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>
We already know the pfn for the page to be modified in make_coherent,
so let's stop recalculating it unnecessarily.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
update_mmu_cache() is called with a page table already mapped. We
call make_coherent(), which then calls adjust_pte() which wants to
map other page tables. This causes kmap_atomic() to BUG() because
the slot its trying to use is already taken.
Since do_adjust_pte() modifies the page tables, we are also missing
any form of locking, so we're risking corrupting the page tables.
Fix this by using pte_offset_map_nested(), and taking the pte page
table lock around do_adjust_pte().
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
It is unpredictable to have the same memory mapped using different
shared bit settings for ARMv6 and ARMv7 CPUs. Fix this for the CPU
write buffer bug test.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The zero page is read-only, and has its cache state cleared during
boot. No further maintanence for this page is required.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
On ARM, update_mmu_cache() does dcache flush for a page only if
it has a kernel mapping (page_mapping(page) != NULL). The correct
behavior would be to force the flush based on dcache_dirty bit only.
One of the cases where present logic would be a problem is when
a RAM based block device[1] is used as a swap disk. In this case,
we would have in-memory data corruption as shown in steps below:
do_swap_page()
{
- Allocate a new page (if not already in swap cache)
- Issue read from swap disk
- Block driver issues flush_dcache_page()
- flush_dcache_page() simply sets PG_dcache_dirty bit and does not
actually issue a flush since this page has no user space mapping yet.
- Now, if swap disk is almost full, this newly read page is removed
from swap cache and corrsponding swap slot is freed.
- Map this page anonymously in user space.
- update_mmu_cache()
- Since this page does not have kernel mapping (its not in page/swap
cache and is mapped anonymously), it does not issue dcache flush
even if dcache_dirty bit is set by flush_dcache_page() above.
<user now gets stale data since dcache was never flushed>
}
Same problem exists on mips too.
[1] example:
- brd (RAM based block device)
- ramzswap (RAM based compressed swap device)
Signed-off-by: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
When there are multiple L1-aliasing userland mappings of the same physical
page, we currently remap each of them uncached, to prevent VIVT cache
aliasing issues. (E.g. writes to one of the mappings not being immediately
visible via another mapping.) However, when we do this remapping, there
could still be stale data in the L2 cache, and an uncached mapping might
bypass L2 and go straight to RAM. This would cause reads from such
mappings to see old data (until the dirty L2 line is eventually evicted.)
This issue is solved by forcing a L2 cache flush whenever the shared page
is made L1 uncacheable.
Ideally, we would make L1 uncacheable and L2 cacheable as L2 is PIPT. But
Feroceon does not support that combination, and the TEX=5 C=0 B=0 encoding
for XSc3 doesn't appear to work in practice.
Signed-off-by: Nicolas Pitre <nico@marvell.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Provide L_PTE_MT_xxx definitions to describe the memory types that we
use in Linux/ARM. These definitions are carefully picked such that:
1. their LSBs match what is required for pre-ARMv6 CPUs.
2. they all have a unique encoding, including after modification
by build_mem_type_table() (the result being that some have more
than one combination.)
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
arch/arm/kernel/process.c:270:6: warning: symbol 'show_fpregs' was not declared. Should it be static?
This function isn't used, so can be removed.
arch/arm/kernel/setup.c:532:9: warning: symbol 'len' shadows an earlier one
arch/arm/kernel/setup.c:524:6: originally declared here
A function containing two 'len's.
arch/arm/mm/fault-armv.c:188:13: warning: symbol 'check_writebuffer_bugs' was not declared. Should it be static?
arch/arm/mm/mmap.c:122:5: warning: symbol 'valid_phys_addr_range' was not declared. Should it be static?
arch/arm/mm/mmap.c:137:5: warning: symbol 'valid_mmap_phys_addr_range' was not declared. Should it be static?
Missing includes.
arch/arm/kernel/traps.c:71:77: warning: Using plain integer as NULL pointer
arch/arm/mm/ioremap.c:355:46: error: incompatible types in comparison expression (different address spaces)
Sillies.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Rather than pollute asm/cacheflush.h with the cache type definitions,
move them to asm/cachetype.h, and include this new header where
necessary.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The shared mmap code works fine for the test case, which only checked
for two shared maps of the same file. However, three shared maps
result in one mapping remaining cached, resulting in stale data being
visible via that mapping. Fix this.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
This patch adds the I-cache invalidation in update_mmu_cache if the
corresponding vma is marked as executable. It also invalidates the
I-cache if a thread migrates to a CPU it never ran on.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Commit 1c9d3df5e8 added function prototype
__flush_dcache_page() in include/asm-arm/cacheflush.h. So we can remove
the prototype for same in arch/arm/mm/fault-armv.c since it is now
redundant to have it there.
Signed-off-by: George G. Davis <gdavis@mvista.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
L_PTE_ASID is not really required to be stored in every PTE, since we
can identify it via the address passed to set_pte_at(). So, create
set_pte_ext() which takes the address of the PTE to set, the Linux
PTE value, and the additional CPU PTE bits which aren't encoded in
the Linux PTE value.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Prepare arm for the split page_table_lock: three issues.
Signal handling's preserve and restore of iwmmxt context currently involves
reading and writing that context to and from user space, while holding
page_table_lock to secure the user page(s) against kswapd. If we split the
lock, then the structure might span two pages, secured by to read into and
write from a kernel stack buffer, copying that out and in without locking (the
structure is 160 bytes in size, and here we're near the top of the kernel
stack). Or would the overhead be noticeable?
arm_syscall's cmpxchg emulation use pte_offset_map_lock, instead of
pte_offset_map and mm-wide page_table_lock; and strictly, it should now also
take mmap_sem before descending to pmd, to guard against another thread
munmapping, and the page table pulled out beneath this thread.
Updated two comments in fault-armv.c. adjust_pte is interesting, since its
modification of a pte in one part of the mm depends on the lock held when
calling update_mmu_cache for a pte in some other part of that mm. This can't
be done with a split page_table_lock (and we've already taken the lowest lock
in the hierarchy here): so we'll have to disable split on arm, unless
CONFIG_CPU_CACHE_VIPT to ensures adjust_pte never used.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
flush_dcache_page() did nothing for these caches, but since they
suffer from I/D cache coherency issues, we need to ensure that data
is written back to RAM.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
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!
