OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

target-arm queue: 

* target/arm: Fix Neon emulation bugs on big-endian hosts
  * target/arm: fix handling of HCR.FB
  * target/arm: fix LORID_EL1 access check
  * disas/capstone: Fix monitor disassembly of >32 bytes
  * hw/arm/smmuv3: Fix potential integer overflow (CID 1432363)
  * hw/arm/boot: fix SVE for EL3 direct kernel boot
  * hw/display/omap_lcdc: Fix potential NULL pointer dereference
  * hw/display/exynos4210_fimd: Fix potential NULL pointer dereference
  * target/arm: Get correct MMU index for other-security-state
  * configure: Test that gio libs from pkg-config work
  * hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work
  * docs: Fix building with Sphinx 3
  * tests/qtest/npcm7xx_rng-test: Disable randomness tests
 -----BEGIN PGP SIGNATURE-----
 
 iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAl+gPSwZHHBldGVyLm1h
 eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3rBwD/9kNodk0LilJEbE/UVL5niv
 EnLo0xo+qFx8jPR19VVG6Cp3mBwwImV7MVebAuuh6cgzdyofKwpd03h/XMwIOY0T
 gHlfk/npJnob/7bambBU5UTAZnOHj8EnuCwTKq3AuRROdi35p4OqDZTxAYNNJNQa
 1dRRTEODxuPRi/bmwuYLp1esrjXlJa5KSlv+3gjunVG+uEJ6ygHJOZlgJ22704D/
 2IB3rrtwx/oYBsaQCd9TQ/uIVgkvfRo1feQp5/ukeb4nYDNWtjkk5usPYcGh7h5P
 dCgneinXvyTqZXgk9FpT25rVrp01IBZXNkGjEy/HMmpib6ABsKGywBQfif4ZQXc7
 KlO+A8yCvAvRuJcjsVMV71z9j0MIu5eU9aOW7Oqu/ORMnRSlEionCypPaO3J/kF2
 e6XoGQZJaziIo5hg8hxyALcKKtpwgd2ckAdNxQhw3vsNA7uDe1acs6BzJbiT1J1o
 05zZs6Xy4OheHkFGOKoZyVAmSCsfwqgaHspl62owCRrNcT8URLzGpjEal+l4+FHN
 8kMs012aiOSkDAWldPH2hjt0sYV/F4bVDID4PZj5Cwrz9lXQyq8e8Lw6WUvqXEzf
 Kgl/XVu9mZx4wMWLNg78cneXbM+RQNmJsWMMA/qZn5Lh2p/73a1jA9vjRBl406Tt
 RW00VEbywkOYtj1EZKdgqw==
 =PdV9
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20201102' into staging

target-arm queue:
 * target/arm: Fix Neon emulation bugs on big-endian hosts
 * target/arm: fix handling of HCR.FB
 * target/arm: fix LORID_EL1 access check
 * disas/capstone: Fix monitor disassembly of >32 bytes
 * hw/arm/smmuv3: Fix potential integer overflow (CID 1432363)
 * hw/arm/boot: fix SVE for EL3 direct kernel boot
 * hw/display/omap_lcdc: Fix potential NULL pointer dereference
 * hw/display/exynos4210_fimd: Fix potential NULL pointer dereference
 * target/arm: Get correct MMU index for other-security-state
 * configure: Test that gio libs from pkg-config work
 * hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work
 * docs: Fix building with Sphinx 3
 * tests/qtest/npcm7xx_rng-test: Disable randomness tests

# gpg: Signature made Mon 02 Nov 2020 17:09:00 GMT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20201102: (26 commits)
  tests/qtest/npcm7xx_rng-test: Disable randomness tests
  qemu-option-trace.rst.inc: Don't use option:: markup
  scripts/kerneldoc: For Sphinx 3 use c:macro for macros with arguments
  hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work
  configure: Test that gio libs from pkg-config work
  target/arm: Get correct MMU index for other-security-state
  hw/display/exynos4210_fimd: Fix potential NULL pointer dereference
  hw/display/omap_lcdc: Fix potential NULL pointer dereference
  hw/arm/boot: fix SVE for EL3 direct kernel boot
  hw/arm/smmuv3: Fix potential integer overflow (CID 1432363)
  disas/capstone: Fix monitor disassembly of >32 bytes
  target/arm: fix LORID_EL1 access check
  target/arm: fix handling of HCR.FB
  target/arm: Fix VUDOT/VSDOT (scalar) on big-endian hosts
  target/arm: Fix float16 pairwise Neon ops on big-endian hosts
  target/arm: Improve do_prewiden_3d
  target/arm: Simplify do_long_3d and do_2scalar_long
  target/arm: Rename neon_load_reg64 to vfp_load_reg64
  target/arm: Add read/write_neon_element64
  target/arm: Rename neon_load_reg32 to vfp_load_reg32
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2020-11-03 10:38:05 +00:00
parent 8545ae485b ffb4fbf90a
commit c7a7a877b7
17 changed files with 588 additions and 493 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
configure vendored
View File

@ -3489,13 +3489,21 @@ if test "$static" = yes && test "$mingw32" = yes; then
fi
if $pkg_config --atleast-version=$glib_req_ver gio-2.0; then
gio=yes
gio_cflags=$($pkg_config --cflags gio-2.0)
gio_libs=$($pkg_config --libs gio-2.0)
gdbus_codegen=$($pkg_config --variable=gdbus_codegen gio-2.0)
if [ ! -x "$gdbus_codegen" ]; then
gdbus_codegen=
fi
# Check that the libraries actually work -- Ubuntu 18.04 ships
# with pkg-config --static --libs data for gio-2.0 that is missing
# -lblkid and will give a link error.
write_c_skeleton
if compile_prog "" "gio_libs" ; then
gio=yes
else
gio=no
fi
else
gio=no
fi

2
disas/capstone.c
View File

@ -286,7 +286,7 @@ bool cap_disas_monitor(disassemble_info *info, uint64_t pc, int count)
/* Make certain that we can make progress. */
assert(tsize != 0);
info->read_memory_func(pc, cap_buf + csize, tsize, info);
info->read_memory_func(pc + csize, cap_buf + csize, tsize, info);
csize += tsize;
if (cs_disasm_iter(handle, &cbuf, &csize, &pc, insn)) {

6
docs/qemu-option-trace.rst.inc
View File

@ -1,7 +1,7 @@
Specify tracing options.
.. option:: [enable=]PATTERN
``[enable=]PATTERN``
Immediately enable events matching *PATTERN*
(either event name or a globbing pattern). This option is only
@ -11,7 +11,7 @@ Specify tracing options.
Use :option:`-trace help` to print a list of names of trace points.
.. option:: events=FILE
``events=FILE``
Immediately enable events listed in *FILE*.
The file must contain one event name (as listed in the ``trace-events-all``
@ -19,7 +19,7 @@ Specify tracing options.
available if QEMU has been compiled with the ``simple``, ``log`` or
``ftrace`` tracing backend.
.. option:: file=FILE
``file=FILE``
Log output traces to *FILE*.
This option is only available if QEMU has been compiled with

3
hw/arm/boot.c
View File

@ -742,6 +742,9 @@ static void do_cpu_reset(void *opaque)
if (cpu_isar_feature(aa64_mte, cpu)) {
env->cp15.scr_el3 |= SCR_ATA;
}
if (cpu_isar_feature(aa64_sve, cpu)) {
env->cp15.cptr_el[3] |= CPTR_EZ;
}
/* AArch64 kernels never boot in secure mode */
assert(!info->secure_boot);
/* This hook is only supported for AArch32 currently:

3
hw/arm/smmuv3.c
View File

@ -17,6 +17,7 @@
*/
#include "qemu/osdep.h"
#include "qemu/bitops.h"
#include "hw/irq.h"
#include "hw/sysbus.h"
#include "migration/vmstate.h"
@ -864,7 +865,7 @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
scale = CMD_SCALE(cmd);
num = CMD_NUM(cmd);
ttl = CMD_TTL(cmd);
num_pages = (num + 1) * (1 << (scale));
num_pages = (num + 1) * BIT_ULL(scale);
}
if (type == SMMU_CMD_TLBI_NH_VA) {

4
hw/display/exynos4210_fimd.c
View File

@ -1275,12 +1275,14 @@ static void exynos4210_fimd_update(void *opaque)
bool blend = false;
uint8_t *host_fb_addr;
bool is_dirty = false;
const int global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1;
int global_width;
if (!s || !s->console || !s->enabled ||
surface_bits_per_pixel(qemu_console_surface(s->console)) == 0) {
return;
}
global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1;
exynos4210_update_resolution(s);
surface = qemu_console_surface(s->console);

10
hw/display/omap_lcdc.c
View File

@ -78,14 +78,18 @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s)
static void omap_update_display(void *opaque)
{
struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque;
DisplaySurface *surface = qemu_console_surface(omap_lcd->con);
DisplaySurface *surface;
draw_line_func draw_line;
int size, height, first, last;
int width, linesize, step, bpp, frame_offset;
hwaddr frame_base;
if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable ||
!surface_bits_per_pixel(surface)) {
if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable) {
return;
}
surface = qemu_console_surface(omap_lcd->con);
if (!surface_bits_per_pixel(surface)) {
return;
}

5
hw/intc/arm_gicv3_cpuif.c
View File

@ -399,6 +399,7 @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs)
int irqlevel = 0;
int fiqlevel = 0;
int maintlevel = 0;
ARMCPU *cpu = ARM_CPU(cs->cpu);
idx = hppvi_index(cs);
trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx);
@ -424,7 +425,7 @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs)
qemu_set_irq(cs->parent_vfiq, fiqlevel);
qemu_set_irq(cs->parent_virq, irqlevel);
qemu_set_irq(cs->maintenance_irq, maintlevel);
qemu_set_irq(cpu->gicv3_maintenance_interrupt, maintlevel);
}
static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri)
@ -2624,8 +2625,6 @@ void gicv3_init_cpuif(GICv3State *s)
&& cpu->gic_num_lrs) {
int j;
cs->maintenance_irq = cpu->gicv3_maintenance_interrupt;
cs->num_list_regs = cpu->gic_num_lrs;
cs->vpribits = cpu->gic_vpribits;
cs->vprebits = cpu->gic_vprebits;

1
include/hw/intc/arm_gicv3_common.h
View File

@ -153,7 +153,6 @@ struct GICv3CPUState {
qemu_irq parent_fiq;
qemu_irq parent_virq;
qemu_irq parent_vfiq;
qemu_irq maintenance_irq;
/* Redistributor */
uint32_t level; /* Current IRQ level */

18
scripts/kernel-doc
View File

@ -839,7 +839,23 @@ sub output_function_rst(%) {
output_highlight_rst($args{'purpose'});
$start = "\n\n**Syntax**\n\n ``";
} else {
print ".. c:function:: ";
if ((split(/\./, $sphinx_version))[0] >= 3) {
# Sphinx 3 and later distinguish macros and functions and
# complain if you use c:function with something that's not
# syntactically valid as a function declaration.
# We assume that anything with a return type is a function
# and anything without is a macro.
if ($args{'functiontype'} ne "") {
print ".. c:function:: ";
} else {
print ".. c:macro:: ";
}
} else {
# Older Sphinx don't support documenting macros that take
# arguments with c:macro, and don't complain about the use
# of c:function for this.
print ".. c:function:: ";
}
}
if ($args{'functiontype'} ne "") {
$start .= $args{'functiontype'} . " " . $args{'function'} . " (";

24
target/arm/helper.c
View File

@ -731,13 +731,12 @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
/*
* Non-IS variants of TLB operations are upgraded to
* IS versions if we are at NS EL1 and HCR_EL2.FB is set to
* IS versions if we are at EL1 and HCR_EL2.FB is effectively set to
* force broadcast of these operations.
*/
static bool tlb_force_broadcast(CPUARMState *env)
{
return (env->cp15.hcr_el2 & HCR_FB) &&
arm_current_el(env) == 1 && arm_is_secure_below_el3(env);
return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB);
}
static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri,
@ -6680,9 +6679,10 @@ static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri)
#endif
/* Shared logic between LORID and the rest of the LOR* registers.
* Secure state has already been delt with.
* Secure state exclusion has already been dealt with.
*/
static CPAccessResult access_lor_ns(CPUARMState *env)
static CPAccessResult access_lor_ns(CPUARMState *env,
const ARMCPRegInfo *ri, bool isread)
{
int el = arm_current_el(env);
@ -6695,16 +6695,6 @@ static CPAccessResult access_lor_ns(CPUARMState *env)
return CP_ACCESS_OK;
}
static CPAccessResult access_lorid(CPUARMState *env, const ARMCPRegInfo *ri,
bool isread)
{
if (arm_is_secure_below_el3(env)) {
/* Access ok in secure mode. */
return CP_ACCESS_OK;
}
return access_lor_ns(env);
}
static CPAccessResult access_lor_other(CPUARMState *env,
const ARMCPRegInfo *ri, bool isread)
{
@ -6712,7 +6702,7 @@ static CPAccessResult access_lor_other(CPUARMState *env,
/* Access denied in secure mode. */
return CP_ACCESS_TRAP;
}
return access_lor_ns(env);
return access_lor_ns(env, ri, isread);
}
/*
@ -6739,7 +6729,7 @@ static const ARMCPRegInfo lor_reginfo[] = {
.type = ARM_CP_CONST, .resetvalue = 0 },
{ .name = "LORID_EL1", .state = ARM_CP_STATE_AA64,
.opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7,
.access = PL1_R, .accessfn = access_lorid,
.access = PL1_R, .accessfn = access_lor_ns,
.type = ARM_CP_CONST, .resetvalue = 0 },
REGINFO_SENTINEL
};

3
target/arm/m_helper.c
View File

@ -2719,7 +2719,8 @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env,
/* Return the MMU index for a v7M CPU in the specified security state */
ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate)
{
bool priv = arm_current_el(env) != 0;
bool priv = arm_v7m_is_handler_mode(env) ||
!(env->v7m.control[secstate] & 1);
return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv);
}

472
target/arm/translate-neon.c.inc
View File

@ -60,25 +60,6 @@ static inline int neon_3same_fp_size(DisasContext *s, int x)
#include "decode-neon-ls.c.inc"
#include "decode-neon-shared.c.inc"
/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
* where 0 is the least significant end of the register.
*/
static inline long
neon_element_offset(int reg, int element, MemOp size)
{
int element_size = 1 << size;
int ofs = element * element_size;
#ifdef HOST_WORDS_BIGENDIAN
/* Calculate the offset assuming fully little-endian,
* then XOR to account for the order of the 8-byte units.
*/
if (element_size < 8) {
ofs ^= 8 - element_size;
}
#endif
return neon_reg_offset(reg, 0) + ofs;
}
static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
{
long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
@ -585,12 +566,12 @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a)
* We cannot write 16 bytes at once because the
* destination is unaligned.
*/
tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0),
tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd),
8, 8, tmp);
tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0),
neon_reg_offset(vd, 0), 8, 8);
tcg_gen_gvec_mov(0, neon_full_reg_offset(vd + 1),
neon_full_reg_offset(vd), 8, 8);
} else {
tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0),
tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd),
vec_size, vec_size, tmp);
}
tcg_gen_addi_i32(addr, addr, 1 << size);
@ -691,9 +672,9 @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn)
{
int vec_size = a->q ? 16 : 8;
int rd_ofs = neon_reg_offset(a->vd, 0);
int rn_ofs = neon_reg_offset(a->vn, 0);
int rm_ofs = neon_reg_offset(a->vm, 0);
int rd_ofs = neon_full_reg_offset(a->vd);
int rn_ofs = neon_full_reg_offset(a->vn);
int rm_ofs = neon_full_reg_offset(a->vm);
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -975,18 +956,24 @@ static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn)
* early. Since Q is 0 there are always just two passes, so instead
* of a complicated loop over each pass we just unroll.
*/
tmp = neon_load_reg(a->vn, 0);
tmp2 = neon_load_reg(a->vn, 1);
tmp = tcg_temp_new_i32();
tmp2 = tcg_temp_new_i32();
tmp3 = tcg_temp_new_i32();
read_neon_element32(tmp, a->vn, 0, MO_32);
read_neon_element32(tmp2, a->vn, 1, MO_32);
fn(tmp, tmp, tmp2);
tcg_temp_free_i32(tmp2);
tmp3 = neon_load_reg(a->vm, 0);
tmp2 = neon_load_reg(a->vm, 1);
read_neon_element32(tmp3, a->vm, 0, MO_32);
read_neon_element32(tmp2, a->vm, 1, MO_32);
fn(tmp3, tmp3, tmp2);
tcg_temp_free_i32(tmp2);
neon_store_reg(a->vd, 0, tmp);
neon_store_reg(a->vd, 1, tmp3);
write_neon_element32(tmp, a->vd, 0, MO_32);
write_neon_element32(tmp3, a->vd, 1, MO_32);
tcg_temp_free_i32(tmp);
tcg_temp_free_i32(tmp2);
tcg_temp_free_i32(tmp3);
return true;
}
@ -1177,8 +1164,8 @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn)
{
/* Handle a 2-reg-shift insn which can be vectorized. */
int vec_size = a->q ? 16 : 8;
int rd_ofs = neon_reg_offset(a->vd, 0);
int rm_ofs = neon_reg_offset(a->vm, 0);
int rd_ofs = neon_full_reg_offset(a->vd);
int rm_ofs = neon_full_reg_offset(a->vm);
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -1278,9 +1265,9 @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a,
for (pass = 0; pass < a->q + 1; pass++) {
TCGv_i64 tmp = tcg_temp_new_i64();
neon_load_reg64(tmp, a->vm + pass);
read_neon_element64(tmp, a->vm, pass, MO_64);
fn(tmp, cpu_env, tmp, constimm);
neon_store_reg64(tmp, a->vd + pass);
write_neon_element64(tmp, a->vd, pass, MO_64);
tcg_temp_free_i64(tmp);
}
tcg_temp_free_i64(constimm);
@ -1294,7 +1281,7 @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a,
* 2-reg-and-shift operations, size < 3 case, where the
* helper needs to be passed cpu_env.
*/
TCGv_i32 constimm;
TCGv_i32 constimm, tmp;
int pass;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@ -1320,12 +1307,14 @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a,
* by immediate using the variable shift operations.
*/
constimm = tcg_const_i32(dup_const(a->size, a->shift));
tmp = tcg_temp_new_i32();
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 tmp = neon_load_reg(a->vm, pass);
read_neon_element32(tmp, a->vm, pass, MO_32);
fn(tmp, cpu_env, tmp, constimm);
neon_store_reg(a->vd, pass, tmp);
write_neon_element32(tmp, a->vd, pass, MO_32);
}
tcg_temp_free_i32(tmp);
tcg_temp_free_i32(constimm);
return true;
}
@ -1383,21 +1372,21 @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
constimm = tcg_const_i64(-a->shift);
rm1 = tcg_temp_new_i64();
rm2 = tcg_temp_new_i64();
rd = tcg_temp_new_i32();
/* Load both inputs first to avoid potential overwrite if rm == rd */
neon_load_reg64(rm1, a->vm);
neon_load_reg64(rm2, a->vm + 1);
read_neon_element64(rm1, a->vm, 0, MO_64);
read_neon_element64(rm2, a->vm, 1, MO_64);
shiftfn(rm1, rm1, constimm);
rd = tcg_temp_new_i32();
narrowfn(rd, cpu_env, rm1);
neon_store_reg(a->vd, 0, rd);
write_neon_element32(rd, a->vd, 0, MO_32);
shiftfn(rm2, rm2, constimm);
rd = tcg_temp_new_i32();
narrowfn(rd, cpu_env, rm2);
neon_store_reg(a->vd, 1, rd);
write_neon_element32(rd, a->vd, 1, MO_32);
tcg_temp_free_i32(rd);
tcg_temp_free_i64(rm1);
tcg_temp_free_i64(rm2);
tcg_temp_free_i64(constimm);
@ -1447,10 +1436,14 @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a,
constimm = tcg_const_i32(imm);
/* Load all inputs first to avoid potential overwrite */
rm1 = neon_load_reg(a->vm, 0);
rm2 = neon_load_reg(a->vm, 1);
rm3 = neon_load_reg(a->vm + 1, 0);
rm4 = neon_load_reg(a->vm + 1, 1);
rm1 = tcg_temp_new_i32();
rm2 = tcg_temp_new_i32();
rm3 = tcg_temp_new_i32();
rm4 = tcg_temp_new_i32();
read_neon_element32(rm1, a->vm, 0, MO_32);
read_neon_element32(rm2, a->vm, 1, MO_32);
read_neon_element32(rm3, a->vm, 2, MO_32);
read_neon_element32(rm4, a->vm, 3, MO_32);
rtmp = tcg_temp_new_i64();
shiftfn(rm1, rm1, constimm);
@ -1460,7 +1453,8 @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a,
tcg_temp_free_i32(rm2);
narrowfn(rm1, cpu_env, rtmp);
neon_store_reg(a->vd, 0, rm1);
write_neon_element32(rm1, a->vd, 0, MO_32);
tcg_temp_free_i32(rm1);
shiftfn(rm3, rm3, constimm);
shiftfn(rm4, rm4, constimm);
@ -1471,7 +1465,8 @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a,
narrowfn(rm3, cpu_env, rtmp);
tcg_temp_free_i64(rtmp);
neon_store_reg(a->vd, 1, rm3);
write_neon_element32(rm3, a->vd, 1, MO_32);
tcg_temp_free_i32(rm3);
return true;
}
@ -1572,8 +1567,10 @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a,
widen_mask = dup_const(a->size + 1, widen_mask);
}
rm0 = neon_load_reg(a->vm, 0);
rm1 = neon_load_reg(a->vm, 1);
rm0 = tcg_temp_new_i32();
rm1 = tcg_temp_new_i32();
read_neon_element32(rm0, a->vm, 0, MO_32);
read_neon_element32(rm1, a->vm, 1, MO_32);
tmp = tcg_temp_new_i64();
widenfn(tmp, rm0);
@ -1582,7 +1579,7 @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a,
tcg_gen_shli_i64(tmp, tmp, a->shift);
tcg_gen_andi_i64(tmp, tmp, ~widen_mask);
}
neon_store_reg64(tmp, a->vd);
write_neon_element64(tmp, a->vd, 0, MO_64);
widenfn(tmp, rm1);
tcg_temp_free_i32(rm1);
@ -1590,7 +1587,7 @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a,
tcg_gen_shli_i64(tmp, tmp, a->shift);
tcg_gen_andi_i64(tmp, tmp, ~widen_mask);
}
neon_store_reg64(tmp, a->vd + 1);
write_neon_element64(tmp, a->vd, 1, MO_64);
tcg_temp_free_i64(tmp);
return true;
}
@ -1620,8 +1617,8 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
{
/* FP operations in 2-reg-and-shift group */
int vec_size = a->q ? 16 : 8;
int rd_ofs = neon_reg_offset(a->vd, 0);
int rm_ofs = neon_reg_offset(a->vm, 0);
int rd_ofs = neon_full_reg_offset(a->vd);
int rm_ofs = neon_full_reg_offset(a->vm);
TCGv_ptr fpst;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@ -1756,7 +1753,7 @@ static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a,
return true;
}
reg_ofs = neon_reg_offset(a->vd, 0);
reg_ofs = neon_full_reg_offset(a->vd);
vec_size = a->q ? 16 : 8;
imm = asimd_imm_const(a->imm, a->cmode, a->op);
@ -1791,11 +1788,10 @@ static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a)
static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
NeonGenWidenFn *widenfn,
NeonGenTwo64OpFn *opfn,
bool src1_wide)
int src1_mop, int src2_mop)
{
/* 3-regs different lengths, prewidening case (VADDL/VSUBL/VAADW/VSUBW) */
TCGv_i64 rn0_64, rn1_64, rm_64;
TCGv_i32 rm;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -1807,12 +1803,12 @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
return false;
}
if (!widenfn || !opfn) {
if (!opfn) {
/* size == 3 case, which is an entirely different insn group */
return false;
}
if ((a->vd & 1) || (src1_wide && (a->vn & 1))) {
if ((a->vd & 1) || (src1_mop == MO_Q && (a->vn & 1))) {
return false;
}
@ -1824,38 +1820,50 @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
rn1_64 = tcg_temp_new_i64();
rm_64 = tcg_temp_new_i64();
if (src1_wide) {
neon_load_reg64(rn0_64, a->vn);
if (src1_mop >= 0) {
read_neon_element64(rn0_64, a->vn, 0, src1_mop);
} else {
TCGv_i32 tmp = neon_load_reg(a->vn, 0);
TCGv_i32 tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vn, 0, MO_32);
widenfn(rn0_64, tmp);
tcg_temp_free_i32(tmp);
}
rm = neon_load_reg(a->vm, 0);
if (src2_mop >= 0) {
read_neon_element64(rm_64, a->vm, 0, src2_mop);
} else {
TCGv_i32 tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vm, 0, MO_32);
widenfn(rm_64, tmp);
tcg_temp_free_i32(tmp);
}
widenfn(rm_64, rm);
tcg_temp_free_i32(rm);
opfn(rn0_64, rn0_64, rm_64);
/*
* Load second pass inputs before storing the first pass result, to
* avoid incorrect results if a narrow input overlaps with the result.
*/
if (src1_wide) {
neon_load_reg64(rn1_64, a->vn + 1);
if (src1_mop >= 0) {
read_neon_element64(rn1_64, a->vn, 1, src1_mop);
} else {
TCGv_i32 tmp = neon_load_reg(a->vn, 1);
TCGv_i32 tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vn, 1, MO_32);
widenfn(rn1_64, tmp);
tcg_temp_free_i32(tmp);
}
rm = neon_load_reg(a->vm, 1);
if (src2_mop >= 0) {
read_neon_element64(rm_64, a->vm, 1, src2_mop);
} else {
TCGv_i32 tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vm, 1, MO_32);
widenfn(rm_64, tmp);
tcg_temp_free_i32(tmp);
}
neon_store_reg64(rn0_64, a->vd);
write_neon_element64(rn0_64, a->vd, 0, MO_64);
widenfn(rm_64, rm);
tcg_temp_free_i32(rm);
opfn(rn1_64, rn1_64, rm_64);
neon_store_reg64(rn1_64, a->vd + 1);
write_neon_element64(rn1_64, a->vd, 1, MO_64);
tcg_temp_free_i64(rn0_64);
tcg_temp_free_i64(rn1_64);
@ -1864,14 +1872,13 @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
return true;
}
#define DO_PREWIDEN(INSN, S, EXT, OP, SRC1WIDE) \
#define DO_PREWIDEN(INSN, S, OP, SRC1WIDE, SIGN) \
static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \
{ \
static NeonGenWidenFn * const widenfn[] = { \
gen_helper_neon_widen_##S##8, \
gen_helper_neon_widen_##S##16, \
tcg_gen_##EXT##_i32_i64, \
NULL, \
NULL, NULL, \
}; \
static NeonGenTwo64OpFn * const addfn[] = { \
gen_helper_neon_##OP##l_u16, \
@ -1879,18 +1886,20 @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
tcg_gen_##OP##_i64, \
NULL, \
}; \
return do_prewiden_3d(s, a, widenfn[a->size], \
addfn[a->size], SRC1WIDE); \
int narrow_mop = a->size == MO_32 ? MO_32 | SIGN : -1; \
return do_prewiden_3d(s, a, widenfn[a->size], addfn[a->size], \
SRC1WIDE ? MO_Q : narrow_mop, \
narrow_mop); \
}
DO_PREWIDEN(VADDL_S, s, ext, add, false)
DO_PREWIDEN(VADDL_U, u, extu, add, false)
DO_PREWIDEN(VSUBL_S, s, ext, sub, false)
DO_PREWIDEN(VSUBL_U, u, extu, sub, false)
DO_PREWIDEN(VADDW_S, s, ext, add, true)
DO_PREWIDEN(VADDW_U, u, extu, add, true)
DO_PREWIDEN(VSUBW_S, s, ext, sub, true)
DO_PREWIDEN(VSUBW_U, u, extu, sub, true)
DO_PREWIDEN(VADDL_S, s, add, false, MO_SIGN)
DO_PREWIDEN(VADDL_U, u, add, false, 0)
DO_PREWIDEN(VSUBL_S, s, sub, false, MO_SIGN)
DO_PREWIDEN(VSUBL_U, u, sub, false, 0)
DO_PREWIDEN(VADDW_S, s, add, true, MO_SIGN)
DO_PREWIDEN(VADDW_U, u, add, true, 0)
DO_PREWIDEN(VSUBW_S, s, sub, true, MO_SIGN)
DO_PREWIDEN(VSUBW_U, u, sub, true, 0)
static bool do_narrow_3d(DisasContext *s, arg_3diff *a,
NeonGenTwo64OpFn *opfn, NeonGenNarrowFn *narrowfn)
@ -1927,23 +1936,25 @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a,
rd0 = tcg_temp_new_i32();
rd1 = tcg_temp_new_i32();
neon_load_reg64(rn_64, a->vn);
neon_load_reg64(rm_64, a->vm);
read_neon_element64(rn_64, a->vn, 0, MO_64);
read_neon_element64(rm_64, a->vm, 0, MO_64);
opfn(rn_64, rn_64, rm_64);
narrowfn(rd0, rn_64);
neon_load_reg64(rn_64, a->vn + 1);
neon_load_reg64(rm_64, a->vm + 1);
read_neon_element64(rn_64, a->vn, 1, MO_64);
read_neon_element64(rm_64, a->vm, 1, MO_64);
opfn(rn_64, rn_64, rm_64);
narrowfn(rd1, rn_64);
neon_store_reg(a->vd, 0, rd0);
neon_store_reg(a->vd, 1, rd1);
write_neon_element32(rd0, a->vd, 0, MO_32);
write_neon_element32(rd1, a->vd, 1, MO_32);
tcg_temp_free_i32(rd0);
tcg_temp_free_i32(rd1);
tcg_temp_free_i64(rn_64);
tcg_temp_free_i64(rm_64);
@ -2018,14 +2029,14 @@ static bool do_long_3d(DisasContext *s, arg_3diff *a,
rd0 = tcg_temp_new_i64();
rd1 = tcg_temp_new_i64();
rn = neon_load_reg(a->vn, 0);
rm = neon_load_reg(a->vm, 0);
rn = tcg_temp_new_i32();
rm = tcg_temp_new_i32();
read_neon_element32(rn, a->vn, 0, MO_32);
read_neon_element32(rm, a->vm, 0, MO_32);
opfn(rd0, rn, rm);
tcg_temp_free_i32(rn);
tcg_temp_free_i32(rm);
rn = neon_load_reg(a->vn, 1);
rm = neon_load_reg(a->vm, 1);
read_neon_element32(rn, a->vn, 1, MO_32);
read_neon_element32(rm, a->vm, 1, MO_32);
opfn(rd1, rn, rm);
tcg_temp_free_i32(rn);
tcg_temp_free_i32(rm);
@ -2033,18 +2044,15 @@ static bool do_long_3d(DisasContext *s, arg_3diff *a,
/* Don't store results until after all loads: they might overlap */
if (accfn) {
tmp = tcg_temp_new_i64();
neon_load_reg64(tmp, a->vd);
accfn(tmp, tmp, rd0);
neon_store_reg64(tmp, a->vd);
neon_load_reg64(tmp, a->vd + 1);
accfn(tmp, tmp, rd1);
neon_store_reg64(tmp, a->vd + 1);
read_neon_element64(tmp, a->vd, 0, MO_64);
accfn(rd0, tmp, rd0);
read_neon_element64(tmp, a->vd, 1, MO_64);
accfn(rd1, tmp, rd1);
tcg_temp_free_i64(tmp);
} else {
neon_store_reg64(rd0, a->vd);
neon_store_reg64(rd1, a->vd + 1);
}
write_neon_element64(rd0, a->vd, 0, MO_64);
write_neon_element64(rd1, a->vd, 1, MO_64);
tcg_temp_free_i64(rd0);
tcg_temp_free_i64(rd1);
@ -2300,9 +2308,9 @@ static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a)
return true;
}
tcg_gen_gvec_3_ool(neon_reg_offset(a->vd, 0),
neon_reg_offset(a->vn, 0),
neon_reg_offset(a->vm, 0),
tcg_gen_gvec_3_ool(neon_full_reg_offset(a->vd),
neon_full_reg_offset(a->vn),
neon_full_reg_offset(a->vm),
16, 16, 0, fn_gvec);
return true;
}
@ -2327,16 +2335,16 @@ static void gen_neon_dup_high16(TCGv_i32 var)
static inline TCGv_i32 neon_get_scalar(int size, int reg)
{
TCGv_i32 tmp;
if (size == 1) {
tmp = neon_load_reg(reg & 7, reg >> 4);
TCGv_i32 tmp = tcg_temp_new_i32();
if (size == MO_16) {
read_neon_element32(tmp, reg & 7, reg >> 4, MO_32);
if (reg & 8) {
gen_neon_dup_high16(tmp);
} else {
gen_neon_dup_low16(tmp);
}
} else {
tmp = neon_load_reg(reg & 15, reg >> 4);
read_neon_element32(tmp, reg & 15, reg >> 4, MO_32);
}
return tmp;
}
@ -2350,7 +2358,7 @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a,
* perform an accumulation operation of that result into the
* destination.
*/
TCGv_i32 scalar;
TCGv_i32 scalar, tmp;
int pass;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@ -2377,17 +2385,20 @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a,
}
scalar = neon_get_scalar(a->size, a->vm);
tmp = tcg_temp_new_i32();
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 tmp = neon_load_reg(a->vn, pass);
read_neon_element32(tmp, a->vn, pass, MO_32);
opfn(tmp, tmp, scalar);
if (accfn) {
TCGv_i32 rd = neon_load_reg(a->vd, pass);
TCGv_i32 rd = tcg_temp_new_i32();
read_neon_element32(rd, a->vd, pass, MO_32);
accfn(tmp, rd, tmp);
tcg_temp_free_i32(rd);
}
neon_store_reg(a->vd, pass, tmp);
write_neon_element32(tmp, a->vd, pass, MO_32);
}
tcg_temp_free_i32(tmp);
tcg_temp_free_i32(scalar);
return true;
}
@ -2445,8 +2456,8 @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a,
{
/* Two registers and a scalar, using gvec */
int vec_size = a->q ? 16 : 8;
int rd_ofs = neon_reg_offset(a->vd, 0);
int rn_ofs = neon_reg_offset(a->vn, 0);
int rd_ofs = neon_full_reg_offset(a->vd);
int rn_ofs = neon_full_reg_offset(a->vn);
int rm_ofs;
int idx;
TCGv_ptr fpstatus;
@ -2477,7 +2488,7 @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a,
/* a->vm is M:Vm, which encodes both register and index */
idx = extract32(a->vm, a->size + 2, 2);
a->vm = extract32(a->vm, 0, a->size + 2);
rm_ofs = neon_reg_offset(a->vm, 0);
rm_ofs = neon_full_reg_offset(a->vm);
fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD);
tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus,
@ -2542,7 +2553,7 @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a,
* performs a kind of fused op-then-accumulate using a helper
* function that takes all of rd, rn and the scalar at once.
*/
TCGv_i32 scalar;
TCGv_i32 scalar, rn, rd;
int pass;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@ -2573,14 +2584,17 @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a,
}
scalar = neon_get_scalar(a->size, a->vm);
rn = tcg_temp_new_i32();
rd = tcg_temp_new_i32();
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 rn = neon_load_reg(a->vn, pass);
TCGv_i32 rd = neon_load_reg(a->vd, pass);
read_neon_element32(rn, a->vn, pass, MO_32);
read_neon_element32(rd, a->vd, pass, MO_32);
opfn(rd, cpu_env, rn, scalar, rd);
tcg_temp_free_i32(rn);
neon_store_reg(a->vd, pass, rd);
write_neon_element32(rd, a->vd, pass, MO_32);
}
tcg_temp_free_i32(rn);
tcg_temp_free_i32(rd);
tcg_temp_free_i32(scalar);
return true;
@ -2647,12 +2661,12 @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a,
scalar = neon_get_scalar(a->size, a->vm);
/* Load all inputs before writing any outputs, in case of overlap */
rn = neon_load_reg(a->vn, 0);
rn = tcg_temp_new_i32();
read_neon_element32(rn, a->vn, 0, MO_32);
rn0_64 = tcg_temp_new_i64();
opfn(rn0_64, rn, scalar);
tcg_temp_free_i32(rn);
rn = neon_load_reg(a->vn, 1);
read_neon_element32(rn, a->vn, 1, MO_32);
rn1_64 = tcg_temp_new_i64();
opfn(rn1_64, rn, scalar);
tcg_temp_free_i32(rn);
@ -2660,17 +2674,15 @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a,
if (accfn) {
TCGv_i64 t64 = tcg_temp_new_i64();
neon_load_reg64(t64, a->vd);
accfn(t64, t64, rn0_64);
neon_store_reg64(t64, a->vd);
neon_load_reg64(t64, a->vd + 1);
accfn(t64, t64, rn1_64);
neon_store_reg64(t64, a->vd + 1);
read_neon_element64(t64, a->vd, 0, MO_64);
accfn(rn0_64, t64, rn0_64);
read_neon_element64(t64, a->vd, 1, MO_64);
accfn(rn1_64, t64, rn1_64);
tcg_temp_free_i64(t64);
} else {
neon_store_reg64(rn0_64, a->vd);
neon_store_reg64(rn1_64, a->vd + 1);
}
write_neon_element64(rn0_64, a->vd, 0, MO_64);
write_neon_element64(rn1_64, a->vd, 1, MO_64);
tcg_temp_free_i64(rn0_64);
tcg_temp_free_i64(rn1_64);
return true;
@ -2803,10 +2815,10 @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a)
right = tcg_temp_new_i64();
dest = tcg_temp_new_i64();
neon_load_reg64(right, a->vn);
neon_load_reg64(left, a->vm);
read_neon_element64(right, a->vn, 0, MO_64);
read_neon_element64(left, a->vm, 0, MO_64);
tcg_gen_extract2_i64(dest, right, left, a->imm * 8);
neon_store_reg64(dest, a->vd);
write_neon_element64(dest, a->vd, 0, MO_64);
tcg_temp_free_i64(left);
tcg_temp_free_i64(right);
@ -2822,21 +2834,21 @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a)
destright = tcg_temp_new_i64();
if (a->imm < 8) {
neon_load_reg64(right, a->vn);
neon_load_reg64(middle, a->vn + 1);
read_neon_element64(right, a->vn, 0, MO_64);
read_neon_element64(middle, a->vn, 1, MO_64);
tcg_gen_extract2_i64(destright, right, middle, a->imm * 8);
neon_load_reg64(left, a->vm);
read_neon_element64(left, a->vm, 0, MO_64);
tcg_gen_extract2_i64(destleft, middle, left, a->imm * 8);
} else {
neon_load_reg64(right, a->vn + 1);
neon_load_reg64(middle, a->vm);
read_neon_element64(right, a->vn, 1, MO_64);
read_neon_element64(middle, a->vm, 0, MO_64);
tcg_gen_extract2_i64(destright, right, middle, (a->imm - 8) * 8);
neon_load_reg64(left, a->vm + 1);
read_neon_element64(left, a->vm, 1, MO_64);
tcg_gen_extract2_i64(destleft, middle, left, (a->imm - 8) * 8);
}
neon_store_reg64(destright, a->vd);
neon_store_reg64(destleft, a->vd + 1);
write_neon_element64(destright, a->vd, 0, MO_64);
write_neon_element64(destleft, a->vd, 1, MO_64);
tcg_temp_free_i64(destright);
tcg_temp_free_i64(destleft);
@ -2876,30 +2888,34 @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)
return false;
}
n <<= 3;
tmp = tcg_temp_new_i32();
if (a->op) {
tmp = neon_load_reg(a->vd, 0);
read_neon_element32(tmp, a->vd, 0, MO_32);
} else {
tmp = tcg_temp_new_i32();
tcg_gen_movi_i32(tmp, 0);
}
tmp2 = neon_load_reg(a->vm, 0);
tmp2 = tcg_temp_new_i32();
read_neon_element32(tmp2, a->vm, 0, MO_32);
ptr1 = vfp_reg_ptr(true, a->vn);
tmp4 = tcg_const_i32(n);
gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4);
tcg_temp_free_i32(tmp);
if (a->op) {
tmp = neon_load_reg(a->vd, 1);
read_neon_element32(tmp, a->vd, 1, MO_32);
} else {
tmp = tcg_temp_new_i32();
tcg_gen_movi_i32(tmp, 0);
}
tmp3 = neon_load_reg(a->vm, 1);
tmp3 = tcg_temp_new_i32();
read_neon_element32(tmp3, a->vm, 1, MO_32);
gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4);
tcg_temp_free_i32(tmp);
tcg_temp_free_i32(tmp4);
tcg_temp_free_ptr(ptr1);
neon_store_reg(a->vd, 0, tmp2);
neon_store_reg(a->vd, 1, tmp3);
tcg_temp_free_i32(tmp);
write_neon_element32(tmp2, a->vd, 0, MO_32);
write_neon_element32(tmp3, a->vd, 1, MO_32);
tcg_temp_free_i32(tmp2);
tcg_temp_free_i32(tmp3);
return true;
}
@ -2923,7 +2939,7 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
return true;
}
tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0),
tcg_gen_gvec_dup_mem(a->size, neon_full_reg_offset(a->vd),
neon_element_offset(a->vm, a->index, a->size),
a->q ? 16 : 8, a->q ? 16 : 8);
return true;
@ -2932,6 +2948,7 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
{
int pass, half;
TCGv_i32 tmp[2];
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -2955,11 +2972,12 @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
return true;
}
for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
TCGv_i32 tmp[2];
tmp[0] = tcg_temp_new_i32();
tmp[1] = tcg_temp_new_i32();
for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
for (half = 0; half < 2; half++) {
tmp[half] = neon_load_reg(a->vm, pass * 2 + half);
read_neon_element32(tmp[half], a->vm, pass * 2 + half, MO_32);
switch (a->size) {
case 0:
tcg_gen_bswap32_i32(tmp[half], tmp[half]);
@ -2973,9 +2991,12 @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
g_assert_not_reached();
}
}
neon_store_reg(a->vd, pass * 2, tmp[1]);
neon_store_reg(a->vd, pass * 2 + 1, tmp[0]);
write_neon_element32(tmp[1], a->vd, pass * 2, MO_32);
write_neon_element32(tmp[0], a->vd, pass * 2 + 1, MO_32);
}
tcg_temp_free_i32(tmp[0]);
tcg_temp_free_i32(tmp[1]);
return true;
}
@ -3020,23 +3041,25 @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a,
rm0_64 = tcg_temp_new_i64();
rm1_64 = tcg_temp_new_i64();
rd_64 = tcg_temp_new_i64();
tmp = neon_load_reg(a->vm, pass * 2);
tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vm, pass * 2, MO_32);
widenfn(rm0_64, tmp);
tcg_temp_free_i32(tmp);
tmp = neon_load_reg(a->vm, pass * 2 + 1);
read_neon_element32(tmp, a->vm, pass * 2 + 1, MO_32);
widenfn(rm1_64, tmp);
tcg_temp_free_i32(tmp);
opfn(rd_64, rm0_64, rm1_64);
tcg_temp_free_i64(rm0_64);
tcg_temp_free_i64(rm1_64);
if (accfn) {
TCGv_i64 tmp64 = tcg_temp_new_i64();
neon_load_reg64(tmp64, a->vd + pass);
read_neon_element64(tmp64, a->vd, pass, MO_64);
accfn(rd_64, tmp64, rd_64);
tcg_temp_free_i64(tmp64);
}
neon_store_reg64(rd_64, a->vd + pass);
write_neon_element64(rd_64, a->vd, pass, MO_64);
tcg_temp_free_i64(rd_64);
}
return true;
@ -3234,12 +3257,14 @@ static bool do_vmovn(DisasContext *s, arg_2misc *a,
rd0 = tcg_temp_new_i32();
rd1 = tcg_temp_new_i32();
neon_load_reg64(rm, a->vm);
read_neon_element64(rm, a->vm, 0, MO_64);
narrowfn(rd0, cpu_env, rm);
neon_load_reg64(rm, a->vm + 1);
read_neon_element64(rm, a->vm, 1, MO_64);
narrowfn(rd1, cpu_env, rm);
neon_store_reg(a->vd, 0, rd0);
neon_store_reg(a->vd, 1, rd1);
write_neon_element32(rd0, a->vd, 0, MO_32);
write_neon_element32(rd1, a->vd, 1, MO_32);
tcg_temp_free_i32(rd0);
tcg_temp_free_i32(rd1);
tcg_temp_free_i64(rm);
return true;
}
@ -3296,16 +3321,18 @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a)
}
rd = tcg_temp_new_i64();
rm0 = tcg_temp_new_i32();
rm1 = tcg_temp_new_i32();
rm0 = neon_load_reg(a->vm, 0);
rm1 = neon_load_reg(a->vm, 1);
read_neon_element32(rm0, a->vm, 0, MO_32);
read_neon_element32(rm1, a->vm, 1, MO_32);
widenfn(rd, rm0);
tcg_gen_shli_i64(rd, rd, 8 << a->size);
neon_store_reg64(rd, a->vd);
write_neon_element64(rd, a->vd, 0, MO_64);
widenfn(rd, rm1);
tcg_gen_shli_i64(rd, rd, 8 << a->size);
neon_store_reg64(rd, a->vd + 1);
write_neon_element64(rd, a->vd, 1, MO_64);
tcg_temp_free_i64(rd);
tcg_temp_free_i32(rm0);
@ -3339,21 +3366,25 @@ static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a)
fpst = fpstatus_ptr(FPST_STD);
ahp = get_ahp_flag();
tmp = neon_load_reg(a->vm, 0);
tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vm, 0, MO_32);
gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
tmp2 = neon_load_reg(a->vm, 1);
tmp2 = tcg_temp_new_i32();
read_neon_element32(tmp2, a->vm, 1, MO_32);
gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp);
tcg_gen_shli_i32(tmp2, tmp2, 16);
tcg_gen_or_i32(tmp2, tmp2, tmp);
tcg_temp_free_i32(tmp);
tmp = neon_load_reg(a->vm, 2);
read_neon_element32(tmp, a->vm, 2, MO_32);
gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
tmp3 = neon_load_reg(a->vm, 3);
neon_store_reg(a->vd, 0, tmp2);
tmp3 = tcg_temp_new_i32();
read_neon_element32(tmp3, a->vm, 3, MO_32);
write_neon_element32(tmp2, a->vd, 0, MO_32);
tcg_temp_free_i32(tmp2);
gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp);
tcg_gen_shli_i32(tmp3, tmp3, 16);
tcg_gen_or_i32(tmp3, tmp3, tmp);
neon_store_reg(a->vd, 1, tmp3);
write_neon_element32(tmp3, a->vd, 1, MO_32);
tcg_temp_free_i32(tmp3);
tcg_temp_free_i32(tmp);
tcg_temp_free_i32(ahp);
tcg_temp_free_ptr(fpst);
@ -3388,21 +3419,25 @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a)
fpst = fpstatus_ptr(FPST_STD);
ahp = get_ahp_flag();
tmp3 = tcg_temp_new_i32();
tmp = neon_load_reg(a->vm, 0);
tmp2 = neon_load_reg(a->vm, 1);
tmp2 = tcg_temp_new_i32();
tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vm, 0, MO_32);
read_neon_element32(tmp2, a->vm, 1, MO_32);
tcg_gen_ext16u_i32(tmp3, tmp);
gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
neon_store_reg(a->vd, 0, tmp3);
write_neon_element32(tmp3, a->vd, 0, MO_32);
tcg_gen_shri_i32(tmp, tmp, 16);
gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp);
neon_store_reg(a->vd, 1, tmp);
tmp3 = tcg_temp_new_i32();
write_neon_element32(tmp, a->vd, 1, MO_32);
tcg_temp_free_i32(tmp);
tcg_gen_ext16u_i32(tmp3, tmp2);
gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
neon_store_reg(a->vd, 2, tmp3);
write_neon_element32(tmp3, a->vd, 2, MO_32);
tcg_temp_free_i32(tmp3);
tcg_gen_shri_i32(tmp2, tmp2, 16);
gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp);
neon_store_reg(a->vd, 3, tmp2);
write_neon_element32(tmp2, a->vd, 3, MO_32);
tcg_temp_free_i32(tmp2);
tcg_temp_free_i32(ahp);
tcg_temp_free_ptr(fpst);
@ -3412,8 +3447,8 @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a)
static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn)
{
int vec_size = a->q ? 16 : 8;
int rd_ofs = neon_reg_offset(a->vd, 0);
int rm_ofs = neon_reg_offset(a->vm, 0);
int rd_ofs = neon_full_reg_offset(a->vd);
int rm_ofs = neon_full_reg_offset(a->vm);
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -3508,6 +3543,7 @@ DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2)
static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn)
{
TCGv_i32 tmp;
int pass;
/* Handle a 2-reg-misc operation by iterating 32 bits at a time */
@ -3533,11 +3569,13 @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn)
return true;
}
tmp = tcg_temp_new_i32();
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
TCGv_i32 tmp = neon_load_reg(a->vm, pass);
read_neon_element32(tmp, a->vm, pass, MO_32);
fn(tmp, tmp);
neon_store_reg(a->vd, pass, tmp);
write_neon_element32(tmp, a->vd, pass, MO_32);
}
tcg_temp_free_i32(tmp);
return true;
}
@ -3812,10 +3850,10 @@ static bool trans_VSWP(DisasContext *s, arg_2misc *a)
rm = tcg_temp_new_i64();
rd = tcg_temp_new_i64();
for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
neon_load_reg64(rm, a->vm + pass);
neon_load_reg64(rd, a->vd + pass);
neon_store_reg64(rm, a->vd + pass);
neon_store_reg64(rd, a->vm + pass);
read_neon_element64(rm, a->vm, pass, MO_64);
read_neon_element64(rd, a->vd, pass, MO_64);
write_neon_element64(rm, a->vd, pass, MO_64);
write_neon_element64(rd, a->vm, pass, MO_64);
}
tcg_temp_free_i64(rm);
tcg_temp_free_i64(rd);
@ -3890,25 +3928,29 @@ static bool trans_VTRN(DisasContext *s, arg_2misc *a)
return true;
}
if (a->size == 2) {
tmp = tcg_temp_new_i32();
tmp2 = tcg_temp_new_i32();
if (a->size == MO_32) {
for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) {
tmp = neon_load_reg(a->vm, pass);
tmp2 = neon_load_reg(a->vd, pass + 1);
neon_store_reg(a->vm, pass, tmp2);
neon_store_reg(a->vd, pass + 1, tmp);
read_neon_element32(tmp, a->vm, pass, MO_32);
read_neon_element32(tmp2, a->vd, pass + 1, MO_32);
write_neon_element32(tmp2, a->vm, pass, MO_32);
write_neon_element32(tmp, a->vd, pass + 1, MO_32);
}
} else {
for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
tmp = neon_load_reg(a->vm, pass);
tmp2 = neon_load_reg(a->vd, pass);
if (a->size == 0) {
read_neon_element32(tmp, a->vm, pass, MO_32);
read_neon_element32(tmp2, a->vd, pass, MO_32);
if (a->size == MO_8) {
gen_neon_trn_u8(tmp, tmp2);
} else {
gen_neon_trn_u16(tmp, tmp2);
}
neon_store_reg(a->vm, pass, tmp2);
neon_store_reg(a->vd, pass, tmp);
write_neon_element32(tmp2, a->vm, pass, MO_32);
write_neon_element32(tmp, a->vd, pass, MO_32);
}
}
tcg_temp_free_i32(tmp);
tcg_temp_free_i32(tmp2);
return true;
}

341
target/arm/translate-vfp.c.inc
View File

@ -236,8 +236,8 @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a)
tcg_gen_ext_i32_i64(nf, cpu_NF);
tcg_gen_ext_i32_i64(vf, cpu_VF);
neon_load_reg64(frn, rn);
neon_load_reg64(frm, rm);
vfp_load_reg64(frn, rn);
vfp_load_reg64(frm, rm);
switch (a->cc) {
case 0: /* eq: Z */
tcg_gen_movcond_i64(TCG_COND_EQ, dest, zf, zero,
@ -264,7 +264,7 @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a)
tcg_temp_free_i64(tmp);
break;
}
neon_store_reg64(dest, rd);
vfp_store_reg64(dest, rd);
tcg_temp_free_i64(frn);
tcg_temp_free_i64(frm);
tcg_temp_free_i64(dest);
@ -283,8 +283,8 @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a)
frn = tcg_temp_new_i32();
frm = tcg_temp_new_i32();
dest = tcg_temp_new_i32();
neon_load_reg32(frn, rn);
neon_load_reg32(frm, rm);
vfp_load_reg32(frn, rn);
vfp_load_reg32(frm, rm);
switch (a->cc) {
case 0: /* eq: Z */
tcg_gen_movcond_i32(TCG_COND_EQ, dest, cpu_ZF, zero,
@ -315,7 +315,7 @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a)
if (sz == 1) {
tcg_gen_andi_i32(dest, dest, 0xffff);
}
neon_store_reg32(dest, rd);
vfp_store_reg32(dest, rd);
tcg_temp_free_i32(frn);
tcg_temp_free_i32(frm);
tcg_temp_free_i32(dest);
@ -385,9 +385,9 @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a)
TCGv_i64 tcg_res;
tcg_op = tcg_temp_new_i64();
tcg_res = tcg_temp_new_i64();
neon_load_reg64(tcg_op, rm);
vfp_load_reg64(tcg_op, rm);
gen_helper_rintd(tcg_res, tcg_op, fpst);
neon_store_reg64(tcg_res, rd);
vfp_store_reg64(tcg_res, rd);
tcg_temp_free_i64(tcg_op);
tcg_temp_free_i64(tcg_res);
} else {
@ -395,13 +395,13 @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a)
TCGv_i32 tcg_res;
tcg_op = tcg_temp_new_i32();
tcg_res = tcg_temp_new_i32();
neon_load_reg32(tcg_op, rm);
vfp_load_reg32(tcg_op, rm);
if (sz == 1) {
gen_helper_rinth(tcg_res, tcg_op, fpst);
} else {
gen_helper_rints(tcg_res, tcg_op, fpst);
}
neon_store_reg32(tcg_res, rd);
vfp_store_reg32(tcg_res, rd);
tcg_temp_free_i32(tcg_op);
tcg_temp_free_i32(tcg_res);
}
@ -463,14 +463,14 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
tcg_double = tcg_temp_new_i64();
tcg_res = tcg_temp_new_i64();
tcg_tmp = tcg_temp_new_i32();
neon_load_reg64(tcg_double, rm);
vfp_load_reg64(tcg_double, rm);
if (is_signed) {
gen_helper_vfp_tosld(tcg_res, tcg_double, tcg_shift, fpst);
} else {
gen_helper_vfp_tould(tcg_res, tcg_double, tcg_shift, fpst);
}
tcg_gen_extrl_i64_i32(tcg_tmp, tcg_res);
neon_store_reg32(tcg_tmp, rd);
vfp_store_reg32(tcg_tmp, rd);
tcg_temp_free_i32(tcg_tmp);
tcg_temp_free_i64(tcg_res);
tcg_temp_free_i64(tcg_double);
@ -478,7 +478,7 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
TCGv_i32 tcg_single, tcg_res;
tcg_single = tcg_temp_new_i32();
tcg_res = tcg_temp_new_i32();
neon_load_reg32(tcg_single, rm);
vfp_load_reg32(tcg_single, rm);
if (sz == 1) {
if (is_signed) {
gen_helper_vfp_toslh(tcg_res, tcg_single, tcg_shift, fpst);
@ -492,7 +492,7 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst);
}
}
neon_store_reg32(tcg_res, rd);
vfp_store_reg32(tcg_res, rd);
tcg_temp_free_i32(tcg_res);
tcg_temp_free_i32(tcg_single);
}
@ -511,11 +511,9 @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a)
{
/* VMOV scalar to general purpose register */
TCGv_i32 tmp;
int pass;
uint32_t offset;
/* SIZE == 2 is a VFP instruction; otherwise NEON. */
if (a->size == 2
/* SIZE == MO_32 is a VFP instruction; otherwise NEON. */
if (a->size == MO_32
? !dc_isar_feature(aa32_fpsp_v2, s)
: !arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -526,44 +524,12 @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a)
return false;
}
offset = a->index << a->size;
pass = extract32(offset, 2, 1);
offset = extract32(offset, 0, 2) * 8;
if (!vfp_access_check(s)) {
return true;
}
tmp = neon_load_reg(a->vn, pass);
switch (a->size) {
case 0:
if (offset) {
tcg_gen_shri_i32(tmp, tmp, offset);
}
if (a->u) {
gen_uxtb(tmp);
} else {
gen_sxtb(tmp);
}
break;
case 1:
if (a->u) {
if (offset) {
tcg_gen_shri_i32(tmp, tmp, 16);
} else {
gen_uxth(tmp);
}
} else {
if (offset) {
tcg_gen_sari_i32(tmp, tmp, 16);
} else {
gen_sxth(tmp);
}
}
break;
case 2:
break;
}
tmp = tcg_temp_new_i32();
read_neon_element32(tmp, a->vn, a->index, a->size | (a->u ? 0 : MO_SIGN));
store_reg(s, a->rt, tmp);
return true;
@ -572,12 +538,10 @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a)
static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a)
{
/* VMOV general purpose register to scalar */
TCGv_i32 tmp, tmp2;
int pass;
uint32_t offset;
TCGv_i32 tmp;
/* SIZE == 2 is a VFP instruction; otherwise NEON. */
if (a->size == 2
/* SIZE == MO_32 is a VFP instruction; otherwise NEON. */
if (a->size == MO_32
? !dc_isar_feature(aa32_fpsp_v2, s)
: !arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
@ -588,30 +552,13 @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a)
return false;
}
offset = a->index << a->size;
pass = extract32(offset, 2, 1);
offset = extract32(offset, 0, 2) * 8;
if (!vfp_access_check(s)) {
return true;
}
tmp = load_reg(s, a->rt);
switch (a->size) {
case 0:
tmp2 = neon_load_reg(a->vn, pass);
tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 8);
tcg_temp_free_i32(tmp2);
break;
case 1:
tmp2 = neon_load_reg(a->vn, pass);
tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 16);
tcg_temp_free_i32(tmp2);
break;
case 2:
break;
}
neon_store_reg(a->vn, pass, tmp);
write_neon_element32(tmp, a->vn, a->index, a->size);
tcg_temp_free_i32(tmp);
return true;
}
@ -653,7 +600,7 @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a)
}
tmp = load_reg(s, a->rt);
tcg_gen_gvec_dup_i32(size, neon_reg_offset(a->vn, 0),
tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(a->vn),
vec_size, vec_size, tmp);
tcg_temp_free_i32(tmp);
@ -829,14 +776,14 @@ static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a)
if (a->l) {
/* VFP to general purpose register */
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vn);
vfp_load_reg32(tmp, a->vn);
tcg_gen_andi_i32(tmp, tmp, 0xffff);
store_reg(s, a->rt, tmp);
} else {
/* general purpose register to VFP */
tmp = load_reg(s, a->rt);
tcg_gen_andi_i32(tmp, tmp, 0xffff);
neon_store_reg32(tmp, a->vn);
vfp_store_reg32(tmp, a->vn);
tcg_temp_free_i32(tmp);
}
@ -858,7 +805,7 @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a)
if (a->l) {
/* VFP to general purpose register */
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vn);
vfp_load_reg32(tmp, a->vn);
if (a->rt == 15) {
/* Set the 4 flag bits in the CPSR. */
gen_set_nzcv(tmp);
@ -869,7 +816,7 @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a)
} else {
/* general purpose register to VFP */
tmp = load_reg(s, a->rt);
neon_store_reg32(tmp, a->vn);
vfp_store_reg32(tmp, a->vn);
tcg_temp_free_i32(tmp);
}
@ -895,18 +842,18 @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a)
if (a->op) {
/* fpreg to gpreg */
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
store_reg(s, a->rt, tmp);
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm + 1);
vfp_load_reg32(tmp, a->vm + 1);
store_reg(s, a->rt2, tmp);
} else {
/* gpreg to fpreg */
tmp = load_reg(s, a->rt);
neon_store_reg32(tmp, a->vm);
vfp_store_reg32(tmp, a->vm);
tcg_temp_free_i32(tmp);
tmp = load_reg(s, a->rt2);
neon_store_reg32(tmp, a->vm + 1);
vfp_store_reg32(tmp, a->vm + 1);
tcg_temp_free_i32(tmp);
}
@ -938,18 +885,18 @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a)
if (a->op) {
/* fpreg to gpreg */
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm * 2);
vfp_load_reg32(tmp, a->vm * 2);
store_reg(s, a->rt, tmp);
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm * 2 + 1);
vfp_load_reg32(tmp, a->vm * 2 + 1);
store_reg(s, a->rt2, tmp);
} else {
/* gpreg to fpreg */
tmp = load_reg(s, a->rt);
neon_store_reg32(tmp, a->vm * 2);
vfp_store_reg32(tmp, a->vm * 2);
tcg_temp_free_i32(tmp);
tmp = load_reg(s, a->rt2);
neon_store_reg32(tmp, a->vm * 2 + 1);
vfp_store_reg32(tmp, a->vm * 2 + 1);
tcg_temp_free_i32(tmp);
}
@ -980,9 +927,9 @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a)
tmp = tcg_temp_new_i32();
if (a->l) {
gen_aa32_ld16u(s, tmp, addr, get_mem_index(s));
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
} else {
neon_load_reg32(tmp, a->vd);
vfp_load_reg32(tmp, a->vd);
gen_aa32_st16(s, tmp, addr, get_mem_index(s));
}
tcg_temp_free_i32(tmp);
@ -1014,9 +961,9 @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a)
tmp = tcg_temp_new_i32();
if (a->l) {
gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
} else {
neon_load_reg32(tmp, a->vd);
vfp_load_reg32(tmp, a->vd);
gen_aa32_st32(s, tmp, addr, get_mem_index(s));
}
tcg_temp_free_i32(tmp);
@ -1055,9 +1002,9 @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a)
tmp = tcg_temp_new_i64();
if (a->l) {
gen_aa32_ld64(s, tmp, addr, get_mem_index(s));
neon_store_reg64(tmp, a->vd);
vfp_store_reg64(tmp, a->vd);
} else {
neon_load_reg64(tmp, a->vd);
vfp_load_reg64(tmp, a->vd);
gen_aa32_st64(s, tmp, addr, get_mem_index(s));
}
tcg_temp_free_i64(tmp);
@ -1119,10 +1066,10 @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a)
if (a->l) {
/* load */
gen_aa32_ld32u(s, tmp, addr, get_mem_index(s));
neon_store_reg32(tmp, a->vd + i);
vfp_store_reg32(tmp, a->vd + i);
} else {
/* store */
neon_load_reg32(tmp, a->vd + i);
vfp_load_reg32(tmp, a->vd + i);
gen_aa32_st32(s, tmp, addr, get_mem_index(s));
}
tcg_gen_addi_i32(addr, addr, offset);
@ -1202,10 +1149,10 @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a)
if (a->l) {
/* load */
gen_aa32_ld64(s, tmp, addr, get_mem_index(s));
neon_store_reg64(tmp, a->vd + i);
vfp_store_reg64(tmp, a->vd + i);
} else {
/* store */
neon_load_reg64(tmp, a->vd + i);
vfp_load_reg64(tmp, a->vd + i);
gen_aa32_st64(s, tmp, addr, get_mem_index(s));
}
tcg_gen_addi_i32(addr, addr, offset);
@ -1338,15 +1285,15 @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn,
fd = tcg_temp_new_i32();
fpst = fpstatus_ptr(FPST_FPCR);
neon_load_reg32(f0, vn);
neon_load_reg32(f1, vm);
vfp_load_reg32(f0, vn);
vfp_load_reg32(f1, vm);
for (;;) {
if (reads_vd) {
neon_load_reg32(fd, vd);
vfp_load_reg32(fd, vd);
}
fn(fd, f0, f1, fpst);
neon_store_reg32(fd, vd);
vfp_store_reg32(fd, vd);
if (veclen == 0) {
break;
@ -1356,10 +1303,10 @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn,
veclen--;
vd = vfp_advance_sreg(vd, delta_d);
vn = vfp_advance_sreg(vn, delta_d);
neon_load_reg32(f0, vn);
vfp_load_reg32(f0, vn);
if (delta_m) {
vm = vfp_advance_sreg(vm, delta_m);
neon_load_reg32(f1, vm);
vfp_load_reg32(f1, vm);
}
}
@ -1402,14 +1349,14 @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn,
fd = tcg_temp_new_i32();
fpst = fpstatus_ptr(FPST_FPCR_F16);
neon_load_reg32(f0, vn);
neon_load_reg32(f1, vm);
vfp_load_reg32(f0, vn);
vfp_load_reg32(f1, vm);
if (reads_vd) {
neon_load_reg32(fd, vd);
vfp_load_reg32(fd, vd);
}
fn(fd, f0, f1, fpst);
neon_store_reg32(fd, vd);
vfp_store_reg32(fd, vd);
tcg_temp_free_i32(f0);
tcg_temp_free_i32(f1);
@ -1469,15 +1416,15 @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn,
fd = tcg_temp_new_i64();
fpst = fpstatus_ptr(FPST_FPCR);
neon_load_reg64(f0, vn);
neon_load_reg64(f1, vm);
vfp_load_reg64(f0, vn);
vfp_load_reg64(f1, vm);
for (;;) {
if (reads_vd) {
neon_load_reg64(fd, vd);
vfp_load_reg64(fd, vd);
}
fn(fd, f0, f1, fpst);
neon_store_reg64(fd, vd);
vfp_store_reg64(fd, vd);
if (veclen == 0) {
break;
@ -1486,10 +1433,10 @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn,
veclen--;
vd = vfp_advance_dreg(vd, delta_d);
vn = vfp_advance_dreg(vn, delta_d);
neon_load_reg64(f0, vn);
vfp_load_reg64(f0, vn);
if (delta_m) {
vm = vfp_advance_dreg(vm, delta_m);
neon_load_reg64(f1, vm);
vfp_load_reg64(f1, vm);
}
}
@ -1542,11 +1489,11 @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
f0 = tcg_temp_new_i32();
fd = tcg_temp_new_i32();
neon_load_reg32(f0, vm);
vfp_load_reg32(f0, vm);
for (;;) {
fn(fd, f0);
neon_store_reg32(fd, vd);
vfp_store_reg32(fd, vd);
if (veclen == 0) {
break;
@ -1556,7 +1503,7 @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
/* single source one-many */
while (veclen--) {
vd = vfp_advance_sreg(vd, delta_d);
neon_store_reg32(fd, vd);
vfp_store_reg32(fd, vd);
}
break;
}
@ -1565,7 +1512,7 @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
veclen--;
vd = vfp_advance_sreg(vd, delta_d);
vm = vfp_advance_sreg(vm, delta_m);
neon_load_reg32(f0, vm);
vfp_load_reg32(f0, vm);
}
tcg_temp_free_i32(f0);
@ -1598,9 +1545,9 @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
}
f0 = tcg_temp_new_i32();
neon_load_reg32(f0, vm);
vfp_load_reg32(f0, vm);
fn(f0, f0);
neon_store_reg32(f0, vd);
vfp_store_reg32(f0, vd);
tcg_temp_free_i32(f0);
return true;
@ -1652,11 +1599,11 @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm)
f0 = tcg_temp_new_i64();
fd = tcg_temp_new_i64();
neon_load_reg64(f0, vm);
vfp_load_reg64(f0, vm);
for (;;) {
fn(fd, f0);
neon_store_reg64(fd, vd);
vfp_store_reg64(fd, vd);
if (veclen == 0) {
break;
@ -1666,7 +1613,7 @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm)
/* single source one-many */
while (veclen--) {
vd = vfp_advance_dreg(vd, delta_d);
neon_store_reg64(fd, vd);
vfp_store_reg64(fd, vd);
}
break;
}
@ -1675,7 +1622,7 @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm)
veclen--;
vd = vfp_advance_dreg(vd, delta_d);
vd = vfp_advance_dreg(vm, delta_m);
neon_load_reg64(f0, vm);
vfp_load_reg64(f0, vm);
}
tcg_temp_free_i64(f0);
@ -2090,20 +2037,20 @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d)
vm = tcg_temp_new_i32();
vd = tcg_temp_new_i32();
neon_load_reg32(vn, a->vn);
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vn, a->vn);
vfp_load_reg32(vm, a->vm);
if (neg_n) {
/* VFNMS, VFMS */
gen_helper_vfp_negh(vn, vn);
}
neon_load_reg32(vd, a->vd);
vfp_load_reg32(vd, a->vd);
if (neg_d) {
/* VFNMA, VFNMS */
gen_helper_vfp_negh(vd, vd);
}
fpst = fpstatus_ptr(FPST_FPCR_F16);
gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst);
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(vn);
@ -2155,20 +2102,20 @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d)
vm = tcg_temp_new_i32();
vd = tcg_temp_new_i32();
neon_load_reg32(vn, a->vn);
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vn, a->vn);
vfp_load_reg32(vm, a->vm);
if (neg_n) {
/* VFNMS, VFMS */
gen_helper_vfp_negs(vn, vn);
}
neon_load_reg32(vd, a->vd);
vfp_load_reg32(vd, a->vd);
if (neg_d) {
/* VFNMA, VFNMS */
gen_helper_vfp_negs(vd, vd);
}
fpst = fpstatus_ptr(FPST_FPCR);
gen_helper_vfp_muladds(vd, vn, vm, vd, fpst);
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(vn);
@ -2226,20 +2173,20 @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d)
vm = tcg_temp_new_i64();
vd = tcg_temp_new_i64();
neon_load_reg64(vn, a->vn);
neon_load_reg64(vm, a->vm);
vfp_load_reg64(vn, a->vn);
vfp_load_reg64(vm, a->vm);
if (neg_n) {
/* VFNMS, VFMS */
gen_helper_vfp_negd(vn, vn);
}
neon_load_reg64(vd, a->vd);
vfp_load_reg64(vd, a->vd);
if (neg_d) {
/* VFNMA, VFNMS */
gen_helper_vfp_negd(vd, vd);
}
fpst = fpstatus_ptr(FPST_FPCR);
gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst);
neon_store_reg64(vd, a->vd);
vfp_store_reg64(vd, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i64(vn);
@ -2283,7 +2230,7 @@ static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a)
}
fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm));
neon_store_reg32(fd, a->vd);
vfp_store_reg32(fd, a->vd);
tcg_temp_free_i32(fd);
return true;
}
@ -2323,7 +2270,7 @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a)
fd = tcg_const_i32(vfp_expand_imm(MO_32, a->imm));
for (;;) {
neon_store_reg32(fd, vd);
vfp_store_reg32(fd, vd);
if (veclen == 0) {
break;
@ -2378,7 +2325,7 @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a)
fd = tcg_const_i64(vfp_expand_imm(MO_64, a->imm));
for (;;) {
neon_store_reg64(fd, vd);
vfp_store_reg64(fd, vd);
if (veclen == 0) {
break;
@ -2450,11 +2397,11 @@ static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a)
vd = tcg_temp_new_i32();
vm = tcg_temp_new_i32();
neon_load_reg32(vd, a->vd);
vfp_load_reg32(vd, a->vd);
if (a->z) {
tcg_gen_movi_i32(vm, 0);
} else {
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
}
if (a->e) {
@ -2489,11 +2436,11 @@ static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a)
vd = tcg_temp_new_i32();
vm = tcg_temp_new_i32();
neon_load_reg32(vd, a->vd);
vfp_load_reg32(vd, a->vd);
if (a->z) {
tcg_gen_movi_i32(vm, 0);
} else {
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
}
if (a->e) {
@ -2533,11 +2480,11 @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a)
vd = tcg_temp_new_i64();
vm = tcg_temp_new_i64();
neon_load_reg64(vd, a->vd);
vfp_load_reg64(vd, a->vd);
if (a->z) {
tcg_gen_movi_i64(vm, 0);
} else {
neon_load_reg64(vm, a->vm);
vfp_load_reg64(vm, a->vm);
}
if (a->e) {
@ -2572,7 +2519,7 @@ static bool trans_VCVT_f32_f16(DisasContext *s, arg_VCVT_f32_f16 *a)
/* The T bit tells us if we want the low or high 16 bits of Vm */
tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t));
gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp_mode);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_i32(ahp_mode);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tmp);
@ -2610,7 +2557,7 @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a)
tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t));
vd = tcg_temp_new_i64();
gen_helper_vfp_fcvt_f16_to_f64(vd, tmp, fpst, ahp_mode);
neon_store_reg64(vd, a->vd);
vfp_store_reg64(vd, a->vd);
tcg_temp_free_i32(ahp_mode);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tmp);
@ -2636,7 +2583,7 @@ static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a)
ahp_mode = get_ahp_flag();
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp_mode);
tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t));
tcg_temp_free_i32(ahp_mode);
@ -2674,7 +2621,7 @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a)
tmp = tcg_temp_new_i32();
vm = tcg_temp_new_i64();
neon_load_reg64(vm, a->vm);
vfp_load_reg64(vm, a->vm);
gen_helper_vfp_fcvt_f64_to_f16(tmp, vm, fpst, ahp_mode);
tcg_temp_free_i64(vm);
tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t));
@ -2698,10 +2645,10 @@ static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a)
}
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR_F16);
gen_helper_rinth(tmp, tmp, fpst);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tmp);
return true;
@ -2721,10 +2668,10 @@ static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a)
}
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
gen_helper_rints(tmp, tmp, fpst);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tmp);
return true;
@ -2753,10 +2700,10 @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a)
}
tmp = tcg_temp_new_i64();
neon_load_reg64(tmp, a->vm);
vfp_load_reg64(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
gen_helper_rintd(tmp, tmp, fpst);
neon_store_reg64(tmp, a->vd);
vfp_store_reg64(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i64(tmp);
return true;
@ -2777,13 +2724,13 @@ static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a)
}
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR_F16);
tcg_rmode = tcg_const_i32(float_round_to_zero);
gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
gen_helper_rinth(tmp, tmp, fpst);
gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tcg_rmode);
tcg_temp_free_i32(tmp);
@ -2805,13 +2752,13 @@ static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a)
}
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
tcg_rmode = tcg_const_i32(float_round_to_zero);
gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
gen_helper_rints(tmp, tmp, fpst);
gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tcg_rmode);
tcg_temp_free_i32(tmp);
@ -2842,13 +2789,13 @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a)
}
tmp = tcg_temp_new_i64();
neon_load_reg64(tmp, a->vm);
vfp_load_reg64(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
tcg_rmode = tcg_const_i32(float_round_to_zero);
gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
gen_helper_rintd(tmp, tmp, fpst);
gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
neon_store_reg64(tmp, a->vd);
vfp_store_reg64(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i64(tmp);
tcg_temp_free_i32(tcg_rmode);
@ -2869,10 +2816,10 @@ static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a)
}
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR_F16);
gen_helper_rinth_exact(tmp, tmp, fpst);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tmp);
return true;
@ -2892,10 +2839,10 @@ static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a)
}
tmp = tcg_temp_new_i32();
neon_load_reg32(tmp, a->vm);
vfp_load_reg32(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
gen_helper_rints_exact(tmp, tmp, fpst);
neon_store_reg32(tmp, a->vd);
vfp_store_reg32(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i32(tmp);
return true;
@ -2924,10 +2871,10 @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a)
}
tmp = tcg_temp_new_i64();
neon_load_reg64(tmp, a->vm);
vfp_load_reg64(tmp, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
gen_helper_rintd_exact(tmp, tmp, fpst);
neon_store_reg64(tmp, a->vd);
vfp_store_reg64(tmp, a->vd);
tcg_temp_free_ptr(fpst);
tcg_temp_free_i64(tmp);
return true;
@ -2953,9 +2900,9 @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a)
vm = tcg_temp_new_i32();
vd = tcg_temp_new_i64();
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
gen_helper_vfp_fcvtds(vd, vm, cpu_env);
neon_store_reg64(vd, a->vd);
vfp_store_reg64(vd, a->vd);
tcg_temp_free_i32(vm);
tcg_temp_free_i64(vd);
return true;
@ -2981,9 +2928,9 @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a)
vd = tcg_temp_new_i32();
vm = tcg_temp_new_i64();
neon_load_reg64(vm, a->vm);
vfp_load_reg64(vm, a->vm);
gen_helper_vfp_fcvtsd(vd, vm, cpu_env);
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_i32(vd);
tcg_temp_free_i64(vm);
return true;
@ -3003,7 +2950,7 @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a)
}
vm = tcg_temp_new_i32();
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
fpst = fpstatus_ptr(FPST_FPCR_F16);
if (a->s) {
/* i32 -> f16 */
@ -3012,7 +2959,7 @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a)
/* u32 -> f16 */
gen_helper_vfp_uitoh(vm, vm, fpst);
}
neon_store_reg32(vm, a->vd);
vfp_store_reg32(vm, a->vd);
tcg_temp_free_i32(vm);
tcg_temp_free_ptr(fpst);
return true;
@ -3032,7 +2979,7 @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a)
}
vm = tcg_temp_new_i32();
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
if (a->s) {
/* i32 -> f32 */
@ -3041,7 +2988,7 @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a)
/* u32 -> f32 */
gen_helper_vfp_uitos(vm, vm, fpst);
}
neon_store_reg32(vm, a->vd);
vfp_store_reg32(vm, a->vd);
tcg_temp_free_i32(vm);
tcg_temp_free_ptr(fpst);
return true;
@ -3068,7 +3015,7 @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a)
vm = tcg_temp_new_i32();
vd = tcg_temp_new_i64();
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
fpst = fpstatus_ptr(FPST_FPCR);
if (a->s) {
/* i32 -> f64 */
@ -3077,7 +3024,7 @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a)
/* u32 -> f64 */
gen_helper_vfp_uitod(vd, vm, fpst);
}
neon_store_reg64(vd, a->vd);
vfp_store_reg64(vd, a->vd);
tcg_temp_free_i32(vm);
tcg_temp_free_i64(vd);
tcg_temp_free_ptr(fpst);
@ -3108,9 +3055,9 @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a)
vm = tcg_temp_new_i64();
vd = tcg_temp_new_i32();
neon_load_reg64(vm, a->vm);
vfp_load_reg64(vm, a->vm);
gen_helper_vjcvt(vd, vm, cpu_env);
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_i64(vm);
tcg_temp_free_i32(vd);
return true;
@ -3133,7 +3080,7 @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a)
frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm);
vd = tcg_temp_new_i32();
neon_load_reg32(vd, a->vd);
vfp_load_reg32(vd, a->vd);
fpst = fpstatus_ptr(FPST_FPCR_F16);
shift = tcg_const_i32(frac_bits);
@ -3168,7 +3115,7 @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a)
g_assert_not_reached();
}
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_i32(vd);
tcg_temp_free_i32(shift);
tcg_temp_free_ptr(fpst);
@ -3192,7 +3139,7 @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a)
frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm);
vd = tcg_temp_new_i32();
neon_load_reg32(vd, a->vd);
vfp_load_reg32(vd, a->vd);
fpst = fpstatus_ptr(FPST_FPCR);
shift = tcg_const_i32(frac_bits);
@ -3227,7 +3174,7 @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a)
g_assert_not_reached();
}
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_i32(vd);
tcg_temp_free_i32(shift);
tcg_temp_free_ptr(fpst);
@ -3257,7 +3204,7 @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a)
frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm);
vd = tcg_temp_new_i64();
neon_load_reg64(vd, a->vd);
vfp_load_reg64(vd, a->vd);
fpst = fpstatus_ptr(FPST_FPCR);
shift = tcg_const_i32(frac_bits);
@ -3292,7 +3239,7 @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a)
g_assert_not_reached();
}
neon_store_reg64(vd, a->vd);
vfp_store_reg64(vd, a->vd);
tcg_temp_free_i64(vd);
tcg_temp_free_i32(shift);
tcg_temp_free_ptr(fpst);
@ -3314,7 +3261,7 @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a)
fpst = fpstatus_ptr(FPST_FPCR_F16);
vm = tcg_temp_new_i32();
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
if (a->s) {
if (a->rz) {
@ -3329,7 +3276,7 @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a)
gen_helper_vfp_touih(vm, vm, fpst);
}
}
neon_store_reg32(vm, a->vd);
vfp_store_reg32(vm, a->vd);
tcg_temp_free_i32(vm);
tcg_temp_free_ptr(fpst);
return true;
@ -3350,7 +3297,7 @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a)
fpst = fpstatus_ptr(FPST_FPCR);
vm = tcg_temp_new_i32();
neon_load_reg32(vm, a->vm);
vfp_load_reg32(vm, a->vm);
if (a->s) {
if (a->rz) {
@ -3365,7 +3312,7 @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a)
gen_helper_vfp_touis(vm, vm, fpst);
}
}
neon_store_reg32(vm, a->vd);
vfp_store_reg32(vm, a->vd);
tcg_temp_free_i32(vm);
tcg_temp_free_ptr(fpst);
return true;
@ -3393,7 +3340,7 @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a)
fpst = fpstatus_ptr(FPST_FPCR);
vm = tcg_temp_new_i64();
vd = tcg_temp_new_i32();
neon_load_reg64(vm, a->vm);
vfp_load_reg64(vm, a->vm);
if (a->s) {
if (a->rz) {
@ -3408,7 +3355,7 @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a)
gen_helper_vfp_touid(vd, vm, fpst);
}
}
neon_store_reg32(vd, a->vd);
vfp_store_reg32(vd, a->vd);
tcg_temp_free_i32(vd);
tcg_temp_free_i64(vm);
tcg_temp_free_ptr(fpst);
@ -3521,10 +3468,10 @@ static bool trans_VINS(DisasContext *s, arg_VINS *a)
/* Insert low half of Vm into high half of Vd */
rm = tcg_temp_new_i32();
rd = tcg_temp_new_i32();
neon_load_reg32(rm, a->vm);
neon_load_reg32(rd, a->vd);
vfp_load_reg32(rm, a->vm);
vfp_load_reg32(rd, a->vd);
tcg_gen_deposit_i32(rd, rd, rm, 16, 16);
neon_store_reg32(rd, a->vd);
vfp_store_reg32(rd, a->vd);
tcg_temp_free_i32(rm);
tcg_temp_free_i32(rd);
return true;
@ -3548,9 +3495,9 @@ static bool trans_VMOVX(DisasContext *s, arg_VINS *a)
/* Set Vd to high half of Vm */
rm = tcg_temp_new_i32();
neon_load_reg32(rm, a->vm);
vfp_load_reg32(rm, a->vm);
tcg_gen_shri_i32(rm, rm, 16);
neon_store_reg32(rm, a->vd);
vfp_store_reg32(rm, a->vd);
tcg_temp_free_i32(rm);
return true;
}

153
target/arm/translate.c
View File

@ -1094,64 +1094,141 @@ static inline void gen_hlt(DisasContext *s, int imm)
unallocated_encoding(s);
}
static inline long vfp_reg_offset(bool dp, unsigned reg)
/*
* Return the offset of a "full" NEON Dreg.
*/
static long neon_full_reg_offset(unsigned reg)
{
return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]);
}
/*
* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
* where 0 is the least significant end of the register.
*/
static long neon_element_offset(int reg, int element, MemOp memop)
{
int element_size = 1 << (memop & MO_SIZE);
int ofs = element * element_size;
#ifdef HOST_WORDS_BIGENDIAN
/*
* Calculate the offset assuming fully little-endian,
* then XOR to account for the order of the 8-byte units.
*/
if (element_size < 8) {
ofs ^= 8 - element_size;
}
#endif
return neon_full_reg_offset(reg) + ofs;
}
/* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */
static long vfp_reg_offset(bool dp, unsigned reg)
{
if (dp) {
return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]);
return neon_element_offset(reg, 0, MO_64);
} else {
long ofs = offsetof(CPUARMState, vfp.zregs[reg >> 2].d[(reg >> 1) & 1]);
if (reg & 1) {
ofs += offsetof(CPU_DoubleU, l.upper);
} else {
ofs += offsetof(CPU_DoubleU, l.lower);
}
return ofs;
return neon_element_offset(reg >> 1, reg & 1, MO_32);
}
}
/* Return the offset of a 32-bit piece of a NEON register.
zero is the least significant end of the register. */
static inline long
neon_reg_offset (int reg, int n)
static inline void vfp_load_reg64(TCGv_i64 var, int reg)
{
int sreg;
sreg = reg * 2 + n;
return vfp_reg_offset(0, sreg);
tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg));
}
static TCGv_i32 neon_load_reg(int reg, int pass)
static inline void vfp_store_reg64(TCGv_i64 var, int reg)
{
TCGv_i32 tmp = tcg_temp_new_i32();
tcg_gen_ld_i32(tmp, cpu_env, neon_reg_offset(reg, pass));
return tmp;
tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg));
}
static void neon_store_reg(int reg, int pass, TCGv_i32 var)
{
tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass));
tcg_temp_free_i32(var);
}
static inline void neon_load_reg64(TCGv_i64 var, int reg)
{
tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg));
}
static inline void neon_store_reg64(TCGv_i64 var, int reg)
{
tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg));
}
static inline void neon_load_reg32(TCGv_i32 var, int reg)
static inline void vfp_load_reg32(TCGv_i32 var, int reg)
{
tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg));
}
static inline void neon_store_reg32(TCGv_i32 var, int reg)
static inline void vfp_store_reg32(TCGv_i32 var, int reg)
{
tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg));
}
static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop)
{
long off = neon_element_offset(reg, ele, memop);
switch (memop) {
case MO_SB:
tcg_gen_ld8s_i32(dest, cpu_env, off);
break;
case MO_UB:
tcg_gen_ld8u_i32(dest, cpu_env, off);
break;
case MO_SW:
tcg_gen_ld16s_i32(dest, cpu_env, off);
break;
case MO_UW:
tcg_gen_ld16u_i32(dest, cpu_env, off);
break;
case MO_UL:
case MO_SL:
tcg_gen_ld_i32(dest, cpu_env, off);
break;
default:
g_assert_not_reached();
}
}
static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop)
{
long off = neon_element_offset(reg, ele, memop);
switch (memop) {
case MO_SL:
tcg_gen_ld32s_i64(dest, cpu_env, off);
break;
case MO_UL:
tcg_gen_ld32u_i64(dest, cpu_env, off);
break;
case MO_Q:
tcg_gen_ld_i64(dest, cpu_env, off);
break;
default:
g_assert_not_reached();
}
}
static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop)
{
long off = neon_element_offset(reg, ele, memop);
switch (memop) {
case MO_8:
tcg_gen_st8_i32(src, cpu_env, off);
break;
case MO_16:
tcg_gen_st16_i32(src, cpu_env, off);
break;
case MO_32:
tcg_gen_st_i32(src, cpu_env, off);
break;
default:
g_assert_not_reached();
}
}
static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop)
{
long off = neon_element_offset(reg, ele, memop);
switch (memop) {
case MO_64:
tcg_gen_st_i64(src, cpu_env, off);
break;
default:
g_assert_not_reached();
}
}
static TCGv_ptr vfp_reg_ptr(bool dp, int reg)
{
TCGv_ptr ret = tcg_temp_new_ptr();

12
target/arm/vec_helper.c
View File

@ -293,7 +293,7 @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
intptr_t index = simd_data(desc);
uint32_t *d = vd;
int8_t *n = vn;
int8_t *m_indexed = (int8_t *)vm + index * 4;
int8_t *m_indexed = (int8_t *)vm + H4(index) * 4;
/* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd.
* Otherwise opr_sz is a multiple of 16.
@ -324,7 +324,7 @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
intptr_t index = simd_data(desc);
uint32_t *d = vd;
uint8_t *n = vn;
uint8_t *m_indexed = (uint8_t *)vm + index * 4;
uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4;
/* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd.
* Otherwise opr_sz is a multiple of 16.
@ -1858,10 +1858,10 @@ DO_ABA(gvec_uaba_d, uint64_t)
r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \
r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \
\
d[H4(0)] = r0; \
d[H4(1)] = r1; \
d[H4(2)] = r2; \
d[H4(3)] = r3; \
d[H2(0)] = r0; \
d[H2(1)] = r1; \
d[H2(2)] = r2; \
d[H2(3)] = r3; \
}
DO_NEON_PAIRWISE(neon_padd, add)

14
tests/qtest/npcm7xx_rng-test.c
View File

@ -265,10 +265,16 @@ int main(int argc, char **argv)
qtest_add_func("npcm7xx_rng/enable_disable", test_enable_disable);
qtest_add_func("npcm7xx_rng/rosel", test_rosel);
qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit);
qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs);
qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit);
qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs);
/*
* These tests fail intermittently; only run them on explicit
* request until we figure out why.
*/
if (getenv("QEMU_TEST_FLAKY_RNG_TESTS")) {
qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit);
qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs);
qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit);
qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs);
}
qtest_start("-machine npcm750-evb");
ret = g_test_run();