Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but
the destination register must be the same as one of the source
registers.
We defer the decode of the size in bit 28 to the individual insn
patterns rather than doing it in the format, because otherwise we
would have a single insn pattern that overlapped with two groups (eg
VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn
patterns per insn seems clearer than a complex multilevel nesting
of overlapping and non-overlapping groups.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Implement the MVE VCMUL and VCMLA insns.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Implement the MVE VFMA and VFMS insns.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Implement the MVE VCADD insn. Note that here the size bit is the
opposite sense to the other 2-operand fp insns.
We don't check for the sz == 1 && Qd == Qm UNPREDICTABLE case,
because that would mean we can't use the DO_2OP_FP macro in
translate-mve.c.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Implement more simple 2-operand floating point MVE insns.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Implement the MVE VADD (floating-point) insn. Handling of this is
similar to the 2-operand integer insns, except that we must take care
to only update the floating point exception status if the least
significant bit of the predicate mask for each element is active.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Currently we rely on all the callsites of cpsr_write() to rebuild the
cached hflags if they change one of the CPSR bits which we use as a
TB flag and cache in hflags. This is a bit awkward when we want to
change the set of CPSR bits that we cache, because it means we need
to re-audit all the cpsr_write() callsites to see which flags they
are writing and whether they now need to rebuild the hflags.
Switch instead to making cpsr_write() call arm_rebuild_hflags()
itself if one of the bits being changed is a cached bit.
We don't do the rebuild for the CPSRWriteRaw write type, because that
kind of write is generally doing something special anyway. For the
CPSRWriteRaw callsites in the KVM code and inbound migration we
definitely don't want to recalculate the hflags; the callsites in
boot.c and arm-powerctl.c have to do a rebuild-hflags call themselves
anyway because of other CPU state changes they make.
This allows us to drop explicit arm_rebuild_hflags() calls in a
couple of places where the only reason we needed to call it was the
CPSR write.
This fixes a bug where we were incorrectly failing to rebuild hflags
in the code path for a gdbstub write to CPSR, which meant that you
could make QEMU assert by breaking into a running guest, altering the
CPSR to change the value of, for example, CPSR.E, and then
continuing.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210817201843.3829-1-peter.maydell@linaro.org
In v7A, the HSTR register has a TJDBX bit which traps NS EL0/EL1
access to the JOSCR and JMCR trivial Jazelle registers, and also BXJ.
Implement these traps. In v8A this HSTR bit doesn't exist, so don't
trap for v8A CPUs.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210816180305.20137-3-peter.maydell@linaro.org
In v7, the HSTR register has a TTEE bit which allows EL0/EL1 accesses
to the Thumb2EE TEECR and TEEHBR registers to be trapped to the
hypervisor. Implement these traps.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210816180305.20137-2-peter.maydell@linaro.org
KVM cannot support multiple address spaces per CPU; if you try to
create more than one then cpu_address_space_init() will assert.
In the Arm CPU realize function, detect the configurations which
would cause us to need more than one AS, and cleanly fail the
realize rather than blundering on into the assertion. This
turns this:
$ qemu-system-aarch64 -enable-kvm -display none -cpu max -machine raspi3b
qemu-system-aarch64: ../../softmmu/physmem.c:747: cpu_address_space_init: Assertion `asidx == 0 || !kvm_enabled()' failed.
Aborted
into:
$ qemu-system-aarch64 -enable-kvm -display none -machine raspi3b
qemu-system-aarch64: Cannot enable KVM when guest CPU has EL3 enabled
and this:
$ qemu-system-aarch64 -enable-kvm -display none -machine mps3-an524
qemu-system-aarch64: ../../softmmu/physmem.c:747: cpu_address_space_init: Assertion `asidx == 0 || !kvm_enabled()' failed.
Aborted
into:
$ qemu-system-aarch64 -enable-kvm -display none -machine mps3-an524
qemu-system-aarch64: Cannot enable KVM when using an M-profile guest CPU
Fixes: https://gitlab.com/qemu-project/qemu/-/issues/528
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210816135842.25302-3-peter.maydell@linaro.org
Future CPU types may specify which vector lengths are supported.
We can apply nearly the same logic to validate those lengths
as we do for KVM's supported vector lengths. We merge the code
where we can, but unfortunately can't completely merge it because
KVM requires all vector lengths, power-of-two or not, smaller than
the maximum enabled length to also be enabled. The architecture
only requires all the power-of-two lengths, though, so TCG will
only enforce that.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210823160647.34028-5-drjones@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Now that we have an ARMCPU member sve_vq_supported we no longer
need the local kvm_supported bitmap for KVM's supported vector
lengths.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210823160647.34028-4-drjones@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
bitmap_clear() only clears the given range. While the given
range should be sufficient in this case we might as well be
100% sure all bits are zeroed by using bitmap_zero().
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210823160647.34028-3-drjones@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Allow CPUs that support SVE to specify which SVE vector lengths they
support by setting them in this bitmap. Currently only the 'max' and
'host' CPU types supports SVE and 'host' requires KVM which obtains
its supported bitmap from the host. So, we only need to initialize the
bitmap for 'max' with TCG. And, since 'max' should support all SVE
vector lengths we simply fill the bitmap. Future CPU types may have
less trivial maps though.
Signed-off-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210823160647.34028-2-drjones@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
As per commit 5626f8c6d4 ("rcu: Add automatically released rcu_read_lock
variants"), RCU_READ_LOCK_GUARD() should be used instead of
rcu_read_{un}lock().
Signed-off-by: Hamza Mahfooz <someguy@effective-light.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 20210727235201.11491-1-someguy@effective-light.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Unlike A-profile, for M-profile the UDIV and SDIV insns can be
configured to raise an exception on division by zero, using the CCR
DIV_0_TRP bit.
Implement support for setting this bit by making the helper functions
raise the appropriate exception.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210730151636.17254-3-peter.maydell@linaro.org
We're about to make a code change to the sdiv and udiv helper
functions, so first fix their indentation and coding style.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210730151636.17254-2-peter.maydell@linaro.org
Implement the MVE interleaving load/store functions VLD2, VLD4, VST2
and VST4. VLD2 loads 16 bytes of data from memory and writes to 2
consecutive Qregs; VLD4 loads 16 bytes of data from memory and writes
to 4 consecutive Qregs. The 'pattern' field in the encoding
determines the offset into memory which is accessed and also which
elements in the Qregs are written to. (The intention is that a
sequence of four consecutive VLD4 with different pattern values
performs a complete de-interleaving load of 64 bytes into all
elements of the 4 Qregs.) VST2 and VST4 do the same, but for stores.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VLDR/VSTR insns which do scatter-gather using base
addresses from Qm plus or minus an immediate offset (possibly with
writeback). Note that writeback is not predicated but it does have
to honour ECI state, so we have to add an eci_mask check to the
VSTR_SG macros (the VLDR_SG macros already needed this to be able
to distinguish "skip beat" from "set predicated element to 0").
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE gather-loads and scatter-stores which
form the address by adding a base value from a scalar
register to an offset in each element of a vector.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VCTP insn, which sets the VPR.P0 predicate bits so
as to predicate any element at index Rn or greater is predicated. As
with VPNOT, this insn itself is predicable and subject to beatwise
execution.
The calculation of the mask is the same as is used to determine
ltpmask in mve_element_mask(), but we precalculate masklen in
generated code to avoid having to have 4 helpers specialized by size.
We put the decode line in with the low-overhead-loop insns in
t32.decode because it's logically part of that collection of insn
patterns, even though it is an MVE only insn.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VPNOT insn, which inverts the bits in VPR.P0
(subject to both predication and to beatwise execution).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VMOV forms that move data between 2 general-purpose
registers and 2 32-bit lanes in a vector register.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VMAXA and VMINA insns, which take the absolute
value of the signed elements in the input vector and then accumulate
the unsigned max or min into the destination vector.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE 1-operand saturating operations VQABS and VQNEG.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE saturating doubling multiply accumulate insns
VQDMLAH, VQRDMLAH, VQDMLASH and VQRDMLASH. These perform a multiply,
double, add the accumulator shifted by the element size, possibly
round, saturate to twice the element size, then take the high half of
the result. The *MLAH insns do vector * scalar + vector, and the
*MLASH insns do vector * vector + scalar.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VMLA insn, which multiplies a vector by a scalar
and accumulates into another vector.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and
VMLSLDAV insns already implemented, these accumulate multiplied
vector elements; but they accumulate a 32-bit result rather than a
64-bit one.
Note that these encodings overlap with what would be RdaHi=0b111 for
VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
The MVEGenDualAccOpFn is a bit misnamed, since it is used for
the "long dual accumulate" operations that use a 64-bit
accumulator. Rename it to MVEGenLongDualAccOpFn so we can
use the former name for the 32-bit accumulator insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN.
These take a double-width input, narrow it (possibly saturating) and
store the result to either the top or bottom half of the output
element.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VABAV insn, which computes absolute differences
between elements of two vectors and accumulates the result into
a general purpose register.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE integer min/max across vector insns
VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum
from the vector elements and a general purpose register,
and store the maximum back into the general purpose
register.
These insns overlap with VRMLALDAVH (they use what would
be RdaHi=0b110).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
All the users of the vmlaldav formats have an 'x bit in bit 12 and an
'a' bit in bit 5; move these to the format rather than specifying them
in each insn pattern.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE instructions which perform shifts by a scalar.
These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the
shift amount in a general purpose register and shift every element in
the vector by that amount.
Mostly we can reuse the helper functions for shift-by-immediate; we
do need two new helpers for VQRSHL.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VMLAS insn, which multiplies a vector by a vector
and adds a scalar.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VPSEL insn, which sets each byte of the destination
vector Qd to the byte from either Qn or Qm depending on the value of
the corresponding bit in VPR.P0.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE integer vector comparison instructions that compare
each element against a scalar from a general purpose register. These
are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)"
encodings T4, T5 and T6.
We have to move the decodetree pattern for VPST, because it
overlaps with VCMP T4 with size = 0b11.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE integer vector comparison instructions. These are
"VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings
T1, T2 and T3.
These insns compare corresponding elements in each vector, and update
the VPR.P0 predicate bits with the results of the comparison. VPT
also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively
"VCMP then VPST".
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Factor out the "generate code to update VPR.MASK01/MASK23" part of
trans_VPST(); we are going to want to reuse it for the VPT insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP,
VIWDUP and VDWDUP. These fill the elements of a vector with
successively incrementing values, starting at the offset specified in
a general purpose register. The final value of the offset is written
back to this register. The wrapping variants take a second general
purpose register which specifies the point where the count should
wrap back to 0.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Implement the MVE VMULL (polynomial) insn. Unlike Neon, this comes
in two flavours: 8x8->16 and a 16x16->32. Also unlike Neon, the
inputs are in either the low or the high half of each double-width
element.
The assembler for this insn indicates the size with "P8" or "P16",
encoded into bit 28 as size = 0 or 1. We choose to follow the
same encoding as VQDMULL and decode this into a->size as MO_16
or MO_32 indicating the size of the result elements. This then
carries through to the helper function names where it then
matches up with the existing pmull_h() which does an 8x8->16
operation and a new pmull_w() which does the 16x16->32.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
For vector loads, predicated elements are zeroed, instead of
retaining their previous values (as happens for most data
processing operations). This means we need to distinguish
"beat not executed due to ECI" (don't touch destination
element) from "beat executed but predicated out" (zero
destination element).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
We were not paying attention to the ECI state when advancing the VPT
state. Architecturally, VPT state advance happens for every beat
(see the pseudocode VPTAdvance()), so on every beat the 4 bits of
VPR.P0 corresponding to the current beat are inverted if required,
and at the end of beats 1 and 3 the VPR MASK fields are updated.
This means that if the ECI state says we should not be executing all
4 beats then we need to skip some of the updating of the VPR that we
currently do in mve_advance_vpt().
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
In some situations we need a mask telling us which parts of the
vector correspond to beats that are not being executed because of
ECI, separately from the combined "which bytes are predicated away"
mask. Factor this mask calculation out of mve_element_mask() into
its own function.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
In mve_element_mask(), we calculate a mask for tail predication which
should have a number of 1 bits based on the value of LR. However,
our MAKE_64BIT_MASK() macro has undefined behaviour when passed a
zero length. Special case this to give the all-zeroes mask we
require.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
We got an edge case wrong in the 48-bit SQRSHRL implementation: if
the shift is to the right, although it always makes the result
smaller than the input value it might not be within the 48-bit range
the result is supposed to be if the input had some bits in [63..48]
set and the shift didn't bring all of those within the [47..0] range.
Handle this similarly to the way we already do for this case in
do_uqrshl48_d(): extend the calculated result from 48 bits,
and return that if not saturating or if it doesn't change the
result; otherwise fall through to return a saturated value.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
In do_sqrshl48_d() and do_uqrshl48_d() we got some of the edge
cases wrong and failed to saturate correctly:
(1) In do_sqrshl48_d() we used the same code that do_shrshl_bhs()
does to obtain the saturated most-negative and most-positive 48-bit
signed values for the large-shift-left case. This gives (1 << 47)
for saturate-to-most-negative, but we weren't sign-extending this
value to the 64-bit output as the pseudocode requires.
(2) For left shifts by less than 48, we copied the "8/16 bit" code
from do_sqrshl_bhs() and do_uqrshl_bhs(). This doesn't do the right
thing because it assumes the C type we're working with is at least
twice the number of bits we're saturating to (so that a shift left by
bits-1 can't shift anything off the top of the value). This isn't
true for bits == 48, so we would incorrectly return 0 rather than the
most-positive value for situations like "shift (1 << 44) right by
20". Instead check for saturation by doing the shift and signextend
and then testing whether shifting back left again gives the original
value.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
In the MVE helpers for the narrowing operations (DO_VSHRN and
DO_VSHRN_SAT) we were using the wrong bits of the predicate mask for
the 'top' versions of the insn. This is because the loop works over
the double-sized input elements and shifts the predicate mask by that
many bits each time, but when we write out the half-sized output we
must look at the mask bits for whichever half of the element we are
writing to.
Correct this by shifting the whole mask right by ESIZE bits for the
'top' insns. This allows us also to simplify the saturation bit
checking (where we had noticed that we needed to look at a different
mask bit for the 'top' insn.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
A cut-and-paste error meant we handled signed VADDV like
unsigned VADDV; fix the type used.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
In the MVE shift-and-insert insns, we special case VSLI by 0
and VSRI by <dt>. VSRI by <dt> means "don't update the destination",
which is what we've implemented. However VSLI by 0 is "set
destination to the input", so we don't want to use the same
special-casing that we do for VSRI by <dt>.
Since the generic logic gives the right answer for a shift
by 0, just use that.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Include the MVE VPR register value in the CPU dumps produced by
arm_cpu_dump_state() if we are printing FPU information. This
makes it easier to interpret debug logs when predication is
active.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Although the architecture doesn't define it as an alias, VMOVL
(vector move long) is encoded as a VSHLL with a zero shift.
Add a comment in the decode file noting that we handle VMOVL
as part of VSHLL.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Mirror the behavour of /proc/sys/abi/sve_default_vector_length
under the real linux kernel. We have no way of passing along
a real default across exec like the kernel can, but this is a
decent way of adjusting the startup vector length of a process.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/482
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20210723203344.968563-4-richard.henderson@linaro.org
[PMM: tweaked docs formatting, document -1 special-case,
added fixup patch from RTH mentioning QEMU's maximum veclen.]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Rename from sve_zcr_get_valid_len and make accessible
from outside of helper.c.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20210723203344.968563-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Currently, our only caller is sve_zcr_len_for_el, which has
already masked the length extracted from ZCR_ELx, so the
masking done here is a nop. But we will shortly have uses
from other locations, where the length will be unmasked.
Saturate the length to ARM_MAX_VQ instead of truncating to
the low 4 bits.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20210723203344.968563-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
For M-profile, we weren't reporting alignment faults triggered by the
generic TCG code correctly to the guest. These get passed into
arm_v7m_cpu_do_interrupt() as an EXCP_DATA_ABORT with an A-profile
style exception.fsr value of 1. We didn't check for this, and so
they fell through into the default of "assume this is an MPU fault"
and were reported to the guest as a data access violation MPU fault.
Report these alignment faults as UsageFaults which set the UNALIGNED
bit in the UFSR.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210723162146.5167-4-peter.maydell@linaro.org
In do_v7m_exception_exit(), we perform various checks as part of
performing the exception return. If one of these checks fails, the
architecture requires that we take an appropriate exception on the
existing stackframe. We implement this by calling
v7m_exception_taken() to set up to take the new exception, and then
immediately returning from do_v7m_exception_exit() without proceeding
any further with the unstack-and-exception-return process.
In a couple of checks that are new in v8.1M, we forgot the "return"
statement, with the effect that if bad code in the guest tripped over
these checks we would set up to take a UsageFault exception but then
blunder on trying to also unstack and return from the original
exception, with the probable result that the guest would crash.
Add the missing return statements.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210723162146.5167-3-peter.maydell@linaro.org
For M-profile, unlike A-profile, the low 2 bits of SP are defined to be
RES0H, which is to say that they must be hardwired to zero so that
guest attempts to write non-zero values to them are ignored.
Implement this behaviour by masking out the low bits:
* for writes to r13 by the gdbstub
* for writes to any of the various flavours of SP via MSR
* for writes to r13 via store_reg() in generated code
Note that all the direct uses of cpu_R[] in translate.c are in places
where the register is definitely not r13 (usually because that has
been checked for as an UNDEFINED or UNPREDICTABLE case and handled as
UNDEF).
All the other writes to regs[13] in C code are either:
* A-profile only code
* writes of values we can guarantee to be aligned, such as
- writes of previous-SP-value plus or minus a 4-aligned constant
- writes of the value in an SP limit register (which we already
enforce to be aligned)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210723162146.5167-2-peter.maydell@linaro.org
The hook is now unused, with breakpoints checked outside translation.
Tested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reuse the code at the bottom of helper_check_breakpoints,
which is what we currently call from *_tr_breakpoint_check.
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Always provide the atomic interface using TCGMemOpIdx oi
and uintptr_t retaddr. Rename from helper_* to cpu_* so
as to (mostly) match the exec/cpu_ldst.h functions, and
to emphasize that they are not callable from TCG directly.
Tested-by: Cole Robinson <crobinso@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
The Neon and SVE decoders use private 'plus1' functions to implement
"add one" for the !function decoder syntax. We have a generic
"plus_1" function in translate.h, so use that instead.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210715095341.701-1-peter.maydell@linaro.org
The functions vmsa_ttbcr_write and vmsa_ttbcr_raw_write expect
the offset to be for the complete TCR structure, not the offset
to the low 32-bits of a uint64_t. Using offsetoflow32 in this
case breaks big-endian hosts.
For TTBCR2, we do want the high 32-bits of a uint64_t.
Use cp15.tcr_el[*].raw_tcr as the offsetofhigh32 argument to
clarify this.
Buglink: https://gitlab.com/qemu-project/qemu/-/issues/187
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210709230621.938821-2-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Just use translator_use_goto_tb directly at the one call site,
rather than maintaining a local wrapper.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
We have not needed to end a TB for I/O since ba3e792669
("icount: clean up cpu_can_io at the entry to the block"),
and gdbstub singlestep is handled by the generic function.
Drop the unused 'n' argument to use_goto_tb.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Using gen_goto_tb directly misses the single-step check.
Let the branch or debug exception be emitted by arm_tr_tb_stop.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
The root trace-events only declares a single TCG event:
$ git grep -w tcg trace-events
trace-events:115:# tcg/tcg-op.c
trace-events:137:vcpu tcg guest_mem_before(TCGv vaddr, uint16_t info) "info=%d", "vaddr=0x%016"PRIx64" info=%d"
and only a tcg/tcg-op.c uses it:
$ git grep -l trace_guest_mem_before_tcg
tcg/tcg-op.c
therefore it is pointless to include "trace-tcg.h" in each target
(because it is not used). Remove it.
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210629050935.2570721-1-f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Add a target-specific Kconfig. We need the definitions in Kconfig so
the minikconf tool can verify they exits. However CONFIG_FOO is only
enabled for target foo via the meson.build rules.
Two architecture have a particularity, ARM and MIPS. As their
translators have been split you can potentially build a plain 32 bit
build along with a 64-bit version including the 32-bit subset.
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210131111316.232778-6-f4bug@amsat.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20210707131744.26027-2-alex.bennee@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Nick Hudson <hnick@vmware.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Implement the MVE shifts by register, which perform
shifts on a single general-purpose register.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-19-peter.maydell@linaro.org
Implement the MVE shifts by immediate, which perform shifts
on a single general-purpose register.
These patterns overlap with the long-shift-by-immediates,
so we have to rearrange the grouping a little here.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-18-peter.maydell@linaro.org
Implement the MVE long shifts by register, which perform shifts on a
pair of general-purpose registers treated as a 64-bit quantity, with
the shift count in another general-purpose register, which might be
either positive or negative.
Like the long-shifts-by-immediate, these encodings sit in the space
that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15.
Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and
also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases),
we have to move the CSEL pattern into the same decodetree group.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-17-peter.maydell@linaro.org
The MVE extension to v8.1M includes some new shift instructions which
sit entirely within the non-coprocessor part of the encoding space
and which operate only on general-purpose registers. They take up
the space which was previously UNPREDICTABLE MOVS and ORRS encodings
with Rm == 13 or 15.
Implement the long shifts by immediate, which perform shifts on a
pair of general-purpose registers treated as a 64-bit quantity, with
an immediate shift count between 1 and 32.
Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for
the Rm==13,15 case, we need to explicitly emit code to UNDEF for the
cases where v8.1M now requires that. (Trying to change MOVS and ORRS
is too difficult, because the functions that generate the code are
shared between a dozen different kinds of arithmetic or logical
instruction for all A32, T16 and T32 encodings, and for some insns
and some encodings Rm==13,15 are valid.)
We make the helper functions we need for UQSHLL and SQSHLL take
a 32-bit value which the helper casts to int8_t because we'll need
these helpers also for the shift-by-register insns, where the shift
count might be < 0 or > 32.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-16-peter.maydell@linaro.org
Implement the MVE VADDLV insn; this is similar to VADDV, except
that it accumulates 32-bit elements into a 64-bit accumulator
stored in a pair of general-purpose registers.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-15-peter.maydell@linaro.org
Implement the MVE VSHLC insn, which performs a shift left of the
entire vector with carry in bits provided from a general purpose
register and carry out bits written back to that register.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-14-peter.maydell@linaro.org
Implement the MVE saturating shift-right-and-narrow insns
VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN.
do_srshr() is borrowed from sve_helper.c.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-13-peter.maydell@linaro.org
Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN.
do_urshr() is borrowed from sve_helper.c.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-12-peter.maydell@linaro.org
Implement the MVE VSRI and VSLI insns, which perform a
shift-and-insert operation.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-11-peter.maydell@linaro.org
Implement the MVE VHLL (vector shift left long) insn. This has two
encodings: the T1 encoding is the usual shift-by-immediate format,
and the T2 encoding is a special case where the shift count is always
equal to the element size.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
Implement the MVE vector shift right by immediate insns VSHRI and
VRSHRI. As with Neon, we implement these by using helper functions
which perform left shifts but allow negative shift counts to indicate
right shifts.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-9-peter.maydell@linaro.org
Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL
and VQSHLU.
The size-and-immediate encoding here is the same as Neon, and we
handle it the same way neon-dp.decode does.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-8-peter.maydell@linaro.org
Implement the MVE logical-immediate insns (VMOV, VMVN,
VORR and VBIC). These have essentially the same encoding
as their Neon equivalents, and we implement the decode
in the same way.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
Use dup_const() instead of bitfield_replicate() in
disas_simd_mod_imm().
(We can't replace the other use of bitfield_replicate() in this file,
in logic_imm_decode_wmask(), because that location needs to handle 2
and 4 bit elements, which dup_const() cannot.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-6-peter.maydell@linaro.org
The A64 AdvSIMD modified-immediate grouping uses almost the same
constant encoding that A32 Neon does; reuse asimd_imm_const() (to
which we add the AArch64-specific case for cmode 15 op 1) instead of
reimplementing it all.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-5-peter.maydell@linaro.org
The function asimd_imm_const() in translate-neon.c is an
implementation of the pseudocode AdvSIMDExpandImm(), which we will
also want for MVE. Move the implementation to translate.c, with a
prototype in translate.h.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-4-peter.maydell@linaro.org
The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH
insns had some bugs:
* the 32x32 multiply of elements was being done as 32x32->32,
not 32x32->64
* we were incorrectly maintaining the accumulator in its full
72-bit form across all 4 beats of the insn; in the pseudocode
it is squashed back into the 64 bits of the RdaHi:RdaLo
registers after each beat
In particular, fixing the second of these allows us to recast
the implementation to avoid 128-bit arithmetic entirely.
Since the element size here is always 4, we can also drop the
parameterization of ESIZE to make the code a little more readable.
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-3-peter.maydell@linaro.org
In do_ldst(), the calculation of the offset needs to be based on the
size of the memory access, not the size of the elements in the
vector. This meant we were getting it wrong for the widening and
narrowing variants of the various VLDR and VSTR insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210628135835.6690-2-peter.maydell@linaro.org
If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute
FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will
assert due to fpst->default_nan_mode being set.
To avoid this, we check to see what NaN mode we're running in before we call
floatxx_silence_nan().
Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
The new bswap flags can implement the semantics exactly.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
We can eliminate the requirement for a zero-extended output,
because the following store will ignore any garbage high bits.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
For the sf version, we are performing two 32-bit bswaps
in either half of the register. This is equivalent to
performing one 64-bit bswap followed by a rotate.
For the non-sf version, we can remove TCG_BSWAP_IZ
and the preceding zero-extension.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Implement the new semantics in the fallback expansion.
Change all callers to supply the flags that keep the
semantics unchanged locally.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
MTE3 introduces an asymmetric tag checking mode, in which loads are
checked synchronously and stores are checked asynchronously. Add
support for it.
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210616195614.11785-1-pcc@google.com
[PMM: Add line to emulation.rst]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In a CPU with MVE, the VMOV (vector lane to general-purpose register)
and VMOV (general-purpose register to vector lane) insns are not
predicated, but they are subject to beatwise execution if they
are not in an IT block.
Since our implementation always executes all 4 beats in one tick,
this means only that we need to handle PSR.ECI:
* we must do the usual check for bad ECI state
* we must advance ECI state if the insn succeeds
* if ECI says we should not be executing the beat corresponding
to the lane of the vector register being accessed then we
should skip performing the move
Note that if PSR.ECI is non-zero then we cannot be in an IT block.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-45-peter.maydell@linaro.org
Implement the MVE VADDV insn, which performs an addition
across vector lanes.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-44-peter.maydell@linaro.org
Implement the MVE VHCADD insn, which is similar to VCADD
but performs a halving step. This one overlaps with VADC.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-43-peter.maydell@linaro.org
Implement the MVE VCADD insn, which performs a complex add with
rotate. Note that the size=0b11 encoding is VSBC.
The architecture grants some leeway for the "destination and Vm
source overlap" case for the size MO_32 case, but we choose not to
make use of it, instead always calculating all 16 bytes worth of
results before setting the destination register.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-42-peter.maydell@linaro.org
Implement the MVE VADC and VSBC insns. These perform an
add-with-carry or subtract-with-carry of the 32-bit elements in each
lane of the input vectors, where the carry-out of each add is the
carry-in of the next. The initial carry input is either 1 or is from
FPSCR.C; the carry out at the end is written back to FPSCR.C.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-41-peter.maydell@linaro.org
Implement the MVE VRHADD insn, which performs a rounded halving
addition.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-40-peter.maydell@linaro.org
Implement the vector form of the MVE VQDMULL insn.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-39-peter.maydell@linaro.org
Implement the MVE VQDMLSDH and VQRDMLSDH insns, which are
like VQDMLADH and VQRDMLADH except that products are subtracted
rather than added.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-38-peter.maydell@linaro.org
Implement the MVE VQDMLADH and VQRDMLADH insns. These multiply
elements, and then add pairs of products, double, possibly round,
saturate and return the high half of the result.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-37-peter.maydell@linaro.org
Implement the MV VQRSHL (vector) insn. Again, the code to perform
the actual shifts is borrowed from neon_helper.c.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-34-peter.maydell@linaro.org
Implement the MVE VQSHL insn (encoding T4, which is the
vector-shift-by-vector version).
The DO_SQSHL_OP and DO_UQSHL_OP macros here are derived from
the neon_helper.c code for qshl_u{8,16,32} and qshl_s{8,16,32}.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-33-peter.maydell@linaro.org
Implement the vector forms of the MVE VQADD and VQSUB insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-32-peter.maydell@linaro.org
Implement the vector forms of the MVE VQDMULH and VQRDMULH insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-31-peter.maydell@linaro.org
Implement the MVE VQDMULL scalar insn. This multiplies the top or
bottom half of each element by the scalar, doubles and saturates
to a double-width result.
Note that this encoding overlaps with VQADD and VQSUB; it uses
what in VQADD and VQSUB would be the 'size=0b11' encoding.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-30-peter.maydell@linaro.org
Implement the MVE VQDMULH and VQRDMULH scalar insns, which multiply
elements by the scalar, double, possibly round, take the high half
and saturate.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-29-peter.maydell@linaro.org
Implement the MVE VQADD and VQSUB insns, which perform saturating
addition of a scalar to each element. Note that individual bytes of
each result element are used or discarded according to the predicate
mask, but FPSCR.QC is only set if the predicate mask for the lowest
byte of the element is set.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-28-peter.maydell@linaro.org
Implement the MVE VPST insn, which sets the predicate mask
fields in the VPR to the immediate value encoded in the insn.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-27-peter.maydell@linaro.org
Implement the MVE VBRSR insn, which reverses a specified
number of bits in each element, setting the rest to zero.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-26-peter.maydell@linaro.org
Implement the scalar variants of the MVE VHADD and VHSUB insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-25-peter.maydell@linaro.org
Implement the scalar forms of the MVE VSUB and VMUL insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-24-peter.maydell@linaro.org
Implement the scalar form of the MVE VADD insn. This takes the
scalar operand from a general purpose register.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-23-peter.maydell@linaro.org
Implement the MVE VRMLALDAVH and VRMLSLDAVH insns, which accumulate
the results of a rounded multiply of pairs of elements into a 72-bit
accumulator, returning the top 64 bits in a pair of general purpose
registers.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-22-peter.maydell@linaro.org
Implement the MVE insn VMLSLDAV, which multiplies source elements,
alternately adding and subtracting them, and accumulates into a
64-bit result in a pair of general purpose registers.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-21-peter.maydell@linaro.org
Implement the MVE VMLALDAV insn, which multiplies pairs of integer
elements, accumulating them into a 64-bit result in a pair of
general-purpose registers.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-20-peter.maydell@linaro.org
Implement the MVE VMULL insn, which multiplies two single
width integer elements to produce a double width result.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-19-peter.maydell@linaro.org
Implement MVE VHADD and VHSUB insns, which perform an addition
or subtraction and then halve the result.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-18-peter.maydell@linaro.org
Implement the MVE VABD insn.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-17-peter.maydell@linaro.org
Implement the MVE VMAX and VMIN insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-16-peter.maydell@linaro.org
Implement the MVE VRMULH insn, which performs a rounding multiply
and then returns the high half.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-15-peter.maydell@linaro.org
Implement the MVE VMULH insn, which performs a vector
multiply and returns the high half of the result.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-14-peter.maydell@linaro.org
Implement the MVE VADD, VSUB and VMUL insns.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-13-peter.maydell@linaro.org
Implement the MVE vector logical operations operating
on two registers.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-12-peter.maydell@linaro.org
Implement the MVE VDUP insn, which duplicates a value from
a general-purpose register into every lane of a vector
register (subject to predication).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-11-peter.maydell@linaro.org
Implement the MVE VNEG insn (both integer and floating point forms).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-9-peter.maydell@linaro.org
Implement the MVE VABS functions (both integer and floating point).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-8-peter.maydell@linaro.org
Implement the MVE VMVN(register) operation. Note that for
predication this operation is byte-by-byte.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-7-peter.maydell@linaro.org
Implement the MVE instructions VREV16, VREV32 and VREV64.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-6-peter.maydell@linaro.org
Implement the MVE VCLS insn.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-5-peter.maydell@linaro.org
Implement the MVE VCLZ insn (and the necessary machinery
for MVE 1-input vector ops).
Note that for non-load instructions predication is always performed
at a byte level granularity regardless of element size (R_ZLSJ),
and so the masking logic here differs from that used in the VLDR
and VSTR helpers.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
Implement the variants of MVE VLDR (encodings T1, T2) which perform
"widening" loads where bytes or halfwords are loaded from memory and
zero or sign-extended into halfword or word length vector elements,
and the narrowing MVE VSTR (encodings T1, T2) where bytes or
halfwords are stored from halfword or word elements.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-3-peter.maydell@linaro.org
Implement the forms of the MVE VLDR and VSTR insns which perform
non-widening loads of bytes, halfwords or words from memory into
vector elements of the same width (encodings T5, T6, T7).
(At the moment we know for MVE and M-profile in general that
vfp_access_check() can never return false, but we include the
conventional return-true-on-failure check for consistency
with non-M-profile translation code.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-2-peter.maydell@linaro.org
Instead of open-coding the "take NOCP exception if FPU disabled,
otherwise call gen_preserve_fp_state()" code in the accessors for
FPCXT_NS, add an argument to vfp_access_check_m() which tells it to
skip the gen_update_fp_context() call, so we can use it for the
FPCXT_NS case.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-8-peter.maydell@linaro.org
vfp_access_check and its helper routine full_vfp_access_check() has
gradually grown and is now an awkward mix of A-profile only and
M-profile only pieces. Refactor it into an A-profile only and an
M-profile only version, taking advantage of the fact that now the
only direct call to full_vfp_access_check() is in A-profile-only
code.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-7-peter.maydell@linaro.org
Factor the code in full_vfp_access_check() which updates the
ownership of the FP context and creates a new FP context
out into its own function.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-6-peter.maydell@linaro.org
A few subcases of VLDR/VSTR sysreg succeed but do not perform a
memory access:
* VSTR of VPR when unprivileged
* VLDR to VPR when unprivileged
* VLDR to FPCXT_NS when fpInactive
In these cases, even though we don't do the memory access we should
still update the base register and perform the stack limit check if
the insn's addressing mode specifies writeback. Our implementation
failed to do this, because we handle these side-effects inside the
memory_to_fp_sysreg() and fp_sysreg_to_memory() callback functions,
which are only called if there's something to load or store.
Fix this by adding an extra argument to the callbacks which is set to
true to actually perform the access and false to only do side effects
like writeback, and calling the callback with do_access = false
for the three cases listed above.
This produces slightly suboptimal code for the case of a write
to FPCXT_NS when the FPU is inactive and the insn didn't have
side effects (ie no writeback, or via VMSR), in which case we'll
generate a conditional branch over an unconditional branch.
But this doesn't seem to be important enough to merit requiring
the callback to report back whether it generated any code or not.
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-5-peter.maydell@linaro.org
The M-profile architecture requires that accesses to FPCXT_NS when
there is no active FP state must not take a NOCP fault even if the
FPU is disabled. We were not implementing this correctly, because
in our decode we catch the NOCP faults early in m-nocp.decode.
Fix this bug by moving all the handling of M-profile FP system
register accesses from vfp.decode into m-nocp.decode and putting
it above the NOCP blocks. This provides the correct behaviour:
* for accesses other than FPCXT_NS the trans functions call
vfp_access_check(), which will check for FPU disabled and
raise a NOCP exception if necessary
* for FPCXT_NS we have the special case code that doesn't
call vfp_access_check()
* when these trans functions want to raise an UNDEF they return
false, so the decoder will fall through into the NOCP blocks.
This means that NOCP correctly takes precedence over UNDEF
for these insns. (This is a difference from the other insns
handled by m-nocp.decode, where UNDEF takes precedence and
which we implement by having those trans functions call
unallocated_encoding() in the appropriate places.)
[Note for backport to stable: this commit has a semantic dependency
on commit 9a486856e9, which was not marked as cc-stable because
we didn't know we'd need it for a for-stable bugfix.]
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-4-peter.maydell@linaro.org
If the guest makes an FPCXT_NS access when the FPU is disabled,
one of two things happens:
* if there is no active FP context, then the insn behaves the
same way as if the FPU was enabled: writes ignored, reads
same value as FPDSCR_NS
* if there is an active FP context, then we take a NOCP
exception
Add code to the sysreg read/write functions which emits
code to take the NOCP exception in the latter case.
At the moment this will never be used, because the NOCP checks in
m-nocp.decode happen first, and so the trans functions are never
called when the FPU is disabled. The code will be needed when we
move the sysreg access insns to before the NOCP patterns in the
following commit.
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-3-peter.maydell@linaro.org
In the code for handling VFP system register accesses there is some
stray whitespace after a unary '-' operator, and also some incorrect
indent in a couple of function prototypes. We're about to move this
code to another file, so fix the code style issues first so
checkpatch doesn't complain about the code-movement patch.
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210618141019.10671-2-peter.maydell@linaro.org
The virt_is_acpi_enabled() function is specific to the virt board, as
is the check for its 'ras' property. Use the new acpi_ghes_present()
function to check whether we should report memory errors via
acpi_ghes_record_errors().
This avoids a link error if QEMU was built without support for the
virt board, and provides a mechanism that can be used by any future
board models that want to add ACPI memory error reporting support
(they only need to call acpi_ghes_add_fw_cfg()).
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Dongjiu Geng <gengdongjiu1@gmail.com>
Message-id: 20210603171259.27962-4-peter.maydell@linaro.org
Currently the ARM SVE helper code defines locally some utility
functions for swapping 16-bit halfwords within 32-bit or 64-bit
values and for swapping 32-bit words within 64-bit values,
parallel to the byte-swapping bswap16/32/64 functions.
We want these also for the ARM MVE code, and they're potentially
generally useful for other targets, so move them to bitops.h.
(We don't put them in bswap.h with the bswap* functions because
they are implemented in terms of the rotate operations also
defined in bitops.h, and including bitops.h from bswap.h seems
better avoided.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210614151007.4545-17-peter.maydell@linaro.org
For MVE, we want to re-use the large data table from expand_pred_b().
Move the data table to vec_helper.c so it is no longer in an SVE
specific source file.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210614151007.4545-14-peter.maydell@linaro.org
Add the framework for decoding MVE insns, with the necessary new
files and the meson.build rules, but no actual content yet.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210614151007.4545-11-peter.maydell@linaro.org
Implement the MVE LETP insn. This is like the existing LE loop-end
insn, but it must perform an FPU-enabled check, and on loop-exit it
resets LTPSIZE to 4.
To accommodate the requirement to do something on loop-exit, we drop
the use of condlabel and instead manage both the TB exits manually,
in the same way we already do in trans_WLS().
The other MVE-specific change to the LE insn is that we must raise an
INVSTATE UsageFault insn if LTPSIZE is not 4.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210614151007.4545-10-peter.maydell@linaro.org
Peter Maydell
Andrew Jones
Hamza Mahfooz
Richard Henderson
Philippe Mathieu-Daudé
hnick@vmware.com
Joe Komlodi
Peter Collingbourne