Fix the x86 instruction decoder to decode bsr/bsf/jmpe with
operand-size prefix (66h). This fixes the test case failure
reported by Linus, attached below.
bsf/bsr/jmpe have a special encoding. Opcode map in
Intel Software Developers Manual vol2 says they have
TZCNT/LZCNT variants if it has F3h prefix. However, there
is no information if it has other 66h or F2h prefixes.
Current instruction decoder supposes that those are
bad instructions, but it actually accepts at least
operand-size prefixes.
H. Peter Anvin further explains:
" TZCNT/LZCNT are F3 + BSF/BSR exactly because the F2 and
F3 prefixes have historically been no-ops with most instructions.
This allows software to unconditionally use the prefixed versions
and get TZCNT/LZCNT on the processors that have them if they don't
care about the difference. "
This fixes errors reported by test_get_len:
Warning: arch/x86/tools/test_get_len found difference at <em_bsf>:ffffffff81036d87
Warning: ffffffff81036de5: 66 0f bc c2 bsf %dx,%ax
Warning: objdump says 4 bytes, but insn_get_length() says 3
Warning: arch/x86/tools/test_get_len found difference at <em_bsr>:ffffffff81036ea6
Warning: ffffffff81036f04: 66 0f bd c2 bsr %dx,%ax
Warning: objdump says 4 bytes, but insn_get_length() says 3
Warning: decoded and checked 13298882 instructions with 2 warnings
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <yrl.pp-manager.tt@hitachi.com>
Link: http://lkml.kernel.org/r/20120604150911.22338.43296.stgit@localhost.localdomain
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This throws away the old x86-specific functions in favor of the generic
optimized version.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The generic strncpy_from_user() is not really optimal, since it is
designed to work on both little-endian and big-endian. And on
little-endian you can simplify much of the logic to find the first zero
byte, since little-endian arithmetic doesn't have to worry about the
carry bit propagating into earlier bytes (only later bytes, which we
don't care about).
But I have patches to make the generic routines use the architecture-
specific <asm/word-at-a-time.h> infrastructure, so that we can regain
the little-endian optimizations. But before we do that, switch over to
the generic routines to make the patches each do just one well-defined
thing.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull exception table generation updates from Ingo Molnar:
"The biggest change here is to allow the build-time sorting of the
exception table, to speed up booting. This is achieved by the
architecture enabling BUILDTIME_EXTABLE_SORT. This option is enabled
for x86 and MIPS currently.
On x86 a number of fixes and changes were needed to allow build-time
sorting of the exception table, in particular a relocation invariant
exception table format was needed. This required the abstracting out
of exception table protocol and the removal of 20 years of accumulated
assumptions about the x86 exception table format.
While at it, this tree also cleans up various other aspects of
exception handling, such as early(er) exception handling for
rdmsr_safe() et al.
All in one, as the result of these changes the x86 exception code is
now pretty nice and modern. As an added bonus any regressions in this
code will be early and violent crashes, so if you see any of those,
you'll know whom to blame!"
Fix up trivial conflicts in arch/{mips,x86}/Kconfig files due to nearby
modifications of other core architecture options.
* 'x86-extable-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits)
Revert "x86, extable: Disable presorted exception table for now"
scripts/sortextable: Handle relative entries, and other cleanups
x86, extable: Switch to relative exception table entries
x86, extable: Disable presorted exception table for now
x86, extable: Add _ASM_EXTABLE_EX() macro
x86, extable: Remove open-coded exception table entries in arch/x86/ia32/ia32entry.S
x86, extable: Remove open-coded exception table entries in arch/x86/include/asm/xsave.h
x86, extable: Remove open-coded exception table entries in arch/x86/include/asm/kvm_host.h
x86, extable: Remove the now-unused __ASM_EX_SEC macros
x86, extable: Remove open-coded exception table entries in arch/x86/xen/xen-asm_32.S
x86, extable: Remove open-coded exception table entries in arch/x86/um/checksum_32.S
x86, extable: Remove open-coded exception table entries in arch/x86/lib/usercopy_32.c
x86, extable: Remove open-coded exception table entries in arch/x86/lib/putuser.S
x86, extable: Remove open-coded exception table entries in arch/x86/lib/getuser.S
x86, extable: Remove open-coded exception table entries in arch/x86/lib/csum-copy_64.S
x86, extable: Remove open-coded exception table entries in arch/x86/lib/copy_user_nocache_64.S
x86, extable: Remove open-coded exception table entries in arch/x86/lib/copy_user_64.S
x86, extable: Remove open-coded exception table entries in arch/x86/lib/checksum_32.S
x86, extable: Remove open-coded exception table entries in arch/x86/kernel/test_rodata.c
x86, extable: Remove open-coded exception table entries in arch/x86/kernel/entry_64.S
...
This makes the newly optimized x86 strncpy_from_user clear the final
bytes in the word past the final NUL character, rather than copy them as
the word they were in the source.
NOTE! Unlike the silly semantics of the libc 'strncpy()' function, the
kernel strncpy_from_user() has never cleared all of the end of the
destination buffer. And neither does it do so now: it only clears the
bytes at the end of the last word it copied.
So why make this change at all? It doesn't really cost us anything extra
(we have to calculate the mask to get the length anyway), and it means
that *if* any user actually cares about zeroing the whole buffer, they
can do a "memset()" before the strncpy_from_user(), and we will no
longer write random bytes after the NUL character.
In particular, the buffer contents will now at no point contain random
source data from beyond the end of the string.
In other words, it makes behavior a bit more repeatable at no new cost,
so it's a small cleanup. I've been carrying this as a patch for the
last few weeks or so in my tree (done at the same time the sign error
was fixed in commit 12e993b894), I might as well commit it.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The 'max' range needs to be unsigned, since the size of the user address
space is bigger than 2GB.
We know that 'count' is positive in 'long' (that is checked in the
caller), so we will truncate 'max' down to something that fits in a
signed long, but before we actually do that, that comparison needs to be
done in unsigned.
Bug introduced in commit 92ae03f2ef ("x86: merge 32/64-bit versions of
'strncpy_from_user()' and speed it up"). On x86-64 you can't trigger
this, since the user address space is much smaller than 63 bits, and on
x86-32 it works in practice, since you would seldom hit the strncpy
limits anyway.
I had actually tested the corner-cases, I had only tested them on
x86-64. Besides, I had only worried about the case of a pointer *close*
to the end of the address space, rather than really far away from it ;)
This also changes the "we hit the user-specified maximum" to return
'res', for the trivial reason that gcc seems to generate better code
that way. 'res' and 'count' are the same in that case, so it really
doesn't matter which one we return.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This merges the 32- and 64-bit versions of the x86 strncpy_from_user()
by just rewriting it in C rather than the ancient inline asm versions
that used lodsb/stosb and had been duplicated for (trivial) differences
between the 32-bit and 64-bit versions.
While doing that, it also speeds them up by doing the accesses a word at
a time. Finally, the new routines also properly handle the case of
hitting the end of the address space, which we have never done correctly
before (fs/namei.c has a hack around it for that reason).
Despite all these improvements, it actually removes more lines than it
adds, due to the de-duplication. Also, we no longer export (or define)
the legacy __strncpy_from_user() function (that was defined to not do
the user permission checks), since it's not actually used anywhere, and
the user address space checks are built in to the new code.
Other architecture maintainers have been notified that the old hack in
fs/namei.c will be going away in the 3.5 merge window, in case they
copied the x86 approach of being a bit cavalier about the end of the
address space.
Cc: linux-arch@vger.kernel.org
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Anvin" <hpa@zytor.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull x86/asm changes from Ingo Molnar
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86: Include probe_roms.h in probe_roms.c
x86/32: Print control and debug registers for kerenel context
x86: Tighten dependencies of CPU_SUP_*_32
x86/numa: Improve internode cache alignment
x86: Fix the NMI nesting comments
x86-64: Improve insn scheduling in SAVE_ARGS_IRQ
x86-64: Fix CFI annotations for NMI nesting code
bitops: Add missing parentheses to new get_order macro
bitops: Optimise get_order()
bitops: Adjust the comment on get_order() to describe the size==0 case
x86/spinlocks: Eliminate TICKET_MASK
x86-64: Handle byte-wise tail copying in memcpy() without a loop
x86-64: Fix memcpy() to support sizes of 4Gb and above
x86-64: Fix memset() to support sizes of 4Gb and above
x86-64: Slightly shorten copy_page()
Pull kmap_atomic cleanup from Cong Wang.
It's been in -next for a long time, and it gets rid of the (no longer
used) second argument to k[un]map_atomic().
Fix up a few trivial conflicts in various drivers, and do an "evil
merge" to catch some new uses that have come in since Cong's tree.
* 'kmap_atomic' of git://github.com/congwang/linux: (59 commits)
feature-removal-schedule.txt: schedule the deprecated form of kmap_atomic() for removal
highmem: kill all __kmap_atomic() [swarren@nvidia.com: highmem: Fix ARM build break due to __kmap_atomic rename]
drbd: remove the second argument of k[un]map_atomic()
zcache: remove the second argument of k[un]map_atomic()
gma500: remove the second argument of k[un]map_atomic()
dm: remove the second argument of k[un]map_atomic()
tomoyo: remove the second argument of k[un]map_atomic()
sunrpc: remove the second argument of k[un]map_atomic()
rds: remove the second argument of k[un]map_atomic()
net: remove the second argument of k[un]map_atomic()
mm: remove the second argument of k[un]map_atomic()
lib: remove the second argument of k[un]map_atomic()
power: remove the second argument of k[un]map_atomic()
kdb: remove the second argument of k[un]map_atomic()
udf: remove the second argument of k[un]map_atomic()
ubifs: remove the second argument of k[un]map_atomic()
squashfs: remove the second argument of k[un]map_atomic()
reiserfs: remove the second argument of k[un]map_atomic()
ocfs2: remove the second argument of k[un]map_atomic()
ntfs: remove the second argument of k[un]map_atomic()
...
Commit f0fbf0abc0 ("x86: integrate delay functions") converted
delay_tsc() into a random delay generator for 64 bit. The reason is
that it merged the mostly identical versions of delay_32.c and
delay_64.c. Though the subtle difference of the result was:
static void delay_tsc(unsigned long loops)
{
- unsigned bclock, now;
+ unsigned long bclock, now;
Now the function uses rdtscl() which returns the lower 32bit of the
TSC. On 32bit that's not problematic as unsigned long is 32bit. On 64
bit this fails when the lower 32bit are close to wrap around when
bclock is read, because the following check
if ((now - bclock) >= loops)
break;
evaluated to true on 64bit for e.g. bclock = 0xffffffff and now = 0
because the unsigned long (now - bclock) of these values results in
0xffffffff00000001 which is definitely larger than the loops
value. That explains Tvortkos observation:
"Because I am seeing udelay(500) (_occasionally_) being short, and
that by delaying for some duration between 0us (yep) and 491us."
Make those variables explicitely u32 again, so this works for both 32
and 64 bit.
Reported-by: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org # >= 2.6.27
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix to decode grouped AVX with VEX pp bits which should be
handled as same as last-prefixes. This fixes below warnings
in posttest with CONFIG_CRYPTO_SHA1_SSSE3=y.
Warning: arch/x86/tools/test_get_len found difference at <sha1_transform_avx>:ffffffff810d5fc0
Warning: ffffffff810d6069: c5 f9 73 de 04 vpsrldq $0x4,%xmm6,%xmm0
Warning: objdump says 5 bytes, but insn_get_length() says 4
...
With this change, test_get_len can decode it correctly.
$ arch/x86/tools/test_get_len -v -y
ffffffff810d6069: c5 f9 73 de 04 vpsrldq $0x4,%xmm6,%xmm0
Succeed: decoded and checked 1 instructions
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: yrl.pp-manager.tt@hitachi.com
Link: http://lkml.kernel.org/r/20120210053340.30429.73410.stgit@localhost.localdomain
Signed-off-by: Ingo Molnar <mingo@elte.hu>
