Currently, we get to the slow path for any unaligned access in the
backend, because we effectively preserve the bottom address bits
below the alignment requirement when comparing with the TLB entry,
so any non-0 bit there will cause the compare to fail.
For the same number of instructions, we can instead add the access
size - 1 to the address and stick to clearing all the bottom bits.
That means that normal unaligned accesses will not fallback (the HW
will handle them fine). Only when crossing a page boundary well we
end up having a mismatch because we'll end up pointing to the next
page which cannot possibly be in that same TLB entry.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Message-Id: <1437455978.5809.2.camel@kernel.crashing.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Rather than allow arbitrary shift+trunc, only concern ourselves
with low and high parts. This is all that was being used anyway.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Implement real ext_i32_i64 and extu_i32_i64 ops. They ensure that a
32-bit value is always converted to a 64-bit value and not propagated
through the register allocator or the optimizer.
Cc: Andrzej Zaborowski <balrogg@gmail.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Blue Swirl <blauwirbel@gmail.com>
Cc: Stefan Weil <sw@weilnetz.de>
Acked-by: Claudio Fontana <claudio.fontana@huawei.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>
The op is sometimes named trunc_shr_i32 and sometimes trunc_shr_i64_i32,
and the name in the README doesn't match the name offered to the
frontends.
Always use the long name to make it clear it is a size changing op.
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>
The addition of MO_AMASK means that places that used inverted masks
need to be changed to use positive masks, and places that failed to
mask the intended bits need updating.
Reviewed-by: Yongbok Kim <yongbok.kim@imgtec.com>
Tested-by: Yongbok Kim <yongbok.kim@imgtec.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
This will be used to size the TLB when more than 8 MMU modes are
used by the target. Limitations come from the limited size of
the immediate fields (which sometimes, as in the case of Aarch64,
extend to instructions that shift the immediate).
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <1424436345-37924-2-git-send-email-pbonzini@redhat.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Alexander Graf <agraf@suse.de>
The extra information is not yet used but it is now available.
This requires minor changes through all of the tcg backends.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
At the tcg opcode level, not at the tcg-op.h generator level.
This requires minor changes through all of the tcg backends,
but none of the cpu translators.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
This is less about improved type checking than enabling a
subsequent change to the representation of labels.
Acked-by: Claudio Fontana <claudio.fontana@huawei.com>
Tested-by: Claudio Fontana <claudio.fontana@huawei.com>
Cc: Andrzej Zaborowski <balrogg@gmail.com>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Blue Swirl <blauwirbel@gmail.com>
Cc: Stefan Weil <sw@weilnetz.de>
Reviewed-by: Bastian Koppelmann <kbastian@mail.uni-paderborn.de>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Add back in the support for 64-bit PPC MacOSX hosts that was
broken in the recent merge of the 32-bit and 64-bit TCG backends.
Reported-by: Andreas Färber <andreas.faerber@web.de>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Tested-by: Andreas Färber <andreas.faerber@web.de>
With rt != r0 on loads, we use rt for scratch. If we need an index
register different from base, we can't use rt, but r0 is usable.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Message-id: 1403843160-30332-1-git-send-email-rth@twiddle.net
Tested-by: Cédric Le Goater <clg@fr.ibm.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This can significantly reduce code size for generation of (some)
64-bit constants. With the side effect that we know for a fact
that exit_tb can use the register to good effect.
Tested-by: Tom Musta <tommusta@gmail.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
As a "utility", it only supported ppc, and in a way that other
tcg backends provided directly in tcg-target.h. Removing this
disparity is easier now that the two ppc backends are merged.
Tested-by: Tom Musta <tommusta@gmail.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
The other tcg backends that support 32- and 64-bit modes
use the 32-bit name for the port. Follow suit.
Tested-by: Tom Musta <tommusta@gmail.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Since all backends have been converted, remove the compatibility code.
Acked-by: Claudio Fontana <claudio.fontana@huawei.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
The INDEX_op_call case has just been obsoleted; the mov and movi
cases have not been reachable for years. Attempt to document this
both in each tcg_out_op switch, and via TCG_OPF_NOT_PRESENT.
Because of the TCG_OPF_NOT_PRESENT change, this must be done for
all targets in a single commit.
Signed-off-by: Richard Henderson <rth@twiddle.net>
And use tcg pointer differencing functions as appropriate.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Instead require either mulu2_i32 or muluh_i32. The code in tcg-op.h
already supports looking for both. Previous incomplete conversion?
Signed-off-by: Richard Henderson <rth@twiddle.net>
Most 64-bit targets need to be able to ignore the high bits
of a TCG_TYPE_I32 value.
Suggested-by: Stuart Brady <sdb@zubnet.me.uk>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Static code analyzers complain about signed bitfields with only a single
bit. is_ld is used as a boolean value, so make it bool.
ppc64 already used bool for the 2nd argument is_ld of the local function
add_qemu_ldst_label. Modify all other TCG targets to do follow this
example.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Step two in the transition, adding the new ldst opcodes. Keep the old
opcodes around until all backends support the new opcodes.
Signed-off-by: Richard Henderson <rth@twiddle.net>
The fix is that sparc has so many mmu modes that the last one overflowed
the 16-bit signed offset we assumed would fit. Handle this, and check
the new assumption at compile time.
Load the tlb addend earlier for the fast path.
Remove the explicit address + addend and make use of index addressing.
Adjust constraints for qemu_ld64 such that we don't clobber the address
register or tlb addend before loading both values.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Coding style fixes. Use TCGReg enumeration values instead of raw
numbers. Don't needlessly pull the whole TCGLabelQemuLdst struct
into local variables. Less conditional compilation.
No functional changes.
Signed-off-by: Richard Henderson <rth@twiddle.net>
While these are rare from code that's been through the optimizer,
it's not uncommon within the tcg backend.
Signed-off-by: Richard Henderson <rth@twiddle.net>
These use a 32-bit load-of-immediate to save a mflr+addi+mtlr sequence.
Tested with a Windows 98 guest (pretty much the most recent thing I
could run on my PPC machine) and kvm-unit-tests's sieve.flat. The
speed up for sieve.flat is as high as 10% for qemu-system-i386, 25%
(no kidding) for qemu-system-x86_64 on my PowerBook G4.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
For the AIX ABI, the function pointer and small area pointer need
to be loaded in the trampoline. The trampoline instead is called
with a normal BL instruction.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
The _cmmu helpers can be moved to exec-all.h. The helpers that are
used from TCG will shortly need access to tcg_target_long so move
their declarations into tcg.h.
This requires minor include adjustments to all TCG backends.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Use them in places where mulu2 and muls2 are used.
Optimize mulx2 with dead low part to mulxh.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>
There are several hosts with only a "div" insn. Remainder is computed
manually from the quotient and inputs. We can do this generically.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Commit 0b0d3320db (TCG: Final globals
clean-up) moved code_gen_prologue but forgot to update ppc code.
This broke the build on 32-bit ppc. ppc64 is unaffected.
Cc: Evgeny Voevodin <evgenyvoevodin@gmail.com>
Cc: Blue Swirl <blauwirbel@gmail.com>
Signed-off-by: Andreas Färber <andreas.faerber@web.de>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
mmu access looks something like:
<check tlb>
if miss goto slow_path
<fast path>
done:
...
; end of the TB
slow_path:
<pre process>
mr r3, r27 ; move areg0 to r3
; (r3 holds the first argument for all the PPC32 ABIs)
<call mmu_helper>
b $+8
.long done
<post process>
b done
On ppc32 <call mmu_helper> is:
(SysV and Darwin)
mmu_helper is most likely not within direct branching distance from
the call site, necessitating
a. moving 32 bit offset of mmu_helper into a GPR ; 8 bytes
b. moving GPR to CTR/LR ; 4 bytes
c. (finally) branching to CTR/LR ; 4 bytes
r3 setting - 4 bytes
call - 16 bytes
dummy jump over retaddr - 4 bytes
embedded retaddr - 4 bytes
Total overhead - 28 bytes
(PowerOpen (AIX))
a. moving 32 bit offset of mmu_helper's TOC into a GPR1 ; 8 bytes
b. loading 32 bit function pointer into GPR2 ; 4 bytes
c. moving GPR2 to CTR/LR ; 4 bytes
d. loading 32 bit small area pointer into R2 ; 4 bytes
e. (finally) branching to CTR/LR ; 4 bytes
r3 setting - 4 bytes
call - 24 bytes
dummy jump over retaddr - 4 bytes
embedded retaddr - 4 bytes
Total overhead - 36 bytes
Following is done to trim the code size of slow path sections:
In tcg_target_qemu_prologue trampolines are emitted that look like this:
trampoline:
mfspr r3, LR
addi r3, 4
mtspr LR, r3 ; fixup LR to point over embedded retaddr
mr r3, r27
<jump mmu_helper> ; tail call of sorts
And slow path becomes:
slow_path:
<pre process>
<call trampoline>
.long done
<post process>
b done
call - 4 bytes (trampoline is within code gen buffer
and most likely accessible via
direct branch)
embedded retaddr - 4 bytes
Total overhead - 8 bytes
In the end the icache pressure is decreased by 20/28 bytes at the cost
of an extra jump to trampoline and adjusting LR (to skip over embedded
retaddr) once inside.
Signed-off-by: malc <av1474@comtv.ru>
