Let's allow for specifying a thread context via the "prealloc-context"
property. When set, preallcoation threads will be crated via the
thread context -- inheriting the same CPU affinity as the thread
context.
Pinning preallcoation threads to CPUs can heavily increase performance
in NUMA setups, because, preallocation from a CPU close to the target
NUMA node(s) is faster then preallocation from a CPU further remote,
simply because of memory bandwidth for initializing memory with zeroes.
This is especially relevant for very large VMs backed by huge/gigantic
pages, whereby preallocation is mandatory.
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Message-Id: <20221014134720.168738-7-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
... and implement it under POSIX. When a ThreadContext is provided,
create new threads via the context such that these new threads obtain a
properly configured CPU affinity.
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Message-Id: <20221014134720.168738-6-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Let's make it easier to pin threads created via a ThreadContext to
all host CPUs currently belonging to a given set of host NUMA nodes --
which is the common case.
"node-affinity" is simply a shortcut for setting "cpu-affinity" manually
to the list of host CPUs belonging to the set of host nodes. This property
can only be written.
A simple QEMU example to set the CPU affinity to host node 1 on a system
with two nodes, 24 CPUs each, whereby odd-numbered host CPUs belong to
host node 1:
qemu-system-x86_64 -S \
-object thread-context,id=tc1,node-affinity=1
And we can query the cpu-affinity via HMP/QMP:
(qemu) qom-get tc1 cpu-affinity
[
1,
3,
5,
7,
9,
11,
13,
15,
17,
19,
21,
23,
25,
27,
29,
31,
33,
35,
37,
39,
41,
43,
45,
47
]
We cannot query the node-affinity:
(qemu) qom-get tc1 node-affinity
Error: Insufficient permission to perform this operation
But note that due to dynamic library loading this example will not work
before we actually make use of thread_context_create_thread() in QEMU
code, because the type will otherwise not get registered. We'll wire
this up next to make it work.
Note that if the host CPUs for a host node change due do CPU hot(un)plug
CPU onlining/offlining (i.e., lscpu output changes) after the ThreadContext
was started, the CPU affinity will not get updated.
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20221014134720.168738-5-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Setting the CPU affinity of QEMU threads is a bit problematic, because
QEMU doesn't always have permissions to set the CPU affinity itself,
for example, with seccomp after initialized by QEMU:
-sandbox enable=on,resourcecontrol=deny
General information about CPU affinities can be found in the man page of
taskset:
CPU affinity is a scheduler property that "bonds" a process to a given
set of CPUs on the system. The Linux scheduler will honor the given CPU
affinity and the process will not run on any other CPUs.
While upper layers are already aware of how to handle CPU affinities for
long-lived threads like iothreads or vcpu threads, especially short-lived
threads, as used for memory-backend preallocation, are more involved to
handle. These threads are created on demand and upper layers are not even
able to identify and configure them.
Introduce the concept of a ThreadContext, that is essentially a thread
used for creating new threads. All threads created via that context
thread inherit the configured CPU affinity. Consequently, it's
sufficient to create a ThreadContext and configure it once, and have all
threads created via that ThreadContext inherit the same CPU affinity.
The CPU affinity of a ThreadContext can be configured two ways:
(1) Obtaining the thread id via the "thread-id" property and setting the
CPU affinity manually (e.g., via taskset).
(2) Setting the "cpu-affinity" property and letting QEMU try set the
CPU affinity itself. This will fail if QEMU doesn't have permissions
to do so anymore after seccomp was initialized.
A simple QEMU example to set the CPU affinity to host CPU 0,1,6,7 would be:
qemu-system-x86_64 -S \
-object thread-context,id=tc1,cpu-affinity=0-1,cpu-affinity=6-7
And we can query it via HMP/QMP:
(qemu) qom-get tc1 cpu-affinity
[
0,
1,
6,
7
]
But note that due to dynamic library loading this example will not work
before we actually make use of thread_context_create_thread() in QEMU
code, because the type will otherwise not get registered. We'll wire
this up next to make it work.
In general, the interface behaves like pthread_setaffinity_np(): host
CPU numbers that are currently not available are ignored; only host CPU
numbers that are impossible with the current kernel will fail. If the
list of host CPU numbers does not include a single CPU that is
available, setting the CPU affinity will fail.
A ThreadContext can be reused, simply by reconfiguring the CPU affinity.
Note that the CPU affinity of previously created threads will not get
adjusted.
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20221014134720.168738-4-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Usually, we let upper layers handle CPU pinning, because
pthread_setaffinity_np() (-> sched_setaffinity()) is blocked via
seccomp when starting QEMU with
-sandbox enable=on,resourcecontrol=deny
However, we want to configure and observe the CPU affinity of threads
from QEMU directly in some cases when the sandbox option is either not
enabled or not active yet.
So let's add a way to configure CPU pinning via
qemu_thread_set_affinity() and obtain CPU affinity via
qemu_thread_get_affinity() and implement them under POSIX using
pthread_setaffinity_np() + pthread_getaffinity_np().
Implementation under Windows is possible using SetProcessAffinityMask()
+ GetProcessAffinityMask(), however, that is left as future work.
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Message-Id: <20221014134720.168738-3-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Let's
* give the function a "qemu_*" style name
* make sure the parameters in the implementation match the prototype
* rename smp_cpus to max_threads, which makes the semantics of that
parameter clearer
... and add a function documentation.
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Message-Id: <20221014134720.168738-2-david@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
In the ACPI specification [1], the 'unarmed' bit is set when a device
cannot accept a persistent write. This means that when a memdev is
read-only, the 'unarmed' flag must be turned on. The logic is correct,
just changing the error message.
[1] ACPI NFIT NVDIMM Region Mapping Structure "NVDIMM State Flags" Bit 3
Fixes: dbd730e859 ("nvdimm: check -object memory-backend-file, readonly=on option")
Signed-off-by: Julia Suvorova <jusual@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Acked-by: David Hildenbrand <david@redhat.com>
Message-Id: <20221023195812.15523-1-jusual@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Currently the microdrive code uses device_legacy_reset() to reset
itself, and has its reset method call reset on the IDE bus as the
last thing it does. Switch to using device_cold_reset().
The only concrete microdrive device is the TYPE_DSCM1XXXX; it is not
command-line pluggable, so it is used only by the old pxa2xx Arm
boards 'akita', 'borzoi', 'spitz', 'terrier' and 'tosa'.
You might think that this would result in the IDE bus being
reset automatically, but it does not, because the IDEBus type
does not set the BusClass::reset method. Instead the controller
must explicitly call ide_bus_reset(). We therefore leave that
call in md_reset().
Note also that because the PCMCIA card device is a direct subclass of
TYPE_DEVICE and we don't model the PCMCIA controller-to-card
interface as a qbus, PCMCIA cards are not on any qbus and so they
don't get reset when the system is reset. The reset only happens via
the dscm1xxxx_attach() and dscm1xxxx_detach() functions during
machine creation.
Because our aim here is merely to try to get rid of calls to the
device_legacy_reset() function, we leave these other dubious
reset-related issues alone. (They all stem from this code being
absolutely ancient.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20221013174042.1602926-1-peter.maydell@linaro.org
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-10-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on absolute values.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on absolute values.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on absolute values.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on absolute values.
Since we always pass dc->pc_curr, fold the arithmetic to zero displacement.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-6-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on absolute values.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on
absolute values by passing in pc difference.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
In preparation for TARGET_TB_PCREL, reduce reliance on absolute values.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
A simple helper to retrieve the length of the current insn.
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221020030641.2066807-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
The return type of the functions is already bool, but in a few
instances we used an integer type with the return statement.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
So far, limit the change to S1_ptw_translate, arm_ldl_ptw, and
arm_ldq_ptw. Use probe_access_full to find the host address,
and if so use a host load. If the probe fails, we've got our
fault info already. On the off chance that page tables are not
in RAM, continue to use the address_space_ld* functions.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Hoist this test out of arm_ld[lq]_ptw into S1_ptw_translate.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Before using softmmu page tables for the ptw, plumb down
a debug parameter so that we can query page table entries
from gdbstub without modifying cpu state.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Consolidate most of the inputs and outputs of S1_ptw_translate
into a single structure. Plumb this through arm_ld*_ptw from
the controlling get_phys_addr_* routine.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20221011031911.2408754-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Compare only the VMID field when considering whether we need to flush.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20221011031911.2408754-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
We had been marking this ARM_MMU_IDX_NOTLB, move it to a real tlb.
Flush the tlb when invalidating stage 1+2 translations. Re-use
alle1_tlbmask() for other instances of EL1&0 + Stage2.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20221011031911.2408754-6-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Not yet used, but add mmu indexes for 1-1 mapping
to physical addresses.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Add a field to TARGET_PAGE_ENTRY_EXTRA to hold the guarded bit.
In is_guarded_page, use probe_access_full instead of just guessing
that the tlb entry is still present. Also handles the FIXME about
executing from device memory.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
The CPUTLBEntryFull structure now stores the original pte attributes, as
well as the physical address. Therefore, we no longer need a separate
bit in MemTxAttrs, nor do we need to walk the tree of memory regions.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Copy attrs and shareability, into the TLB. This will eventually
be used by S1_ptw_translate to report stage1 translation failures,
and by do_ats_write to fill in PAR_EL1.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20221011031911.2408754-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
QEMU doesn't model micro-architectural details which includes most
chip errata. The ARM_ERRATA_798181 work around in the Linux
kernel (see erratum_a15_798181_init) currently detects QEMU's
cortex-a15 as broken and triggers additional expensive TLB flushes as
a result.
Change the MIDR to report what the latest silicon would (r4p0). We
explicitly set the IMPDEF revidr bits to 0 because we don't need to
set anything other than the silicon revision to indicate these flushes
are not needed. This cuts about 5s from my Debian kernel boot with the
latest 6.0rc1 kernel (29s->24s).
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Message-id: 20221010153225.506394-1-alex.bennee@linaro.org
Cc: Arnd Bergmann <arnd@linaro.org>
Cc: Anders Roxell <anders.roxell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Message-Id: <20220906172257.2776521-1-alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
The PL011 TRM says that "UARTIBRD = 0 is invalid and UARTFBRD is ignored
when this is the case". But the code looks at FBRD for the invalid case.
Fix this.
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Message-id: 1408f62a2e45665816527d4845ffde650957d5ab.1665051588.git.baruchs-c@neureality.ai
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This queue contains improvements in the e500 and ppc4xx boards, changes
in the maintainership of the project, a new QMP/HMP command and bug
fixes:
- Cedric is stepping back from qemu-ppc maintainership;
- ppc4xx_sdram: QOMification and clean ups;
- e500: add new types of flash and clean ups;
- QMP/HMP: introduce dumpdtb command;
- spapr_pci, booke doorbell interrupt and xvcmp* bit fixes;
The 'dumpdtb' implementation is also making changes to RISC-V files that
were acked by Alistair Francis and are being included in this queue.
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQQX6/+ZI9AYAK8oOBk82cqW3gMxZAUCY02qEgAKCRA82cqW3gMx
ZIadAQCYY9f+NFrSJBm3z4JjUaP+GmbgEjibjZW05diyKwbqzQEAjE1KXFCcd40D
3Brs2Dm4YruaJCwb68vswVQAYteXaQ8=
=hl94
-----END PGP SIGNATURE-----
Merge tag 'pull-ppc-20221017' of https://gitlab.com/danielhb/qemu into staging
ppc patch queue for 2022-10-18:
This queue contains improvements in the e500 and ppc4xx boards, changes
in the maintainership of the project, a new QMP/HMP command and bug
fixes:
- Cedric is stepping back from qemu-ppc maintainership;
- ppc4xx_sdram: QOMification and clean ups;
- e500: add new types of flash and clean ups;
- QMP/HMP: introduce dumpdtb command;
- spapr_pci, booke doorbell interrupt and xvcmp* bit fixes;
The 'dumpdtb' implementation is also making changes to RISC-V files that
were acked by Alistair Francis and are being included in this queue.
# -----BEGIN PGP SIGNATURE-----
#
# iHUEABYKAB0WIQQX6/+ZI9AYAK8oOBk82cqW3gMxZAUCY02qEgAKCRA82cqW3gMx
# ZIadAQCYY9f+NFrSJBm3z4JjUaP+GmbgEjibjZW05diyKwbqzQEAjE1KXFCcd40D
# 3Brs2Dm4YruaJCwb68vswVQAYteXaQ8=
# =hl94
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 17 Oct 2022 15:16:34 EDT
# gpg: using EDDSA key 17EBFF9923D01800AF2838193CD9CA96DE033164
# gpg: Good signature from "Daniel Henrique Barboza <danielhb413@gmail.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 17EB FF99 23D0 1800 AF28 3819 3CD9 CA96 DE03 3164
* tag 'pull-ppc-20221017' of https://gitlab.com/danielhb/qemu: (38 commits)
hw/riscv: set machine->fdt in spike_board_init()
hw/riscv: set machine->fdt in sifive_u_machine_init()
hw/ppc: set machine->fdt in spapr machine
hw/ppc: set machine->fdt in pnv_reset()
hw/ppc: set machine->fdt in pegasos2_machine_reset()
hw/ppc: set machine->fdt in xilinx_load_device_tree()
hw/ppc: set machine->fdt in sam460ex_load_device_tree()
hw/ppc: set machine->fdt in bamboo_load_device_tree()
hw/nios2: set machine->fdt in nios2_load_dtb()
qmp/hmp, device_tree.c: introduce dumpdtb
hw/ppc/spapr_pci.c: Use device_cold_reset() rather than device_legacy_reset()
target/ppc: Fix xvcmp* clearing FI bit
hw/ppc/e500: Remove if statement which is now always true
hw/ppc/mpc8544ds: Add platform bus
hw/ppc/mpc8544ds: Rename wrongly named method
hw/ppc/e500: Reduce usage of sysbus API
docs/system/ppc/ppce500: Add heading for networking chapter
hw/gpio/meson: Introduce dedicated config switch for hw/gpio/mpc8xxx
hw/ppc/meson: Allow e500 boards to be enabled separately
ppc440_uc.c: Remove unneeded parenthesis
...
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
With all SSE (and AVX!) instructions now implemented in disas_insn_new,
it's possible to remove gen_sse, as well as the helpers for instructions
that now use gvec.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This adds another kind of weirdness when you thought you had seen it all:
an opcode byte that comes _after_ the address, not before. It's not
worth adding a new X86_SPECIAL_* constant for it, but it's actually
not unlike VCMP; so, forgive me for exploiting the similarity and just
deciding to dispatch to the right gen_helper_* call in a single code
generation function.
In fact, the old decoder had a bug where s->rip_offset should have
been set to 1 for 3DNow! instructions, and it's fixed now.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Extracted from a patch by Paul Brook <paul@nowt.org>.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Include AVX, AVX2 and VAES in the guest cpuid features supported by TCG.
Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-40-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
These are exactly the same as the non-VEX version, but one has to be careful
that only VEX.L=0 is allowed.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Here the code is a bit uglier due to the truncation and extension
of registers to and from 32-bit. There is also a mistake in the
manual with respect to the size of the memory operand of CVTPS2PI
and CVTTPS2PI, reported by Ricky Zhou.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
These are mostly moves, and yet are a total pain. The main issue
is that:
1) some instructions are selected by mod==11 (register operand)
vs. mod=00/01/10 (memory operand)
2) stores to memory are two-operand operations, while the 3-register
and load-from-memory versions operate on the entire contents of the
destination; this makes it easier to separate the gen_* function for
the store case
3) it's inefficient to load into xmm_T0 only to move the value out
again, so the gen_* function for the load case is separated too
The manual also has various mistakes in the operands here, for example
the store case of MOVHPS operates on a 128-bit source (albeit discarding
the bottom 64 bits) and therefore should be Mq,Vdq rather than Mq,Vq.
Likewise for the destination and source of MOVHLPS.
VUNPCK?PS and VUNPCK?PD are the same as VUNPCK?DQ and VUNPCK?QDQ,
but encoded as prefixes rather than separate operands. The helpers
can be reused however.
For MOVSLDUP, MOVSHDUP and MOVDDUP I chose to reimplement them as
helpers. I named the helper for MOVDDUP "movdldup" in preparation
for possible future introduction of MOVDHDUP and to clarify the
similarity with MOVSLDUP.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Nothing special going on here, for once.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There are several special cases here:
1) extending moves have different widths for the helpers vs. for the
memory loads, and the width for memory loads depends on VEX.L too.
This is represented by X86_SPECIAL_AVXExtMov.
2) some instructions, such as variable-width shifts, select the vector element
size via REX.W.
3) VSIB instructions (VGATHERxPy, VPGATHERxy) are also part of this group,
and they have (among other things) two output operands.
3) the macros for 4-operand blends (which are under 0x0f 0x3a) have to be
extended to support 2-operand blends. The 2-operand variant actually
came a few years earlier, but it is clearer to implement them in the
opposite order.
X86_TYPE_WM, introduced earlier for unaligned loads, is reused for helpers
that accept a Reg* but have a M argument.
These three-byte opcodes also include AVX new instructions, for which
the helpers were originally implemented by Paul Brook <paul@nowt.org>.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
As pmovmskb is used by strlen et al, this is the third
highest overhead sse operation at %0.8.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
[Reorganize to generate code for any vector size. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The more complicated operations here are insertions and extractions.
Otherwise, there are just more entries than usual because the PS/PD/SS/SD
variations are encoded in the opcode rater than in the prefixes.
These three-byte opcodes also include AVX new instructions, whose
implementation in the helpers was originally done by Paul Brook
<paul@nowt.org>.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Three-byte opcodes from the 0F3Ah area all have an immediate byte which
is usually unsigned. Clarify in the helper code that it is unsigned;
the new decoder treats immediates as signed by default, and seeing
an intN_t in the prototype might give the wrong impression that one
can use decode->immediate directly.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The more complicated ones here are d6-d7, e6-e7, f7. The others
are trivial.
For LDDQU, using gen_load_sse directly might corrupt the register if
the second part of the load fails. Therefore, add a custom X86_TYPE_WM
value; like X86_TYPE_W it does call gen_load(), but it also rejects a
value of 11 in the ModRM field like X86_TYPE_M.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This includes shifts by immediate, which use bits 3-5 of the ModRM byte
as an opcode extension. With the exception of 128-bit shifts, they are
implemented using gvec.
This also covers VZEROALL and VZEROUPPER, which use the same opcode
as EMMS. If we were wanting to optimize out gen_clear_ymmh then this
would be one of the starting points. The implementation of the VZEROALL
and VZEROUPPER helpers is by Paul Brook.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
These are a mixed batch, including the first two horizontal
(66 and F2 only) operations, more moves, and SSE4a extract/insert.
Because SSE4a is pretty rare, I chose to leave the helper as they are,
but it is possible to unify them by loading index and length from the
source XMM register and generating deposit or extract TCG ops.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
