dir and module_pg_dir, several if conditions
can be eliminated from the tlb exception handler. The reason they
can be combined is that, the effective virtual address of vmalloc
returned is at the bottom, and of module_alloc returned is at the
top. It also fixes the bug in vmalloc(), which happens when its
return address is not covered by the first pgd.
Signed-off-by: Wu Fei <at.wufei@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Some of the were relying into smp.h being dragged in by another header
which of course is fragile. <asm/cpu-info.h> uses smp_processor_id()
only in macros and including smp.h there leads to an include loop, so
don't change cpu-info.h.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Commit 351336929c (kernel.org) rsp.
b3594a089f1c17ff919f8f78505c3f20e1f6f8ce (linux-mips.org):
> From: Chris Dearman <chris@mips.com>
> Date: Wed, 19 Sep 2007 00:58:24 +0100
> Subject: [PATCH] [MIPS] Allow setting of the cache attribute at run time.
>
> Slightly tacky, but there is a precedent in the sparc archirecture code.
introduces the variable _page_cachable_default, which defaults to zero and.
is used to create the prototype PTE for __kmap_atomic in
arch/mips/mm/init.c:kmap_init before initialization in
arch/mips/mm/c-r4k.c:coherency_setup, so the default value of 0 will be
used as the CCA of kmap atomic pages which on many processors is not a
defined CCA value and may result in writes to kmap_atomic pages getting
corrupted. Debugged by Jon Fraser (jfraser@broadcom.com).
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
No users for the copy_from_user_page() routine exist outside of the
core kernel code. Therefore, EXPORT_SYMBOL(copy_from_user_page) is
useless, and this patch removes it.
Signed-off-by: Dmitri Vorobiev <dmitri.vorobiev@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The copy_to_user_page() function is called only in the core kernel
code. Therefore, there is no need to export it. This patch removes
EXPORT_SYMBOL(copy_to_user_page).
Signed-off-by: Dmitri Vorobiev <dmitri.vorobiev@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The copy_user_highpage() routine has no users outside of the
core kernel code, so exporting this symbol is pointless.
This patch removes EXPORT_SYMBOL(copy_user_highpage).
Signed-off-by: Dmitri Vorobiev <dmitri.vorobiev@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
kmap_coherent will only work correctly if the page it is called on is
not marked dirty. If it's dirty the kernel address of the page should
be used instead of a temporary mapping.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Sibyte SOCs only have 32-bit PCI. Due to the sparse use of the address
space only the first 1GB of memory is mapped at physical addresses
below 1GB. If a system has more than 1GB of memory 32-bit DMA will
not be able to reach all of it.
For now this patch is good enough to keep Sibyte users happy but it seems
eventually something like swiotlb will be needed for Sibyte.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Turns out b868868ae0 wasn't quite right.
When called for a page that isn't marked dirty it would artificially
create an alias instead of doing the obvious thing and access the page
via KSEG0.
The same issue also exists in copy_to_user_page and copy_from_user_page
which was causing the machine to die under rare circumstances for example
when running ps if the BUG_ON() assertion added by the earlier fix was
getting triggered.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Copy_user_highpage was written assuming it was only being called for
breaking COW pages in which case the source page isn't cached as in
marked cachable under it kernel virtual address. If it is called anyway
the aliasing avoidance strategy implemented by kmap_coherent will fail.
Avoid the use of kmap_coherent for pages marked dirty and to avoid
another instance of this sort of bug, place a BUG_ON in kmap_coherent.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
> WARNING: vmlinux.o(.text+0xbf20): Section mismatch: reference to
> .init.text:prom_free_prom_memory (between 'free_initmem' and 'copy_from_user_page')
prom_free_prom_memory() is called _before_ freeing init sections, so
it is false positive. __init_refok can be used for such cases.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This fixes some sparse warnings.
pgtable-32.c:15:6: warning: symbol 'pgd_init' was not declared. Should it be static?
pgtable-32.c:32:13: warning: symbol 'pagetable_init' was not declared. Should it be static?
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This get rid of some undesirable hole in BSS section due to random
order of placement.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This patch makes a better usage of these two globals.
'min_low_pfn' is now correctly setup for all configs, which
allow us to rely on it in boot memory code init.
Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Current prom_free_prom_memory() implementations are almost same as
free_init_pages(), or no-op. Make free_init_pages() extern (again)
and make prom_free_prom_memory() use it.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Provide a custom copy_user_highpage() to deal with aliasing issues on
MIPS. It uses kmap_coherent() to map an user page for kernel with same
color. Rewrite copy_to_user_page() and copy_from_user_page() with the
new interfaces to avoid extra cache flushing.
The main part of this patch was originally written by Ralf Baechle;
Atushi Nemoto did the the debugging.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch makes paging_init() use highend_pfn/highstart_pfn globals.
It removes the need of 'high' local which was needed only by HIGHMEM config.
More important perhaps, it fixes a bug when HIGHMEM is set but there's
actually no physical highmem (highend_pfn = 0)
Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
It allows caller of this function to not care about CKSEG0/XKPHYS
address mixes. It's now automatically done by free_init_pages().
We can now safely remove hack needed by 64 bit kernels with
CONFIG_BUILD_ELF64=n in free_initmem().
Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
__pa() was used by virt_to_page() and virt_addr_valid(). These
latter are used when kernel is initialised so __pa() is not
appropriate, we use virt_to_phys() instead.
Futhermore __pa() is going to take care of CKSEG0/XKPHYS
address mix for 64 bit kernels. This makes __pa() more complex
than virt_to_phys() and this extra work is not needed by
virt_to_page() and virt_addr_valid().
Eventually it consolidates virt_to_phys() prototype by making
its argument 'const'. this avoids some warnings that was due
to some virt_to_page() usages which pass const pointer.
Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The current implementation uses a sequence of a cacheflush and a copy.
This is racy in case of a multithreaded debuggee and renders GDB
virtually unusable.
Aside this fixes a performance hog rendering access to /proc/cmdline very
slow and resulting in a enough cache stalls for the 34K AP/SP programming
model to make the bare metal code on the non-Linux VPE miss RT deadlines.
The main part of this patch was originally written by Ralf Baechle;
Atushi Nemoto did the the debugging.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Fix array initialization in lots of arches
The number of zones may now be reduced from 4 to 2 for many arches. Fix the
array initialization for the zones array for all architectures so that it is
not initializing a fixed number of elements.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
With some memory model other than FLATMEM, the single node can
contains some holes so there might be many invalid pages. For
example, with two 256M memory and one 256M hole, some variables
(num_physpage, totalpages, nr_kernel_pages, nr_all_pages, etc.) will
indicate that there are 768MB on this system. This is not desired
because, for example, alloc_large_system_hash() allocates too many
entries.
Use free_area_init_node() with counted zholes_size[] instead of
free_area_init().
For num_physpages, use number of ram pages instead of max_low_pfn.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Move memory_present() in arch/mips/kernel/setup.c. When using sparsemem
extreme, this function does an allocate for bootmem. This would always
fail since init_bootmem hasn't been called yet.
Move memory_present after free_bootmem. This only marks actual memory
ranges as present instead of the entire address space.
Signed-off-by: Chad Reese <creese@caviumnetworks.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
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 <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
set_page_count usage outside mm/ is limited to setting the refcount to 1.
Remove set_page_count from outside mm/, and replace those users with
init_page_count() and set_page_refcounted().
This allows more debug checking, and tighter control on how code is allowed
to play around with page->_count.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Have an explicit mm call to split higher order pages into individual pages.
Should help to avoid bugs and be more explicit about the code's intention.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
Signed-off-by: Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
I'm pretty sure that the CKSEG0 bits are wrong, but I did need to
cover that region - because the SB-1 kernel links at 0xffffffff80100000
or so, disassembly and printing static variables don't work unless the
debugger can read that region.
Signed-off-by: Daniel Jacobowitz <dan@codesourcery.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
