When a memblock allocation APIs are called with align = 0, the alignment
is implicitly set to SMP_CACHE_BYTES.
Implicit alignment is done deep in the memblock allocator and it can
come as a surprise. Not that such an alignment would be wrong even
when used incorrectly but it is better to be explicit for the sake of
clarity and the prinicple of the least surprise.
Replace all such uses of memblock APIs with the 'align' parameter
explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment
in the memblock internal allocation functions.
For the case when memblock APIs are used via helper functions, e.g. like
iommu_arena_new_node() in Alpha, the helper functions were detected with
Coccinelle's help and then manually examined and updated where
appropriate.
The direct memblock APIs users were updated using the semantic patch below:
@@
expression size, min_addr, max_addr, nid;
@@
(
|
- memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid)
+ memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr,
nid)
|
- memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid)
+ memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr,
nid)
|
- memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid)
+ memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid)
|
- memblock_alloc(size, 0)
+ memblock_alloc(size, SMP_CACHE_BYTES)
|
- memblock_alloc_raw(size, 0)
+ memblock_alloc_raw(size, SMP_CACHE_BYTES)
|
- memblock_alloc_from(size, 0, min_addr)
+ memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr)
|
- memblock_alloc_nopanic(size, 0)
+ memblock_alloc_nopanic(size, SMP_CACHE_BYTES)
|
- memblock_alloc_low(size, 0)
+ memblock_alloc_low(size, SMP_CACHE_BYTES)
|
- memblock_alloc_low_nopanic(size, 0)
+ memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES)
|
- memblock_alloc_from_nopanic(size, 0, min_addr)
+ memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr)
|
- memblock_alloc_node(size, 0, nid)
+ memblock_alloc_node(size, SMP_CACHE_BYTES, nid)
)
[mhocko@suse.com: changelog update]
[akpm@linux-foundation.org: coding-style fixes]
[rppt@linux.ibm.com: fix missed uses of implicit alignment]
Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx
Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Suggested-by: Michal Hocko <mhocko@suse.com>
Acked-by: Paul Burton <paul.burton@mips.com> [MIPS]
Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc]
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We implement regs_set_return_value() and override_function_with_return()
for this purpose.
On powerpc, a return from a function (blr) just branches to the location
contained in the link register. So, we can just update pt_regs rather
than redirecting execution to a dummy function that returns.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reviewed-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Back when I added -Werror in commit ba55bd7436 ("powerpc: Add
configurable -Werror for arch/powerpc") I did it by adding it to most
of the arch Makefiles.
At the time we excluded math-emu, because apparently it didn't build
cleanly. But that seems to have been fixed somewhere in the interim.
So move the -Werror addition to the top-level of the arch, this saves
us from repeating it in every Makefile and means we won't forget to
add it to any new sub-dirs.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In order to avoid multiple conversions, handover directly a
pgprot_t to map_kernel_page() as already done for radix.
Do the same for __ioremap_caller() and __ioremap_at().
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Commit 51c3c62b58 ("powerpc: Avoid code patching freed init
sections") accesses 'init_mem_is_free' flag too early, before the
kernel is relocated. This provokes early boot failure (before the
console is active).
As it is not necessary to do this verification that early, this
patch moves the test into patch_instruction() instead of
__patch_instruction().
This modification also has the advantage of avoiding unnecessary
remappings.
Fixes: 51c3c62b58 ("powerpc: Avoid code patching freed init sections")
Cc: stable@vger.kernel.org # 4.13+
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
On little endian platforms, csum_ipv6_magic() keeps len and proto in
CPU byte order. This generates a bad results leading to ICMPv6 packets
from other hosts being dropped by powerpc64le platforms.
In order to fix this, len and proto should be converted to network
byte order ie bigendian byte order. However checksumming 0x12345678
and 0x56341278 provide the exact same result so it is enough to
rotate the sum of len and proto by 1 byte.
PPC32 only support bigendian so the fix is needed for PPC64 only
Fixes: e9c4943a10 ("powerpc: Implement csum_ipv6_magic in assembly")
Reported-by: Jianlin Shi <jishi@redhat.com>
Reported-by: Xin Long <lucien.xin@gmail.com>
Cc: <stable@vger.kernel.org> # 4.18+
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This stops us from doing code patching in init sections after they've
been freed.
In this chain:
kvm_guest_init() ->
kvm_use_magic_page() ->
fault_in_pages_readable() ->
__get_user() ->
__get_user_nocheck() ->
barrier_nospec();
We have a code patching location at barrier_nospec() and
kvm_guest_init() is an init function. This whole chain gets inlined,
so when we free the init section (hence kvm_guest_init()), this code
goes away and hence should no longer be patched.
We seen this as userspace memory corruption when using a memory
checker while doing partition migration testing on powervm (this
starts the code patching post migration via
/sys/kernel/mobility/migration). In theory, it could also happen when
using /sys/kernel/debug/powerpc/barrier_nospec.
Cc: stable@vger.kernel.org # 4.13+
Signed-off-by: Michael Neuling <mikey@neuling.org>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Static branch hints override dynamic branch prediction on recent
POWER CPUs. We should only use them when we are overwhelmingly
sure of the direction.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The symbol memcpy_nocache_branch defined in order to allow patching
of memset function once cache is enabled leads to confusing reports
by perf tool.
Using the new patch_site functionality solves this issue.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In __copy_tofrom_user, if we encounter an exception on a store, we
stop copying and return the number of bytes not copied. However,
if the store is wider than one byte and is to an unaligned address,
it is possible that the store operand overlaps a page boundary
and the exception occurred on the latter part of the store operand,
meaning that it would be possible to copy a few more bytes. Since
copy_to_user is generally expected to copy as much as possible,
it would be better to copy those extra few bytes. This adds code
to do that. Since this edge case is not performance-critical,
the code has been written to be compact rather than as fast as
possible.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The hand-coded assembler 64-bit copy routines include feature sections
that select one code path or another depending on which CPU we are
executing on. The self-tests for these copy routines end up testing
just one path. This adds a mechanism for selecting any desired code
path at compile time, and makes 2 or 3 versions of each test, each
using a different code path, so as to cover all the possible paths.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
[mpe: Add -mcpu=power4 to CFLAGS for older compilers]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This aims to make the generation of exception table entries for the
loads and stores in __copy_tofrom_user_base clearer and easier to
verify. Instead of having a series of local labels on the loads and
stores, with a series of corresponding labels later for the exception
handlers, we now use macros to generate exception table entries at the
point of each load and store that could potentially trap. We do this
with the macros lex (load exception) and stex (store exception).
These macros are used right before the load or store to which they
apply.
Some complexity is introduced by the fact that we have some more work
to do after hitting an exception, because we need to calculate and
return the number of bytes not copied. The code uses r3 as the
current pointer into the destination buffer, that is, the address of
the first byte of the destination that has not been modified.
However, at various points in the copy loops, r3 can be 4, 8, 16 or 24
bytes behind that point.
To express this offset in an understandable way, we define a symbol
r3_offset which is updated at various points so that it equal to the
difference between the address of the first unmodified byte of the
destination and the value in r3. (In fact it only needs to be
accurate at the point of each lex or stex macro invocation.)
The rules for updating r3_offset are as follows:
* It starts out at 0
* An addi r3,r3,N instruction decreases r3_offset by N
* A store instruction (stb, sth, stw, std) to N(r3)
increases r3_offset by the width of the store (1, 2, 4, 8)
* A store with update instruction (stbu, sthu, stwu, stdu) to N(r3)
sets r3_offset to the width of the store.
There is some trickiness to the way that the lex and stex macros and
the associated exception handlers work. I would have liked to use
the current value of r3_offset in the name of the symbol used as
the exception handler, as in ".Lld_exc_$(r3_offset)" and then
have symbols .Lld_exc_0, .Lld_exc_8, .Lld_exc_16 etc. corresponding
to the offsets that needed to be added to r3. However, I couldn't
see a way to do that with gas.
Instead, the exception handler address is .Lld_exc - r3_offset or
.Lst_exc - r3_offset, that is, the distance ahead of .Lld_exc/.Lst_exc
that we start executing is equal to the amount that we need to add to
r3. This works because r3_offset is always a small multiple of 4,
and our instructions are 4 bytes long. This means that before
.Lld_exc and .Lst_exc, we have a sequence of instructions that
increments r3 by 4, 8, 16 or 24 depending on where we start. The
sequence increments r3 by 4 per instruction (on average).
We also replace the exception table for the 4k copy loop by a
macro per load or store. These loads and stores all use exactly
the same exception handler, which simply resets the argument registers
r3, r4 and r5 to there original values and re-does the whole copy
using the slower loop.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add a macro and some helper C functions for patching single asm
instructions.
The gas macro means we can do something like:
1: nop
patch_site 1b, patch__foo
Which is less visually distracting than defining a GLOBAL symbol at 1,
and also doesn't pollute the symbol table which can confuse eg. perf.
These are obviously similar to our existing feature sections, but are
not automatically patched based on CPU/MMU features, rather they are
designed to be manually patched by C code at some arbitrary point.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Implement the barrier_nospec as a isync;sync instruction sequence.
The implementation uses the infrastructure built for BOOK3S 64.
Signed-off-by: Diana Craciun <diana.craciun@nxp.com>
[mpe: Split out of larger patch]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add a config symbol to encode which platforms support the
barrier_nospec speculation barrier. Currently this is just Book3S 64
but we will add Book3E in a future patch.
Signed-off-by: Diana Craciun <diana.craciun@nxp.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The generic implementation of strlen() reads strings byte per byte.
This patch implements strlen() in assembly based on a read of entire
words, in the same spirit as what some other arches and glibc do.
On a 8xx the time spent in strlen is reduced by 3/4 for long strings.
strlen() selftest on an 8xx provides the following values:
Before the patch (ie with the generic strlen() in lib/string.c):
len 256 : time = 1.195055
len 016 : time = 0.083745
len 008 : time = 0.046828
len 004 : time = 0.028390
After the patch:
len 256 : time = 0.272185 ==> 78% improvment
len 016 : time = 0.040632 ==> 51% improvment
len 008 : time = 0.033060 ==> 29% improvment
len 004 : time = 0.029149 ==> 2% degradation
On a 832x:
Before the patch:
len 256 : time = 0.236125
len 016 : time = 0.018136
len 008 : time = 0.011000
len 004 : time = 0.007229
After the patch:
len 256 : time = 0.094950 ==> 60% improvment
len 016 : time = 0.013357 ==> 26% improvment
len 008 : time = 0.010586 ==> 4% improvment
len 004 : time = 0.008784
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
files not using feature fixup don't need asm/feature-fixups.h
files using feature fixup need asm/feature-fixups.h
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Only include linux/stringify.h is files using __stringify()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This patch moves ASM_CONST() and stringify_in_c() into
dedicated asm-const.h, then cleans all related inclusions.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: asm-compat.h should include asm-const.h]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This patch is based on the previous VMX patch on memcmp().
To optimize ppc64 memcmp() with VMX instruction, we need to think about
the VMX penalty brought with: If kernel uses VMX instruction, it needs
to save/restore current thread's VMX registers. There are 32 x 128 bits
VMX registers in PPC, which means 32 x 16 = 512 bytes for load and store.
The major concern regarding the memcmp() performance in kernel is KSM,
who will use memcmp() frequently to merge identical pages. So it will
make sense to take some measures/enhancement on KSM to see whether any
improvement can be done here. Cyril Bur indicates that the memcmp() for
KSM has a higher possibility to fail (unmatch) early in previous bytes
in following mail.
https://patchwork.ozlabs.org/patch/817322/#1773629
And I am taking a follow-up on this with this patch.
Per some testing, it shows KSM memcmp() will fail early at previous 32
bytes. More specifically:
- 76% cases will fail/unmatch before 16 bytes;
- 83% cases will fail/unmatch before 32 bytes;
- 84% cases will fail/unmatch before 64 bytes;
So 32 bytes looks a better choice than other bytes for pre-checking.
The early failure is also true for memcmp() for non-KSM case. With a
non-typical call load, it shows ~73% cases fail before first 32 bytes.
This patch adds a 32 bytes pre-checking firstly before jumping into VMX
operations, to avoid the unnecessary VMX penalty. It is not limited to
KSM case. And the testing shows ~20% improvement on memcmp() average
execution time with this patch.
And note the 32B pre-checking is only performed when the compare size
is long enough (>=4K currently) to allow VMX operation.
The detail data and analysis is at:
https://github.com/justdoitqd/publicFiles/blob/master/memcmp/README.md
Signed-off-by: Simon Guo <wei.guo.simon@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This patch add VMX primitives to do memcmp() in case the compare size
is equal or greater than 4K bytes. KSM feature can benefit from this.
Test result with following test program(replace the "^>" with ""):
------
># cat tools/testing/selftests/powerpc/stringloops/memcmp.c
>#include <malloc.h>
>#include <stdlib.h>
>#include <string.h>
>#include <time.h>
>#include "utils.h"
>#define SIZE (1024 * 1024 * 900)
>#define ITERATIONS 40
int test_memcmp(const void *s1, const void *s2, size_t n);
static int testcase(void)
{
char *s1;
char *s2;
unsigned long i;
s1 = memalign(128, SIZE);
if (!s1) {
perror("memalign");
exit(1);
}
s2 = memalign(128, SIZE);
if (!s2) {
perror("memalign");
exit(1);
}
for (i = 0; i < SIZE; i++) {
s1[i] = i & 0xff;
s2[i] = i & 0xff;
}
for (i = 0; i < ITERATIONS; i++) {
int ret = test_memcmp(s1, s2, SIZE);
if (ret) {
printf("return %d at[%ld]! should have returned zero\n", ret, i);
abort();
}
}
return 0;
}
int main(void)
{
return test_harness(testcase, "memcmp");
}
------
Without this patch (but with the first patch "powerpc/64: Align bytes
before fall back to .Lshort in powerpc64 memcmp()." in the series):
4.726728762 seconds time elapsed ( +- 3.54%)
With VMX patch:
4.234335473 seconds time elapsed ( +- 2.63%)
There is ~+10% improvement.
Testing with unaligned and different offset version (make s1 and s2 shift
random offset within 16 bytes) can archieve higher improvement than 10%..
Signed-off-by: Simon Guo <wei.guo.simon@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently memcmp() 64bytes version in powerpc will fall back to .Lshort
(compare per byte mode) if either src or dst address is not 8 bytes aligned.
It can be opmitized in 2 situations:
1) if both addresses are with the same offset with 8 bytes boundary:
memcmp() can compare the unaligned bytes within 8 bytes boundary firstly
and then compare the rest 8-bytes-aligned content with .Llong mode.
2) If src/dst addrs are not with the same offset of 8 bytes boundary:
memcmp() can align src addr with 8 bytes, increment dst addr accordingly,
then load src with aligned mode and load dst with unaligned mode.
This patch optmizes memcmp() behavior in the above 2 situations.
Tested with both little/big endian. Performance result below is based on
little endian.
Following is the test result with src/dst having the same offset case:
(a similar result was observed when src/dst having different offset):
(1) 256 bytes
Test with the existing tools/testing/selftests/powerpc/stringloops/memcmp:
- without patch
29.773018302 seconds time elapsed ( +- 0.09% )
- with patch
16.485568173 seconds time elapsed ( +- 0.02% )
-> There is ~+80% percent improvement
(2) 32 bytes
To observe performance impact on < 32 bytes, modify
tools/testing/selftests/powerpc/stringloops/memcmp.c with following:
-------
#include <string.h>
#include "utils.h"
-#define SIZE 256
+#define SIZE 32
#define ITERATIONS 10000
int test_memcmp(const void *s1, const void *s2, size_t n);
--------
- Without patch
0.244746482 seconds time elapsed ( +- 0.36%)
- with patch
0.215069477 seconds time elapsed ( +- 0.51%)
-> There is ～+13% improvement
(3) 0~8 bytes
To observe <8 bytes performance impact, modify
tools/testing/selftests/powerpc/stringloops/memcmp.c with following:
-------
#include <string.h>
#include "utils.h"
-#define SIZE 256
-#define ITERATIONS 10000
+#define SIZE 8
+#define ITERATIONS 1000000
int test_memcmp(const void *s1, const void *s2, size_t n);
-------
- Without patch
1.845642503 seconds time elapsed ( +- 0.12% )
- With patch
1.849767135 seconds time elapsed ( +- 0.26% )
-> They are nearly the same. (-0.2%)
Signed-off-by: Simon Guo <wei.guo.simon@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Mike Rapoport
Naveen N. Rao
Michael Ellerman
Christophe Leroy
Michael Neuling
Anton Blanchard
Paul Mackerras
Diana Craciun
Simon Guo