When the data cache is PIPT or VIPT non-aliasing, and cache operations
are broadcast by the hardware, we can always postpone the flush in
flush_dcache_page(). A similar change was done for ARM64 in commit
b5b6c9e914 ("arm64: Avoid cache flushing in flush_dcache_page()").
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Rabin Vincent <rabinv@axis.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Let's define page_mapped() to be true for compound pages if any
sub-pages of the compound page is mapped (with PMD or PTE).
On other hand page_mapcount() return mapcount for this particular small
page.
This will make cases like page_get_anon_vma() behave correctly once we
allow huge pages to be mapped with PTE.
Most users outside core-mm should use page_mapcount() instead of
page_mapped().
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With new refcounting we don't need to mark PMDs splitting. Let's drop
code to handle this.
pmdp_splitting_flush() is not needed too: on splitting PMD we will do
pmdp_clear_flush() + set_pte_at(). pmdp_clear_flush() will do IPI as
needed for fast_gup.
[arnd@arndb.de: fix unterminated ifdef in header file]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add an extension to the heavy barrier code to allow a SoC specific
memory barrier function to be provided. This is needed for platforms
where the interconnect has weak ordering, and thus needs assistance
to ensure that memory writes are properly visible in the correct order
to other parts of the system.
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Richard Woodruff <r-woodruff2@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The existing memory barrier macro causes a significant amount of code
to be inserted inline at every call site. For example, in
gpio_set_irq_type(), we have this for mb():
c0344c08: f57ff04e dsb st
c0344c0c: e59f8190 ldr r8, [pc, #400] ; c0344da4 <gpio_set_irq_type+0x230>
c0344c10: e3590004 cmp r9, #4
c0344c14: e5983014 ldr r3, [r8, #20]
c0344c18: 0a000054 beq c0344d70 <gpio_set_irq_type+0x1fc>
c0344c1c: e3530000 cmp r3, #0
c0344c20: 0a000004 beq c0344c38 <gpio_set_irq_type+0xc4>
c0344c24: e50b2030 str r2, [fp, #-48] ; 0xffffffd0
c0344c28: e50bc034 str ip, [fp, #-52] ; 0xffffffcc
c0344c2c: e12fff33 blx r3
c0344c30: e51bc034 ldr ip, [fp, #-52] ; 0xffffffcc
c0344c34: e51b2030 ldr r2, [fp, #-48] ; 0xffffffd0
c0344c38: e5963004 ldr r3, [r6, #4]
Moving the outer_cache_sync() call out of line reduces the impact of
the barrier:
c0344968: f57ff04e dsb st
c034496c: e35a0004 cmp sl, #4
c0344970: e50b2030 str r2, [fp, #-48] ; 0xffffffd0
c0344974: 0a000044 beq c0344a8c <gpio_set_irq_type+0x1b8>
c0344978: ebf363dd bl c001d8f4 <arm_heavy_mb>
c034497c: e5953004 ldr r3, [r5, #4]
This should reduce the cache footprint of this code. Overall, this
results in a reduction of around 20K in the kernel size:
text data bss dec hex filename
10773970 667392 10369656 21811018 14ccf4a ../build/imx6/vmlinux-old
10754219 667392 10369656 21791267 14c8223 ../build/imx6/vmlinux-new
Another advantage to this approach is that we can finally resolve the
issue of SoCs which have their own memory barrier requirements within
multiplatform kernels (such as OMAP.) Here, the bus interconnects
need additional handling to ensure that writes become visible in the
correct order (eg, between dma_map() operations, writes to DMA
coherent memory, and MMIO accesses.)
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Richard Woodruff <r-woodruff2@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
L1_CACHE_BYTES could be larger than real L1 cache line size.
In that case, flush_pfn_alias() would omit to flush last bytes
as much as L1_CACHE_BYTES - real cache line size.
So fix end address to "to + PAGE_SIZE - 1". The bottom bits of the address
is LINELEN. that is ignored by mcrr.
Signed-off-by: Jungseung Lee <js07.lee@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Activate the RCU fast_gup for ARM. We also need to force THP splits to
broadcast an IPI s.t. we block in the fast_gup page walker. As THP
splits are comparatively rare, this should not lead to a noticeable
performance degradation.
Some pre-requisite functions pud_write and pud_page are also added.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dann Frazier <dann.frazier@canonical.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
After instruction write into xol area, on ARM V7
architecture code need to flush dcache and icache to sync
them up for given set of addresses. Having just
'flush_dcache_page(page)' call is not enough - it is
possible to have stale instruction sitting in icache
for given xol area slot address.
Introduce arch_uprobe_ixol_copy weak function
that by default calls uprobes copy_to_page function and
than flush_dcache_page function and on ARM define new one
that handles xol slot copy in ARM specific way
flush_uprobe_xol_access function shares/reuses implementation
with/of flush_ptrace_access function and takes care of writing
instruction to user land address space on given variety of
different cache types on ARM CPUs. Because
flush_uprobe_xol_access does not have vma around
flush_ptrace_access was split into two parts. First that
retrieves set of condition from vma and common that receives
those conditions as flags.
Note ARM cache flush function need kernel address
through which instruction write happened, so instead
of using uprobes copy_to_page function changed
code to explicitly map page and do memcpy.
Note arch_uprobe_copy_ixol function, in similar way as
copy_to_user_page function, has preempt_disable/preempt_enable.
Signed-off-by: Victor Kamensky <victor.kamensky@linaro.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: David A. Long <dave.long@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
When given a compound high page, __flush_dcache_page will only flush
the first page of the compound page repeatedly rather than the entire
set of constituent pages.
This error was introduced by:
0b19f93 ARM: mm: Add support for flushing HugeTLB pages.
This patch corrects the logic such that all constituent pages are now
flushed.
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Commit f8b63c1 made flush_kernel_dcache_page a no-op assuming that
the pages it needs to handle are kernel mapped only. However, for
example when doing direct I/O, pages with user space mappings may
occur.
Thus, continue to do lazy flushing if there are no user space
mappings. Otherwise, flush the kernel cache lines directly.
Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: <stable@vger.kernel.org> # 3.2+
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Currently flush_dcache_page() thinks pages as non-mapped if
mapping_mapped(mapping) return false. This approach is very
coase:
- mmap on part of file may cause all pages backed on
the file being thought as mmaped
- file-backed pages aren't mapped into user space actually
if the memory mmaped on the file isn't accessed
This patch uses page_mapped() to decide if the page has been
mapped.
From the attached test code, I find there is much performance
improvement(>25%) when accessing page caches via read under this
situations, so memcpy benefits a lot from not flushing cache
under this situation.
No. read time without the patch No. read time with the patch
================================================================
No. 0, time 22615636 us No. 0, time 22014717 us
No. 1, time 4387851 us No. 1, time 3113184 us
No. 2, time 4276535 us No. 2, time 3005244 us
No. 3, time 4259821 us No. 3, time 3001565 us
No. 4, time 4263811 us No. 4, time 3002748 us
No. 5, time 4258486 us No. 5, time 3004104 us
No. 6, time 4253009 us No. 6, time 3002188 us
No. 7, time 4262809 us No. 7, time 2998196 us
No. 8, time 4264525 us No. 8, time 3007255 us
No. 9, time 4267795 us No. 9, time 3005094 us
1), No.0. is to read the file from storage device, and others are
to read the file from page caches basically.
2), file size is 512M, and is on ext4 over usb mass storage.
3), the test is done on Pandaboard.
unsigned int sum = 0;
unsigned long sum_val = 0;
static unsigned long tv_diff(struct timeval *tv1, struct timeval *tv2)
{
return (tv2->tv_sec - tv1->tv_sec) * 1000000 +
(tv2->tv_usec - tv1->tv_usec);
}
int main(int argc, char *argv[])
{
char *mbuf, fbuf;
int fd;
int i;
unsigned long page_size, size;
struct stat stat;
struct timeval t1, t2;
unsigned char *rbuf = malloc(32 * page_size);
if (!rbuf) {
printf(" %sn", "malloc failed");
exit(-1);
}
page_size = getpagesize();
fd = open(argv[1], O_RDWR);
assert(fd >= 0);
fstat(fd, &stat);
size = stat.st_size;
printf("%s: file %s, size %lu, page size %lun",
argv[0],
argv[1], size, page_size);
gettimeofday(&t1, NULL);
mbuf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
if (!mbuf) {
printf(" %sn", "mmap failed");
exit(-1);
}
for (i = 0 ; i < size ; i += (page_size * 32)) {
int rcnt;
lseek(fd, i, SEEK_SET);
rcnt = read(fd, rbuf, page_size * 32);
if (rcnt != page_size * 32) {
printf("%s: read faildn", __func__);
exit(-1);
}
}
free(rbuf);
munmap(mbuf, size);
gettimeofday(&t2, NULL);
printf("tread mmaped time: %luusn", tv_diff(&t1, &t2));
close(fd);
}
Cc: Michel Lespinasse <walken@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
On ARM we use the __flush_dcache_page function to flush the dcache
of pages when needed; usually when the PG_dcache_clean bit is unset
and we are setting a PTE.
A HugeTLB page is represented as a compound page consisting of an
array of pages. Thus to flush the dcache of a HugeTLB page, one must
flush more than a single page.
This patch modifies __flush_dcache_page such that all constituent
pages of a HugeTLB page are flushed.
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Reviewed-by: Will Deacon <will.deacon@arm.com>
In kmap_atomic(), kmap_high_get() is invoked for checking already
mapped area. In __flush_dcache_page() and dma_cache_maint_page(),
we explicitly call kmap_high_get() before kmap_atomic()
when cache_is_vipt(), so kmap_high_get() can be invoked twice.
This is useless operation, so remove one.
v2: change cache_is_vipt() to cache_is_vipt_nonaliasing() in order to
be self-documented
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Implement an interval tree as a replacement for the VMA prio_tree. The
algorithms are similar to lib/interval_tree.c; however that code can't be
directly reused as the interval endpoints are not explicitly stored in the
VMA. So instead, the common algorithm is moved into a template and the
details (node type, how to get interval endpoints from the node, etc) are
filled in using the C preprocessor.
Once the interval tree functions are available, using them as a
replacement to the VMA prio tree is a relatively simple, mechanical job.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Swap entries are encoding in ptes such that !pte_present(pte) and
pte_file(pte). The remaining bits of the descriptor are used to identify
the swapfile and offset within it to the swap entry.
When writing such a pte for a user virtual address, set_pte_at
unconditionally sets the nG bit, which (in the case of LPAE) will
corrupt the swapfile offset and lead to a BUG:
[ 140.494067] swap_free: Unused swap offset entry 000763b4
[ 140.509989] BUG: Bad page map in process rs:main Q:Reg pte:0ec76800 pmd:8f92e003
This patch fixes the problem by only setting the nG bit for user
mappings that are actually present.
Cc: <stable@vger.kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Pull more ARM updates from Russell King.
This got a fair number of conflicts with the <asm/system.h> split, but
also with some other sparse-irq and header file include cleanups. They
all looked pretty trivial, though.
* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (59 commits)
ARM: fix Kconfig warning for HAVE_BPF_JIT
ARM: 7361/1: provide XIP_VIRT_ADDR for no-MMU builds
ARM: 7349/1: integrator: convert to sparse irqs
ARM: 7259/3: net: JIT compiler for packet filters
ARM: 7334/1: add jump label support
ARM: 7333/2: jump label: detect %c support for ARM
ARM: 7338/1: add support for early console output via semihosting
ARM: use set_current_blocked() and block_sigmask()
ARM: exec: remove redundant set_fs(USER_DS)
ARM: 7332/1: extract out code patch function from kprobes
ARM: 7331/1: extract out insn generation code from ftrace
ARM: 7330/1: ftrace: use canonical Thumb-2 wide instruction format
ARM: 7351/1: ftrace: remove useless memory checks
ARM: 7316/1: kexec: EOI active and mask all interrupts in kexec crash path
ARM: Versatile Express: add NO_IOPORT
ARM: get rid of asm/irq.h in asm/prom.h
ARM: 7319/1: Print debug info for SIGBUS in user faults
ARM: 7318/1: gic: refactor irq_start assignment
ARM: 7317/1: irq: avoid NULL check in for_each_irq_desc loop
ARM: 7315/1: perf: add support for the Cortex-A7 PMU
...
Disintegrate asm/system.h for ARM.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Russell King <linux@arm.linux.org.uk>
cc: linux-arm-kernel@lists.infradead.org
A number of places establish a PTE in our top page table and
immediately flush the TLB. Rather than having this at every callsite,
provide an inline function for this purpose.
This changes some global tlb flushes to be local; each time we setup
one of these mappings, we always do it with preemption disabled which
would prevent us migrating to another CPU.
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Move the TOP_PTE address definitions to one central place so that it's
easy to discover what they're being used for. This helps to ensure
that there are no overlaps.
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
when cache_is_vipt_nonaliasing(), we always have pte_exec() true at
the end of this function, so no need for the additional check.
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Saeed Bishara <saeed@marvell.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Since commit 3e4d3af501 "mm: stack based kmap_atomic()", it is no longer
necessary to carry an ad hoc version of kmap_atomic() added in commit
7e5a69e83b "ARM: 6007/1: fix highmem with VIPT cache and DMA" to cope
with reentrancy.
In fact, it is now actively wrong to rely on fixed kmap type indices
(namely KM_L1_CACHE) as kmap_atomic() totally ignores them now and a
concurrent instance of it may reuse any slot for any purpose.
Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>
It's enough to include the asm/smp_plat.h once in arch/arm/mm/flush.c
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
copy_to_user_page can be used by access_process_vm to write to an
executable page of a process using a mapping acquired by kmap.
For systems with I-cache aliasing, flushing the I-cache using the
Kernel mapping may leave stale data in the I-cache if the user
mapping is of a different colour.
This patch introduces a flush_icache_alias function to flush.c,
which calls flush_icache_range with a mapping of the specified
colour. flush_ptrace_access is then modified to call this new
function instead of coherent_kern_range in the case of an aliasing
I-cache and a non-aliasing D-cache.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
ARMv7 processors like Cortex-A9 broadcast the cache maintenance
operations in hardware. This patch allows the
flush_dcache_page/update_mmu_cache pair to work in lazy flushing mode
similar to the UP case.
Note that cache flushing on SMP systems now takes place via the
set_pte_at() call (__sync_icache_dcache) and there is no race with other
CPUs executing code from the new PTE before the cache flushing took
place.
Tested-by: Rabin Vincent <rabin.vincent@stericsson.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
On SMP systems, there is a small chance of a PTE becoming visible to a
different CPU before the current cache maintenance operations in
update_mmu_cache(). To avoid this, cache maintenance must be handled in
set_pte_at() (similar to IA-64 and PowerPC).
This patch provides a unified VIPT cache handling mechanism and
implements the __sync_icache_dcache() function for ARMv6 onwards
architectures. It is called from set_pte_at() and replaces the
update_mmu_cache(). The latter is still used on VIVT hardware where a
vm_area_struct is required.
Tested-by: Rabin Vincent <rabin.vincent@stericsson.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
There are places in Linux where writes to newly allocated page cache
pages happen without a subsequent call to flush_dcache_page() (several
PIO drivers including USB HCD). This patch changes the meaning of
PG_arch_1 to be PG_dcache_clean and always flush the D-cache for a newly
mapped page in update_mmu_cache().
The patch also sets the PG_arch_1 bit in the DMA cache maintenance
function to avoid additional cache flushing in update_mmu_cache().
Tested-by: Rabin Vincent <rabin.vincent@stericsson.com>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Commit d73cd42 forced non-lazy cache flushing of highmem pages in
flush_dcache_page(). This isn't needed since __flush_dcache_page()
(called lazily from update_mmu_cache) can handle highmem pages (fixed by
commit 7e5a69e).
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The VIVT cache of a highmem page is always flushed before the page
is unmapped. This cache flush is explicit through flush_cache_kmaps()
in flush_all_zero_pkmaps(), or through __cpuc_flush_dcache_area() in
kunmap_atomic(). There is also an implicit flush of those highmem pages
that were part of a process that just terminated making those pages free
as the whole VIVT cache has to be flushed on every task switch. Hence
unmapped highmem pages need no cache maintenance in that case.
However unmapped pages may still be cached with a VIPT cache because the
cache is tagged with physical addresses. There is no need for a whole
cache flush during task switching for that reason, and despite the
explicit cache flushes in flush_all_zero_pkmaps() and kunmap_atomic(),
some highmem pages that were mapped in user space end up still cached
even when they become unmapped.
So, we do have to perform cache maintenance on those unmapped highmem
pages in the context of DMA when using a VIPT cache. Unfortunately,
it is not possible to perform that cache maintenance using physical
addresses as all the L1 cache maintenance coprocessor functions accept
virtual addresses only. Therefore we have no choice but to set up a
temporary virtual mapping for that purpose.
And of course the explicit cache flushing when unmapping a highmem page
on a system with a VIPT cache now can go, which should increase
performance.
While at it, because the code in __flush_dcache_page() has to be modified
anyway, let's also make sure the mapped highmem pages are pinned with
kmap_high_get() for the duration of the cache maintenance operation.
Because kunmap() does unmap highmem pages lazily, it was reported by
Gary King <GKing@nvidia.com> that those pages ended up being unmapped
during cache maintenance on SMP causing segmentation faults.
Signed-off-by: Nicolas Pitre <nico@marvell.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Dirk Behme reported instability on ARM11 SMP (VIPT non-aliasing cache)
caused by the dynamic linker changing protection on text pages to write
GOT entries. The problem is due to an interaction between the write
faulting code providing new anonymous pages which are incoherent with
the I-cache due to write buffering, and the I-cache not having been
invalidated.
a4db94d plugs the hole with the data cache coherency. This patch
provides the other half of the fix by flushing the I-cache in
flush_cache_range() for VM_EXEC VMAs (which is what we have when the
region is being made executable again.) This ensures that the I-cache
will be up to date with the newly COW'd pages.
Note: if users are writing instructions, then they still need to use
the ARM sys_cacheflush API to ensure that the caches are correctly
synchronized.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
flush_cache_mm() is called in two cases:
1. when a process exits, just before the page tables are torn down.
We can allow the stale lines to evict themselves over time without
causing any harm.
2. when a process forks, and we've allocated a new ASID.
The instruction cache issues are dealt with as pages are brought
into the new process address space. Flushing the I-cache here is
therefore unnecessary.
However, we must keep the VIPT aliasing D-cache flush to ensure that
any dirty cache lines are not written back after the pages have been
reallocated for some other use - which would result in corruption.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Both call sites for __flush_dcache_page() end up calling
__flush_icache_all() themselves, so having __flush_dcache_page() do
this as well is wasteful. Remove the duplicated icache flushing.
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>
page_address() is a function call rather than a macro, and so:
if (page_address(page))
do_something(page_address(page));
results in two calls to this function. This is unnecessary; remove
the duplication.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
We had two copies of the wrapper code for VIVT cache flushing - one in
asm/cacheflush.h and one in arch/arm/mm/flush.c. Reduce this down to
one common copy.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Errata 411920 indicates that any "invalidate entire instruction cache"
operation can fail if the right conditions are present. This is not
limited just to those operations in flush.c, but elsewhere. Place the
workaround in the already existing __flush_icache_all() function
instead.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Makes code futureproof against the impending change to mm->cpu_vm_mask.
It's also a chance to use the new cpumask_ ops which take a pointer
(the older ones are deprecated, but there's no hurry for arch code).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
In xdr_partial_copy_from_skb() there is that sequence:
kaddr = kmap_atomic(*ppage, KM_SKB_SUNRPC_DATA);
[...]
flush_dcache_page(*ppage);
kunmap_atomic(kaddr, KM_SKB_SUNRPC_DATA);
Mixing flush_dcache_page() and kmap_atomic() is a bit odd,
especially since kunmap_atomic() must deal with cache issues
already. OTOH the non-highmem case must use flush_dcache_page()
as kunmap_atomic() becomes a no op with no cache maintenance.
Problem is that with highmem the implementation of kmap_atomic()
doesn't set page->virtual, and page_address(page) returns 0 in
that case. Here flush_dcache_page() calls __flush_dcache_page()
which calls __cpuc_flush_dcache_page(page_address(page)) resulting
in a kernel oops.
None of the kmap_atomic() implementations uses set_page_address().
Hence we can assume page_address() is always expected to return 0 in
that case. Let's conditionally call __cpuc_flush_dcache_page() only
when the page address is non zero, and perform that test only when
highmem is configured.
Signed-off-by: Nicolas Pitre <nico@marvell.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
This patch implements the recommended workaround for erratum 411920
(ARM1136, ARM1156, ARM1176).
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The kmap virtual area borrows a 2MB range at the top of the 16MB area
below PAGE_OFFSET currently reserved for kernel modules and/or the
XIP kernel. This 2MB corresponds to the range covered by 2 consecutive
second-level page tables, or a single pmd entry as seen by the Linux
page table abstraction. Because XIP kernels are unlikely to be seen
on systems needing highmem support, there shouldn't be any shortage of
VM space for modules (14 MB for modules is still way more than twice the
typical usage).
Because the virtual mapping of highmem pages can go away at any moment
after kunmap() is called on them, we need to bypass the delayed cache
flushing provided by flush_dcache_page() in that case.
The atomic kmap versions are based on fixmaps, and
__cpuc_flush_dcache_page() is used directly in that case.
Signed-off-by: Nicolas Pitre <nico@marvell.com>
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>