Series comparison

Big fat pullreq this time around, because it has all of RTH's
SVE2 emulation patchset in it.

-- PMM

The following changes since commit 0dab1d36f55c3ed649bb8e4c74b9269ef3a63049:

Merge remote-tracking branch 'remotes/stefanha-gitlab/tags/block-pull-request' into staging (2021-05-24 15:48:08 +0100)

are available in the Git repository at:

https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210525

for you to fetch changes up to f8680aaa6e5bfc6022b75157c23db7d2ea98ab11:

target/arm: Enable SVE2 and related extensions (2021-05-25 16:01:44 +0100)

----------------------------------------------------------------
target-arm queue:
 * Implement SVE2 emulation
 * Implement integer matrix multiply accumulate
 * Implement FEAT_TLBIOS
 * Implement FEAT_TLBRANGE
 * disas/libvixl: Protect C system header for C++ compiler
 * Use correct SP in M-profile exception return
 * AN524, AN547: Correct modelling of internal SRAMs
 * hw/intc/arm_gicv3_cpuif: Fix EOIR write access check logic
 * hw/arm/smmuv3: Another range invalidation fix

----------------------------------------------------------------
Eric Auger (1):
      hw/arm/smmuv3: Another range invalidation fix

Peter Maydell (8):
      hw/intc/arm_gicv3_cpuif: Fix EOIR write access check logic
      hw/arm/mps2-tz: Don't duplicate modelling of SRAM in AN524
      hw/arm/mps2-tz: Make SRAM_ADDR_WIDTH board-specific
      hw/arm/armsse.c: Correct modelling of SSE-300 internal SRAMs
      hw/arm/armsse: Convert armsse_realize() to use ERRP_GUARD
      hw/arm/mps2-tz: Allow board to specify a boot RAM size
      hw/arm: Model TCMs in the SSE-300, not the AN547
      target/arm: Use correct SP in M-profile exception return

Philippe Mathieu-Daudé (1):
      disas/libvixl: Protect C system header for C++ compiler

Rebecca Cran (3):
      target/arm: Add support for FEAT_TLBIRANGE
      target/arm: Add support for FEAT_TLBIOS
      target/arm: set ID_AA64ISAR0.TLB to 2 for max AARCH64 CPU type

Richard Henderson (84):
      accel/tcg: Replace g_new() + memcpy() by g_memdup()
      accel/tcg: Pass length argument to tlb_flush_range_locked()
      accel/tlb: Rename TLBFlushPageBitsByMMUIdxData -> TLBFlushRangeData
      accel/tcg: Remove {encode,decode}_pbm_to_runon
      accel/tcg: Add tlb_flush_range_by_mmuidx()
      accel/tcg: Add tlb_flush_range_by_mmuidx_all_cpus()
      accel/tlb: Add tlb_flush_range_by_mmuidx_all_cpus_synced()
      accel/tcg: Rename tlb_flush_page_bits -> range]_by_mmuidx_async_0
      accel/tlb: Rename tlb_flush_[page_bits > range]_by_mmuidx_async_[2 > 1]
      target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2
      target/arm: Implement SVE2 Integer Multiply - Unpredicated
      target/arm: Implement SVE2 integer pairwise add and accumulate long
      target/arm: Implement SVE2 integer unary operations (predicated)
      target/arm: Split out saturating/rounding shifts from neon
      target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated)
      target/arm: Implement SVE2 integer halving add/subtract (predicated)
      target/arm: Implement SVE2 integer pairwise arithmetic
      target/arm: Implement SVE2 saturating add/subtract (predicated)
      target/arm: Implement SVE2 integer add/subtract long
      target/arm: Implement SVE2 integer add/subtract interleaved long
      target/arm: Implement SVE2 integer add/subtract wide
      target/arm: Implement SVE2 integer multiply long
      target/arm: Implement SVE2 PMULLB, PMULLT
      target/arm: Implement SVE2 bitwise shift left long
      target/arm: Implement SVE2 bitwise exclusive-or interleaved
      target/arm: Implement SVE2 bitwise permute
      target/arm: Implement SVE2 complex integer add
      target/arm: Implement SVE2 integer absolute difference and accumulate long
      target/arm: Implement SVE2 integer add/subtract long with carry
      target/arm: Implement SVE2 bitwise shift right and accumulate
      target/arm: Implement SVE2 bitwise shift and insert
      target/arm: Implement SVE2 integer absolute difference and accumulate
      target/arm: Implement SVE2 saturating extract narrow
      target/arm: Implement SVE2 SHRN, RSHRN
      target/arm: Implement SVE2 SQSHRUN, SQRSHRUN
      target/arm: Implement SVE2 UQSHRN, UQRSHRN
      target/arm: Implement SVE2 SQSHRN, SQRSHRN
      target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS
      target/arm: Implement SVE2 WHILERW, WHILEWR
      target/arm: Implement SVE2 bitwise ternary operations
      target/arm: Implement SVE2 saturating multiply-add long
      target/arm: Implement SVE2 saturating multiply-add high
      target/arm: Implement SVE2 integer multiply-add long
      target/arm: Implement SVE2 complex integer multiply-add
      target/arm: Implement SVE2 XAR
      target/arm: Use correct output type for gvec_sdot_*_b
      target/arm: Pass separate addend to {U, S}DOT helpers
      target/arm: Pass separate addend to FCMLA helpers
      target/arm: Split out formats for 2 vectors + 1 index
      target/arm: Split out formats for 3 vectors + 1 index
      target/arm: Implement SVE2 integer multiply (indexed)
      target/arm: Implement SVE2 integer multiply-add (indexed)
      target/arm: Implement SVE2 saturating multiply-add high (indexed)
      target/arm: Implement SVE2 saturating multiply-add (indexed)
      target/arm: Implement SVE2 saturating multiply (indexed)
      target/arm: Implement SVE2 signed saturating doubling multiply high
      target/arm: Implement SVE2 saturating multiply high (indexed)
      target/arm: Implement SVE2 multiply-add long (indexed)
      target/arm: Implement SVE2 integer multiply long (indexed)
      target/arm: Implement SVE2 complex integer multiply-add (indexed)
      target/arm: Implement SVE2 complex integer dot product
      target/arm: Macroize helper_gvec_{s,u}dot_{b,h}
      target/arm: Macroize helper_gvec_{s,u}dot_idx_{b,h}
      target/arm: Implement SVE mixed sign dot product (indexed)
      target/arm: Implement SVE mixed sign dot product
      target/arm: Implement SVE2 crypto unary operations
      target/arm: Implement SVE2 crypto destructive binary operations
      target/arm: Implement SVE2 crypto constructive binary operations
      target/arm: Implement SVE2 FCVTNT
      target/arm: Share table of sve load functions
      target/arm: Tidy do_ldrq
      target/arm: Implement SVE2 LD1RO
      target/arm: Implement 128-bit ZIP, UZP, TRN
      target/arm: Move endian adjustment macros to vec_internal.h
      target/arm: Implement aarch64 SUDOT, USDOT
      target/arm: Split out do_neon_ddda_fpst
      target/arm: Remove unused fpst from VDOT_scalar
      target/arm: Fix decode for VDOT (indexed)
      target/arm: Split out do_neon_ddda
      target/arm: Split decode of VSDOT and VUDOT
      target/arm: Implement aarch32 VSUDOT, VUSDOT
      target/arm: Implement integer matrix multiply accumulate
      linux-user/aarch64: Enable hwcap bits for sve2 and related extensions
      target/arm: Enable SVE2 and related extensions

Stephen Long (17):
      target/arm: Implement SVE2 floating-point pairwise
      target/arm: Implement SVE2 MATCH, NMATCH
      target/arm: Implement SVE2 ADDHNB, ADDHNT
      target/arm: Implement SVE2 RADDHNB, RADDHNT
      target/arm: Implement SVE2 SUBHNB, SUBHNT
      target/arm: Implement SVE2 RSUBHNB, RSUBHNT
      target/arm: Implement SVE2 HISTCNT, HISTSEG
      target/arm: Implement SVE2 scatter store insns
      target/arm: Implement SVE2 gather load insns
      target/arm: Implement SVE2 FMMLA
      target/arm: Implement SVE2 SPLICE, EXT
      target/arm: Implement SVE2 TBL, TBX
      target/arm: Implement SVE2 FCVTLT
      target/arm: Implement SVE2 FCVTXNT, FCVTX
      target/arm: Implement SVE2 FLOGB
      target/arm: Implement SVE2 bitwise shift immediate
      target/arm: Implement SVE2 fp multiply-add long

From: Eric Auger <eric.auger@redhat.com>

6d9cd115b9 ("hw/arm/smmuv3: Enforce invalidation on a power of two range")
failed to completely fix misalignment issues with range
invalidation. For instance invalidations patterns like "invalidate 32
4kB pages starting from 0xff395000 are not correctly handled" due
to the fact the previous fix only made sure the number of invalidated
pages were a power of 2 but did not properly handle the start
address was not aligned with the range. This can be noticed when
boothing a fedora 33 with protected virtio-blk-pci.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Fixes: 6d9cd115b9 ("hw/arm/smmuv3: Enforce invalidation on a power of two range")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/smmuv3.c | 50 +++++++++++++++++++++++++------------------------
 1 file changed, 26 insertions(+), 24 deletions(-)

diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -XXX,XX +XXX,XX @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova,
 
 static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
 {
-    uint8_t scale = 0, num = 0, ttl = 0;
-    dma_addr_t addr = CMD_ADDR(cmd);
+    dma_addr_t end, addr = CMD_ADDR(cmd);
     uint8_t type = CMD_TYPE(cmd);
     uint16_t vmid = CMD_VMID(cmd);
+    uint8_t scale = CMD_SCALE(cmd);
+    uint8_t num = CMD_NUM(cmd);
+    uint8_t ttl = CMD_TTL(cmd);
     bool leaf = CMD_LEAF(cmd);
     uint8_t tg = CMD_TG(cmd);
-    uint64_t first_page = 0, last_page;
-    uint64_t num_pages = 1;
+    uint64_t num_pages;
+    uint8_t granule;
     int asid = -1;
 
-    if (tg) {
-        scale = CMD_SCALE(cmd);
-        num = CMD_NUM(cmd);
-        ttl = CMD_TTL(cmd);
-        num_pages = (num + 1) * BIT_ULL(scale);
-    }
-
     if (type == SMMU_CMD_TLBI_NH_VA) {
         asid = CMD_ASID(cmd);
     }
 
+    if (!tg) {
+        trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, 1, ttl, leaf);
+        smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1);
+        smmu_iotlb_inv_iova(s, asid, addr, tg, 1, ttl);
+        return;
+    }
+
+    /* RIL in use */
+
+    num_pages = (num + 1) * BIT_ULL(scale);
+    granule = tg * 2 + 10;
+
     /* Split invalidations into ^2 range invalidations */
-    last_page = num_pages - 1;
-    while (num_pages) {
-        uint8_t granule = tg * 2 + 10;
-        uint64_t mask, count;
+    end = addr + (num_pages << granule) - 1;
 
-        mask = dma_aligned_pow2_mask(first_page, last_page, 64 - granule);
-        count = mask + 1;
+    while (addr != end + 1) {
+        uint64_t mask = dma_aligned_pow2_mask(addr, end, 64);
 
-        trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, count, ttl, leaf);
-        smmuv3_inv_notifiers_iova(s, asid, addr, tg, count);
-        smmu_iotlb_inv_iova(s, asid, addr, tg, count, ttl);
-
-        num_pages -= count;
-        first_page += count;
-        addr += count * BIT_ULL(granule);
+        num_pages = (mask + 1) >> granule;
+        trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
+        smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages);
+        smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl);
+        addr += mask + 1;
     }
 }
 
-- 
2.20.1

In icc_eoir_write() we assume that we can identify the group of the
IRQ being completed based purely on which register is being written
to and the current CPU state, and that "CPU state matches group
indicated by register" is the only necessary access check.

This isn't correct: if the CPU is not in Secure state then EOIR1 will
only complete Group 1 NS IRQs, but if the CPU is in EL3 it can
complete both Group 1 S and Group 1 NS IRQs.  (The pseudocode
ICC_EOIR1_EL1 makes this clear.) We were also missing the logic to
prevent EOIR0 writes completing G0 IRQs when they should not.

Rearrange the logic to first identify the group of the current
highest priority interrupt and then look at whether we should
complete it or ignore the access based on which register was accessed
and the state of the CPU.  The resulting behavioural change is:
 * EL3 can now complete G1NS interrupts
 * G0 interrupt completion is now ignored if the GIC
   and the CPU have the security extension enabled and
   the CPU is not secure

Reported-by: Chan Kim <ckim@etri.re.kr>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510150016.24910-1-peter.maydell@linaro.org
---
 hw/intc/arm_gicv3_cpuif.c | 48 ++++++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/intc/arm_gicv3_cpuif.c
+++ b/hw/intc/arm_gicv3_cpuif.c
@@ -XXX,XX +XXX,XX @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri,
     GICv3CPUState *cs = icc_cs_from_env(env);
     int irq = value & 0xffffff;
     int grp;
+    bool is_eoir0 = ri->crm == 8;
 
-    if (icv_access(env, ri->crm == 8 ? HCR_FMO : HCR_IMO)) {
+    if (icv_access(env, is_eoir0 ? HCR_FMO : HCR_IMO)) {
         icv_eoir_write(env, ri, value);
         return;
     }
 
-    trace_gicv3_icc_eoir_write(ri->crm == 8 ? 0 : 1,
+    trace_gicv3_icc_eoir_write(is_eoir0 ? 0 : 1,
                                gicv3_redist_affid(cs), value);
 
-    if (ri->crm == 8) {
-        /* EOIR0 */
-        grp = GICV3_G0;
-    } else {
-        /* EOIR1 */
-        if (arm_is_secure(env)) {
-            grp = GICV3_G1;
-        } else {
-            grp = GICV3_G1NS;
-        }
-    }
-
     if (irq >= cs->gic->num_irq) {
         /* This handles two cases:
          * 1. If software writes the ID of a spurious interrupt [ie 1020-1023]
@@ -XXX,XX +XXX,XX @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri,
         return;
     }
 
-    if (icc_highest_active_group(cs) != grp) {
-        return;
+    grp = icc_highest_active_group(cs);
+    switch (grp) {
+    case GICV3_G0:
+        if (!is_eoir0) {
+            return;
+        }
+        if (!(cs->gic->gicd_ctlr & GICD_CTLR_DS)
+            && arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env)) {
+            return;
+        }
+        break;
+    case GICV3_G1:
+        if (is_eoir0) {
+            return;
+        }
+        if (!arm_is_secure(env)) {
+            return;
+        }
+        break;
+    case GICV3_G1NS:
+        if (is_eoir0) {
+            return;
+        }
+        if (!arm_is_el3_or_mon(env) && arm_is_secure(env)) {
+            return;
+        }
+        break;
+    default:
+        g_assert_not_reached();
     }
 
     icc_drop_prio(cs, grp);
-- 
2.20.1

The SRAM at 0x2000_0000 is part of the SSE-200 itself, and we model
it that way in hw/arm/armsse.c (along with the associated MPCs).  We
incorrectly also added an entry to the RAMInfo array for the AN524 in
hw/arm/mps2-tz.c, which was pointless because the CPU would never see
it.  Delete it.

The bug had no guest-visible effect because devices in the SSE-200
take priority over those in the board model (armsse.c maps
s->board_memory at priority -2).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510190844.17799-2-peter.maydell@linaro.org
---
 hw/arm/mps2-tz.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -XXX,XX +XXX,XX @@ static const RAMInfo an524_raminfo[] = { {
         .size = 512 * KiB,
         .mpc = 0,
         .mrindex = 0,
-    }, {
-        .name = "sram",
-        .base = 0x20000000,
-        .size = 32 * 4 * KiB,
-        .mpc = -1,
-        .mrindex = 1,
     }, {
         /* We don't model QSPI flash yet; for now expose it as simple ROM */
         .name = "QSPI",
         .base = 0x28000000,
         .size = 8 * MiB,
         .mpc = 1,
-        .mrindex = 2,
+        .mrindex = 1,
         .flags = IS_ROM,
     }, {
         .name = "DDR",
-- 
2.20.1

The AN547 sets the SRAM_ADDR_WIDTH for the SSE-300 to 21;
since this is not the default value for the SSE-300, model this
in mps2-tz.c as a per-board value.

Reported-by: Devaraj Ranganna <devaraj.ranganna@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510190844.17799-3-peter.maydell@linaro.org
---
 hw/arm/mps2-tz.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass {
     int numirq; /* Number of external interrupts */
     int uart_overflow_irq; /* number of the combined UART overflow IRQ */
     uint32_t init_svtor; /* init-svtor setting for SSE */
+    uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */
     const RAMInfo *raminfo;
     const char *armsse_type;
 };
@@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine)
                              OBJECT(system_memory), &error_abort);
     qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq);
     qdev_prop_set_uint32(iotkitdev, "init-svtor", mmc->init_svtor);
+    qdev_prop_set_uint32(iotkitdev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width);
     qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk);
     qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk);
     sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal);
@@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data)
     mmc->numirq = 92;
     mmc->uart_overflow_irq = 47;
     mmc->init_svtor = 0x10000000;
+    mmc->sram_addr_width = 15;
     mmc->raminfo = an505_raminfo;
     mmc->armsse_type = TYPE_IOTKIT;
     mps2tz_set_default_ram_info(mmc);
@@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data)
     mmc->numirq = 92;
     mmc->uart_overflow_irq = 47;
     mmc->init_svtor = 0x10000000;
+    mmc->sram_addr_width = 15;
     mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */
     mmc->armsse_type = TYPE_SSE200;
     mps2tz_set_default_ram_info(mmc);
@@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data)
     mmc->numirq = 95;
     mmc->uart_overflow_irq = 47;
     mmc->init_svtor = 0x10000000;
+    mmc->sram_addr_width = 15;
     mmc->raminfo = an524_raminfo;
     mmc->armsse_type = TYPE_SSE200;
     mps2tz_set_default_ram_info(mmc);
@@ -XXX,XX +XXX,XX @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data)
     mmc->numirq = 96;
     mmc->uart_overflow_irq = 48;
     mmc->init_svtor = 0x00000000;
+    mmc->sram_addr_width = 21;
     mmc->raminfo = an547_raminfo;
     mmc->armsse_type = TYPE_SSE300;
     mps2tz_set_default_ram_info(mmc);
-- 
2.20.1

The SSE-300 was not correctly modelling its internal SRAMs:
 * the SRAM address width default is 18
 * the SRAM is mapped at 0x2100_0000, not 0x2000_0000 like
   the SSE-200 and IoTKit

The default address width is no longer guest-visible since
our only SSE-300 board sets it explicitly to a non-default
value, but following the hardware's default will help for
any future boards we need to model.

Reported-by: Devaraj Ranganna <devaraj.ranganna@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510190844.17799-4-peter.maydell@linaro.org
---
 hw/arm/armsse.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/armsse.c
+++ b/hw/arm/armsse.c
@@ -XXX,XX +XXX,XX @@ struct ARMSSEInfo {
     const char *cpu_type;
     uint32_t sse_version;
     int sram_banks;
+    uint32_t sram_bank_base;
     int num_cpus;
     uint32_t sys_version;
     uint32_t iidr;
@@ -XXX,XX +XXX,XX @@ static Property sse300_properties[] = {
     DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION,
                      MemoryRegion *),
     DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64),
-    DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15),
+    DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 18),
     DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000),
     DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true),
     DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true),
@@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = {
         .sse_version = ARMSSE_IOTKIT,
         .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"),
         .sram_banks = 1,
+        .sram_bank_base = 0x20000000,
         .num_cpus = 1,
         .sys_version = 0x41743,
         .iidr = 0,
@@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = {
         .sse_version = ARMSSE_SSE200,
         .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"),
         .sram_banks = 4,
+        .sram_bank_base = 0x20000000,
         .num_cpus = 2,
         .sys_version = 0x22041743,
         .iidr = 0,
@@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = {
         .sse_version = ARMSSE_SSE300,
         .cpu_type = ARM_CPU_TYPE_NAME("cortex-m55"),
         .sram_banks = 2,
+        .sram_bank_base = 0x21000000,
         .num_cpus = 1,
         .sys_version = 0x7e00043b,
         .iidr = 0x74a0043b,
@@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp)
         /* Map the upstream end of the MPC into the right place... */
         sbd_mpc = SYS_BUS_DEVICE(&s->mpc[i]);
         memory_region_add_subregion(&s->container,
-                                    0x20000000 + i * sram_bank_size,
+                                    info->sram_bank_base + i * sram_bank_size,
                                     sysbus_mmio_get_region(sbd_mpc, 1));
         /* ...and its register interface */
         memory_region_add_subregion(&s->container, 0x50083000 + i * 0x1000,
-- 
2.20.1

Convert armsse_realize() to use ERRP_GUARD(), following
the rules in include/qapi/error.h.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510190844.17799-5-peter.maydell@linaro.org
---
 hw/arm/armsse.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/armsse.c
+++ b/hw/arm/armsse.c
@@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp)
     const ARMSSEDeviceInfo *devinfo;
     int i;
     MemoryRegion *mr;
-    Error *err = NULL;
     SysBusDevice *sbd_apb_ppc0;
     SysBusDevice *sbd_secctl;
     DeviceState *dev_apb_ppc0;
@@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp)
     DeviceState *dev_splitter;
     uint32_t addr_width_max;
 
+    ERRP_GUARD();
+
     if (!s->board_memory) {
         error_setg(errp, "memory property was not set");
         return;
@@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp)
         uint32_t sram_bank_size = 1 << s->sram_addr_width;
 
         memory_region_init_ram(&s->sram[i], NULL, ramname,
-                               sram_bank_size, &err);
+                               sram_bank_size, errp);
         g_free(ramname);
-        if (err) {
-            error_propagate(errp, err);
+        if (*errp) {
             return;
         }
         object_property_set_link(OBJECT(&s->mpc[i]), "downstream",
-- 
2.20.1

Currently we model the ITCM in the AN547's RAMInfo list. This is incorrect
because this RAM is really a part of the SSE-300. We can't just delete
it from the RAMInfo list, though, because this would make boot_ram_size()
assert because it wouldn't be able to find an entry in the list covering
guest address 0.

Allow a board to specify a boot RAM size manually if it doesn't have
any RAM itself at address 0 and is relying on the SSE for that, and
set the correct value for the AN547. The other boards can continue
to use the "look it up from the RAMInfo list" logic.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510190844.17799-6-peter.maydell@linaro.org
---
 hw/arm/mps2-tz.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass {
     uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */
     const RAMInfo *raminfo;
     const char *armsse_type;
+    uint32_t boot_ram_size; /* size of ram at address 0; 0 == find in raminfo */
 };
 
 struct MPS2TZMachineState {
@@ -XXX,XX +XXX,XX @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms)
     const RAMInfo *p;
     MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms);
 
+    /*
+     * Use a per-board specification (for when the boot RAM is in
+     * the SSE and so doesn't have a RAMInfo list entry)
+     */
+    if (mmc->boot_ram_size) {
+        return mmc->boot_ram_size;
+    }
+
     for (p = mmc->raminfo; p->name; p++) {
         if (p->base == boot_mem_base(mms)) {
             return p->size;
@@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data)
     mmc->sram_addr_width = 15;
     mmc->raminfo = an505_raminfo;
     mmc->armsse_type = TYPE_IOTKIT;
+    mmc->boot_ram_size = 0;
     mps2tz_set_default_ram_info(mmc);
 }
 
@@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data)
     mmc->sram_addr_width = 15;
     mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */
     mmc->armsse_type = TYPE_SSE200;
+    mmc->boot_ram_size = 0;
     mps2tz_set_default_ram_info(mmc);
 }
 
@@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data)
     mmc->sram_addr_width = 15;
     mmc->raminfo = an524_raminfo;
     mmc->armsse_type = TYPE_SSE200;
+    mmc->boot_ram_size = 0;
     mps2tz_set_default_ram_info(mmc);
 
     object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap);
@@ -XXX,XX +XXX,XX @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data)
     mmc->sram_addr_width = 21;
     mmc->raminfo = an547_raminfo;
     mmc->armsse_type = TYPE_SSE300;
+    mmc->boot_ram_size = 512 * KiB;
     mps2tz_set_default_ram_info(mmc);
 }
 
-- 
2.20.1

The SSE-300 has an ITCM at 0x0000_0000 and a DTCM at 0x2000_0000.
Currently we model these in the AN547 board, but this is conceptually
wrong, because they are a part of the SSE-300 itself. Move the
modelling of the TCMs out of mps2-tz.c into sse300.c.

This has no guest-visible effects.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210510190844.17799-7-peter.maydell@linaro.org
---
 include/hw/arm/armsse.h |  2 ++
 hw/arm/armsse.c         | 19 +++++++++++++++++++
 hw/arm/mps2-tz.c        | 12 ------------
 3 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/armsse.h
+++ b/include/hw/arm/armsse.h
@@ -XXX,XX +XXX,XX @@ struct ARMSSE {
     MemoryRegion alias2;
     MemoryRegion alias3[SSE_MAX_CPUS];
     MemoryRegion sram[MAX_SRAM_BANKS];
+    MemoryRegion itcm;
+    MemoryRegion dtcm;
 
     qemu_irq *exp_irqs[SSE_MAX_CPUS];
     qemu_irq ppc0_irq;
diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/armsse.c
+++ b/hw/arm/armsse.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/log.h"
 #include "qemu/module.h"
 #include "qemu/bitops.h"
+#include "qemu/units.h"
 #include "qapi/error.h"
 #include "trace.h"
 #include "hw/sysbus.h"
@@ -XXX,XX +XXX,XX @@ struct ARMSSEInfo {
     bool has_cpuid;
     bool has_cpu_pwrctrl;
     bool has_sse_counter;
+    bool has_tcms;
     Property *props;
     const ARMSSEDeviceInfo *devinfo;
     const bool *irq_is_common;
@@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = {
         .has_cpuid = false,
         .has_cpu_pwrctrl = false,
         .has_sse_counter = false,
+        .has_tcms = false,
         .props = iotkit_properties,
         .devinfo = iotkit_devices,
         .irq_is_common = sse200_irq_is_common,
@@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = {
         .has_cpuid = true,
         .has_cpu_pwrctrl = false,
         .has_sse_counter = false,
+        .has_tcms = false,
         .props = sse200_properties,
         .devinfo = sse200_devices,
         .irq_is_common = sse200_irq_is_common,
@@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = {
         .has_cpuid = true,
         .has_cpu_pwrctrl = true,
         .has_sse_counter = true,
+        .has_tcms = true,
         .props = sse300_properties,
         .devinfo = sse300_devices,
         .irq_is_common = sse300_irq_is_common,
@@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp)
                                     sysbus_mmio_get_region(sbd, 1));
     }
 
+    if (info->has_tcms) {
+        /* The SSE-300 has an ITCM at 0x0000_0000 and a DTCM at 0x2000_0000 */
+        memory_region_init_ram(&s->itcm, NULL, "sse300-itcm", 512 * KiB, errp);
+        if (*errp) {
+            return;
+        }
+        memory_region_init_ram(&s->dtcm, NULL, "sse300-dtcm", 512 * KiB, errp);
+        if (*errp) {
+            return;
+        }
+        memory_region_add_subregion(&s->container, 0x00000000, &s->itcm);
+        memory_region_add_subregion(&s->container, 0x20000000, &s->dtcm);
+    }
+
     /* Devices behind APB PPC0:
      *   0x40000000: timer0
      *   0x40001000: timer1
diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -XXX,XX +XXX,XX @@ static const RAMInfo an524_raminfo[] = { {
 };
 
 static const RAMInfo an547_raminfo[] = { {
-        .name = "itcm",
-        .base = 0x00000000,
-        .size = 512 * KiB,
-        .mpc = -1,
-        .mrindex = 0,
-    }, {
         .name = "sram",
         .base = 0x01000000,
         .size = 2 * MiB,
         .mpc = 0,
         .mrindex = 1,
-    }, {
-        .name = "dtcm",
-        .base = 0x20000000,
-        .size = 4 * 128 * KiB,
-        .mpc = -1,
-        .mrindex = 2,
     }, {
         .name = "sram 2",
         .base = 0x21000000,
-- 
2.20.1

When an M-profile CPU is restoring registers from the stack on
exception return, the stack pointer to use is determined based on
bits in the magic exception return type value.  We were not getting
this logic entirely correct.

Whether we use one of the Secure stack pointers or one of the
Non-Secure stack pointers depends on the EXCRET.S bit.  However,
whether we use the MSP or the PSP then depends on the SPSEL bit in
either the CONTROL_S or CONTROL_NS register.  We were incorrectly
selecting MSP vs PSP based on the EXCRET.SPSEL bit.

(In the pseudocode this is in the PopStack() function, which calls
LookUpSp_with_security_mode() which in turn looks at the relevant
CONTROL.SPSEL bit.)

The buggy behaviour wasn't noticeable in most cases, because we write
EXCRET.SPSEL to the CONTROL.SPSEL bit for the S/NS register selected
by EXCRET.ES, so we only do the wrong thing when EXCRET.S and
EXCRET.ES are different.  This will happen when secure code takes a
secure exception, which then tail-chains to a non-secure exception
which finally returns to the original secure code.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520130905.2049-1-peter.maydell@linaro.org
---
 target/arm/m_helper.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/m_helper.c
+++ b/target/arm/m_helper.c
@@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu)
          * We use this limited C variable scope so we don't accidentally
          * use 'frame_sp_p' after we do something that makes it invalid.
          */
+        bool spsel = env->v7m.control[return_to_secure] & R_V7M_CONTROL_SPSEL_MASK;
         uint32_t *frame_sp_p = get_v7m_sp_ptr(env,
                                               return_to_secure,
                                               !return_to_handler,
-                                              return_to_sp_process);
+                                              spsel);
         uint32_t frameptr = *frame_sp_p;
         bool pop_ok = true;
         ARMMMUIdx mmu_idx;
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Using g_memdup is a bit more compact than g_new + memcpy.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-2-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/cputlb.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
     } else if (encode_pbm_to_runon(&runon, d)) {
         async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
     } else {
-        TLBFlushPageBitsByMMUIdxData *p
-            = g_new(TLBFlushPageBitsByMMUIdxData, 1);
-
         /* Otherwise allocate a structure, freed by the worker.  */
-        *p = d;
+        TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d));
         async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2,
                          RUN_ON_CPU_HOST_PTR(p));
     }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
         flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
     } else {
         CPUState *dst_cpu;
-        TLBFlushPageBitsByMMUIdxData *p;
 
         /* Allocate a separate data block for each destination cpu.  */
         CPU_FOREACH(dst_cpu) {
             if (dst_cpu != src_cpu) {
-                p = g_new(TLBFlushPageBitsByMMUIdxData, 1);
-                *p = d;
+                TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d));
                 async_run_on_cpu(dst_cpu,
                                  tlb_flush_page_bits_by_mmuidx_async_2,
                                  RUN_ON_CPU_HOST_PTR(p));
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
         /* Allocate a separate data block for each destination cpu.  */
         CPU_FOREACH(dst_cpu) {
             if (dst_cpu != src_cpu) {
-                p = g_new(TLBFlushPageBitsByMMUIdxData, 1);
-                *p = d;
+                p = g_memdup(&d, sizeof(d));
                 async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
                                  RUN_ON_CPU_HOST_PTR(p));
             }
         }
 
-        p = g_new(TLBFlushPageBitsByMMUIdxData, 1);
-        *p = d;
+        p = g_memdup(&d, sizeof(d));
         async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
                               RUN_ON_CPU_HOST_PTR(p));
     }
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Rename tlb_flush_page_bits_locked() -> tlb_flush_range_locked(), and
have callers pass a length argument (currently TARGET_PAGE_SIZE) via
the TLBFlushPageBitsByMMUIdxData structure.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-3-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/cputlb.c | 48 +++++++++++++++++++++++++++++++---------------
 1 file changed, 33 insertions(+), 15 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr)
     tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS);
 }
 
-static void tlb_flush_page_bits_locked(CPUArchState *env, int midx,
-                                       target_ulong page, unsigned bits)
+static void tlb_flush_range_locked(CPUArchState *env, int midx,
+                                   target_ulong addr, target_ulong len,
+                                   unsigned bits)
 {
     CPUTLBDesc *d = &env_tlb(env)->d[midx];
     CPUTLBDescFast *f = &env_tlb(env)->f[midx];
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx,
      * If @bits is smaller than the tlb size, there may be multiple entries
      * within the TLB; otherwise all addresses that match under @mask hit
      * the same TLB entry.
-     *
      * TODO: Perhaps allow bits to be a few bits less than the size.
      * For now, just flush the entire TLB.
+     *
+     * If @len is larger than the tlb size, then it will take longer to
+     * test all of the entries in the TLB than it will to flush it all.
      */
-    if (mask < f->mask) {
+    if (mask < f->mask || len > f->mask) {
         tlb_debug("forcing full flush midx %d ("
-                  TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
-                  midx, page, mask);
+                  TARGET_FMT_lx "/" TARGET_FMT_lx "+" TARGET_FMT_lx ")\n",
+                  midx, addr, mask, len);
         tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
         return;
     }
 
-    /* Check if we need to flush due to large pages.  */
-    if ((page & d->large_page_mask) == d->large_page_addr) {
+    /*
+     * Check if we need to flush due to large pages.
+     * Because large_page_mask contains all 1's from the msb,
+     * we only need to test the end of the range.
+     */
+    if (((addr + len - 1) & d->large_page_mask) == d->large_page_addr) {
         tlb_debug("forcing full flush midx %d ("
                   TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
                   midx, d->large_page_addr, d->large_page_mask);
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx,
         return;
     }
 
-    if (tlb_flush_entry_mask_locked(tlb_entry(env, midx, page), page, mask)) {
-        tlb_n_used_entries_dec(env, midx);
+    for (target_ulong i = 0; i < len; i += TARGET_PAGE_SIZE) {
+        target_ulong page = addr + i;
+        CPUTLBEntry *entry = tlb_entry(env, midx, page);
+
+        if (tlb_flush_entry_mask_locked(entry, page, mask)) {
+            tlb_n_used_entries_dec(env, midx);
+        }
+        tlb_flush_vtlb_page_mask_locked(env, midx, page, mask);
     }
-    tlb_flush_vtlb_page_mask_locked(env, midx, page, mask);
 }
 
 typedef struct {
     target_ulong addr;
+    target_ulong len;
     uint16_t idxmap;
     uint16_t bits;
 } TLBFlushPageBitsByMMUIdxData;
@@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
 
     assert_cpu_is_self(cpu);
 
-    tlb_debug("page addr:" TARGET_FMT_lx "/%u mmu_map:0x%x\n",
-              d.addr, d.bits, d.idxmap);
+    tlb_debug("range:" TARGET_FMT_lx "/%u+" TARGET_FMT_lx " mmu_map:0x%x\n",
+              d.addr, d.bits, d.len, d.idxmap);
 
     qemu_spin_lock(&env_tlb(env)->c.lock);
     for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
         if ((d.idxmap >> mmu_idx) & 1) {
-            tlb_flush_page_bits_locked(env, mmu_idx, d.addr, d.bits);
+            tlb_flush_range_locked(env, mmu_idx, d.addr, d.len, d.bits);
         }
     }
     qemu_spin_unlock(&env_tlb(env)->c.lock);
 
-    tb_flush_jmp_cache(cpu, d.addr);
+    for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) {
+        tb_flush_jmp_cache(cpu, d.addr + i);
+    }
 }
 
 static bool encode_pbm_to_runon(run_on_cpu_data *out,
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
 
     /* This should already be page aligned */
     d.addr = addr & TARGET_PAGE_MASK;
+    d.len = TARGET_PAGE_SIZE;
     d.idxmap = idxmap;
     d.bits = bits;
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
 
     /* This should already be page aligned */
     d.addr = addr & TARGET_PAGE_MASK;
+    d.len = TARGET_PAGE_SIZE;
     d.idxmap = idxmap;
     d.bits = bits;
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
 
     /* This should already be page aligned */
     d.addr = addr & TARGET_PAGE_MASK;
+    d.len = TARGET_PAGE_SIZE;
     d.idxmap = idxmap;
     d.bits = bits;
 
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Rename the structure to match the rename of tlb_flush_range_locked.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-4-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/cputlb.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ typedef struct {
     target_ulong len;
     uint16_t idxmap;
     uint16_t bits;
-} TLBFlushPageBitsByMMUIdxData;
+} TLBFlushRangeData;
 
 static void
 tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
-                                      TLBFlushPageBitsByMMUIdxData d)
+                                      TLBFlushRangeData d)
 {
     CPUArchState *env = cpu->env_ptr;
     int mmu_idx;
@@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
 }
 
 static bool encode_pbm_to_runon(run_on_cpu_data *out,
-                                TLBFlushPageBitsByMMUIdxData d)
+                                TLBFlushRangeData d)
 {
     /* We need 6 bits to hold to hold @bits up to 63. */
     if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) {
@@ -XXX,XX +XXX,XX @@ static bool encode_pbm_to_runon(run_on_cpu_data *out,
     return false;
 }
 
-static TLBFlushPageBitsByMMUIdxData
+static TLBFlushRangeData
 decode_runon_to_pbm(run_on_cpu_data data)
 {
     target_ulong addr_map_bits = (target_ulong) data.target_ptr;
-    return (TLBFlushPageBitsByMMUIdxData){
+    return (TLBFlushRangeData){
         .addr = addr_map_bits & TARGET_PAGE_MASK,
         .idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6,
         .bits = addr_map_bits & 0x3f
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu,
 static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
                                                   run_on_cpu_data data)
 {
-    TLBFlushPageBitsByMMUIdxData *d = data.host_ptr;
+    TLBFlushRangeData *d = data.host_ptr;
     tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d);
     g_free(d);
 }
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
 void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
                                    uint16_t idxmap, unsigned bits)
 {
-    TLBFlushPageBitsByMMUIdxData d;
+    TLBFlushRangeData d;
     run_on_cpu_data runon;
 
     /* If all bits are significant, this devolves to tlb_flush_page. */
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
         async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
     } else {
         /* Otherwise allocate a structure, freed by the worker.  */
-        TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d));
+        TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
         async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2,
                          RUN_ON_CPU_HOST_PTR(p));
     }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
                                             uint16_t idxmap,
                                             unsigned bits)
 {
-    TLBFlushPageBitsByMMUIdxData d;
+    TLBFlushRangeData d;
     run_on_cpu_data runon;
 
     /* If all bits are significant, this devolves to tlb_flush_page. */
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
         /* Allocate a separate data block for each destination cpu.  */
         CPU_FOREACH(dst_cpu) {
             if (dst_cpu != src_cpu) {
-                TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d));
+                TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
                 async_run_on_cpu(dst_cpu,
                                  tlb_flush_page_bits_by_mmuidx_async_2,
                                  RUN_ON_CPU_HOST_PTR(p));
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                                    uint16_t idxmap,
                                                    unsigned bits)
 {
-    TLBFlushPageBitsByMMUIdxData d;
+    TLBFlushRangeData d;
     run_on_cpu_data runon;
 
     /* If all bits are significant, this devolves to tlb_flush_page. */
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                               runon);
     } else {
         CPUState *dst_cpu;
-        TLBFlushPageBitsByMMUIdxData *p;
+        TLBFlushRangeData *p;
 
         /* Allocate a separate data block for each destination cpu.  */
         CPU_FOREACH(dst_cpu) {
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

We will not be able to fit address + length into a 64-bit packet.
Drop this optimization before re-organizing this code.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-10-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
[PMM: Moved patch earlier in the series]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/cputlb.c | 86 +++++++++++-----------------------------------
 1 file changed, 20 insertions(+), 66 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
     }
 }
 
-static bool encode_pbm_to_runon(run_on_cpu_data *out,
-                                TLBFlushRangeData d)
-{
-    /* We need 6 bits to hold to hold @bits up to 63. */
-    if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) {
-        *out = RUN_ON_CPU_TARGET_PTR(d.addr | (d.idxmap << 6) | d.bits);
-        return true;
-    }
-    return false;
-}
-
-static TLBFlushRangeData
-decode_runon_to_pbm(run_on_cpu_data data)
-{
-    target_ulong addr_map_bits = (target_ulong) data.target_ptr;
-    return (TLBFlushRangeData){
-        .addr = addr_map_bits & TARGET_PAGE_MASK,
-        .idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6,
-        .bits = addr_map_bits & 0x3f
-    };
-}
-
-static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu,
-                                                  run_on_cpu_data runon)
-{
-    tlb_flush_page_bits_by_mmuidx_async_0(cpu, decode_runon_to_pbm(runon));
-}
-
 static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
                                                   run_on_cpu_data data)
 {
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
                                    uint16_t idxmap, unsigned bits)
 {
     TLBFlushRangeData d;
-    run_on_cpu_data runon;
 
     /* If all bits are significant, this devolves to tlb_flush_page. */
     if (bits >= TARGET_LONG_BITS) {
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
 
     if (qemu_cpu_is_self(cpu)) {
         tlb_flush_page_bits_by_mmuidx_async_0(cpu, d);
-    } else if (encode_pbm_to_runon(&runon, d)) {
-        async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
     } else {
         /* Otherwise allocate a structure, freed by the worker.  */
         TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
                                             unsigned bits)
 {
     TLBFlushRangeData d;
-    run_on_cpu_data runon;
+    CPUState *dst_cpu;
 
     /* If all bits are significant, this devolves to tlb_flush_page. */
     if (bits >= TARGET_LONG_BITS) {
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
     d.idxmap = idxmap;
     d.bits = bits;
 
-    if (encode_pbm_to_runon(&runon, d)) {
-        flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
-    } else {
-        CPUState *dst_cpu;
-
-        /* Allocate a separate data block for each destination cpu.  */
-        CPU_FOREACH(dst_cpu) {
-            if (dst_cpu != src_cpu) {
-                TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
-                async_run_on_cpu(dst_cpu,
-                                 tlb_flush_page_bits_by_mmuidx_async_2,
-                                 RUN_ON_CPU_HOST_PTR(p));
-            }
+    /* Allocate a separate data block for each destination cpu.  */
+    CPU_FOREACH(dst_cpu) {
+        if (dst_cpu != src_cpu) {
+            TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
+            async_run_on_cpu(dst_cpu,
+                             tlb_flush_page_bits_by_mmuidx_async_2,
+                             RUN_ON_CPU_HOST_PTR(p));
         }
     }
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                                    uint16_t idxmap,
                                                    unsigned bits)
 {
-    TLBFlushRangeData d;
-    run_on_cpu_data runon;
+    TLBFlushRangeData d, *p;
+    CPUState *dst_cpu;
 
     /* If all bits are significant, this devolves to tlb_flush_page. */
     if (bits >= TARGET_LONG_BITS) {
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
     d.idxmap = idxmap;
     d.bits = bits;
 
-    if (encode_pbm_to_runon(&runon, d)) {
-        flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon);
-        async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1,
-                              runon);
-    } else {
-        CPUState *dst_cpu;
-        TLBFlushRangeData *p;
-
-        /* Allocate a separate data block for each destination cpu.  */
-        CPU_FOREACH(dst_cpu) {
-            if (dst_cpu != src_cpu) {
-                p = g_memdup(&d, sizeof(d));
-                async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
-                                 RUN_ON_CPU_HOST_PTR(p));
-            }
+    /* Allocate a separate data block for each destination cpu.  */
+    CPU_FOREACH(dst_cpu) {
+        if (dst_cpu != src_cpu) {
+            p = g_memdup(&d, sizeof(d));
+            async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+                             RUN_ON_CPU_HOST_PTR(p));
         }
-
-        p = g_memdup(&d, sizeof(d));
-        async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
-                              RUN_ON_CPU_HOST_PTR(p));
     }
+
+    p = g_memdup(&d, sizeof(d));
+    async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+                          RUN_ON_CPU_HOST_PTR(p));
 }
 
 /* update the TLBs so that writes to code in the virtual page 'addr'
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Forward tlb_flush_page_bits_by_mmuidx to tlb_flush_range_by_mmuidx
passing TARGET_PAGE_SIZE.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-5-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/exec/exec-all.h | 19 +++++++++++++++++++
 accel/tcg/cputlb.c      | 20 +++++++++++++++-----
 2 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr,
 void tlb_flush_page_bits_by_mmuidx_all_cpus_synced
     (CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits);
 
+/**
+ * tlb_flush_range_by_mmuidx
+ * @cpu: CPU whose TLB should be flushed
+ * @addr: virtual address of the start of the range to be flushed
+ * @len: length of range to be flushed
+ * @idxmap: bitmap of mmu indexes to flush
+ * @bits: number of significant bits in address
+ *
+ * For each mmuidx in @idxmap, flush all pages within [@addr,@addr+@len),
+ * comparing only the low @bits worth of each virtual page.
+ */
+void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
+                               target_ulong len, uint16_t idxmap,
+                               unsigned bits);
 /**
  * tlb_set_page_with_attrs:
  * @cpu: CPU to add this TLB entry for
@@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, target_ulong addr,
                                               uint16_t idxmap, unsigned bits)
 {
 }
+static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
+                                             target_ulong len, uint16_t idxmap,
+                                             unsigned bits)
+{
+}
 #endif
 /**
  * probe_access:
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
     g_free(d);
 }
 
-void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
-                                   uint16_t idxmap, unsigned bits)
+void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
+                               target_ulong len, uint16_t idxmap,
+                               unsigned bits)
 {
     TLBFlushRangeData d;
 
-    /* If all bits are significant, this devolves to tlb_flush_page. */
-    if (bits >= TARGET_LONG_BITS) {
+    /*
+     * If all bits are significant, and len is small,
+     * this devolves to tlb_flush_page.
+     */
+    if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) {
         tlb_flush_page_by_mmuidx(cpu, addr, idxmap);
         return;
     }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
 
     /* This should already be page aligned */
     d.addr = addr & TARGET_PAGE_MASK;
-    d.len = TARGET_PAGE_SIZE;
+    d.len = len;
     d.idxmap = idxmap;
     d.bits = bits;
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
     }
 }
 
+void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
+                                   uint16_t idxmap, unsigned bits)
+{
+    tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits);
+}
+
 void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
                                             target_ulong addr,
                                             uint16_t idxmap,
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Forward tlb_flush_page_bits_by_mmuidx_all_cpus to
tlb_flush_range_by_mmuidx_all_cpus passing TARGET_PAGE_SIZE.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-6-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/exec/exec-all.h | 13 +++++++++++++
 accel/tcg/cputlb.c      | 24 +++++++++++++++++-------
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced
 void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
                                target_ulong len, uint16_t idxmap,
                                unsigned bits);
+
+/* Similarly, with broadcast and syncing. */
+void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr,
+                                        target_ulong len, uint16_t idxmap,
+                                        unsigned bits);
+
 /**
  * tlb_set_page_with_attrs:
  * @cpu: CPU to add this TLB entry for
@@ -XXX,XX +XXX,XX @@ static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
                                              unsigned bits)
 {
 }
+static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu,
+                                                      target_ulong addr,
+                                                      target_ulong len,
+                                                      uint16_t idxmap,
+                                                      unsigned bits)
+{
+}
 #endif
 /**
  * probe_access:
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
     tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits);
 }
 
-void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
-                                            target_ulong addr,
-                                            uint16_t idxmap,
-                                            unsigned bits)
+void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu,
+                                        target_ulong addr, target_ulong len,
+                                        uint16_t idxmap, unsigned bits)
 {
     TLBFlushRangeData d;
     CPUState *dst_cpu;
 
-    /* If all bits are significant, this devolves to tlb_flush_page. */
-    if (bits >= TARGET_LONG_BITS) {
+    /*
+     * If all bits are significant, and len is small,
+     * this devolves to tlb_flush_page.
+     */
+    if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) {
         tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap);
         return;
     }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
 
     /* This should already be page aligned */
     d.addr = addr & TARGET_PAGE_MASK;
-    d.len = TARGET_PAGE_SIZE;
+    d.len = len;
     d.idxmap = idxmap;
     d.bits = bits;
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
     tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d);
 }
 
+void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
+                                            target_ulong addr,
+                                            uint16_t idxmap, unsigned bits)
+{
+    tlb_flush_range_by_mmuidx_all_cpus(src_cpu, addr, TARGET_PAGE_SIZE,
+                                       idxmap, bits);
+}
+
 void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                                    target_ulong addr,
                                                    uint16_t idxmap,
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Forward tlb_flush_page_bits_by_mmuidx_all_cpus_synced to
tlb_flush_range_by_mmuidx_all_cpus_synced passing TARGET_PAGE_SIZE.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-7-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/exec/exec-all.h | 12 ++++++++++++
 accel/tcg/cputlb.c      | 27 ++++++++++++++++++++-------
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
 void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr,
                                         target_ulong len, uint16_t idxmap,
                                         unsigned bits);
+void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu,
+                                               target_ulong addr,
+                                               target_ulong len,
+                                               uint16_t idxmap,
+                                               unsigned bits);
 
 /**
  * tlb_set_page_with_attrs:
@@ -XXX,XX +XXX,XX @@ static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu,
                                                       unsigned bits)
 {
 }
+static inline void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu,
+                                                             target_ulong addr,
+                                                             target_long len,
+                                                             uint16_t idxmap,
+                                                             unsigned bits)
+{
+}
 #endif
 /**
  * probe_access:
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
                                        idxmap, bits);
 }
 
-void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
-                                                   target_ulong addr,
-                                                   uint16_t idxmap,
-                                                   unsigned bits)
+void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
+                                               target_ulong addr,
+                                               target_ulong len,
+                                               uint16_t idxmap,
+                                               unsigned bits)
 {
     TLBFlushRangeData d, *p;
     CPUState *dst_cpu;
 
-    /* If all bits are significant, this devolves to tlb_flush_page. */
-    if (bits >= TARGET_LONG_BITS) {
+    /*
+     * If all bits are significant, and len is small,
+     * this devolves to tlb_flush_page.
+     */
+    if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) {
         tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap);
         return;
     }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
 
     /* This should already be page aligned */
     d.addr = addr & TARGET_PAGE_MASK;
-    d.len = TARGET_PAGE_SIZE;
+    d.len = len;
     d.idxmap = idxmap;
     d.bits = bits;
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                           RUN_ON_CPU_HOST_PTR(p));
 }
 
+void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
+                                                   target_ulong addr,
+                                                   uint16_t idxmap,
+                                                   unsigned bits)
+{
+    tlb_flush_range_by_mmuidx_all_cpus_synced(src_cpu, addr, TARGET_PAGE_SIZE,
+                                              idxmap, bits);
+}
+
 /* update the TLBs so that writes to code in the virtual page 'addr'
    can be detected */
 void tlb_protect_code(ram_addr_t ram_addr)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Rename to match tlb_flush_range_locked.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-8-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/cputlb.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ typedef struct {
     uint16_t bits;
 } TLBFlushRangeData;
 
-static void
-tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
-                                      TLBFlushRangeData d)
+static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu,
+                                              TLBFlushRangeData d)
 {
     CPUArchState *env = cpu->env_ptr;
     int mmu_idx;
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
                                                   run_on_cpu_data data)
 {
     TLBFlushRangeData *d = data.host_ptr;
-    tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d);
+    tlb_flush_range_by_mmuidx_async_0(cpu, *d);
     g_free(d);
 }
 
@@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
     d.bits = bits;
 
     if (qemu_cpu_is_self(cpu)) {
-        tlb_flush_page_bits_by_mmuidx_async_0(cpu, d);
+        tlb_flush_range_by_mmuidx_async_0(cpu, d);
     } else {
         /* Otherwise allocate a structure, freed by the worker.  */
         TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
@@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu,
         }
     }
 
-    tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d);
+    tlb_flush_range_by_mmuidx_async_0(src_cpu, d);
 }
 
 void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Rename to match tlb_flush_range_locked.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-id: 20210509151618.2331764-9-f4bug@amsat.org
Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org>
[PMD: Split from bigger patch]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/cputlb.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -XXX,XX +XXX,XX @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu,
     }
 }
 
-static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
-                                                  run_on_cpu_data data)
+static void tlb_flush_range_by_mmuidx_async_1(CPUState *cpu,
+                                              run_on_cpu_data data)
 {
     TLBFlushRangeData *d = data.host_ptr;
     tlb_flush_range_by_mmuidx_async_0(cpu, *d);
@@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr,
     } else {
         /* Otherwise allocate a structure, freed by the worker.  */
         TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
-        async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+        async_run_on_cpu(cpu, tlb_flush_range_by_mmuidx_async_1,
                          RUN_ON_CPU_HOST_PTR(p));
     }
 }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu,
         if (dst_cpu != src_cpu) {
             TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
             async_run_on_cpu(dst_cpu,
-                             tlb_flush_page_bits_by_mmuidx_async_2,
+                             tlb_flush_range_by_mmuidx_async_1,
                              RUN_ON_CPU_HOST_PTR(p));
         }
     }
@@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
     CPU_FOREACH(dst_cpu) {
         if (dst_cpu != src_cpu) {
             p = g_memdup(&d, sizeof(d));
-            async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+            async_run_on_cpu(dst_cpu, tlb_flush_range_by_mmuidx_async_1,
                              RUN_ON_CPU_HOST_PTR(p));
         }
     }
 
     p = g_memdup(&d, sizeof(d));
-    async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+    async_safe_run_on_cpu(src_cpu, tlb_flush_range_by_mmuidx_async_1,
                           RUN_ON_CPU_HOST_PTR(p));
 }
 
-- 
2.20.1

From: Rebecca Cran <rebecca@nuviainc.com>

ARMv8.4 adds the mandatory FEAT_TLBIRANGE. It provides TLBI
maintenance instructions that apply to a range of input addresses.

Signed-off-by: Rebecca Cran <rebecca@nuviainc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210512182337.18563-2-rebecca@nuviainc.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h    |   5 +
 target/arm/helper.c | 281 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 286 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pauth_arch(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0;
 }
 
+static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2;
+}
+
 static inline bool isar_feature_aa64_sb(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0;
diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
                                                   ARMMMUIdxBit_SE3, bits);
 }
 
+#ifdef TARGET_AARCH64
+static uint64_t tlbi_aa64_range_get_length(CPUARMState *env,
+                                           uint64_t value)
+{
+    unsigned int page_shift;
+    unsigned int page_size_granule;
+    uint64_t num;
+    uint64_t scale;
+    uint64_t exponent;
+    uint64_t length;
+
+    num = extract64(value, 39, 4);
+    scale = extract64(value, 44, 2);
+    page_size_granule = extract64(value, 46, 2);
+
+    page_shift = page_size_granule * 2 + 12;
+
+    if (page_size_granule == 0) {
+        qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n",
+                      page_size_granule);
+        return 0;
+    }
+
+    exponent = (5 * scale) + 1;
+    length = (num + 1) << (exponent + page_shift);
+
+    return length;
+}
+
+static uint64_t tlbi_aa64_range_get_base(CPUARMState *env, uint64_t value,
+                                        bool two_ranges)
+{
+    /* TODO: ARMv8.7 FEAT_LPA2 */
+    uint64_t pageaddr;
+
+    if (two_ranges) {
+        pageaddr = sextract64(value, 0, 37) << TARGET_PAGE_BITS;
+    } else {
+        pageaddr = extract64(value, 0, 37) << TARGET_PAGE_BITS;
+    }
+
+    return pageaddr;
+}
+
+static void do_rvae_write(CPUARMState *env, uint64_t value,
+                          int idxmap, bool synced)
+{
+    ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap);
+    bool two_ranges = regime_has_2_ranges(one_idx);
+    uint64_t baseaddr, length;
+    int bits;
+
+    baseaddr = tlbi_aa64_range_get_base(env, value, two_ranges);
+    length = tlbi_aa64_range_get_length(env, value);
+    bits = tlbbits_for_regime(env, one_idx, baseaddr);
+
+    if (synced) {
+        tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env),
+                                                  baseaddr,
+                                                  length,
+                                                  idxmap,
+                                                  bits);
+    } else {
+        tlb_flush_range_by_mmuidx(env_cpu(env), baseaddr,
+                                  length, idxmap, bits);
+    }
+}
+
+static void tlbi_aa64_rvae1_write(CPUARMState *env,
+                                  const ARMCPRegInfo *ri,
+                                  uint64_t value)
+{
+    /*
+     * Invalidate by VA range, EL1&0.
+     * Currently handles all of RVAE1, RVAAE1, RVAALE1 and RVALE1,
+     * since we don't support flush-for-specific-ASID-only or
+     * flush-last-level-only.
+     */
+
+    do_rvae_write(env, value, vae1_tlbmask(env),
+                  tlb_force_broadcast(env));
+}
+
+static void tlbi_aa64_rvae1is_write(CPUARMState *env,
+                                    const ARMCPRegInfo *ri,
+                                    uint64_t value)
+{
+    /*
+     * Invalidate by VA range, Inner/Outer Shareable EL1&0.
+     * Currently handles all of RVAE1IS, RVAE1OS, RVAAE1IS, RVAAE1OS,
+     * RVAALE1IS, RVAALE1OS, RVALE1IS and RVALE1OS, since we don't support
+     * flush-for-specific-ASID-only, flush-last-level-only or inner/outer
+     * shareable specific flushes.
+     */
+
+    do_rvae_write(env, value, vae1_tlbmask(env), true);
+}
+
+static int vae2_tlbmask(CPUARMState *env)
+{
+    return (arm_is_secure_below_el3(env)
+            ? ARMMMUIdxBit_SE2 : ARMMMUIdxBit_E2);
+}
+
+static void tlbi_aa64_rvae2_write(CPUARMState *env,
+                                  const ARMCPRegInfo *ri,
+                                  uint64_t value)
+{
+    /*
+     * Invalidate by VA range, EL2.
+     * Currently handles all of RVAE2 and RVALE2,
+     * since we don't support flush-for-specific-ASID-only or
+     * flush-last-level-only.
+     */
+
+    do_rvae_write(env, value, vae2_tlbmask(env),
+                  tlb_force_broadcast(env));
+
+
+}
+
+static void tlbi_aa64_rvae2is_write(CPUARMState *env,
+                                    const ARMCPRegInfo *ri,
+                                    uint64_t value)
+{
+    /*
+     * Invalidate by VA range, Inner/Outer Shareable, EL2.
+     * Currently handles all of RVAE2IS, RVAE2OS, RVALE2IS and RVALE2OS,
+     * since we don't support flush-for-specific-ASID-only,
+     * flush-last-level-only or inner/outer shareable specific flushes.
+     */
+
+    do_rvae_write(env, value, vae2_tlbmask(env), true);
+
+}
+
+static void tlbi_aa64_rvae3_write(CPUARMState *env,
+                                  const ARMCPRegInfo *ri,
+                                  uint64_t value)
+{
+    /*
+     * Invalidate by VA range, EL3.
+     * Currently handles all of RVAE3 and RVALE3,
+     * since we don't support flush-for-specific-ASID-only or
+     * flush-last-level-only.
+     */
+
+    do_rvae_write(env, value, ARMMMUIdxBit_SE3,
+                  tlb_force_broadcast(env));
+}
+
+static void tlbi_aa64_rvae3is_write(CPUARMState *env,
+                                    const ARMCPRegInfo *ri,
+                                    uint64_t value)
+{
+    /*
+     * Invalidate by VA range, EL3, Inner/Outer Shareable.
+     * Currently handles all of RVAE3IS, RVAE3OS, RVALE3IS and RVALE3OS,
+     * since we don't support flush-for-specific-ASID-only,
+     * flush-last-level-only or inner/outer specific flushes.
+     */
+
+    do_rvae_write(env, value, ARMMMUIdxBit_SE3, true);
+}
+#endif
+
 static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri,
                                       bool isread)
 {
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo pauth_reginfo[] = {
     REGINFO_SENTINEL
 };
 
+static const ARMCPRegInfo tlbirange_reginfo[] = {
+    { .name = "TLBI_RVAE1IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 1,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+    { .name = "TLBI_RVAAE1IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 3,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+   { .name = "TLBI_RVALE1IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 5,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+    { .name = "TLBI_RVAALE1IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 7,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+    { .name = "TLBI_RVAE1OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+    { .name = "TLBI_RVAAE1OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 3,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+   { .name = "TLBI_RVALE1OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 5,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+    { .name = "TLBI_RVAALE1OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 7,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1is_write },
+    { .name = "TLBI_RVAE1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1_write },
+    { .name = "TLBI_RVAAE1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 3,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1_write },
+   { .name = "TLBI_RVALE1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 5,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1_write },
+    { .name = "TLBI_RVAALE1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 7,
+      .access = PL1_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae1_write },
+    { .name = "TLBI_RIPAS2E1IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 2,
+      .access = PL2_W, .type = ARM_CP_NOP },
+    { .name = "TLBI_RIPAS2LE1IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 6,
+      .access = PL2_W, .type = ARM_CP_NOP },
+    { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1,
+      .access = PL2_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae2is_write },
+   { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5,
+      .access = PL2_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae2is_write },
+    { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2,
+      .access = PL2_W, .type = ARM_CP_NOP },
+   { .name = "TLBI_RIPAS2LE1", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 6,
+      .access = PL2_W, .type = ARM_CP_NOP },
+   { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1,
+      .access = PL2_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae2is_write },
+   { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5,
+      .access = PL2_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae2is_write },
+    { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1,
+      .access = PL2_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae2_write },
+   { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5,
+      .access = PL2_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae2_write },
+   { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1,
+      .access = PL3_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae3is_write },
+   { .name = "TLBI_RVALE3IS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 5,
+      .access = PL3_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae3is_write },
+   { .name = "TLBI_RVAE3OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 1,
+      .access = PL3_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae3is_write },
+   { .name = "TLBI_RVALE3OS", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 5,
+      .access = PL3_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae3is_write },
+   { .name = "TLBI_RVAE3", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 1,
+      .access = PL3_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae3_write },
+   { .name = "TLBI_RVALE3", .state = ARM_CP_STATE_AA64,
+      .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 5,
+      .access = PL3_W, .type = ARM_CP_NO_RAW,
+      .writefn = tlbi_aa64_rvae3_write },
+    REGINFO_SENTINEL
+};
+
 static uint64_t rndr_readfn(CPUARMState *env, const ARMCPRegInfo *ri)
 {
     Error *err = NULL;
@@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu)
     if (cpu_isar_feature(aa64_rndr, cpu)) {
         define_arm_cp_regs(cpu, rndr_reginfo);
     }
+    if (cpu_isar_feature(aa64_tlbirange, cpu)) {
+        define_arm_cp_regs(cpu, tlbirange_reginfo);
+    }
 #ifndef CONFIG_USER_ONLY
     /* Data Cache clean instructions up to PoP */
     if (cpu_isar_feature(aa64_dcpop, cpu)) {
-- 
2.20.1

From: Rebecca Cran <rebecca@nuviainc.com>

ARMv8.4 adds the mandatory FEAT_TLBIOS. It provides TLBI
maintenance instructions that extend to the Outer Shareable domain.

Signed-off-by: Rebecca Cran <rebecca@nuviainc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210512182337.18563-3-rebecca@nuviainc.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h    |  5 +++++
 target/arm/helper.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

From: Philippe Mathieu-Daudé <f4bug@amsat.org>

When selecting an ARM target on Debian unstable, we get:

Compiling C++ object libcommon.fa.p/disas_libvixl_vixl_utils.cc.o
  FAILED: libcommon.fa.p/disas_libvixl_vixl_utils.cc.o
  c++ -Ilibcommon.fa.p -I. -I.. [...] -o libcommon.fa.p/disas_libvixl_vixl_utils.cc.o -c ../disas/libvixl/vixl/utils.cc
  In file included from /home/philmd/qemu/disas/libvixl/vixl/utils.h:30,
                   from ../disas/libvixl/vixl/utils.cc:27:
  /usr/include/string.h:36:43: error: missing binary operator before token "("
     36 | #if defined __cplusplus && (__GNUC_PREREQ (4, 4) \
        |                                           ^
  /usr/include/string.h:53:62: error: missing binary operator before token "("
     53 | #if defined __USE_MISC || defined __USE_XOPEN || __GLIBC_USE (ISOC2X)
        |                                                              ^
  /usr/include/string.h:165:21: error: missing binary operator before token "("
    165 |      || __GLIBC_USE (LIB_EXT2) || __GLIBC_USE (ISOC2X))
        |                     ^
  /usr/include/string.h:174:43: error: missing binary operator before token "("
    174 | #if defined __USE_XOPEN2K8 || __GLIBC_USE (LIB_EXT2) || __GLIBC_USE (ISOC2X)
        |                                           ^
  /usr/include/string.h:492:19: error: missing binary operator before token "("
    492 | #if __GNUC_PREREQ (3,4)
        |                   ^

Relevant information from the host:

$ lsb_release -d
  Description:    Debian GNU/Linux 11 (bullseye)
  $ gcc --version
  gcc (Debian 10.2.1-6) 10.2.1 20210110
  $ dpkg -S /usr/include/string.h
  libc6-dev: /usr/include/string.h
  $ apt-cache show libc6-dev
  Package: libc6-dev
  Version: 2.31-11

Partially cherry-pick vixl commit 78973f258039f6e96 [*]:

Refactor VIXL to use `extern` block when including C header
  that do not have a C++ counterpart.

which is similar to commit 875df03b221 ('osdep: protect qemu/osdep.h
with extern "C"').

[*] https://git.linaro.org/arm/vixl.git/commit/?id=78973f258039f6e96

Buglink: https://bugs.launchpad.net/qemu/+bug/1914870
Suggested-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-id: 20210516171023.510778-1-f4bug@amsat.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 disas/libvixl/vixl/code-buffer.h |  2 +-
 disas/libvixl/vixl/globals.h     | 16 +++++++++-------
 disas/libvixl/vixl/invalset.h    |  2 +-
 disas/libvixl/vixl/platform.h    |  2 ++
 disas/libvixl/vixl/utils.h       |  2 +-
 disas/libvixl/vixl/utils.cc      |  2 +-
 6 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/disas/libvixl/vixl/code-buffer.h b/disas/libvixl/vixl/code-buffer.h
index XXXXXXX..XXXXXXX 100644
--- a/disas/libvixl/vixl/code-buffer.h
+++ b/disas/libvixl/vixl/code-buffer.h
@@ -XXX,XX +XXX,XX @@
 #ifndef VIXL_CODE_BUFFER_H
 #define VIXL_CODE_BUFFER_H
 
-#include <string.h>
+#include <cstring>
 #include "vixl/globals.h"
 
 namespace vixl {
diff --git a/disas/libvixl/vixl/globals.h b/disas/libvixl/vixl/globals.h
index XXXXXXX..XXXXXXX 100644
--- a/disas/libvixl/vixl/globals.h
+++ b/disas/libvixl/vixl/globals.h
@@ -XXX,XX +XXX,XX @@
 #define __STDC_FORMAT_MACROS
 #endif
 
-#include <stdint.h>
+extern "C" {
 #include <inttypes.h>
-
-#include <assert.h>
-#include <stdarg.h>
-#include <stdio.h>
 #include <stdint.h>
-#include <stdlib.h>
-#include <stddef.h>
+}
+
+#include <cassert>
+#include <cstdarg>
+#include <cstddef>
+#include <cstdio>
+#include <cstdlib>
+
 #include "vixl/platform.h"
 
 
diff --git a/disas/libvixl/vixl/invalset.h b/disas/libvixl/vixl/invalset.h
index XXXXXXX..XXXXXXX 100644
--- a/disas/libvixl/vixl/invalset.h
+++ b/disas/libvixl/vixl/invalset.h
@@ -XXX,XX +XXX,XX @@
 #ifndef VIXL_INVALSET_H_
 #define VIXL_INVALSET_H_
 
-#include <string.h>
+#include <cstring>
 
 #include <algorithm>
 #include <vector>
diff --git a/disas/libvixl/vixl/platform.h b/disas/libvixl/vixl/platform.h
index XXXXXXX..XXXXXXX 100644
--- a/disas/libvixl/vixl/platform.h
+++ b/disas/libvixl/vixl/platform.h
@@ -XXX,XX +XXX,XX @@
 #define PLATFORM_H
 
 // Define platform specific functionalities.
+extern "C" {
 #include <signal.h>
+}
 
 namespace vixl {
 inline void HostBreakpoint() { raise(SIGINT); }
diff --git a/disas/libvixl/vixl/utils.h b/disas/libvixl/vixl/utils.h
index XXXXXXX..XXXXXXX 100644
--- a/disas/libvixl/vixl/utils.h
+++ b/disas/libvixl/vixl/utils.h
@@ -XXX,XX +XXX,XX @@
 #ifndef VIXL_UTILS_H
 #define VIXL_UTILS_H
 
-#include <string.h>
 #include <cmath>
+#include <cstring>
 #include "vixl/globals.h"
 #include "vixl/compiler-intrinsics.h"
 
diff --git a/disas/libvixl/vixl/utils.cc b/disas/libvixl/vixl/utils.cc
index XXXXXXX..XXXXXXX 100644
--- a/disas/libvixl/vixl/utils.cc
+++ b/disas/libvixl/vixl/utils.cc
@@ -XXX,XX +XXX,XX @@
 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #include "vixl/utils.h"
-#include <stdio.h>
+#include <cstdio>
 
 namespace vixl {
 
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Will be used for SVE2 isa subset enablement.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-2-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h    | 16 ++++++++++++++++
 target/arm/helper.c |  3 +--
 target/arm/kvm64.c  | 21 +++++++++++++++------
 3 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ARMCPU {
         uint64_t id_aa64mmfr2;
         uint64_t id_aa64dfr0;
         uint64_t id_aa64dfr1;
+        uint64_t id_aa64zfr0;
     } isar;
     uint64_t midr;
     uint32_t revidr;
@@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4)
 FIELD(ID_AA64DFR0, TRACEFILT, 40, 4)
 FIELD(ID_AA64DFR0, MTPMU, 48, 4)
 
+FIELD(ID_AA64ZFR0, SVEVER, 0, 4)
+FIELD(ID_AA64ZFR0, AES, 4, 4)
+FIELD(ID_AA64ZFR0, BITPERM, 16, 4)
+FIELD(ID_AA64ZFR0, BFLOAT16, 20, 4)
+FIELD(ID_AA64ZFR0, SHA3, 32, 4)
+FIELD(ID_AA64ZFR0, SM4, 40, 4)
+FIELD(ID_AA64ZFR0, I8MM, 44, 4)
+FIELD(ID_AA64ZFR0, F32MM, 52, 4)
+FIELD(ID_AA64ZFR0, F64MM, 56, 4)
+
 FIELD(ID_DFR0, COPDBG, 0, 4)
 FIELD(ID_DFR0, COPSDBG, 4, 4)
 FIELD(ID_DFR0, MMAPDBG, 8, 4)
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0;
 }
 
+static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0;
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 4,
               .access = PL1_R, .type = ARM_CP_CONST,
               .accessfn = access_aa64_tid3,
-              /* At present, only SVEver == 0 is defined anyway.  */
-              .resetvalue = 0 },
+              .resetvalue = cpu->isar.id_aa64zfr0 },
             { .name = "ID_AA64PFR5_EL1_RESERVED", .state = ARM_CP_STATE_AA64,
               .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 5,
               .access = PL1_R, .type = ARM_CP_CONST,
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/kvm64.c
+++ b/target/arm/kvm64.c
@@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
 
     sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0;
 
-    kvm_arm_destroy_scratch_host_vcpu(fdarray);
-
-    if (err < 0) {
-        return false;
-    }
-
     /* Add feature bits that can't appear until after VCPU init. */
     if (sve_supported) {
         t = ahcf->isar.id_aa64pfr0;
         t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1);
         ahcf->isar.id_aa64pfr0 = t;
+
+        /*
+         * Before v5.1, KVM did not support SVE and did not expose
+         * ID_AA64ZFR0_EL1 even as RAZ.  After v5.1, KVM still does
+         * not expose the register to "user" requests like this
+         * unless the host supports SVE.
+         */
+        err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64zfr0,
+                              ARM64_SYS_REG(3, 0, 0, 4, 4));
+    }
+
+    kvm_arm_destroy_scratch_host_vcpu(fdarray);
+
+    if (err < 0) {
+        return false;
     }
 
     /*
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

For MUL, we can rely on generic support.  For SMULH and UMULH,
create some trivial helpers.  For PMUL, back in a21bb78e5817,
we organized helper_gvec_pmul_b in preparation for this use.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h        | 10 ++++
 target/arm/sve.decode      | 10 ++++
 target/arm/translate-sve.c | 50 ++++++++++++++++++++
 target/arm/vec_helper.c    | 96 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 166 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 14 ++++++++++++
 target/arm/sve.decode      |  5 +++++
 target/arm/sve_helper.c    | 44 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 39 +++++++++++++++++++++++++++++++++
 4 files changed, 102 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 13 +++++++++++
 target/arm/sve.decode      |  7 ++++++
 target/arm/sve_helper.c    | 21 +++++++++++++++++
 target/arm/translate-sve.c | 47 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 88 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Split these operations out into a header that can be shared
between neon and sve.  The "sat" pointer acts both as a boolean
for control of saturating behavior and controls the difference
in behavior between neon and sve -- QC bit or no QC bit.

Widen the shift operand in the new helpers, as the SVE2 insns treat
the whole input element as significant.  For the neon uses, truncate
the shift to int8_t while passing the parameter.

Implement right-shift rounding as

tmp = src >> (shift - 1);
    dst = (tmp >> 1) + (tmp & 1);

This is the same number of instructions as the current

tmp = 1 << (shift - 1);
    dst = (src + tmp) >> shift;

without any possibility of intermediate overflow.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-6-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/vec_internal.h | 138 +++++++++++
 target/arm/neon_helper.c  | 507 +++++++-------------------------------
 2 files changed, 221 insertions(+), 424 deletions(-)

diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_internal.h
+++ b/target/arm/vec_internal.h
@@ -XXX,XX +XXX,XX @@ static inline void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz)
     }
 }
 
+static inline int32_t do_sqrshl_bhs(int32_t src, int32_t shift, int bits,
+                                    bool round, uint32_t *sat)
+{
+    if (shift <= -bits) {
+        /* Rounding the sign bit always produces 0. */
+        if (round) {
+            return 0;
+        }
+        return src >> 31;
+    } else if (shift < 0) {
+        if (round) {
+            src >>= -shift - 1;
+            return (src >> 1) + (src & 1);
+        }
+        return src >> -shift;
+    } else if (shift < bits) {
+        int32_t val = src << shift;
+        if (bits == 32) {
+            if (!sat || val >> shift == src) {
+                return val;
+            }
+        } else {
+            int32_t extval = sextract32(val, 0, bits);
+            if (!sat || val == extval) {
+                return extval;
+            }
+        }
+    } else if (!sat || src == 0) {
+        return 0;
+    }
+
+    *sat = 1;
+    return (1u << (bits - 1)) - (src >= 0);
+}
+
+static inline uint32_t do_uqrshl_bhs(uint32_t src, int32_t shift, int bits,
+                                     bool round, uint32_t *sat)
+{
+    if (shift <= -(bits + round)) {
+        return 0;
+    } else if (shift < 0) {
+        if (round) {
+            src >>= -shift - 1;
+            return (src >> 1) + (src & 1);
+        }
+        return src >> -shift;
+    } else if (shift < bits) {
+        uint32_t val = src << shift;
+        if (bits == 32) {
+            if (!sat || val >> shift == src) {
+                return val;
+            }
+        } else {
+            uint32_t extval = extract32(val, 0, bits);
+            if (!sat || val == extval) {
+                return extval;
+            }
+        }
+    } else if (!sat || src == 0) {
+        return 0;
+    }
+
+    *sat = 1;
+    return MAKE_64BIT_MASK(0, bits);
+}
+
+static inline int32_t do_suqrshl_bhs(int32_t src, int32_t shift, int bits,
+                                     bool round, uint32_t *sat)
+{
+    if (sat && src < 0) {
+        *sat = 1;
+        return 0;
+    }
+    return do_uqrshl_bhs(src, shift, bits, round, sat);
+}
+
+static inline int64_t do_sqrshl_d(int64_t src, int64_t shift,
+                                  bool round, uint32_t *sat)
+{
+    if (shift <= -64) {
+        /* Rounding the sign bit always produces 0. */
+        if (round) {
+            return 0;
+        }
+        return src >> 63;
+    } else if (shift < 0) {
+        if (round) {
+            src >>= -shift - 1;
+            return (src >> 1) + (src & 1);
+        }
+        return src >> -shift;
+    } else if (shift < 64) {
+        int64_t val = src << shift;
+        if (!sat || val >> shift == src) {
+            return val;
+        }
+    } else if (!sat || src == 0) {
+        return 0;
+    }
+
+    *sat = 1;
+    return src < 0 ? INT64_MIN : INT64_MAX;
+}
+
+static inline uint64_t do_uqrshl_d(uint64_t src, int64_t shift,
+                                   bool round, uint32_t *sat)
+{
+    if (shift <= -(64 + round)) {
+        return 0;
+    } else if (shift < 0) {
+        if (round) {
+            src >>= -shift - 1;
+            return (src >> 1) + (src & 1);
+        }
+        return src >> -shift;
+    } else if (shift < 64) {
+        uint64_t val = src << shift;
+        if (!sat || val >> shift == src) {
+            return val;
+        }
+    } else if (!sat || src == 0) {
+        return 0;
+    }
+
+    *sat = 1;
+    return UINT64_MAX;
+}
+
+static inline int64_t do_suqrshl_d(int64_t src, int64_t shift,
+                                   bool round, uint32_t *sat)
+{
+    if (sat && src < 0) {
+        *sat = 1;
+        return 0;
+    }
+    return do_uqrshl_d(src, shift, round, sat);
+}
+
 #endif /* TARGET_ARM_VEC_INTERNALS_H */
diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon_helper.c
+++ b/target/arm/neon_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "cpu.h"
 #include "exec/helper-proto.h"
 #include "fpu/softfloat.h"
+#include "vec_internal.h"
 
 #define SIGNBIT (uint32_t)0x80000000
 #define SIGNBIT64 ((uint64_t)1 << 63)
@@ -XXX,XX +XXX,XX @@ NEON_POP(pmax_s16, neon_s16, 2)
 NEON_POP(pmax_u16, neon_u16, 2)
 #undef NEON_FN
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8 || \
-        tmp <= -(ssize_t)sizeof(src1) * 8) { \
-        dest = 0; \
-    } else if (tmp < 0) { \
-        dest = src1 >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, NULL))
 NEON_VOP(shl_u16, neon_u16, 2)
 #undef NEON_FN
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8) { \
-        dest = 0; \
-    } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
-        dest = src1 >> (sizeof(src1) * 8 - 1); \
-    } else if (tmp < 0) { \
-        dest = src1 >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, NULL))
 NEON_VOP(shl_s16, neon_s16, 2)
 #undef NEON_FN
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if ((tmp >= (ssize_t)sizeof(src1) * 8) \
-        || (tmp <= -(ssize_t)sizeof(src1) * 8)) { \
-        dest = 0; \
-    } else if (tmp < 0) { \
-        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, NULL))
 NEON_VOP(rshl_s8, neon_s8, 4)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, NULL))
 NEON_VOP(rshl_s16, neon_s16, 2)
 #undef NEON_FN
 
-/* The addition of the rounding constant may overflow, so we use an
- * intermediate 64 bit accumulator.  */
-uint32_t HELPER(neon_rshl_s32)(uint32_t valop, uint32_t shiftop)
+uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift)
 {
-    int32_t dest;
-    int32_t val = (int32_t)valop;
-    int8_t shift = (int8_t)shiftop;
-    if ((shift >= 32) || (shift <= -32)) {
-        dest = 0;
-    } else if (shift < 0) {
-        int64_t big_dest = ((int64_t)val + (1 << (-1 - shift)));
-        dest = big_dest >> -shift;
-    } else {
-        dest = val << shift;
-    }
-    return dest;
+    return do_sqrshl_bhs(val, (int8_t)shift, 32, true, NULL);
 }
 
-/* Handling addition overflow with 64 bit input values is more
- * tricky than with 32 bit values.  */
-uint64_t HELPER(neon_rshl_s64)(uint64_t valop, uint64_t shiftop)
+uint64_t HELPER(neon_rshl_s64)(uint64_t val, uint64_t shift)
 {
-    int8_t shift = (int8_t)shiftop;
-    int64_t val = valop;
-    if ((shift >= 64) || (shift <= -64)) {
-        val = 0;
-    } else if (shift < 0) {
-        val >>= (-shift - 1);
-        if (val == INT64_MAX) {
-            /* In this case, it means that the rounding constant is 1,
-             * and the addition would overflow. Return the actual
-             * result directly.  */
-            val = 0x4000000000000000LL;
-        } else {
-            val++;
-            val >>= 1;
-        }
-    } else {
-        val <<= shift;
-    }
-    return val;
+    return do_sqrshl_d(val, (int8_t)shift, true, NULL);
 }
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8 || \
-        tmp < -(ssize_t)sizeof(src1) * 8) { \
-        dest = 0; \
-    } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \
-        dest = src1 >> (-tmp - 1); \
-    } else if (tmp < 0) { \
-        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, NULL))
 NEON_VOP(rshl_u8, neon_u8, 4)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, NULL))
 NEON_VOP(rshl_u16, neon_u16, 2)
 #undef NEON_FN
 
-/* The addition of the rounding constant may overflow, so we use an
- * intermediate 64 bit accumulator.  */
-uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shiftop)
+uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift)
 {
-    uint32_t dest;
-    int8_t shift = (int8_t)shiftop;
-    if (shift >= 32 || shift < -32) {
-        dest = 0;
-    } else if (shift == -32) {
-        dest = val >> 31;
-    } else if (shift < 0) {
-        uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift)));
-        dest = big_dest >> -shift;
-    } else {
-        dest = val << shift;
-    }
-    return dest;
+    return do_uqrshl_bhs(val, (int8_t)shift, 32, true, NULL);
 }
 
-/* Handling addition overflow with 64 bit input values is more
- * tricky than with 32 bit values.  */
-uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shiftop)
+uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift)
 {
-    int8_t shift = (uint8_t)shiftop;
-    if (shift >= 64 || shift < -64) {
-        val = 0;
-    } else if (shift == -64) {
-        /* Rounding a 1-bit result just preserves that bit.  */
-        val >>= 63;
-    } else if (shift < 0) {
-        val >>= (-shift - 1);
-        if (val == UINT64_MAX) {
-            /* In this case, it means that the rounding constant is 1,
-             * and the addition would overflow. Return the actual
-             * result directly.  */
-            val = 0x8000000000000000ULL;
-        } else {
-            val++;
-            val >>= 1;
-        }
-    } else {
-        val <<= shift;
-    }
-    return val;
+    return do_uqrshl_d(val, (int8_t)shift, true, NULL);
 }
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8) { \
-        if (src1) { \
-            SET_QC(); \
-            dest = ~0; \
-        } else { \
-            dest = 0; \
-        } \
-    } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
-        dest = 0; \
-    } else if (tmp < 0) { \
-        dest = src1 >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-        if ((dest >> tmp) != src1) { \
-            SET_QC(); \
-            dest = ~0; \
-        } \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_u8, neon_u8, 4)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_u16, neon_u16, 2)
-NEON_VOP_ENV(qshl_u32, neon_u32, 1)
 #undef NEON_FN
 
-uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shiftop)
+uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift)
 {
-    int8_t shift = (int8_t)shiftop;
-    if (shift >= 64) {
-        if (val) {
-            val = ~(uint64_t)0;
-            SET_QC();
-        }
-    } else if (shift <= -64) {
-        val = 0;
-    } else if (shift < 0) {
-        val >>= -shift;
-    } else {
-        uint64_t tmp = val;
-        val <<= shift;
-        if ((val >> shift) != tmp) {
-            SET_QC();
-            val = ~(uint64_t)0;
-        }
-    }
-    return val;
+    return do_uqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc);
 }
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8) { \
-        if (src1) { \
-            SET_QC(); \
-            dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \
-            if (src1 > 0) { \
-                dest--; \
-            } \
-        } else { \
-            dest = src1; \
-        } \
-    } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
-        dest = src1 >> 31; \
-    } else if (tmp < 0) { \
-        dest = src1 >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-        if ((dest >> tmp) != src1) { \
-            SET_QC(); \
-            dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \
-            if (src1 > 0) { \
-                dest--; \
-            } \
-        } \
-    }} while (0)
+uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift)
+{
+    return do_uqrshl_d(val, (int8_t)shift, false, env->vfp.qc);
+}
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_s8, neon_s8, 4)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_s16, neon_s16, 2)
-NEON_VOP_ENV(qshl_s32, neon_s32, 1)
 #undef NEON_FN
 
-uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop)
+uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
 {
-    int8_t shift = (uint8_t)shiftop;
-    int64_t val = valop;
-    if (shift >= 64) {
-        if (val) {
-            SET_QC();
-            val = (val >> 63) ^ ~SIGNBIT64;
-        }
-    } else if (shift <= -64) {
-        val >>= 63;
-    } else if (shift < 0) {
-        val >>= -shift;
-    } else {
-        int64_t tmp = val;
-        val <<= shift;
-        if ((val >> shift) != tmp) {
-            SET_QC();
-            val = (tmp >> 63) ^ ~SIGNBIT64;
-        }
-    }
-    return val;
+    return do_sqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc);
 }
 
-#define NEON_FN(dest, src1, src2) do { \
-    if (src1 & (1 << (sizeof(src1) * 8 - 1))) { \
-        SET_QC(); \
-        dest = 0; \
-    } else { \
-        int8_t tmp; \
-        tmp = (int8_t)src2; \
-        if (tmp >= (ssize_t)sizeof(src1) * 8) { \
-            if (src1) { \
-                SET_QC(); \
-                dest = ~0; \
-            } else { \
-                dest = 0; \
-            } \
-        } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
-            dest = 0; \
-        } else if (tmp < 0) { \
-            dest = src1 >> -tmp; \
-        } else { \
-            dest = src1 << tmp; \
-            if ((dest >> tmp) != src1) { \
-                SET_QC(); \
-                dest = ~0; \
-            } \
-        } \
-    }} while (0)
-NEON_VOP_ENV(qshlu_s8, neon_u8, 4)
-NEON_VOP_ENV(qshlu_s16, neon_u16, 2)
+uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
+{
+    return do_sqrshl_d(val, (int8_t)shift, false, env->vfp.qc);
+}
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_suqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
+NEON_VOP_ENV(qshlu_s8, neon_s8, 4)
 #undef NEON_FN
 
-uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t valop, uint32_t shiftop)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_suqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
+NEON_VOP_ENV(qshlu_s16, neon_s16, 2)
+#undef NEON_FN
+
+uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
 {
-    if ((int32_t)valop < 0) {
-        SET_QC();
-        return 0;
-    }
-    return helper_neon_qshl_u32(env, valop, shiftop);
+    return do_suqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc);
 }
 
-uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop)
+uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
 {
-    if ((int64_t)valop < 0) {
-        SET_QC();
-        return 0;
-    }
-    return helper_neon_qshl_u64(env, valop, shiftop);
+    return do_suqrshl_d(val, (int8_t)shift, false, env->vfp.qc);
 }
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8) { \
-        if (src1) { \
-            SET_QC(); \
-            dest = ~0; \
-        } else { \
-            dest = 0; \
-        } \
-    } else if (tmp < -(ssize_t)sizeof(src1) * 8) { \
-        dest = 0; \
-    } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \
-        dest = src1 >> (sizeof(src1) * 8 - 1); \
-    } else if (tmp < 0) { \
-        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-        if ((dest >> tmp) != src1) { \
-            SET_QC(); \
-            dest = ~0; \
-        } \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc))
 NEON_VOP_ENV(qrshl_u8, neon_u8, 4)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc))
 NEON_VOP_ENV(qrshl_u16, neon_u16, 2)
 #undef NEON_FN
 
-/* The addition of the rounding constant may overflow, so we use an
- * intermediate 64 bit accumulator.  */
-uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shiftop)
+uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift)
 {
-    uint32_t dest;
-    int8_t shift = (int8_t)shiftop;
-    if (shift >= 32) {
-        if (val) {
-            SET_QC();
-            dest = ~0;
-        } else {
-            dest = 0;
-        }
-    } else if (shift < -32) {
-        dest = 0;
-    } else if (shift == -32) {
-        dest = val >> 31;
-    } else if (shift < 0) {
-        uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift)));
-        dest = big_dest >> -shift;
-    } else {
-        dest = val << shift;
-        if ((dest >> shift) != val) {
-            SET_QC();
-            dest = ~0;
-        }
-    }
-    return dest;
+    return do_uqrshl_bhs(val, (int8_t)shift, 32, true, env->vfp.qc);
 }
 
-/* Handling addition overflow with 64 bit input values is more
- * tricky than with 32 bit values.  */
-uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shiftop)
+uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift)
 {
-    int8_t shift = (int8_t)shiftop;
-    if (shift >= 64) {
-        if (val) {
-            SET_QC();
-            val = ~0;
-        }
-    } else if (shift < -64) {
-        val = 0;
-    } else if (shift == -64) {
-        val >>= 63;
-    } else if (shift < 0) {
-        val >>= (-shift - 1);
-        if (val == UINT64_MAX) {
-            /* In this case, it means that the rounding constant is 1,
-             * and the addition would overflow. Return the actual
-             * result directly.  */
-            val = 0x8000000000000000ULL;
-        } else {
-            val++;
-            val >>= 1;
-        }
-    } else { \
-        uint64_t tmp = val;
-        val <<= shift;
-        if ((val >> shift) != tmp) {
-            SET_QC();
-            val = ~0;
-        }
-    }
-    return val;
+    return do_uqrshl_d(val, (int8_t)shift, true, env->vfp.qc);
 }
 
-#define NEON_FN(dest, src1, src2) do { \
-    int8_t tmp; \
-    tmp = (int8_t)src2; \
-    if (tmp >= (ssize_t)sizeof(src1) * 8) { \
-        if (src1) { \
-            SET_QC(); \
-            dest = (typeof(dest))(1 << (sizeof(src1) * 8 - 1)); \
-            if (src1 > 0) { \
-                dest--; \
-            } \
-        } else { \
-            dest = 0; \
-        } \
-    } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
-        dest = 0; \
-    } else if (tmp < 0) { \
-        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \
-    } else { \
-        dest = src1 << tmp; \
-        if ((dest >> tmp) != src1) { \
-            SET_QC(); \
-            dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \
-            if (src1 > 0) { \
-                dest--; \
-            } \
-        } \
-    }} while (0)
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc))
 NEON_VOP_ENV(qrshl_s8, neon_s8, 4)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc))
 NEON_VOP_ENV(qrshl_s16, neon_s16, 2)
 #undef NEON_FN
 
-/* The addition of the rounding constant may overflow, so we use an
- * intermediate 64 bit accumulator.  */
-uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t valop, uint32_t shiftop)
+uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
 {
-    int32_t dest;
-    int32_t val = (int32_t)valop;
-    int8_t shift = (int8_t)shiftop;
-    if (shift >= 32) {
-        if (val) {
-            SET_QC();
-            dest = (val >> 31) ^ ~SIGNBIT;
-        } else {
-            dest = 0;
-        }
-    } else if (shift <= -32) {
-        dest = 0;
-    } else if (shift < 0) {
-        int64_t big_dest = ((int64_t)val + (1 << (-1 - shift)));
-        dest = big_dest >> -shift;
-    } else {
-        dest = val << shift;
-        if ((dest >> shift) != val) {
-            SET_QC();
-            dest = (val >> 31) ^ ~SIGNBIT;
-        }
-    }
-    return dest;
+    return do_sqrshl_bhs(val, (int8_t)shift, 32, true, env->vfp.qc);
 }
 
-/* Handling addition overflow with 64 bit input values is more
- * tricky than with 32 bit values.  */
-uint64_t HELPER(neon_qrshl_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop)
+uint64_t HELPER(neon_qrshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
 {
-    int8_t shift = (uint8_t)shiftop;
-    int64_t val = valop;
-
-    if (shift >= 64) {
-        if (val) {
-            SET_QC();
-            val = (val >> 63) ^ ~SIGNBIT64;
-        }
-    } else if (shift <= -64) {
-        val = 0;
-    } else if (shift < 0) {
-        val >>= (-shift - 1);
-        if (val == INT64_MAX) {
-            /* In this case, it means that the rounding constant is 1,
-             * and the addition would overflow. Return the actual
-             * result directly.  */
-            val = 0x4000000000000000ULL;
-        } else {
-            val++;
-            val >>= 1;
-        }
-    } else {
-        int64_t tmp = val;
-        val <<= shift;
-        if ((val >> shift) != tmp) {
-            SET_QC();
-            val = (tmp >> 63) ^ ~SIGNBIT64;
-        }
-    }
-    return val;
+    return do_sqrshl_d(val, (int8_t)shift, true, env->vfp.qc);
 }
 
 uint32_t HELPER(neon_add_u8)(uint32_t a, uint32_t b)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-7-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 54 +++++++++++++++++++++++
 target/arm/sve.decode      | 17 ++++++++
 target/arm/sve_helper.c    | 87 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 18 ++++++++
 4 files changed, 176 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ URECPE          01000100 .. 000 000 101 ... ..... .....  @rd_pg_rn
 URSQRTE         01000100 .. 000 001 101 ... ..... .....  @rd_pg_rn
 SQABS           01000100 .. 001 000 101 ... ..... .....  @rd_pg_rn
 SQNEG           01000100 .. 001 001 101 ... ..... .....  @rd_pg_rn
+
+### SVE2 saturating/rounding bitwise shift left (predicated)
+
+SRSHL           01000100 .. 000 010 100 ... ..... .....  @rdn_pg_rm
+URSHL           01000100 .. 000 011 100 ... ..... .....  @rdn_pg_rm
+SRSHL           01000100 .. 000 110 100 ... ..... .....  @rdm_pg_rn # SRSHLR
+URSHL           01000100 .. 000 111 100 ... ..... .....  @rdm_pg_rn # URSHLR
+
+SQSHL           01000100 .. 001 000 100 ... ..... .....  @rdn_pg_rm
+UQSHL           01000100 .. 001 001 100 ... ..... .....  @rdn_pg_rm
+SQSHL           01000100 .. 001 100 100 ... ..... .....  @rdm_pg_rn # SQSHLR
+UQSHL           01000100 .. 001 101 100 ... ..... .....  @rdm_pg_rn # UQSHLR
+
+SQRSHL          01000100 .. 001 010 100 ... ..... .....  @rdn_pg_rm
+UQRSHL          01000100 .. 001 011 100 ... ..... .....  @rdn_pg_rm
+SQRSHL          01000100 .. 001 110 100 ... ..... .....  @rdm_pg_rn # SQRSHLR
+UQRSHL          01000100 .. 001 111 100 ... ..... .....  @rdm_pg_rn # UQRSHLR
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "tcg/tcg-gvec-desc.h"
 #include "fpu/softfloat.h"
 #include "tcg/tcg.h"
+#include "vec_internal.h"
 
 
 /* Note that vector data is stored in host-endian 64-bit chunks,
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uadalp_zpzz_h, uint16_t, H1_2, do_uadalp_h)
 DO_ZPZZ(sve2_uadalp_zpzz_s, uint32_t, H1_4, do_uadalp_s)
 DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d)
 
+#define do_srshl_b(n, m)  do_sqrshl_bhs(n, m, 8, true, NULL)
+#define do_srshl_h(n, m)  do_sqrshl_bhs(n, m, 16, true, NULL)
+#define do_srshl_s(n, m)  do_sqrshl_bhs(n, m, 32, true, NULL)
+#define do_srshl_d(n, m)  do_sqrshl_d(n, m, true, NULL)
+
+DO_ZPZZ(sve2_srshl_zpzz_b, int8_t, H1, do_srshl_b)
+DO_ZPZZ(sve2_srshl_zpzz_h, int16_t, H1_2, do_srshl_h)
+DO_ZPZZ(sve2_srshl_zpzz_s, int32_t, H1_4, do_srshl_s)
+DO_ZPZZ_D(sve2_srshl_zpzz_d, int64_t, do_srshl_d)
+
+#define do_urshl_b(n, m)  do_uqrshl_bhs(n, (int8_t)m, 8, true, NULL)
+#define do_urshl_h(n, m)  do_uqrshl_bhs(n, (int16_t)m, 16, true, NULL)
+#define do_urshl_s(n, m)  do_uqrshl_bhs(n, m, 32, true, NULL)
+#define do_urshl_d(n, m)  do_uqrshl_d(n, m, true, NULL)
+
+DO_ZPZZ(sve2_urshl_zpzz_b, uint8_t, H1, do_urshl_b)
+DO_ZPZZ(sve2_urshl_zpzz_h, uint16_t, H1_2, do_urshl_h)
+DO_ZPZZ(sve2_urshl_zpzz_s, uint32_t, H1_4, do_urshl_s)
+DO_ZPZZ_D(sve2_urshl_zpzz_d, uint64_t, do_urshl_d)
+
+/*
+ * Unlike the NEON and AdvSIMD versions, there is no QC bit to set.
+ * We pass in a pointer to a dummy saturation field to trigger
+ * the saturating arithmetic but discard the information about
+ * whether it has occurred.
+ */
+#define do_sqshl_b(n, m) \
+   ({ uint32_t discard; do_sqrshl_bhs(n, m, 8, false, &discard); })
+#define do_sqshl_h(n, m) \
+   ({ uint32_t discard; do_sqrshl_bhs(n, m, 16, false, &discard); })
+#define do_sqshl_s(n, m) \
+   ({ uint32_t discard; do_sqrshl_bhs(n, m, 32, false, &discard); })
+#define do_sqshl_d(n, m) \
+   ({ uint32_t discard; do_sqrshl_d(n, m, false, &discard); })
+
+DO_ZPZZ(sve2_sqshl_zpzz_b, int8_t, H1_2, do_sqshl_b)
+DO_ZPZZ(sve2_sqshl_zpzz_h, int16_t, H1_2, do_sqshl_h)
+DO_ZPZZ(sve2_sqshl_zpzz_s, int32_t, H1_4, do_sqshl_s)
+DO_ZPZZ_D(sve2_sqshl_zpzz_d, int64_t, do_sqshl_d)
+
+#define do_uqshl_b(n, m) \
+   ({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, false, &discard); })
+#define do_uqshl_h(n, m) \
+   ({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, false, &discard); })
+#define do_uqshl_s(n, m) \
+   ({ uint32_t discard; do_uqrshl_bhs(n, m, 32, false, &discard); })
+#define do_uqshl_d(n, m) \
+   ({ uint32_t discard; do_uqrshl_d(n, m, false, &discard); })
+
+DO_ZPZZ(sve2_uqshl_zpzz_b, uint8_t, H1_2, do_uqshl_b)
+DO_ZPZZ(sve2_uqshl_zpzz_h, uint16_t, H1_2, do_uqshl_h)
+DO_ZPZZ(sve2_uqshl_zpzz_s, uint32_t, H1_4, do_uqshl_s)
+DO_ZPZZ_D(sve2_uqshl_zpzz_d, uint64_t, do_uqshl_d)
+
+#define do_sqrshl_b(n, m) \
+   ({ uint32_t discard; do_sqrshl_bhs(n, m, 8, true, &discard); })
+#define do_sqrshl_h(n, m) \
+   ({ uint32_t discard; do_sqrshl_bhs(n, m, 16, true, &discard); })
+#define do_sqrshl_s(n, m) \
+   ({ uint32_t discard; do_sqrshl_bhs(n, m, 32, true, &discard); })
+#define do_sqrshl_d(n, m) \
+   ({ uint32_t discard; do_sqrshl_d(n, m, true, &discard); })
+
+DO_ZPZZ(sve2_sqrshl_zpzz_b, int8_t, H1_2, do_sqrshl_b)
+DO_ZPZZ(sve2_sqrshl_zpzz_h, int16_t, H1_2, do_sqrshl_h)
+DO_ZPZZ(sve2_sqrshl_zpzz_s, int32_t, H1_4, do_sqrshl_s)
+DO_ZPZZ_D(sve2_sqrshl_zpzz_d, int64_t, do_sqrshl_d)
+
+#undef do_sqrshl_d
+
+#define do_uqrshl_b(n, m) \
+   ({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, true, &discard); })
+#define do_uqrshl_h(n, m) \
+   ({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, true, &discard); })
+#define do_uqrshl_s(n, m) \
+   ({ uint32_t discard; do_uqrshl_bhs(n, m, 32, true, &discard); })
+#define do_uqrshl_d(n, m) \
+   ({ uint32_t discard; do_uqrshl_d(n, m, true, &discard); })
+
+DO_ZPZZ(sve2_uqrshl_zpzz_b, uint8_t, H1_2, do_uqrshl_b)
+DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h)
+DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s)
+DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d)
+
+#undef do_uqrshl_d
+
 #undef DO_ZPZZ
 #undef DO_ZPZZ_D
 
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a)
     };
     return do_sve2_zpz_ool(s, a, fns[a->esz]);
 }
+
+#define DO_SVE2_ZPZZ(NAME, name) \
+static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a)                \
+{                                                                         \
+    static gen_helper_gvec_4 * const fns[4] = {                           \
+        gen_helper_sve2_##name##_zpzz_b, gen_helper_sve2_##name##_zpzz_h, \
+        gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d, \
+    };                                                                    \
+    return do_sve2_zpzz_ool(s, a, fns[a->esz]);                           \
+}
+
+DO_SVE2_ZPZZ(SQSHL, sqshl)
+DO_SVE2_ZPZZ(SQRSHL, sqrshl)
+DO_SVE2_ZPZZ(SRSHL, srshl)
+
+DO_SVE2_ZPZZ(UQSHL, uqshl)
+DO_SVE2_ZPZZ(UQRSHL, uqrshl)
+DO_SVE2_ZPZZ(URSHL, urshl)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 54 ++++++++++++++++++++++++++++++++++++++
 target/arm/sve.decode      | 11 ++++++++
 target/arm/sve_helper.c    | 39 +++++++++++++++++++++++++++
 target/arm/translate-sve.c |  8 ++++++
 4 files changed, 112 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 45 ++++++++++++++++++++++
 target/arm/sve.decode      |  8 ++++
 target/arm/sve_helper.c    | 76 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c |  6 +++
 4 files changed, 135 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  54 +++++++++++
 target/arm/sve.decode      |  11 +++
 target/arm/sve_helper.c    | 194 ++++++++++++++++++++++++++-----------
 target/arm/translate-sve.c |   7 ++
 4 files changed, 210 insertions(+), 56 deletions(-)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ SMAXP           01000100 .. 010 100 101 ... ..... .....  @rdn_pg_rm
 UMAXP           01000100 .. 010 101 101 ... ..... .....  @rdn_pg_rm
 SMINP           01000100 .. 010 110 101 ... ..... .....  @rdn_pg_rm
 UMINP           01000100 .. 010 111 101 ... ..... .....  @rdn_pg_rm
+
+### SVE2 saturating add/subtract (predicated)
+
+SQADD_zpzz      01000100 .. 011 000 100 ... ..... .....  @rdn_pg_rm
+UQADD_zpzz      01000100 .. 011 001 100 ... ..... .....  @rdn_pg_rm
+SQSUB_zpzz      01000100 .. 011 010 100 ... ..... .....  @rdn_pg_rm
+UQSUB_zpzz      01000100 .. 011 011 100 ... ..... .....  @rdn_pg_rm
+SUQADD          01000100 .. 011 100 100 ... ..... .....  @rdn_pg_rm
+USQADD          01000100 .. 011 101 100 ... ..... .....  @rdn_pg_rm
+SQSUB_zpzz      01000100 .. 011 110 100 ... ..... .....  @rdm_pg_rn # SQSUBR
+UQSUB_zpzz      01000100 .. 011 111 100 ... ..... .....  @rdm_pg_rn # UQSUBR
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS)
 DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS)
 DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D)
 
+static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max)
+{
+    return val >= max ? max : val <= min ? min : val;
+}
+
+#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX)
+#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX)
+#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX)
+
+static inline int64_t do_sqadd_d(int64_t n, int64_t m)
+{
+    int64_t r = n + m;
+    if (((r ^ n) & ~(n ^ m)) < 0) {
+        /* Signed overflow.  */
+        return r < 0 ? INT64_MAX : INT64_MIN;
+    }
+    return r;
+}
+
+DO_ZPZZ(sve2_sqadd_zpzz_b, int8_t, H1, DO_SQADD_B)
+DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H)
+DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S)
+DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d)
+
+#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX)
+#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX)
+#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX)
+
+static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m)
+{
+    uint64_t r = n + m;
+    return r < n ? UINT64_MAX : r;
+}
+
+DO_ZPZZ(sve2_uqadd_zpzz_b, uint8_t, H1, DO_UQADD_B)
+DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H)
+DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S)
+DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d)
+
+#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX)
+#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX)
+#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX)
+
+static inline int64_t do_sqsub_d(int64_t n, int64_t m)
+{
+    int64_t r = n - m;
+    if (((r ^ n) & (n ^ m)) < 0) {
+        /* Signed overflow.  */
+        return r < 0 ? INT64_MAX : INT64_MIN;
+    }
+    return r;
+}
+
+DO_ZPZZ(sve2_sqsub_zpzz_b, int8_t, H1, DO_SQSUB_B)
+DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H)
+DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S)
+DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d)
+
+#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX)
+#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX)
+#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX)
+
+static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m)
+{
+    return n > m ? n - m : 0;
+}
+
+DO_ZPZZ(sve2_uqsub_zpzz_b, uint8_t, H1, DO_UQSUB_B)
+DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H)
+DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S)
+DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d)
+
+#define DO_SUQADD_B(n, m) \
+    do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX)
+#define DO_SUQADD_H(n, m) \
+    do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX)
+#define DO_SUQADD_S(n, m) \
+    do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX)
+
+static inline int64_t do_suqadd_d(int64_t n, uint64_t m)
+{
+    uint64_t r = n + m;
+
+    if (n < 0) {
+        /* Note that m - abs(n) cannot underflow. */
+        if (r > INT64_MAX) {
+            /* Result is either very large positive or negative. */
+            if (m > -n) {
+                /* m > abs(n), so r is a very large positive. */
+                return INT64_MAX;
+            }
+            /* Result is negative. */
+        }
+    } else {
+        /* Both inputs are positive: check for overflow.  */
+        if (r < m || r > INT64_MAX) {
+            return INT64_MAX;
+        }
+    }
+    return r;
+}
+
+DO_ZPZZ(sve2_suqadd_zpzz_b, uint8_t, H1, DO_SUQADD_B)
+DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H)
+DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S)
+DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d)
+
+#define DO_USQADD_B(n, m) \
+    do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX)
+#define DO_USQADD_H(n, m) \
+    do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX)
+#define DO_USQADD_S(n, m) \
+    do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX)
+
+static inline uint64_t do_usqadd_d(uint64_t n, int64_t m)
+{
+    uint64_t r = n + m;
+
+    if (m < 0) {
+        return n < -m ? 0 : r;
+    }
+    return r < n ? UINT64_MAX : r;
+}
+
+DO_ZPZZ(sve2_usqadd_zpzz_b, uint8_t, H1, DO_USQADD_B)
+DO_ZPZZ(sve2_usqadd_zpzz_h, uint16_t, H1_2, DO_USQADD_H)
+DO_ZPZZ(sve2_usqadd_zpzz_s, uint32_t, H1_4, DO_USQADD_S)
+DO_ZPZZ_D(sve2_usqadd_zpzz_d, uint64_t, do_usqadd_d)
+
 #undef DO_ZPZZ
 #undef DO_ZPZZ_D
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_b)(void *d, void *a, int32_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(int8_t)) {
-        int r = *(int8_t *)(a + i) + b;
-        if (r > INT8_MAX) {
-            r = INT8_MAX;
-        } else if (r < INT8_MIN) {
-            r = INT8_MIN;
-        }
-        *(int8_t *)(d + i) = r;
+        *(int8_t *)(d + i) = DO_SQADD_B(b, *(int8_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_h)(void *d, void *a, int32_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(int16_t)) {
-        int r = *(int16_t *)(a + i) + b;
-        if (r > INT16_MAX) {
-            r = INT16_MAX;
-        } else if (r < INT16_MIN) {
-            r = INT16_MIN;
-        }
-        *(int16_t *)(d + i) = r;
+        *(int16_t *)(d + i) = DO_SQADD_H(b, *(int16_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_s)(void *d, void *a, int64_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(int32_t)) {
-        int64_t r = *(int32_t *)(a + i) + b;
-        if (r > INT32_MAX) {
-            r = INT32_MAX;
-        } else if (r < INT32_MIN) {
-            r = INT32_MIN;
-        }
-        *(int32_t *)(d + i) = r;
+        *(int32_t *)(d + i) = DO_SQADD_S(b, *(int32_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_d)(void *d, void *a, int64_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(int64_t)) {
-        int64_t ai = *(int64_t *)(a + i);
-        int64_t r = ai + b;
-        if (((r ^ ai) & ~(ai ^ b)) < 0) {
-            /* Signed overflow.  */
-            r = (r < 0 ? INT64_MAX : INT64_MIN);
-        }
-        *(int64_t *)(d + i) = r;
+        *(int64_t *)(d + i) = do_sqadd_d(b, *(int64_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_b)(void *d, void *a, int32_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
-        int r = *(uint8_t *)(a + i) + b;
-        if (r > UINT8_MAX) {
-            r = UINT8_MAX;
-        } else if (r < 0) {
-            r = 0;
-        }
-        *(uint8_t *)(d + i) = r;
+        *(uint8_t *)(d + i) = DO_UQADD_B(b, *(uint8_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_h)(void *d, void *a, int32_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
-        int r = *(uint16_t *)(a + i) + b;
-        if (r > UINT16_MAX) {
-            r = UINT16_MAX;
-        } else if (r < 0) {
-            r = 0;
-        }
-        *(uint16_t *)(d + i) = r;
+        *(uint16_t *)(d + i) = DO_UQADD_H(b, *(uint16_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_s)(void *d, void *a, int64_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
-        int64_t r = *(uint32_t *)(a + i) + b;
-        if (r > UINT32_MAX) {
-            r = UINT32_MAX;
-        } else if (r < 0) {
-            r = 0;
-        }
-        *(uint32_t *)(d + i) = r;
+        *(uint32_t *)(d + i) = DO_UQADD_S(b, *(uint32_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_d)(void *d, void *a, uint64_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        uint64_t r = *(uint64_t *)(a + i) + b;
-        if (r < b) {
-            r = UINT64_MAX;
-        }
-        *(uint64_t *)(d + i) = r;
+        *(uint64_t *)(d + i) = do_uqadd_d(b, *(uint64_t *)(a + i));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqsubi_d)(void *d, void *a, uint64_t b, uint32_t desc)
     intptr_t i, oprsz = simd_oprsz(desc);
 
     for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
-        uint64_t ai = *(uint64_t *)(a + i);
-        *(uint64_t *)(d + i) = (ai < b ? 0 : ai - b);
+        *(uint64_t *)(d + i) = do_uqsub_d(*(uint64_t *)(a + i), b);
     }
 }
 
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ(SMAXP, smaxp)
 DO_SVE2_ZPZZ(UMAXP, umaxp)
 DO_SVE2_ZPZZ(SMINP, sminp)
 DO_SVE2_ZPZZ(UMINP, uminp)
+
+DO_SVE2_ZPZZ(SQADD_zpzz, sqadd)
+DO_SVE2_ZPZZ(UQADD_zpzz, uqadd)
+DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub)
+DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub)
+DO_SVE2_ZPZZ(SUQADD, suqadd)
+DO_SVE2_ZPZZ(USQADD, usqadd)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 24 ++++++++++++++++++++
 target/arm/sve.decode      | 19 ++++++++++++++++
 target/arm/sve_helper.c    | 43 +++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 46 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 132 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      | 6 ++++++
 target/arm/translate-sve.c | 4 ++++
 2 files changed, 10 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ SABDLB          01000101 .. 0 ..... 00 1100 ..... .....  @rd_rn_rm
 SABDLT          01000101 .. 0 ..... 00 1101 ..... .....  @rd_rn_rm
 UABDLB          01000101 .. 0 ..... 00 1110 ..... .....  @rd_rn_rm
 UABDLT          01000101 .. 0 ..... 00 1111 ..... .....  @rd_rn_rm
+
+## SVE2 integer add/subtract interleaved long
+
+SADDLBT         01000101 .. 0 ..... 1000 00 ..... .....  @rd_rn_rm
+SSUBLBT         01000101 .. 0 ..... 1000 10 ..... .....  @rd_rn_rm
+SSUBLTB         01000101 .. 0 ..... 1000 11 ..... .....  @rd_rn_rm
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true)
 DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true)
 DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true)
 DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true)
+
+DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true)
+DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true)
+DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 16 ++++++++++++++++
 target/arm/sve.decode      | 12 ++++++++++++
 target/arm/sve_helper.c    | 30 ++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 20 ++++++++++++++++++++
 4 files changed, 78 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Exclude PMULL from this category for the moment.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 15 +++++++++++++++
 target/arm/sve.decode      |  9 +++++++++
 target/arm/sve_helper.c    | 31 +++++++++++++++++++++++++++++++
 target/arm/translate-sve.c |  9 +++++++++
 4 files changed, 64 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-15-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           | 10 ++++++++++
 target/arm/helper-sve.h    |  1 +
 target/arm/sve.decode      |  2 ++
 target/arm/translate-sve.c | 22 ++++++++++++++++++++++
 target/arm/vec_helper.c    | 24 ++++++++++++++++++++++++
 5 files changed, 59 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-16-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |   8 ++
 target/arm/sve.decode      |   8 ++
 target/arm/sve_helper.c    |  22 +++++
 target/arm/translate-sve.c | 159 +++++++++++++++++++++++++++++++++++++
 4 files changed, 197 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-17-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  5 +++++
 target/arm/sve.decode      |  5 +++++
 target/arm/sve_helper.c    | 20 ++++++++++++++++++++
 target/arm/translate-sve.c | 19 +++++++++++++++++++
 4 files changed, 49 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           |  5 +++
 target/arm/helper-sve.h    | 15 ++++++++
 target/arm/sve.decode      |  6 ++++
 target/arm/sve_helper.c    | 73 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 36 +++++++++++++++++++
 5 files changed, 135 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 10 +++++++++
 target/arm/sve.decode      |  9 ++++++++
 target/arm/sve_helper.c    | 42 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 31 ++++++++++++++++++++++++++++
 4 files changed, 92 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-20-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 14 ++++++++++
 target/arm/sve.decode      | 12 +++++++++
 target/arm/sve_helper.c    | 23 ++++++++++++++++
 target/arm/translate-sve.c | 55 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 104 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-21-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  3 +++
 target/arm/sve.decode      |  6 ++++++
 target/arm/sve_helper.c    | 34 ++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 23 +++++++++++++++++++++++
 4 files changed, 66 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-22-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  8 ++++++++
 target/arm/translate-sve.c | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ UABALT          01000101 .. 0 ..... 1100 11 ..... .....  @rda_rn_rm
 # ADC and SBC decoded via size in helper dispatch.
 ADCLB           01000101 .. 0 ..... 11010 0 ..... .....  @rda_rn_rm
 ADCLT           01000101 .. 0 ..... 11010 1 ..... .....  @rda_rn_rm
+
+## SVE2 bitwise shift right and accumulate
+
+# TODO: Use @rda and %reg_movprfx here.
+SSRA            01000101 .. 0 ..... 1110 00 ..... .....  @rd_rn_tszimm_shr
+USRA            01000101 .. 0 ..... 1110 01 ..... .....  @rd_rn_tszimm_shr
+SRSRA           01000101 .. 0 ..... 1110 10 ..... .....  @rd_rn_tszimm_shr
+URSRA           01000101 .. 0 ..... 1110 11 ..... .....  @rd_rn_tszimm_shr
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_ADCLT(DisasContext *s, arg_rrrr_esz *a)
 {
     return do_adcl(s, a, true);
 }
+
+static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn)
+{
+    if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        unsigned rd_ofs = vec_full_reg_offset(s, a->rd);
+        unsigned rn_ofs = vec_full_reg_offset(s, a->rn);
+        fn(a->esz, rd_ofs, rn_ofs, a->imm, vsz, vsz);
+    }
+    return true;
+}
+
+static bool trans_SSRA(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_fn2i(s, a, gen_gvec_ssra);
+}
+
+static bool trans_USRA(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_fn2i(s, a, gen_gvec_usra);
+}
+
+static bool trans_SRSRA(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_fn2i(s, a, gen_gvec_srsra);
+}
+
+static bool trans_URSRA(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_fn2i(s, a, gen_gvec_ursra);
+}
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-23-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  5 +++++
 target/arm/translate-sve.c | 10 ++++++++++
 2 files changed, 15 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ SSRA            01000101 .. 0 ..... 1110 00 ..... .....  @rd_rn_tszimm_shr
 USRA            01000101 .. 0 ..... 1110 01 ..... .....  @rd_rn_tszimm_shr
 SRSRA           01000101 .. 0 ..... 1110 10 ..... .....  @rd_rn_tszimm_shr
 URSRA           01000101 .. 0 ..... 1110 11 ..... .....  @rd_rn_tszimm_shr
+
+## SVE2 bitwise shift and insert
+
+SRI             01000101 .. 0 ..... 11110 0 ..... .....  @rd_rn_tszimm_shr
+SLI             01000101 .. 0 ..... 11110 1 ..... .....  @rd_rn_tszimm_shl
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_URSRA(DisasContext *s, arg_rri_esz *a)
 {
     return do_sve2_fn2i(s, a, gen_gvec_ursra);
 }
+
+static bool trans_SRI(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_fn2i(s, a, gen_gvec_sri);
+}
+
+static bool trans_SLI(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_fn2i(s, a, gen_gvec_sli);
+}
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-24-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  6 ++++++
 target/arm/translate-sve.c | 21 +++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ URSRA           01000101 .. 0 ..... 1110 11 ..... .....  @rd_rn_tszimm_shr
 
 SRI             01000101 .. 0 ..... 11110 0 ..... .....  @rd_rn_tszimm_shr
 SLI             01000101 .. 0 ..... 11110 1 ..... .....  @rd_rn_tszimm_shl
+
+## SVE2 integer absolute difference and accumulate
+
+# TODO: Use @rda and %reg_movprfx here.
+SABA            01000101 .. 0 ..... 11111 0 ..... .....  @rd_rn_rm
+UABA            01000101 .. 0 ..... 11111 1 ..... .....  @rd_rn_rm
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_SLI(DisasContext *s, arg_rri_esz *a)
 {
     return do_sve2_fn2i(s, a, gen_gvec_sli);
 }
+
+static bool do_sve2_fn_zzz(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *fn)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm);
+    }
+    return true;
+}
+
+static bool trans_SABA(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_sve2_fn_zzz(s, a, gen_gvec_saba);
+}
+
+static bool trans_UABA(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_sve2_fn_zzz(s, a, gen_gvec_uaba);
+}
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-25-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  24 ++++
 target/arm/sve.decode      |  12 ++
 target/arm/sve_helper.c    |  56 +++++++++
 target/arm/translate-sve.c | 238 +++++++++++++++++++++++++++++++++++++
 4 files changed, 330 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uabal_d, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_5(sve2_adcl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_adcl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqxtnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_uqxtnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_uqxtnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_uqxtnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqxtunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqxtnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_uqxtnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_uqxtnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_uqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ SLI             01000101 .. 0 ..... 11110 1 ..... .....  @rd_rn_tszimm_shl
 # TODO: Use @rda and %reg_movprfx here.
 SABA            01000101 .. 0 ..... 11111 0 ..... .....  @rd_rn_rm
 UABA            01000101 .. 0 ..... 11111 1 ..... .....  @rd_rn_rm
+
+#### SVE2 Narrowing
+
+## SVE2 saturating extract narrow
+
+# Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0.
+SQXTNB          01000101 .. 1 ..... 010 000 ..... .....  @rd_rn_tszimm_shl
+SQXTNT          01000101 .. 1 ..... 010 001 ..... .....  @rd_rn_tszimm_shl
+UQXTNB          01000101 .. 1 ..... 010 010 ..... .....  @rd_rn_tszimm_shl
+UQXTNT          01000101 .. 1 ..... 010 011 ..... .....  @rd_rn_tszimm_shl
+SQXTUNB         01000101 .. 1 ..... 010 100 ..... .....  @rd_rn_tszimm_shl
+SQXTUNT         01000101 .. 1 ..... 010 101 ..... .....  @rd_rn_tszimm_shl
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t,     , H1_4, DO_ABD)
 
 #undef DO_ZZZW_ACC
 
+#define DO_XTNB(NAME, TYPE, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc)         \
+{                                                            \
+    intptr_t i, opr_sz = simd_oprsz(desc);                   \
+    for (i = 0; i < opr_sz; i += sizeof(TYPE)) {             \
+        TYPE nn = *(TYPE *)(vn + i);                         \
+        nn = OP(nn) & MAKE_64BIT_MASK(0, sizeof(TYPE) * 4);  \
+        *(TYPE *)(vd + i) = nn;                              \
+    }                                                        \
+}
+
+#define DO_XTNT(NAME, TYPE, TYPEN, H, OP)                               \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc)                    \
+{                                                                       \
+    intptr_t i, opr_sz = simd_oprsz(desc), odd = H(sizeof(TYPEN));      \
+    for (i = 0; i < opr_sz; i += sizeof(TYPE)) {                        \
+        TYPE nn = *(TYPE *)(vn + i);                                    \
+        *(TYPEN *)(vd + i + odd) = OP(nn);                              \
+    }                                                                   \
+}
+
+#define DO_SQXTN_H(n)  do_sat_bhs(n, INT8_MIN, INT8_MAX)
+#define DO_SQXTN_S(n)  do_sat_bhs(n, INT16_MIN, INT16_MAX)
+#define DO_SQXTN_D(n)  do_sat_bhs(n, INT32_MIN, INT32_MAX)
+
+DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H)
+DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S)
+DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D)
+
+DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H)
+DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S)
+DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D)
+
+#define DO_UQXTN_H(n)  do_sat_bhs(n, 0, UINT8_MAX)
+#define DO_UQXTN_S(n)  do_sat_bhs(n, 0, UINT16_MAX)
+#define DO_UQXTN_D(n)  do_sat_bhs(n, 0, UINT32_MAX)
+
+DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H)
+DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S)
+DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D)
+
+DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H)
+DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S)
+DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D)
+
+DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H)
+DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S)
+DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D)
+
+DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H)
+DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S)
+DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D)
+
+#undef DO_XTNB
+#undef DO_XTNT
+
 void HELPER(sve2_adcl_s)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_UABA(DisasContext *s, arg_rrr_esz *a)
 {
     return do_sve2_fn_zzz(s, a, gen_gvec_uaba);
 }
+
+static bool do_sve2_narrow_extract(DisasContext *s, arg_rri_esz *a,
+                                   const GVecGen2 ops[3])
+{
+    if (a->esz < 0 || a->esz > MO_32 || a->imm != 0 ||
+        !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_2(vec_full_reg_offset(s, a->rd),
+                        vec_full_reg_offset(s, a->rn),
+                        vsz, vsz, &ops[a->esz]);
+    }
+    return true;
+}
+
+static const TCGOpcode sqxtn_list[] = {
+    INDEX_op_shli_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0
+};
+
+static void gen_sqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t mask = (1ull << halfbits) - 1;
+    int64_t min = -1ull << (halfbits - 1);
+    int64_t max = -min - 1;
+
+    tcg_gen_dupi_vec(vece, t, min);
+    tcg_gen_smax_vec(vece, d, n, t);
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_smin_vec(vece, d, d, t);
+    tcg_gen_dupi_vec(vece, t, mask);
+    tcg_gen_and_vec(vece, d, d, t);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SQXTNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2 ops[3] = {
+        { .fniv = gen_sqxtnb_vec,
+          .opt_opc = sqxtn_list,
+          .fno = gen_helper_sve2_sqxtnb_h,
+          .vece = MO_16 },
+        { .fniv = gen_sqxtnb_vec,
+          .opt_opc = sqxtn_list,
+          .fno = gen_helper_sve2_sqxtnb_s,
+          .vece = MO_32 },
+        { .fniv = gen_sqxtnb_vec,
+          .opt_opc = sqxtn_list,
+          .fno = gen_helper_sve2_sqxtnb_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_narrow_extract(s, a, ops);
+}
+
+static void gen_sqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t mask = (1ull << halfbits) - 1;
+    int64_t min = -1ull << (halfbits - 1);
+    int64_t max = -min - 1;
+
+    tcg_gen_dupi_vec(vece, t, min);
+    tcg_gen_smax_vec(vece, n, n, t);
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_smin_vec(vece, n, n, t);
+    tcg_gen_shli_vec(vece, n, n, halfbits);
+    tcg_gen_dupi_vec(vece, t, mask);
+    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SQXTNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2 ops[3] = {
+        { .fniv = gen_sqxtnt_vec,
+          .opt_opc = sqxtn_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqxtnt_h,
+          .vece = MO_16 },
+        { .fniv = gen_sqxtnt_vec,
+          .opt_opc = sqxtn_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqxtnt_s,
+          .vece = MO_32 },
+        { .fniv = gen_sqxtnt_vec,
+          .opt_opc = sqxtn_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqxtnt_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_narrow_extract(s, a, ops);
+}
+
+static const TCGOpcode uqxtn_list[] = {
+    INDEX_op_shli_vec, INDEX_op_umin_vec, 0
+};
+
+static void gen_uqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t max = (1ull << halfbits) - 1;
+
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_umin_vec(vece, d, n, t);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_UQXTNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2 ops[3] = {
+        { .fniv = gen_uqxtnb_vec,
+          .opt_opc = uqxtn_list,
+          .fno = gen_helper_sve2_uqxtnb_h,
+          .vece = MO_16 },
+        { .fniv = gen_uqxtnb_vec,
+          .opt_opc = uqxtn_list,
+          .fno = gen_helper_sve2_uqxtnb_s,
+          .vece = MO_32 },
+        { .fniv = gen_uqxtnb_vec,
+          .opt_opc = uqxtn_list,
+          .fno = gen_helper_sve2_uqxtnb_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_narrow_extract(s, a, ops);
+}
+
+static void gen_uqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t max = (1ull << halfbits) - 1;
+
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_umin_vec(vece, n, n, t);
+    tcg_gen_shli_vec(vece, n, n, halfbits);
+    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_UQXTNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2 ops[3] = {
+        { .fniv = gen_uqxtnt_vec,
+          .opt_opc = uqxtn_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_uqxtnt_h,
+          .vece = MO_16 },
+        { .fniv = gen_uqxtnt_vec,
+          .opt_opc = uqxtn_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_uqxtnt_s,
+          .vece = MO_32 },
+        { .fniv = gen_uqxtnt_vec,
+          .opt_opc = uqxtn_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_uqxtnt_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_narrow_extract(s, a, ops);
+}
+
+static const TCGOpcode sqxtun_list[] = {
+    INDEX_op_shli_vec, INDEX_op_umin_vec, INDEX_op_smax_vec, 0
+};
+
+static void gen_sqxtunb_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t max = (1ull << halfbits) - 1;
+
+    tcg_gen_dupi_vec(vece, t, 0);
+    tcg_gen_smax_vec(vece, d, n, t);
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_umin_vec(vece, d, d, t);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SQXTUNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2 ops[3] = {
+        { .fniv = gen_sqxtunb_vec,
+          .opt_opc = sqxtun_list,
+          .fno = gen_helper_sve2_sqxtunb_h,
+          .vece = MO_16 },
+        { .fniv = gen_sqxtunb_vec,
+          .opt_opc = sqxtun_list,
+          .fno = gen_helper_sve2_sqxtunb_s,
+          .vece = MO_32 },
+        { .fniv = gen_sqxtunb_vec,
+          .opt_opc = sqxtun_list,
+          .fno = gen_helper_sve2_sqxtunb_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_narrow_extract(s, a, ops);
+}
+
+static void gen_sqxtunt_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    int64_t max = (1ull << halfbits) - 1;
+
+    tcg_gen_dupi_vec(vece, t, 0);
+    tcg_gen_smax_vec(vece, n, n, t);
+    tcg_gen_dupi_vec(vece, t, max);
+    tcg_gen_umin_vec(vece, n, n, t);
+    tcg_gen_shli_vec(vece, n, n, halfbits);
+    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2 ops[3] = {
+        { .fniv = gen_sqxtunt_vec,
+          .opt_opc = sqxtun_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqxtunt_h,
+          .vece = MO_16 },
+        { .fniv = gen_sqxtunt_vec,
+          .opt_opc = sqxtun_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqxtunt_s,
+          .vece = MO_32 },
+        { .fniv = gen_sqxtunt_vec,
+          .opt_opc = sqxtun_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_sqxtunt_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_narrow_extract(s, a, ops);
+}
-- 
2.20.1

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-26-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 35 +++++++++++++++++++++++++++++
 target/arm/sve.decode      |  8 +++++++
 target/arm/sve_helper.c    | 46 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 25 +++++++++++++++++++++
 4 files changed, 114 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-27-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  16 ++++
 target/arm/sve.decode      |   8 ++
 target/arm/sve_helper.c    |  54 ++++++++++++-
 target/arm/translate-sve.c | 160 +++++++++++++++++++++++++++++++++++++
 4 files changed, 236 insertions(+), 2 deletions(-)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_3(sve2_shrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_shrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_rshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_rshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ UQXTNT          01000101 .. 1 ..... 010 011 ..... .....  @rd_rn_tszimm_shl
 SQXTUNB         01000101 .. 1 ..... 010 100 ..... .....  @rd_rn_tszimm_shl
 SQXTUNT         01000101 .. 1 ..... 010 101 ..... .....  @rd_rn_tszimm_shl
 
+## SVE2 bitwise shift right narrow
+
+# Bit 23 == 0 is handled by esz > 0 in the translator.
+SHRNB           01000101 .. 1 ..... 00 0100 ..... .....  @rd_rn_tszimm_shr
+SHRNT           01000101 .. 1 ..... 00 0101 ..... .....  @rd_rn_tszimm_shr
+RSHRNB          01000101 .. 1 ..... 00 0110 ..... .....  @rd_rn_tszimm_shr
+RSHRNT          01000101 .. 1 ..... 00 0111 ..... .....  @rd_rn_tszimm_shr
+
 ## SVE2 floating-point pairwise operations
 
 FADDP           01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc)  \
    when N is negative, add 2**M-1.  */
 #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M)
 
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
+{
+    if (likely(sh < 64)) {
+        return (x >> sh) + ((x >> (sh - 1)) & 1);
+    } else if (sh == 64) {
+        return x >> 63;
+    } else {
+        return 0;
+    }
+}
+
 DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR)
 DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR)
 DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR)
@@ -XXX,XX +XXX,XX @@ DO_ZPZI(sve_asrd_h, int16_t, H1_2, DO_ASRD)
 DO_ZPZI(sve_asrd_s, int32_t, H1_4, DO_ASRD)
 DO_ZPZI_D(sve_asrd_d, int64_t, DO_ASRD)
 
-#undef DO_SHR
-#undef DO_SHL
 #undef DO_ASRD
 #undef DO_ZPZI
 #undef DO_ZPZI_D
 
+#define DO_SHRNB(NAME, TYPEW, TYPEN, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc)         \
+{                                                            \
+    intptr_t i, opr_sz = simd_oprsz(desc);                   \
+    int shift = simd_data(desc);                             \
+    for (i = 0; i < opr_sz; i += sizeof(TYPEW)) {            \
+        TYPEW nn = *(TYPEW *)(vn + i);                       \
+        *(TYPEW *)(vd + i) = (TYPEN)OP(nn, shift);           \
+    }                                                        \
+}
+
+#define DO_SHRNT(NAME, TYPEW, TYPEN, HW, HN, OP)                  \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc)              \
+{                                                                 \
+    intptr_t i, opr_sz = simd_oprsz(desc);                        \
+    int shift = simd_data(desc);                                  \
+    for (i = 0; i < opr_sz; i += sizeof(TYPEW)) {                 \
+        TYPEW nn = *(TYPEW *)(vn + HW(i));                        \
+        *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, shift);   \
+    }                                                             \
+}
+
+DO_SHRNB(sve2_shrnb_h, uint16_t, uint8_t, DO_SHR)
+DO_SHRNB(sve2_shrnb_s, uint32_t, uint16_t, DO_SHR)
+DO_SHRNB(sve2_shrnb_d, uint64_t, uint32_t, DO_SHR)
+
+DO_SHRNT(sve2_shrnt_h, uint16_t, uint8_t, H1_2, H1, DO_SHR)
+DO_SHRNT(sve2_shrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_SHR)
+DO_SHRNT(sve2_shrnt_d, uint64_t, uint32_t,     , H1_4, DO_SHR)
+
+DO_SHRNB(sve2_rshrnb_h, uint16_t, uint8_t, do_urshr)
+DO_SHRNB(sve2_rshrnb_s, uint32_t, uint16_t, do_urshr)
+DO_SHRNB(sve2_rshrnb_d, uint64_t, uint32_t, do_urshr)
+
+DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr)
+DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr)
+DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t,     , H1_4, do_urshr)
+
+#undef DO_SHRNB
+#undef DO_SHRNT
+
 /* Fully general four-operand expander, controlled by a predicate.
  */
 #define DO_ZPZZZ(NAME, TYPE, H, OP)                           \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a)
     return do_sve2_narrow_extract(s, a, ops);
 }
 
+static bool do_sve2_shr_narrow(DisasContext *s, arg_rri_esz *a,
+                               const GVecGen2i ops[3])
+{
+    if (a->esz < 0 || a->esz > MO_32 || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    assert(a->imm > 0 && a->imm <= (8 << a->esz));
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_2i(vec_full_reg_offset(s, a->rd),
+                        vec_full_reg_offset(s, a->rn),
+                        vsz, vsz, a->imm, &ops[a->esz]);
+    }
+    return true;
+}
+
+static void gen_shrnb_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr)
+{
+    int halfbits = 4 << vece;
+    uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits));
+
+    tcg_gen_shri_i64(d, n, shr);
+    tcg_gen_andi_i64(d, d, mask);
+}
+
+static void gen_shrnb16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+    gen_shrnb_i64(MO_16, d, n, shr);
+}
+
+static void gen_shrnb32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+    gen_shrnb_i64(MO_32, d, n, shr);
+}
+
+static void gen_shrnb64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+    gen_shrnb_i64(MO_64, d, n, shr);
+}
+
+static void gen_shrnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    uint64_t mask = MAKE_64BIT_MASK(0, halfbits);
+
+    tcg_gen_shri_vec(vece, n, n, shr);
+    tcg_gen_dupi_vec(vece, t, mask);
+    tcg_gen_and_vec(vece, d, n, t);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SHRNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const TCGOpcode vec_list[] = { INDEX_op_shri_vec, 0 };
+    static const GVecGen2i ops[3] = {
+        { .fni8 = gen_shrnb16_i64,
+          .fniv = gen_shrnb_vec,
+          .opt_opc = vec_list,
+          .fno = gen_helper_sve2_shrnb_h,
+          .vece = MO_16 },
+        { .fni8 = gen_shrnb32_i64,
+          .fniv = gen_shrnb_vec,
+          .opt_opc = vec_list,
+          .fno = gen_helper_sve2_shrnb_s,
+          .vece = MO_32 },
+        { .fni8 = gen_shrnb64_i64,
+          .fniv = gen_shrnb_vec,
+          .opt_opc = vec_list,
+          .fno = gen_helper_sve2_shrnb_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
+static void gen_shrnt_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr)
+{
+    int halfbits = 4 << vece;
+    uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits));
+
+    tcg_gen_shli_i64(n, n, halfbits - shr);
+    tcg_gen_andi_i64(n, n, ~mask);
+    tcg_gen_andi_i64(d, d, mask);
+    tcg_gen_or_i64(d, d, n);
+}
+
+static void gen_shrnt16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+    gen_shrnt_i64(MO_16, d, n, shr);
+}
+
+static void gen_shrnt32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+    gen_shrnt_i64(MO_32, d, n, shr);
+}
+
+static void gen_shrnt64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+    tcg_gen_shri_i64(n, n, shr);
+    tcg_gen_deposit_i64(d, d, n, 32, 32);
+}
+
+static void gen_shrnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(d);
+    int halfbits = 4 << vece;
+    uint64_t mask = MAKE_64BIT_MASK(0, halfbits);
+
+    tcg_gen_shli_vec(vece, n, n, halfbits - shr);
+    tcg_gen_dupi_vec(vece, t, mask);
+    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_temp_free_vec(t);
+}
+
+static bool trans_SHRNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const TCGOpcode vec_list[] = { INDEX_op_shli_vec, 0 };
+    static const GVecGen2i ops[3] = {
+        { .fni8 = gen_shrnt16_i64,
+          .fniv = gen_shrnt_vec,
+          .opt_opc = vec_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_shrnt_h,
+          .vece = MO_16 },
+        { .fni8 = gen_shrnt32_i64,
+          .fniv = gen_shrnt_vec,
+          .opt_opc = vec_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_shrnt_s,
+          .vece = MO_32 },
+        { .fni8 = gen_shrnt64_i64,
+          .fniv = gen_shrnt_vec,
+          .opt_opc = vec_list,
+          .load_dest = true,
+          .fno = gen_helper_sve2_shrnt_d,
+          .vece = MO_64 },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
+static bool trans_RSHRNB(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2i ops[3] = {
+        { .fno = gen_helper_sve2_rshrnb_h },
+        { .fno = gen_helper_sve2_rshrnb_s },
+        { .fno = gen_helper_sve2_rshrnb_d },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
+static bool trans_RSHRNT(DisasContext *s, arg_rri_esz *a)
+{
+    static const GVecGen2i ops[3] = {
+        { .fno = gen_helper_sve2_rshrnt_h },
+        { .fno = gen_helper_sve2_rshrnt_s },
+        { .fno = gen_helper_sve2_rshrnt_d },
+    };
+    return do_sve2_shr_narrow(s, a, ops);
+}
+
 static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a,
                             gen_helper_gvec_4_ptr *fn)
 {
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-28-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 16 +++++++
 target/arm/sve.decode      |  4 ++
 target/arm/sve_helper.c    | 35 ++++++++++++++
 target/arm/translate-sve.c | 98 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 153 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-29-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 16 +++++++
 target/arm/sve.decode      |  4 ++
 target/arm/sve_helper.c    | 24 ++++++++++
 target/arm/translate-sve.c | 93 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 137 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

This completes the section "SVE2 bitwise shift right narrow".

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-30-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  16 ++++++
 target/arm/sve.decode      |   4 ++
 target/arm/sve_helper.c    |  24 +++++++++
 target/arm/translate-sve.c | 105 +++++++++++++++++++++++++++++++++++++
 4 files changed, 149 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Rename the existing sve_while (less-than) helper to sve_whilel
to make room for a new sve_whileg helper for greater-than.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-31-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  3 +-
 target/arm/sve.decode      |  2 +-
 target/arm/sve_helper.c    | 38 +++++++++++++++++++++++++-
 target/arm/translate-sve.c | 56 ++++++++++++++++++++++++++++----------
 4 files changed, 82 insertions(+), 17 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-32-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  3 ++
 target/arm/translate-sve.c | 67 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ CTERM           00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000
 # SVE integer compare scalar count and limit
 WHILE           00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4
 
+# SVE2 pointer conflict compare
+WHILE_ptr       00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
+
 ### SVE Integer Wide Immediate - Unpredicated Group
 
 # SVE broadcast floating-point immediate (unpredicated)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     return true;
 }
 
+static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
+{
+    TCGv_i64 op0, op1, diff, t1, tmax;
+    TCGv_i32 t2, t3;
+    TCGv_ptr ptr;
+    unsigned vsz = vec_full_reg_size(s);
+    unsigned desc = 0;
+
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    op0 = read_cpu_reg(s, a->rn, 1);
+    op1 = read_cpu_reg(s, a->rm, 1);
+
+    tmax = tcg_const_i64(vsz);
+    diff = tcg_temp_new_i64();
+
+    if (a->rw) {
+        /* WHILERW */
+        /* diff = abs(op1 - op0), noting that op0/1 are unsigned. */
+        t1 = tcg_temp_new_i64();
+        tcg_gen_sub_i64(diff, op0, op1);
+        tcg_gen_sub_i64(t1, op1, op0);
+        tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1);
+        tcg_temp_free_i64(t1);
+        /* Round down to a multiple of ESIZE.  */
+        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* If op1 == op0, diff == 0, and the condition is always true. */
+        tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff);
+    } else {
+        /* WHILEWR */
+        tcg_gen_sub_i64(diff, op1, op0);
+        /* Round down to a multiple of ESIZE.  */
+        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* If op0 >= op1, diff <= 0, the condition is always true. */
+        tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff);
+    }
+
+    /* Bound to the maximum.  */
+    tcg_gen_umin_i64(diff, diff, tmax);
+    tcg_temp_free_i64(tmax);
+
+    /* Since we're bounded, pass as a 32-bit type.  */
+    t2 = tcg_temp_new_i32();
+    tcg_gen_extrl_i64_i32(t2, diff);
+    tcg_temp_free_i64(diff);
+
+    desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8);
+    desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
+    t3 = tcg_const_i32(desc);
+
+    ptr = tcg_temp_new_ptr();
+    tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd));
+
+    gen_helper_sve_whilel(t2, ptr, t2, t3);
+    do_pred_flags(t2);
+
+    tcg_temp_free_ptr(ptr);
+    tcg_temp_free_i32(t2);
+    tcg_temp_free_i32(t3);
+    return true;
+}
+
 /*
  *** SVE Integer Wide Immediate - Unpredicated Group
  */
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-33-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |   6 ++
 target/arm/sve.decode      |  12 +++
 target/arm/sve_helper.c    |  50 +++++++++
 target/arm/translate-sve.c | 213 +++++++++++++++++++++++++++++++++++++
 4 files changed, 281 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_eor3, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_bcax, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_bsl1n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_bsl2n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_nbsl, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@
 @rda_rn_rm      ........ esz:2 . rm:5 ... ... rn:5 rd:5 \
                 &rrrr_esz ra=%reg_movprfx
 
+# Four operand with unused vector element size
+@rdn_ra_rm_e0   ........ ... rm:5 ... ... ra:5 rd:5 \
+                &rrrr_esz esz=0 rn=%reg_movprfx
+
 # Three operand with "memory" size, aka immediate left shift
 @rd_rn_msz_rm   ........ ... rm:5 .... imm:2 rn:5 rd:5          &rrri
 
@@ -XXX,XX +XXX,XX @@ ORR_zzz         00000100 01 1 ..... 001 100 ..... .....         @rd_rn_rm_e0
 EOR_zzz         00000100 10 1 ..... 001 100 ..... .....         @rd_rn_rm_e0
 BIC_zzz         00000100 11 1 ..... 001 100 ..... .....         @rd_rn_rm_e0
 
+# SVE2 bitwise ternary operations
+EOR3            00000100 00 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
+BSL             00000100 00 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
+BCAX            00000100 01 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
+BSL1N           00000100 01 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
+BSL2N           00000100 10 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
+NBSL            00000100 11 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
+
 ### SVE Index Generation Group
 
 # SVE index generation (immediate start, immediate increment)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64)
 
 #undef DO_ST1_ZPZ_S
 #undef DO_ST1_ZPZ_D
+
+void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn, *m = vm, *k = vk;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = n[i] ^ m[i] ^ k[i];
+    }
+}
+
+void HELPER(sve2_bcax)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn, *m = vm, *k = vk;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = n[i] ^ (m[i] & ~k[i]);
+    }
+}
+
+void HELPER(sve2_bsl1n)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn, *m = vm, *k = vk;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = (~n[i] & k[i]) | (m[i] & ~k[i]);
+    }
+}
+
+void HELPER(sve2_bsl2n)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn, *m = vm, *k = vk;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = (n[i] & k[i]) | (~m[i] & ~k[i]);
+    }
+}
+
+void HELPER(sve2_nbsl)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn, *m = vm, *k = vk;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = ~((n[i] & k[i]) | (m[i] & ~k[i]));
+    }
+}
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn,
             vec_full_reg_offset(s, rm), vsz, vsz);
 }
 
+/* Invoke a vector expander on four Zregs.  */
+static void gen_gvec_fn_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn,
+                             int esz, int rd, int rn, int rm, int ra)
+{
+    unsigned vsz = vec_full_reg_size(s);
+    gvec_fn(esz, vec_full_reg_offset(s, rd),
+            vec_full_reg_offset(s, rn),
+            vec_full_reg_offset(s, rm),
+            vec_full_reg_offset(s, ra), vsz, vsz);
+}
+
 /* Invoke a vector move on two Zregs.  */
 static bool do_mov_z(DisasContext *s, int rd, int rn)
 {
@@ -XXX,XX +XXX,XX @@ static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a)
     return do_zzz_fn(s, a, tcg_gen_gvec_andc);
 }
 
+static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_fn_zzzz(s, fn, a->esz, a->rd, a->rn, a->rm, a->ra);
+    }
+    return true;
+}
+
+static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k)
+{
+    tcg_gen_xor_i64(d, n, m);
+    tcg_gen_xor_i64(d, d, k);
+}
+
+static void gen_eor3_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+                         TCGv_vec m, TCGv_vec k)
+{
+    tcg_gen_xor_vec(vece, d, n, m);
+    tcg_gen_xor_vec(vece, d, d, k);
+}
+
+static void gen_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+                     uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen4 op = {
+        .fni8 = gen_eor3_i64,
+        .fniv = gen_eor3_vec,
+        .fno = gen_helper_sve2_eor3,
+        .vece = MO_64,
+        .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+    };
+    tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op);
+}
+
+static bool trans_EOR3(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_zzzz_fn(s, a, gen_eor3);
+}
+
+static void gen_bcax_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k)
+{
+    tcg_gen_andc_i64(d, m, k);
+    tcg_gen_xor_i64(d, d, n);
+}
+
+static void gen_bcax_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+                         TCGv_vec m, TCGv_vec k)
+{
+    tcg_gen_andc_vec(vece, d, m, k);
+    tcg_gen_xor_vec(vece, d, d, n);
+}
+
+static void gen_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+                     uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen4 op = {
+        .fni8 = gen_bcax_i64,
+        .fniv = gen_bcax_vec,
+        .fno = gen_helper_sve2_bcax,
+        .vece = MO_64,
+        .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+    };
+    tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op);
+}
+
+static bool trans_BCAX(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_zzzz_fn(s, a, gen_bcax);
+}
+
+static void gen_bsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+                    uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+    /* BSL differs from the generic bitsel in argument ordering. */
+    tcg_gen_gvec_bitsel(vece, d, a, n, m, oprsz, maxsz);
+}
+
+static bool trans_BSL(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_zzzz_fn(s, a, gen_bsl);
+}
+
+static void gen_bsl1n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k)
+{
+    tcg_gen_andc_i64(n, k, n);
+    tcg_gen_andc_i64(m, m, k);
+    tcg_gen_or_i64(d, n, m);
+}
+
+static void gen_bsl1n_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+                          TCGv_vec m, TCGv_vec k)
+{
+    if (TCG_TARGET_HAS_bitsel_vec) {
+        tcg_gen_not_vec(vece, n, n);
+        tcg_gen_bitsel_vec(vece, d, k, n, m);
+    } else {
+        tcg_gen_andc_vec(vece, n, k, n);
+        tcg_gen_andc_vec(vece, m, m, k);
+        tcg_gen_or_vec(vece, d, n, m);
+    }
+}
+
+static void gen_bsl1n(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+                      uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen4 op = {
+        .fni8 = gen_bsl1n_i64,
+        .fniv = gen_bsl1n_vec,
+        .fno = gen_helper_sve2_bsl1n,
+        .vece = MO_64,
+        .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+    };
+    tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op);
+}
+
+static bool trans_BSL1N(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_zzzz_fn(s, a, gen_bsl1n);
+}
+
+static void gen_bsl2n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k)
+{
+    /*
+     * Z[dn] = (n & k) | (~m & ~k)
+     *       =         | ~(m | k)
+     */
+    tcg_gen_and_i64(n, n, k);
+    if (TCG_TARGET_HAS_orc_i64) {
+        tcg_gen_or_i64(m, m, k);
+        tcg_gen_orc_i64(d, n, m);
+    } else {
+        tcg_gen_nor_i64(m, m, k);
+        tcg_gen_or_i64(d, n, m);
+    }
+}
+
+static void gen_bsl2n_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+                          TCGv_vec m, TCGv_vec k)
+{
+    if (TCG_TARGET_HAS_bitsel_vec) {
+        tcg_gen_not_vec(vece, m, m);
+        tcg_gen_bitsel_vec(vece, d, k, n, m);
+    } else {
+        tcg_gen_and_vec(vece, n, n, k);
+        tcg_gen_or_vec(vece, m, m, k);
+        tcg_gen_orc_vec(vece, d, n, m);
+    }
+}
+
+static void gen_bsl2n(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+                      uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen4 op = {
+        .fni8 = gen_bsl2n_i64,
+        .fniv = gen_bsl2n_vec,
+        .fno = gen_helper_sve2_bsl2n,
+        .vece = MO_64,
+        .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+    };
+    tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op);
+}
+
+static bool trans_BSL2N(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_zzzz_fn(s, a, gen_bsl2n);
+}
+
+static void gen_nbsl_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k)
+{
+    tcg_gen_and_i64(n, n, k);
+    tcg_gen_andc_i64(m, m, k);
+    tcg_gen_nor_i64(d, n, m);
+}
+
+static void gen_nbsl_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+                          TCGv_vec m, TCGv_vec k)
+{
+    tcg_gen_bitsel_vec(vece, d, k, n, m);
+    tcg_gen_not_vec(vece, d, d);
+}
+
+static void gen_nbsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
+                     uint32_t a, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen4 op = {
+        .fni8 = gen_nbsl_i64,
+        .fniv = gen_nbsl_vec,
+        .fno = gen_helper_sve2_nbsl,
+        .vece = MO_64,
+        .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+    };
+    tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op);
+}
+
+static bool trans_NBSL(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_zzzz_fn(s, a, gen_nbsl);
+}
+
 /*
  *** SVE Integer Arithmetic - Unpredicated Group
  */
-- 
2.20.1

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-34-richard.henderson@linaro.org
Message-Id: <20200415145915.2859-1-steplong@quicinc.com>
[rth: Expanded comment for do_match2]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 10 ++++++
 target/arm/sve.decode      |  5 +++
 target/arm/sve_helper.c    | 64 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 22 +++++++++++++
 4 files changed, 101 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-35-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 14 ++++++++++
 target/arm/sve.decode      | 14 ++++++++++
 target/arm/sve_helper.c    | 30 +++++++++++++++++++++
 target/arm/translate-sve.c | 54 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 112 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

SVE2 has two additional sizes of the operation and unlike NEON,
there is no saturation flag.  Create new entry points for SVE2
that do not set QC.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-36-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h        |  17 ++++
 target/arm/sve.decode      |   5 ++
 target/arm/translate-sve.c |  18 +++++
 target/arm/vec_helper.c    | 161 +++++++++++++++++++++++++++++++++++--
 4 files changed, 195 insertions(+), 6 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-37-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 28 ++++++++++++++
 target/arm/sve.decode      | 11 ++++++
 target/arm/sve_helper.c    | 18 +++++++++
 target/arm/translate-sve.c | 76 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 133 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-38-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 18 +++++++++++++++
 target/arm/vec_internal.h  |  5 +++++
 target/arm/sve.decode      |  5 +++++
 target/arm/sve_helper.c    | 46 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 32 ++++++++++++++++++++++++++
 target/arm/vec_helper.c    | 15 ++++++-------
 6 files changed, 113 insertions(+), 8 deletions(-)

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-39-richard.henderson@linaro.org
Message-Id: <20200417162231.10374-2-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  8 ++++++++
 target/arm/sve.decode      |  5 +++++
 target/arm/sve_helper.c    | 36 ++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 13 +++++++++++++
 4 files changed, 62 insertions(+)

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-40-richard.henderson@linaro.org
Message-Id: <20200417162231.10374-3-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  8 ++++++++
 target/arm/sve.decode      |  2 ++
 target/arm/sve_helper.c    | 10 ++++++++++
 target/arm/translate-sve.c |  2 ++
 4 files changed, 22 insertions(+)

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-41-richard.henderson@linaro.org
Message-Id: <20200417162231.10374-4-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  8 ++++++++
 target/arm/sve.decode      |  2 ++
 target/arm/sve_helper.c    | 10 ++++++++++
 target/arm/translate-sve.c |  3 +++
 4 files changed, 23 insertions(+)

From: Stephen Long <steplong@quicinc.com>

This completes the section 'SVE2 integer add/subtract narrow high part'

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-42-richard.henderson@linaro.org
Message-Id: <20200417162231.10374-5-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  8 ++++++++
 target/arm/sve.decode      |  2 ++
 target/arm/sve_helper.c    | 10 ++++++++++
 target/arm/translate-sve.c |  2 ++
 4 files changed, 22 insertions(+)

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-43-richard.henderson@linaro.org
Message-Id: <20200416173109.8856-1-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |   7 ++
 target/arm/sve.decode      |   6 ++
 target/arm/sve_helper.c    | 131 +++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c |  19 ++++++
 4 files changed, 163 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

In addition, use the same vector generator interface for AdvSIMD.
This fixes a bug in which the AdvSIMD insn failed to clear the
high bits of the SVE register.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-44-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |   4 ++
 target/arm/helper.h        |   2 +
 target/arm/translate-a64.h |   3 ++
 target/arm/sve.decode      |   4 ++
 target/arm/sve_helper.c    |  39 ++++++++++++++
 target/arm/translate-a64.c |  25 ++-------
 target/arm/translate-sve.c | 104 +++++++++++++++++++++++++++++++++++++
 target/arm/vec_helper.c    |  12 +++++
 8 files changed, 172 insertions(+), 21 deletions(-)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_histcnt_d, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_4(sve2_histseg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(sve2_xar_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_xar_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_xar_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/helper.h b/target/arm/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
 #include "helper-sve.h"
diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.h
+++ b/target/arm/translate-a64.h
@@ -XXX,XX +XXX,XX @@ bool disas_sve(DisasContext *, uint32_t);
 
 void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                    uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                  uint32_t rm_ofs, int64_t shift,
+                  uint32_t opr_sz, uint32_t max_sz);
 
 #endif /* TARGET_ARM_TRANSLATE_A64_H */
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@
 &rr_dbm         rd rn dbm
 &rrri           rd rn rm imm
 &rri_esz        rd rn imm esz
+&rrri_esz       rd rn rm imm esz
 &rrr_esz        rd rn rm esz
 &rpr_esz        rd pg rn esz
 &rpr_s          rd pg rn s
@@ -XXX,XX +XXX,XX @@ ORR_zzz         00000100 01 1 ..... 001 100 ..... .....         @rd_rn_rm_e0
 EOR_zzz         00000100 10 1 ..... 001 100 ..... .....         @rd_rn_rm_e0
 BIC_zzz         00000100 11 1 ..... 001 100 ..... .....         @rd_rn_rm_e0
 
+XAR             00000100 .. 1 ..... 001 101 rm:5  rd:5   &rrri_esz \
+                rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr
+
 # SVE2 bitwise ternary operations
 EOR3            00000100 00 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
 BSL             00000100 00 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_histseg)(void *vd, void *vn, void *vm, uint32_t desc)
         *(uint64_t *)(vd + i + 8) = out1;
     }
 }
+
+void HELPER(sve2_xar_b)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    int shr = simd_data(desc);
+    int shl = 8 - shr;
+    uint64_t mask = dup_const(MO_8, 0xff >> shr);
+    uint64_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz; ++i) {
+        uint64_t t = n[i] ^ m[i];
+        d[i] = ((t >> shr) & mask) | ((t << shl) & ~mask);
+    }
+}
+
+void HELPER(sve2_xar_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    int shr = simd_data(desc);
+    int shl = 16 - shr;
+    uint64_t mask = dup_const(MO_16, 0xffff >> shr);
+    uint64_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz; ++i) {
+        uint64_t t = n[i] ^ m[i];
+        d[i] = ((t >> shr) & mask) | ((t << shl) & ~mask);
+    }
+}
+
+void HELPER(sve2_xar_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 4;
+    int shr = simd_data(desc);
+    uint32_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = ror32(n[i] ^ m[i], shr);
+    }
+}
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn)
     int imm6 = extract32(insn, 10, 6);
     int rn = extract32(insn, 5, 5);
     int rd = extract32(insn, 0, 5);
-    TCGv_i64 tcg_op1, tcg_op2, tcg_res[2];
-    int pass;
 
     if (!dc_isar_feature(aa64_sha3, s)) {
         unallocated_encoding(s);
@@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn)
         return;
     }
 
-    tcg_op1 = tcg_temp_new_i64();
-    tcg_op2 = tcg_temp_new_i64();
-    tcg_res[0] = tcg_temp_new_i64();
-    tcg_res[1] = tcg_temp_new_i64();
-
-    for (pass = 0; pass < 2; pass++) {
-        read_vec_element(s, tcg_op1, rn, pass, MO_64);
-        read_vec_element(s, tcg_op2, rm, pass, MO_64);
-
-        tcg_gen_xor_i64(tcg_res[pass], tcg_op1, tcg_op2);
-        tcg_gen_rotri_i64(tcg_res[pass], tcg_res[pass], imm6);
-    }
-    write_vec_element(s, tcg_res[0], rd, 0, MO_64);
-    write_vec_element(s, tcg_res[1], rd, 1, MO_64);
-
-    tcg_temp_free_i64(tcg_op1);
-    tcg_temp_free_i64(tcg_op2);
-    tcg_temp_free_i64(tcg_res[0]);
-    tcg_temp_free_i64(tcg_res[1]);
+    gen_gvec_xar(MO_64, vec_full_reg_offset(s, rd),
+                 vec_full_reg_offset(s, rn),
+                 vec_full_reg_offset(s, rm), imm6, 16,
+                 vec_full_reg_size(s));
 }
 
 /* Crypto three-reg imm2
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a)
     return do_zzz_fn(s, a, tcg_gen_gvec_andc);
 }
 
+static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh)
+{
+    TCGv_i64 t = tcg_temp_new_i64();
+    uint64_t mask = dup_const(MO_8, 0xff >> sh);
+
+    tcg_gen_xor_i64(t, n, m);
+    tcg_gen_shri_i64(d, t, sh);
+    tcg_gen_shli_i64(t, t, 8 - sh);
+    tcg_gen_andi_i64(d, d, mask);
+    tcg_gen_andi_i64(t, t, ~mask);
+    tcg_gen_or_i64(d, d, t);
+    tcg_temp_free_i64(t);
+}
+
+static void gen_xar16_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh)
+{
+    TCGv_i64 t = tcg_temp_new_i64();
+    uint64_t mask = dup_const(MO_16, 0xffff >> sh);
+
+    tcg_gen_xor_i64(t, n, m);
+    tcg_gen_shri_i64(d, t, sh);
+    tcg_gen_shli_i64(t, t, 16 - sh);
+    tcg_gen_andi_i64(d, d, mask);
+    tcg_gen_andi_i64(t, t, ~mask);
+    tcg_gen_or_i64(d, d, t);
+    tcg_temp_free_i64(t);
+}
+
+static void gen_xar_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, int32_t sh)
+{
+    tcg_gen_xor_i32(d, n, m);
+    tcg_gen_rotri_i32(d, d, sh);
+}
+
+static void gen_xar_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh)
+{
+    tcg_gen_xor_i64(d, n, m);
+    tcg_gen_rotri_i64(d, d, sh);
+}
+
+static void gen_xar_vec(unsigned vece, TCGv_vec d, TCGv_vec n,
+                        TCGv_vec m, int64_t sh)
+{
+    tcg_gen_xor_vec(vece, d, n, m);
+    tcg_gen_rotri_vec(vece, d, d, sh);
+}
+
+void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                  uint32_t rm_ofs, int64_t shift,
+                  uint32_t opr_sz, uint32_t max_sz)
+{
+    static const TCGOpcode vecop[] = { INDEX_op_rotli_vec, 0 };
+    static const GVecGen3i ops[4] = {
+        { .fni8 = gen_xar8_i64,
+          .fniv = gen_xar_vec,
+          .fno = gen_helper_sve2_xar_b,
+          .opt_opc = vecop,
+          .vece = MO_8 },
+        { .fni8 = gen_xar16_i64,
+          .fniv = gen_xar_vec,
+          .fno = gen_helper_sve2_xar_h,
+          .opt_opc = vecop,
+          .vece = MO_16 },
+        { .fni4 = gen_xar_i32,
+          .fniv = gen_xar_vec,
+          .fno = gen_helper_sve2_xar_s,
+          .opt_opc = vecop,
+          .vece = MO_32 },
+        { .fni8 = gen_xar_i64,
+          .fniv = gen_xar_vec,
+          .fno = gen_helper_gvec_xar_d,
+          .opt_opc = vecop,
+          .vece = MO_64 }
+    };
+    int esize = 8 << vece;
+
+    /* The SVE2 range is 1 .. esize; the AdvSIMD range is 0 .. esize-1. */
+    tcg_debug_assert(shift >= 0);
+    tcg_debug_assert(shift <= esize);
+    shift &= esize - 1;
+
+    if (shift == 0) {
+        /* xar with no rotate devolves to xor. */
+        tcg_gen_gvec_xor(vece, rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz);
+    } else {
+        tcg_gen_gvec_3i(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz,
+                        shift, &ops[vece]);
+    }
+}
+
+static bool trans_XAR(DisasContext *s, arg_rrri_esz *a)
+{
+    if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        gen_gvec_xar(a->esz, vec_full_reg_offset(s, a->rd),
+                     vec_full_reg_offset(s, a->rn),
+                     vec_full_reg_offset(s, a->rm), a->imm, vsz, vsz);
+    }
+    return true;
+}
+
 static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn)
 {
     if (!dc_isar_feature(aa64_sve2, s)) {
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_umulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_xar_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    int shr = simd_data(desc);
+    uint64_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = ror64(n[i] ^ m[i], shr);
+    }
+    clear_tail(d, opr_sz * 8, simd_maxsz(desc));
+}
-- 
2.20.1

From: Stephen Long <steplong@quicinc.com>

Add decoding logic for SVE2 64-bit/32-bit scatter non-temporal
store insns.

64-bit
* STNT1B (vector plus scalar)
* STNT1H (vector plus scalar)
* STNT1W (vector plus scalar)
* STNT1D (vector plus scalar)

32-bit
* STNT1B (vector plus scalar)
* STNT1H (vector plus scalar)
* STNT1W (vector plus scalar)

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-45-richard.henderson@linaro.org
Message-Id: <20200422141553.8037-1-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      | 10 ++++++++++
 target/arm/translate-sve.c |  8 ++++++++
 2 files changed, 18 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw     01000100 .. 0 ..... 010 111 ..... .....  @rda_rn_rm
 
 CMLA_zzzz       01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5  ra=%reg_movprfx
 SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
+
+### SVE2 Memory Store Group
+
+# SVE2 64-bit scatter non-temporal store (vector plus scalar)
+STNT1_zprz      1110010 .. 00 ..... 001 ... ..... ..... \
+                @rprr_scatter_store xs=2 esz=3 scale=0
+
+# SVE2 32-bit scatter non-temporal store (vector plus scalar)
+STNT1_zprz      1110010 .. 10 ..... 001 ... ..... ..... \
+                @rprr_scatter_store xs=0 esz=2 scale=0
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a)
     return true;
 }
 
+static bool trans_STNT1_zprz(DisasContext *s, arg_ST1_zprz *a)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return trans_ST1_zprz(s, a);
+}
+
 /*
  * Prefetches
  */
-- 
2.20.1

From: Stephen Long <steplong@quicinc.com>

Add decoding logic for SVE2 64-bit/32-bit gather non-temporal
load insns.

64-bit
* LDNT1SB
* LDNT1B (vector plus scalar)
* LDNT1SH
* LDNT1H (vector plus scalar)
* LDNT1SW
* LDNT1W (vector plus scalar)
* LDNT1D (vector plus scalar)

32-bit
* LDNT1SB
* LDNT1B (vector plus scalar)
* LDNT1SH
* LDNT1H (vector plus scalar)
* LDNT1W (vector plus scalar)

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-46-richard.henderson@linaro.org
Message-Id: <20200422152343.12493-1-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      | 11 +++++++++++
 target/arm/translate-sve.c |  8 ++++++++
 2 files changed, 19 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw     01000100 .. 0 ..... 010 111 ..... .....  @rda_rn_rm
 CMLA_zzzz       01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5  ra=%reg_movprfx
 SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 
+### SVE2 Memory Gather Load Group
+
+# SVE2 64-bit gather non-temporal load
+#   (scalar plus unpacked 32-bit unscaled offsets)
+LDNT1_zprz      1100010 msz:2 00 rm:5 1 u:1 0 pg:3 rn:5 rd:5 \
+                &rprr_gather_load xs=0 esz=3 scale=0 ff=0
+
+# SVE2 32-bit gather non-temporal load (scalar plus 32-bit unscaled offsets)
+LDNT1_zprz      1000010 msz:2 00 rm:5 10 u:1 pg:3 rn:5 rd:5 \
+                &rprr_gather_load xs=0 esz=2 scale=0 ff=0
+
 ### SVE2 Memory Store Group
 
 # SVE2 64-bit scatter non-temporal store (vector plus scalar)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a)
     return true;
 }
 
+static bool trans_LDNT1_zprz(DisasContext *s, arg_LD1_zprz *a)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return trans_LD1_zprz(s, a);
+}
+
 /* Indexed by [mte][be][xs][msz].  */
 static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][2][3] = {
     { /* MTE Inactive */
-- 
2.20.1

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-47-richard.henderson@linaro.org
Message-Id: <20200422165503.13511-1-steplong@quicinc.com>
[rth: Fix indexing in helpers, expand macro to straight functions.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           | 10 ++++++
 target/arm/helper-sve.h    |  3 ++
 target/arm/sve.decode      |  4 +++
 target/arm/sve_helper.c    | 74 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 34 ++++++++++++++++++
 5 files changed, 125 insertions(+)

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-48-richard.henderson@linaro.org
Message-Id: <20200423180347.9403-1-steplong@quicinc.com>
[rth: Rename the trans_* functions to *_sve2.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      | 11 +++++++++--
 target/arm/translate-sve.c | 35 ++++++++++++++++++++++++++++++-----
 2 files changed, 39 insertions(+), 7 deletions(-)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ CPY_z_i         00000101 .. 01 .... 00 . ........ .....   @rdn_pg4 imm=%sh8_i8s
 
 ### SVE Permute - Extract Group
 
-# SVE extract vector (immediate offset)
+# SVE extract vector (destructive)
 EXT             00000101 001 ..... 000 ... rm:5 rd:5 \
                 &rrri rn=%reg_movprfx imm=%imm8_16_10
 
+# SVE2 extract vector (constructive)
+EXT_sve2        00000101 011 ..... 000 ... rn:5 rd:5 \
+                &rri imm=%imm8_16_10
+
 ### SVE Permute - Unpredicated Group
 
 # SVE broadcast general register
@@ -XXX,XX +XXX,XX @@ REVH            00000101 .. 1001 01 100 ... ..... .....         @rd_pg_rn
 REVW            00000101 .. 1001 10 100 ... ..... .....         @rd_pg_rn
 RBIT            00000101 .. 1001 11 100 ... ..... .....         @rd_pg_rn
 
-# SVE vector splice (predicated)
+# SVE vector splice (predicated, destructive)
 SPLICE          00000101 .. 101 100 100 ... ..... .....         @rdn_pg_rm
 
+# SVE2 vector splice (predicated, constructive)
+SPLICE_sve2     00000101 .. 101 101 100 ... ..... .....         @rd_pg_rn
+
 ### SVE Select Vectors Group
 
 # SVE select vector elements (predicated)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_CPY_z_i(DisasContext *s, arg_CPY_z_i *a)
  *** SVE Permute Extract Group
  */
 
-static bool trans_EXT(DisasContext *s, arg_EXT *a)
+static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm)
 {
     if (!sve_access_check(s)) {
         return true;
     }
 
     unsigned vsz = vec_full_reg_size(s);
-    unsigned n_ofs = a->imm >= vsz ? 0 : a->imm;
+    unsigned n_ofs = imm >= vsz ? 0 : imm;
     unsigned n_siz = vsz - n_ofs;
-    unsigned d = vec_full_reg_offset(s, a->rd);
-    unsigned n = vec_full_reg_offset(s, a->rn);
-    unsigned m = vec_full_reg_offset(s, a->rm);
+    unsigned d = vec_full_reg_offset(s, rd);
+    unsigned n = vec_full_reg_offset(s, rn);
+    unsigned m = vec_full_reg_offset(s, rm);
 
     /* Use host vector move insns if we have appropriate sizes
      * and no unfortunate overlap.
@@ -XXX,XX +XXX,XX @@ static bool trans_EXT(DisasContext *s, arg_EXT *a)
     return true;
 }
 
+static bool trans_EXT(DisasContext *s, arg_EXT *a)
+{
+    return do_EXT(s, a->rd, a->rn, a->rm, a->imm);
+}
+
+static bool trans_EXT_sve2(DisasContext *s, arg_rri *a)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return do_EXT(s, a->rd, a->rn, (a->rn + 1) % 32, a->imm);
+}
+
 /*
  *** SVE Permute - Unpredicated Group
  */
@@ -XXX,XX +XXX,XX @@ static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a)
     return true;
 }
 
+static bool trans_SPLICE_sve2(DisasContext *s, arg_rpr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzp(s, gen_helper_sve_splice,
+                          a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz);
+    }
+    return true;
+}
+
 /*
  *** SVE Integer Compare - Vectors Group
  */
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

The signed dot product routines produce a signed result.
Since we use -fwrapv, there is no functional change.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-49-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/vec_helper.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm,
 void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    uint32_t *d = vd;
+    int32_t *d = vd;
     int8_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 4; ++i) {
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc)
 void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    uint64_t *d = vd;
+    int64_t *d = vd;
     int16_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 8; ++i) {
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
     intptr_t index = simd_data(desc);
-    uint32_t *d = vd;
+    int32_t *d = vd;
     int8_t *n = vn;
     int8_t *m_indexed = (int8_t *)vm + H4(index) * 4;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
     intptr_t index = simd_data(desc);
-    uint64_t *d = vd;
+    int64_t *d = vd;
     int16_t *n = vn;
     int16_t *m_indexed = (int16_t *)vm + index * 4;
 
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

For SVE, we potentially have a 4th argument coming from the
movprfx instruction.  Currently we do not optimize movprfx,
so the problem is not visible.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-50-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h         |  20 +++---
 target/arm/sve.decode       |   7 ++-
 target/arm/translate-a64.c  |  15 ++++-
 target/arm/translate-neon.c |  10 +--
 target/arm/translate-sve.c  |  13 ++--
 target/arm/vec_helper.c     | 120 ++++++++++++++++++++----------------
 6 files changed, 109 insertions(+), 76 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_4(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_4(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ UMIN_zzi        00100101 .. 101 011 110 ........ .....          @rdn_i8u
 MUL_zzi         00100101 .. 110 000 110 ........ .....          @rdn_i8s
 
 # SVE integer dot product (unpredicated)
-DOT_zzz         01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5      ra=%reg_movprfx
+DOT_zzzz        01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \
+                ra=%reg_movprfx
 
 # SVE integer dot product (indexed)
-DOT_zzx         01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \
+DOT_zzxw        01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \
                 sz=0 ra=%reg_movprfx
-DOT_zzx         01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \
+DOT_zzxw        01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \
                 sz=1 ra=%reg_movprfx
 
 # SVE floating-point complex add (predicated)
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn,
     tcg_temp_free_ptr(qc_ptr);
 }
 
+/* Expand a 4-operand operation using an out-of-line helper.  */
+static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
+                             int rm, int ra, int data, gen_helper_gvec_4 *fn)
+{
+    tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
+                       vec_full_reg_offset(s, rn),
+                       vec_full_reg_offset(s, rm),
+                       vec_full_reg_offset(s, ra),
+                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
+}
+
 /* Set ZF and NF based on a 64 bit result. This is alas fiddlier
  * than the 32 bit equivalent.
  */
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         return;
 
     case 0x2: /* SDOT / UDOT */
-        gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0,
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0,
                          u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b);
         return;
 
@@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     switch (16 * u + opcode) {
     case 0x0e: /* SDOT */
     case 0x1e: /* UDOT */
-        gen_gvec_op3_ool(s, is_q, rd, rn, rm, index,
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
                          u ? gen_helper_gvec_udot_idx_b
                          : gen_helper_gvec_sdot_idx_b);
         return;
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
 static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
 {
     int opr_sz;
-    gen_helper_gvec_3 *fn_gvec;
+    gen_helper_gvec_4 *fn_gvec;
 
     if (!dc_isar_feature(aa32_dp, s)) {
         return false;
@@ -XXX,XX +XXX,XX @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
 
     opr_sz = (1 + a->q) * 8;
     fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b;
-    tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd),
+    tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd),
                        vfp_reg_offset(1, a->vn),
                        vfp_reg_offset(1, a->vm),
+                       vfp_reg_offset(1, a->vd),
                        opr_sz, opr_sz, 0, fn_gvec);
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
 
 static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
 {
-    gen_helper_gvec_3 *fn_gvec;
+    gen_helper_gvec_4 *fn_gvec;
     int opr_sz;
     TCGv_ptr fpst;
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
     fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b;
     opr_sz = (1 + a->q) * 8;
     fpst = fpstatus_ptr(FPST_STD);
-    tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd),
+    tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd),
                        vfp_reg_offset(1, a->vn),
                        vfp_reg_offset(1, a->rm),
+                       vfp_reg_offset(1, a->vd),
                        opr_sz, opr_sz, a->index, fn_gvec);
     tcg_temp_free_ptr(fpst);
     return true;
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin)
 
 #undef DO_ZZI
 
-static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a)
+static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a)
 {
-    static gen_helper_gvec_3 * const fns[2][2] = {
+    static gen_helper_gvec_4 * const fns[2][2] = {
         { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h },
         { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h }
     };
 
     if (sve_access_check(s)) {
-        gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, 0);
+        gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0);
     }
     return true;
 }
 
-static bool trans_DOT_zzx(DisasContext *s, arg_DOT_zzx *a)
+static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a)
 {
-    static gen_helper_gvec_3 * const fns[2][2] = {
+    static gen_helper_gvec_4 * const fns[2][2] = {
         { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h },
         { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h }
     };
 
     if (sve_access_check(s)) {
-        gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->index);
+        gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm,
+                          a->ra, a->index);
     }
     return true;
 }
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm,
  * All elements are treated equally, no matter where they are.
  */
 
-void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    int32_t *d = vd;
+    int32_t *d = vd, *a = va;
     int8_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 4; ++i) {
-        d[i] += n[i * 4 + 0] * m[i * 4 + 0]
-              + n[i * 4 + 1] * m[i * 4 + 1]
-              + n[i * 4 + 2] * m[i * 4 + 2]
-              + n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                n[i * 4 + 0] * m[i * 4 + 0] +
+                n[i * 4 + 1] * m[i * 4 + 1] +
+                n[i * 4 + 2] * m[i * 4 + 2] +
+                n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    uint32_t *d = vd;
+    uint32_t *d = vd, *a = va;
     uint8_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 4; ++i) {
-        d[i] += n[i * 4 + 0] * m[i * 4 + 0]
-              + n[i * 4 + 1] * m[i * 4 + 1]
-              + n[i * 4 + 2] * m[i * 4 + 2]
-              + n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                n[i * 4 + 0] * m[i * 4 + 0] +
+                n[i * 4 + 1] * m[i * 4 + 1] +
+                n[i * 4 + 2] * m[i * 4 + 2] +
+                n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    int64_t *d = vd;
+    int64_t *d = vd, *a = va;
     int16_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 8; ++i) {
-        d[i] += (int64_t)n[i * 4 + 0] * m[i * 4 + 0]
-              + (int64_t)n[i * 4 + 1] * m[i * 4 + 1]
-              + (int64_t)n[i * 4 + 2] * m[i * 4 + 2]
-              + (int64_t)n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                (int64_t)n[i * 4 + 0] * m[i * 4 + 0] +
+                (int64_t)n[i * 4 + 1] * m[i * 4 + 1] +
+                (int64_t)n[i * 4 + 2] * m[i * 4 + 2] +
+                (int64_t)n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc);
-    uint64_t *d = vd;
+    uint64_t *d = vd, *a = va;
     uint16_t *n = vn, *m = vm;
 
     for (i = 0; i < opr_sz / 8; ++i) {
-        d[i] += (uint64_t)n[i * 4 + 0] * m[i * 4 + 0]
-              + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1]
-              + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2]
-              + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3];
+        d[i] = (a[i] +
+                (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] +
+                (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] +
+                (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] +
+                (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
     intptr_t index = simd_data(desc);
-    int32_t *d = vd;
+    int32_t *d = vd, *a = va;
     int8_t *n = vn;
     int8_t *m_indexed = (int8_t *)vm + H4(index) * 4;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
         int8_t m3 = m_indexed[i * 4 + 3];
 
         do {
-            d[i] += n[i * 4 + 0] * m0
-                  + n[i * 4 + 1] * m1
-                  + n[i * 4 + 2] * m2
-                  + n[i * 4 + 3] * m3;
+            d[i] = (a[i] +
+                    n[i * 4 + 0] * m0 +
+                    n[i * 4 + 1] * m1 +
+                    n[i * 4 + 2] * m2 +
+                    n[i * 4 + 3] * m3);
         } while (++i < segend);
         segend = i + 4;
     } while (i < opr_sz_4);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
     intptr_t index = simd_data(desc);
-    uint32_t *d = vd;
+    uint32_t *d = vd, *a = va;
     uint8_t *n = vn;
     uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
         uint8_t m3 = m_indexed[i * 4 + 3];
 
         do {
-            d[i] += n[i * 4 + 0] * m0
-                  + n[i * 4 + 1] * m1
-                  + n[i * 4 + 2] * m2
-                  + n[i * 4 + 3] * m3;
+            d[i] = (a[i] +
+                    n[i * 4 + 0] * m0 +
+                    n[i * 4 + 1] * m1 +
+                    n[i * 4 + 2] * m2 +
+                    n[i * 4 + 3] * m3);
         } while (++i < segend);
         segend = i + 4;
     } while (i < opr_sz_4);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
     intptr_t index = simd_data(desc);
-    int64_t *d = vd;
+    int64_t *d = vd, *a = va;
     int16_t *n = vn;
     int16_t *m_indexed = (int16_t *)vm + index * 4;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
      * Process the entire segment all at once, writing back the results
      * only after we've consumed all of the inputs.
      */
-    for (i = 0; i < opr_sz_8 ; i += 2) {
-        uint64_t d0, d1;
+    for (i = 0; i < opr_sz_8; i += 2) {
+        int64_t d0, d1;
 
-        d0  = n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0];
+        d0  = a[i + 0];
+        d0 += n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0];
         d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1];
         d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2];
         d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3];
-        d1  = n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0];
+
+        d1  = a[i + 1];
+        d1 += n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0];
         d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1];
         d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2];
         d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3];
 
-        d[i + 0] += d0;
-        d[i + 1] += d1;
+        d[i + 0] = d0;
+        d[i + 1] = d1;
     }
-
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
     intptr_t index = simd_data(desc);
-    uint64_t *d = vd;
+    uint64_t *d = vd, *a = va;
     uint16_t *n = vn;
     uint16_t *m_indexed = (uint16_t *)vm + index * 4;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
      * Process the entire segment all at once, writing back the results
      * only after we've consumed all of the inputs.
      */
-    for (i = 0; i < opr_sz_8 ; i += 2) {
+    for (i = 0; i < opr_sz_8; i += 2) {
         uint64_t d0, d1;
 
-        d0  = n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0];
+        d0  = a[i + 0];
+        d0 += n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0];
         d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1];
         d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2];
         d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3];
-        d1  = n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0];
+
+        d1  = a[i + 1];
+        d1 += n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0];
         d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1];
         d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2];
         d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3];
 
-        d[i + 0] += d0;
-        d[i + 1] += d1;
+        d[i + 0] = d0;
+        d[i + 1] = d1;
     }
-
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

For SVE, we potentially have a 4th argument coming from the
movprfx instruction.  Currently we do not optimize movprfx,
so the problem is not visible.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-51-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h         | 20 +++++++--------
 target/arm/translate-a64.c  | 28 +++++++++++++++++----
 target/arm/translate-neon.c | 10 +++++---
 target/arm/translate-sve.c  |  5 ++--
 target/arm/vec_helper.c     | 50 +++++++++++++++----------------------
 5 files changed, 62 insertions(+), 51 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_5(gvec_fcmlah, TCG_CALL_NO_RWG,
-                   void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlah_idx, TCG_CALL_NO_RWG,
-                   void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlas, TCG_CALL_NO_RWG,
-                   void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
-                   void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG,
-                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
                        is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
 }
 
+/*
+ * Expand a 4-operand + fpstatus pointer + simd data value operation using
+ * an out-of-line helper.
+ */
+static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn,
+                              int rm, int ra, bool is_fp16, int data,
+                              gen_helper_gvec_4_ptr *fn)
+{
+    TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR);
+    tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd),
+                       vec_full_reg_offset(s, rn),
+                       vec_full_reg_offset(s, rm),
+                       vec_full_reg_offset(s, ra), fpst,
+                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
+    tcg_temp_free_ptr(fpst);
+}
+
 /* Set ZF and NF based on a 64 bit result. This is alas fiddlier
  * than the 32 bit equivalent.
  */
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         rot = extract32(opcode, 0, 2);
         switch (size) {
         case 1:
-            gen_gvec_op3_fpst(s, is_q, rd, rn, rm, true, rot,
+            gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, true, rot,
                               gen_helper_gvec_fcmlah);
             break;
         case 2:
-            gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot,
+            gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot,
                               gen_helper_gvec_fcmlas);
             break;
         case 3:
-            gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot,
+            gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot,
                               gen_helper_gvec_fcmlad);
             break;
         default:
@@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
         {
             int rot = extract32(insn, 13, 2);
             int data = (index << 2) | rot;
-            tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
+            tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd),
                                vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm), fpst,
+                               vec_full_reg_offset(s, rm),
+                               vec_full_reg_offset(s, rd), fpst,
                                is_q ? 16 : 8, vec_full_reg_size(s), data,
                                size == MO_64
                                ? gen_helper_gvec_fcmlas_idx
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
 {
     int opr_sz;
     TCGv_ptr fpst;
-    gen_helper_gvec_3_ptr *fn_gvec_ptr;
+    gen_helper_gvec_4_ptr *fn_gvec_ptr;
 
     if (!dc_isar_feature(aa32_vcma, s)
         || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) {
@@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
     fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
     fn_gvec_ptr = (a->size == MO_16) ?
         gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas;
-    tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
+    tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd),
                        vfp_reg_offset(1, a->vn),
                        vfp_reg_offset(1, a->vm),
+                       vfp_reg_offset(1, a->vd),
                        fpst, opr_sz, opr_sz, a->rot,
                        fn_gvec_ptr);
     tcg_temp_free_ptr(fpst);
@@ -XXX,XX +XXX,XX @@ static bool trans_VFML(DisasContext *s, arg_VFML *a)
 
 static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
 {
-    gen_helper_gvec_3_ptr *fn_gvec_ptr;
+    gen_helper_gvec_4_ptr *fn_gvec_ptr;
     int opr_sz;
     TCGv_ptr fpst;
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
         gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx;
     opr_sz = (1 + a->q) * 8;
     fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
-    tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
+    tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd),
                        vfp_reg_offset(1, a->vn),
                        vfp_reg_offset(1, a->vm),
+                       vfp_reg_offset(1, a->vd),
                        fpst, opr_sz, opr_sz,
                        (a->index << 2) | a->rot, fn_gvec_ptr);
     tcg_temp_free_ptr(fpst);
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a)
 
 static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a)
 {
-    static gen_helper_gvec_3_ptr * const fns[2] = {
+    static gen_helper_gvec_4_ptr * const fns[2] = {
         gen_helper_gvec_fcmlah_idx,
         gen_helper_gvec_fcmlas_idx,
     };
@@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a)
     if (sve_access_check(s)) {
         unsigned vsz = vec_full_reg_size(s);
         TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
-        tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
+        tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
                            vec_full_reg_offset(s, a->rn),
                            vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
                            status, vsz, vsz,
                            a->index * 4 + a->rot,
                            fns[a->esz - 1]);
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm,
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, void *va,
                          void *vfpst, uint32_t desc)
 {
     uintptr_t opr_sz = simd_oprsz(desc);
-    float16 *d = vd;
-    float16 *n = vn;
-    float16 *m = vm;
+    float16 *d = vd, *n = vn, *m = vm, *a = va;
     float_status *fpst = vfpst;
     intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
     uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm,
         float16 e4 = e2;
         float16 e3 = m[H2(i + 1 - flip)] ^ neg_imag;
 
-        d[H2(i)] = float16_muladd(e2, e1, d[H2(i)], 0, fpst);
-        d[H2(i + 1)] = float16_muladd(e4, e3, d[H2(i + 1)], 0, fpst);
+        d[H2(i)] = float16_muladd(e2, e1, a[H2(i)], 0, fpst);
+        d[H2(i + 1)] = float16_muladd(e4, e3, a[H2(i + 1)], 0, fpst);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va,
                              void *vfpst, uint32_t desc)
 {
     uintptr_t opr_sz = simd_oprsz(desc);
-    float16 *d = vd;
-    float16 *n = vn;
-    float16 *m = vm;
+    float16 *d = vd, *n = vn, *m = vm, *a = va;
     float_status *fpst = vfpst;
     intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
     uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm,
             float16 e2 = n[H2(j + flip)];
             float16 e4 = e2;
 
-            d[H2(j)] = float16_muladd(e2, e1, d[H2(j)], 0, fpst);
-            d[H2(j + 1)] = float16_muladd(e4, e3, d[H2(j + 1)], 0, fpst);
+            d[H2(j)] = float16_muladd(e2, e1, a[H2(j)], 0, fpst);
+            d[H2(j + 1)] = float16_muladd(e4, e3, a[H2(j + 1)], 0, fpst);
         }
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, void *va,
                          void *vfpst, uint32_t desc)
 {
     uintptr_t opr_sz = simd_oprsz(desc);
-    float32 *d = vd;
-    float32 *n = vn;
-    float32 *m = vm;
+    float32 *d = vd, *n = vn, *m = vm, *a = va;
     float_status *fpst = vfpst;
     intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
     uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm,
         float32 e4 = e2;
         float32 e3 = m[H4(i + 1 - flip)] ^ neg_imag;
 
-        d[H4(i)] = float32_muladd(e2, e1, d[H4(i)], 0, fpst);
-        d[H4(i + 1)] = float32_muladd(e4, e3, d[H4(i + 1)], 0, fpst);
+        d[H4(i)] = float32_muladd(e2, e1, a[H4(i)], 0, fpst);
+        d[H4(i + 1)] = float32_muladd(e4, e3, a[H4(i + 1)], 0, fpst);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va,
                              void *vfpst, uint32_t desc)
 {
     uintptr_t opr_sz = simd_oprsz(desc);
-    float32 *d = vd;
-    float32 *n = vn;
-    float32 *m = vm;
+    float32 *d = vd, *n = vn, *m = vm, *a = va;
     float_status *fpst = vfpst;
     intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
     uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm,
             float32 e2 = n[H4(j + flip)];
             float32 e4 = e2;
 
-            d[H4(j)] = float32_muladd(e2, e1, d[H4(j)], 0, fpst);
-            d[H4(j + 1)] = float32_muladd(e4, e3, d[H4(j + 1)], 0, fpst);
+            d[H4(j)] = float32_muladd(e2, e1, a[H4(j)], 0, fpst);
+            d[H4(j + 1)] = float32_muladd(e4, e3, a[H4(j + 1)], 0, fpst);
         }
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
-void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, void *va,
                          void *vfpst, uint32_t desc)
 {
     uintptr_t opr_sz = simd_oprsz(desc);
-    float64 *d = vd;
-    float64 *n = vn;
-    float64 *m = vm;
+    float64 *d = vd, *n = vn, *m = vm, *a = va;
     float_status *fpst = vfpst;
     intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
     uint64_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
         float64 e4 = e2;
         float64 e3 = m[i + 1 - flip] ^ neg_imag;
 
-        d[i] = float64_muladd(e2, e1, d[i], 0, fpst);
-        d[i + 1] = float64_muladd(e4, e3, d[i + 1], 0, fpst);
+        d[i] = float64_muladd(e2, e1, a[i], 0, fpst);
+        d[i + 1] = float64_muladd(e4, e3, a[i + 1], 0, fpst);
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Currently only used by FMUL, but will shortly be used more.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-52-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Used by FMLA and DOT, but will shortly be used more.
Split FMLA from FMLS to avoid an extra sub field;
similarly for SDOT from UDOT.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-53-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      | 29 +++++++++++++++++++----------
 target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++----------
 2 files changed, 47 insertions(+), 20 deletions(-)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@
 &rprr_s         rd pg rn rm s
 &rprr_esz       rd pg rn rm esz
 &rrrr_esz       rd ra rn rm esz
+&rrxr_esz       rd rn rm ra index esz
 &rprrr_esz      rd pg rn rm ra esz
 &rpri_esz       rd pg rn imm esz
 &ptrue          rd esz pat s
@@ -XXX,XX +XXX,XX @@
 @rrx_2          ........ .. . index:2 rm:3 ...... rn:5 rd:5  &rrx_esz
 @rrx_1          ........ .. . index:1 rm:4 ...... rn:5 rd:5  &rrx_esz
 
+# Three registers and a scalar by N-bit index
+@rrxr_3         ........ .. . ..      rm:3 ...... rn:5 rd:5 \
+                &rrxr_esz ra=%reg_movprfx index=%index3_22_19
+@rrxr_2         ........ .. . index:2 rm:3 ...... rn:5 rd:5 \
+                &rrxr_esz ra=%reg_movprfx
+@rrxr_1         ........ .. . index:1 rm:4 ...... rn:5 rd:5 \
+                &rrxr_esz ra=%reg_movprfx
+
 ###########################################################################
 # Instruction patterns.  Grouped according to the SVE encodingindex.xhtml.
 
@@ -XXX,XX +XXX,XX @@ DOT_zzzz        01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \
                 ra=%reg_movprfx
 
 # SVE integer dot product (indexed)
-DOT_zzxw        01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \
-                sz=0 ra=%reg_movprfx
-DOT_zzxw        01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \
-                sz=1 ra=%reg_movprfx
+SDOT_zzxw_s     01000100 10 1 ..... 000000 ..... .....   @rrxr_2 esz=2
+SDOT_zzxw_d     01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
+UDOT_zzxw_s     01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
+UDOT_zzxw_d     01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
 # SVE floating-point complex add (predicated)
 FCADD           01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \
@@ -XXX,XX +XXX,XX @@ FCMLA_zzxz      01100100 11 1 index:1 rm:4 0001 rot:2 rn:5 rd:5 \
 ### SVE FP Multiply-Add Indexed Group
 
 # SVE floating-point multiply-add (indexed)
-FMLA_zzxz       01100100 0.1 .. rm:3 00000 sub:1 rn:5 rd:5 \
-                ra=%reg_movprfx index=%index3_22_19 esz=1
-FMLA_zzxz       01100100 101 index:2 rm:3 00000 sub:1 rn:5 rd:5 \
-                ra=%reg_movprfx esz=2
-FMLA_zzxz       01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \
-                ra=%reg_movprfx esz=3
+FMLA_zzxz       01100100 0. 1 ..... 000000 ..... .....  @rrxr_3 esz=1
+FMLA_zzxz       01100100 10 1 ..... 000000 ..... .....  @rrxr_2 esz=2
+FMLA_zzxz       01100100 11 1 ..... 000000 ..... .....  @rrxr_1 esz=3
+FMLS_zzxz       01100100 0. 1 ..... 000001 ..... .....  @rrxr_3 esz=1
+FMLS_zzxz       01100100 10 1 ..... 000001 ..... .....  @rrxr_2 esz=2
+FMLS_zzxz       01100100 11 1 ..... 000001 ..... .....  @rrxr_1 esz=3
 
 ### SVE FP Multiply Indexed Group
 
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a)
     return true;
 }
 
-static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a)
+static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a,
+                        gen_helper_gvec_4 *fn)
 {
-    static gen_helper_gvec_4 * const fns[2][2] = {
-        { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h },
-        { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h }
-    };
-
+    if (fn == NULL) {
+        return false;
+    }
     if (sve_access_check(s)) {
-        gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm,
-                          a->ra, a->index);
+        gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index);
     }
     return true;
 }
 
+#define DO_RRXR(NAME, FUNC) \
+    static bool NAME(DisasContext *s, arg_rrxr_esz *a)  \
+    { return do_zzxz_ool(s, a, FUNC); }
+
+DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b)
+DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h)
+DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b)
+DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h)
+
+#undef DO_RRXR
 
 /*
  *** SVE Floating Point Multiply-Add Indexed Group
  */
 
-static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
+static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub)
 {
     static gen_helper_gvec_4_ptr * const fns[3] = {
         gen_helper_gvec_fmla_idx_h,
@@ -XXX,XX +XXX,XX @@ static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
                            vec_full_reg_offset(s, a->rn),
                            vec_full_reg_offset(s, a->rm),
                            vec_full_reg_offset(s, a->ra),
-                           status, vsz, vsz, (a->index << 1) | a->sub,
+                           status, vsz, vsz, (a->index << 1) | sub,
                            fns[a->esz - 1]);
         tcg_temp_free_ptr(status);
     }
     return true;
 }
 
+static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
+{
+    return do_FMLA_zzxz(s, a, false);
+}
+
+static bool trans_FMLS_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
+{
+    return do_FMLA_zzxz(s, a, true);
+}
+
 /*
  *** SVE Floating Point Multiply Indexed Group
  */
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-54-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  7 +++++++
 target/arm/translate-sve.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ MUL_zzi         00100101 .. 110 000 110 ........ .....          @rdn_i8s
 DOT_zzzz        01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \
                 ra=%reg_movprfx
 
+#### SVE Multiply - Indexed
+
 # SVE integer dot product (indexed)
 SDOT_zzxw_s     01000100 10 1 ..... 000000 ..... .....   @rrxr_2 esz=2
 SDOT_zzxw_d     01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
 UDOT_zzxw_s     01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
 UDOT_zzxw_d     01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
+# SVE2 integer multiply (indexed)
+MUL_zzx_h       01000100 0. 1 ..... 111110 ..... .....   @rrx_3 esz=1
+MUL_zzx_s       01000100 10 1 ..... 111110 ..... .....   @rrx_2 esz=2
+MUL_zzx_d       01000100 11 1 ..... 111110 ..... .....   @rrx_1 esz=3
+
 # SVE floating-point complex add (predicated)
 FCADD           01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \
                 rn=%reg_movprfx
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a)
     return true;
 }
 
+/*
+ * SVE Multiply - Indexed
+ */
+
 static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a,
                         gen_helper_gvec_4 *fn)
 {
@@ -XXX,XX +XXX,XX @@ DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h)
 
 #undef DO_RRXR
 
+static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data,
+                             gen_helper_gvec_3 *fn)
+{
+    if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd),
+                           vec_full_reg_offset(s, rn),
+                           vec_full_reg_offset(s, rm),
+                           vsz, vsz, data, fn);
+    }
+    return true;
+}
+
+#define DO_SVE2_RRX(NAME, FUNC) \
+    static bool NAME(DisasContext *s, arg_rrx_esz *a)  \
+    { return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, a->index, FUNC); }
+
+DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h)
+DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s)
+DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
+
+#undef DO_SVE2_RRX
+
 /*
  *** SVE Floating Point Multiply-Add Indexed Group
  */
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-55-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  8 ++++++++
 target/arm/translate-sve.c | 31 +++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ SDOT_zzxw_d     01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
 UDOT_zzxw_s     01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
 UDOT_zzxw_d     01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
+# SVE2 integer multiply-add (indexed)
+MLA_zzxz_h      01000100 0. 1 ..... 000010 ..... .....   @rrxr_3 esz=1
+MLA_zzxz_s      01000100 10 1 ..... 000010 ..... .....   @rrxr_2 esz=2
+MLA_zzxz_d      01000100 11 1 ..... 000010 ..... .....   @rrxr_1 esz=3
+MLS_zzxz_h      01000100 0. 1 ..... 000011 ..... .....   @rrxr_3 esz=1
+MLS_zzxz_s      01000100 10 1 ..... 000011 ..... .....   @rrxr_2 esz=2
+MLS_zzxz_d      01000100 11 1 ..... 000011 ..... .....   @rrxr_1 esz=3
+
 # SVE2 integer multiply (indexed)
 MUL_zzx_h       01000100 0. 1 ..... 111110 ..... .....   @rrx_3 esz=1
 MUL_zzx_s       01000100 10 1 ..... 111110 ..... .....   @rrx_2 esz=2
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
 
 #undef DO_SVE2_RRX
 
+static bool do_sve2_zzzz_data(DisasContext *s, int rd, int rn, int rm, int ra,
+                              int data, gen_helper_gvec_4 *fn)
+{
+    if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
+                           vec_full_reg_offset(s, rn),
+                           vec_full_reg_offset(s, rm),
+                           vec_full_reg_offset(s, ra),
+                           vsz, vsz, data, fn);
+    }
+    return true;
+}
+
+#define DO_SVE2_RRXR(NAME, FUNC) \
+    static bool NAME(DisasContext *s, arg_rrxr_esz *a)  \
+    { return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, a->index, FUNC); }
+
+DO_SVE2_RRXR(trans_MLA_zzxz_h, gen_helper_gvec_mla_idx_h)
+DO_SVE2_RRXR(trans_MLA_zzxz_s, gen_helper_gvec_mla_idx_s)
+DO_SVE2_RRXR(trans_MLA_zzxz_d, gen_helper_gvec_mla_idx_d)
+
+DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h)
+DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s)
+DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d)
+
+#undef DO_SVE2_RRXR
+
 /*
  *** SVE Floating Point Multiply-Add Indexed Group
  */
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-56-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 14 ++++++++++++++
 target/arm/sve.decode      |  8 ++++++++
 target/arm/sve_helper.c    | 36 ++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c |  8 ++++++++
 4 files changed, 66 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-57-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  9 +++++++++
 target/arm/sve.decode      | 18 ++++++++++++++++++
 target/arm/sve_helper.c    | 30 ++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 19 +++++++++++++++++++
 4 files changed, 76 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@
 %size_23        23:2
 %dtype_23_13    23:2 13:2
 %index3_22_19   22:1 19:2
+%index3_19_11   19:2 11:1
+%index2_20_11   20:1 11:1
 
 # A combination of tsz:imm3 -- extract esize.
 %tszimm_esz     22:2 5:5 !function=tszimm_esz
@@ -XXX,XX +XXX,XX @@
 @rrxr_1         ........ .. . index:1 rm:4 ...... rn:5 rd:5 \
                 &rrxr_esz ra=%reg_movprfx
 
+# Three registers and a scalar by N-bit index, alternate
+@rrxr_3a        ........ .. ... rm:3 ...... rn:5 rd:5 \
+                &rrxr_esz ra=%reg_movprfx index=%index3_19_11
+@rrxr_2a        ........ .. ..  rm:4 ...... rn:5 rd:5 \
+                &rrxr_esz ra=%reg_movprfx index=%index2_20_11
+
 ###########################################################################
 # Instruction patterns.  Grouped according to the SVE encodingindex.xhtml.
 
@@ -XXX,XX +XXX,XX @@ SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... .....   @rrxr_3 esz=1
 SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... .....   @rrxr_2 esz=2
 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... .....   @rrxr_1 esz=3
 
+# SVE2 saturating multiply-add (indexed)
+SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... .....   @rrxr_3a esz=2
+SQDMLALB_zzxw_d 01000100 11 1 ..... 0010.0 ..... .....   @rrxr_2a esz=3
+SQDMLALT_zzxw_s 01000100 10 1 ..... 0010.1 ..... .....   @rrxr_3a esz=2
+SQDMLALT_zzxw_d 01000100 11 1 ..... 0010.1 ..... .....   @rrxr_2a esz=3
+SQDMLSLB_zzxw_s 01000100 10 1 ..... 0011.0 ..... .....   @rrxr_3a esz=2
+SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... .....   @rrxr_2a esz=3
+SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... .....   @rrxr_3a esz=2
+SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... .....   @rrxr_2a esz=3
+
 # SVE2 integer multiply (indexed)
 MUL_zzx_h       01000100 0. 1 ..... 111110 ..... .....   @rrx_3 esz=1
 MUL_zzx_s       01000100 10 1 ..... 111110 ..... .....   @rrx_2 esz=2
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t,   , DO_SQRDMLSH_D)
 
 #undef DO_ZZXZ
 
+#define DO_ZZXW(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i, j, oprsz = simd_oprsz(desc);                              \
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN);   \
+    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3) * sizeof(TYPEN); \
+    for (i = 0; i < oprsz; i += 16) {                                     \
+        TYPEW mm = *(TYPEN *)(vm + HN(i + idx));                          \
+        for (j = 0; j < 16; j += sizeof(TYPEW)) {                         \
+            TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel));                  \
+            TYPEW aa = *(TYPEW *)(va + HW(i + j));                        \
+            *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm, aa);                  \
+        }                                                                 \
+    }                                                                     \
+}
+
+#define DO_SQDMLAL_S(N, M, A)  DO_SQADD_S(A, do_sqdmull_s(N, M))
+#define DO_SQDMLAL_D(N, M, A)  do_sqadd_d(A, do_sqdmull_d(N, M))
+
+DO_ZZXW(sve2_sqdmlal_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLAL_S)
+DO_ZZXW(sve2_sqdmlal_idx_d, int64_t, int32_t,     , H1_4, DO_SQDMLAL_D)
+
+#define DO_SQDMLSL_S(N, M, A)  DO_SQSUB_S(A, do_sqdmull_s(N, M))
+#define DO_SQDMLSL_D(N, M, A)  do_sqsub_d(A, do_sqdmull_d(N, M))
+
+DO_ZZXW(sve2_sqdmlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLSL_S)
+DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t,     , H1_4, DO_SQDMLSL_D)
+
+#undef DO_ZZXW
+
 #define DO_BITPERM(NAME, TYPE, OP) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
 {                                                              \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d)
 
 #undef DO_SVE2_RRXR
 
+#define DO_SVE2_RRXR_TB(NAME, FUNC, TOP) \
+    static bool NAME(DisasContext *s, arg_rrxr_esz *a)          \
+    {                                                           \
+        return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->rd, \
+                                 (a->index << 1) | TOP, FUNC);  \
+    }
+
+DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, false)
+DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, false)
+DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, true)
+DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, true)
+
+DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, false)
+DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false)
+DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true)
+DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true)
+
+#undef DO_SVE2_RRXR_TB
+
 /*
  *** SVE Floating Point Multiply-Add Indexed Group
  */
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-58-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  5 +++++
 target/arm/sve.decode      | 12 ++++++++++++
 target/arm/sve_helper.c    | 20 ++++++++++++++++++++
 target/arm/translate-sve.c | 14 ++++++++++++++
 4 files changed, 51 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-59-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h        | 10 +++++
 target/arm/sve.decode      |  4 ++
 target/arm/translate-sve.c | 18 ++++++++
 target/arm/vec_helper.c    | 84 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 116 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-60-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h        | 14 ++++++
 target/arm/sve.decode      |  8 ++++
 target/arm/translate-sve.c |  8 ++++
 target/arm/vec_helper.c    | 88 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 118 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-61-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 17 +++++++++++++++++
 target/arm/sve.decode      | 18 ++++++++++++++++++
 target/arm/sve_helper.c    | 16 ++++++++++++++++
 target/arm/translate-sve.c | 20 ++++++++++++++++++++
 4 files changed, 71 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-62-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  5 +++++
 target/arm/sve.decode      | 10 ++++++++++
 target/arm/sve_helper.c    |  6 ++++++
 target/arm/translate-sve.c | 10 ++++++++++
 4 files changed, 31 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-63-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  9 +++++++++
 target/arm/sve.decode      | 12 ++++++++++++
 target/arm/sve_helper.c    | 28 ++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 15 +++++++++++++++
 4 files changed, 64 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-64-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 10 ++++
 target/arm/sve.decode      |  9 ++++
 target/arm/sve_helper.c    | 99 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 17 +++++++
 4 files changed, 135 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_cdot_zzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_cdot_zzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_cdot_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_cdot_idx_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ MUL_zzi         00100101 .. 110 000 110 ........ .....          @rdn_i8s
 DOT_zzzz        01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \
                 ra=%reg_movprfx
 
+# SVE2 complex dot product (vectors)
+CDOT_zzzz       01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5  ra=%reg_movprfx
+
 #### SVE Multiply - Indexed
 
 # SVE integer dot product (indexed)
@@ -XXX,XX +XXX,XX @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... .....   @rrxr_2a esz=3
 SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... .....   @rrxr_3a esz=2
 SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... .....   @rrxr_2a esz=3
 
+# SVE2 complex integer dot product (indexed)
+CDOT_zzxw_s     01000100 10 1 index:2 rm:3 0100 rot:2 rn:5 rd:5 \
+                ra=%reg_movprfx
+CDOT_zzxw_d     01000100 11 1 index:1 rm:4 0100 rot:2 rn:5 rd:5 \
+                ra=%reg_movprfx
+
 # SVE2 complex integer multiply-add (indexed)
 CMLA_zzxz_h     01000100 10 1 index:2 rm:3 0110 rot:2 rn:5 rd:5 \
                 ra=%reg_movprfx
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S)
 #undef DO_SQRDMLAH_S
 #undef DO_SQRDMLAH_D
 
+/* Note N and M are 4 elements bundled into one unit. */
+static int32_t do_cdot_s(uint32_t n, uint32_t m, int32_t a,
+                         int sel_a, int sel_b, int sub_i)
+{
+    for (int i = 0; i <= 1; i++) {
+        int32_t elt1_r = (int8_t)(n >> (16 * i));
+        int32_t elt1_i = (int8_t)(n >> (16 * i + 8));
+        int32_t elt2_a = (int8_t)(m >> (16 * i + 8 * sel_a));
+        int32_t elt2_b = (int8_t)(m >> (16 * i + 8 * sel_b));
+
+        a += elt1_r * elt2_a + elt1_i * elt2_b * sub_i;
+    }
+    return a;
+}
+
+static int64_t do_cdot_d(uint64_t n, uint64_t m, int64_t a,
+                         int sel_a, int sel_b, int sub_i)
+{
+    for (int i = 0; i <= 1; i++) {
+        int64_t elt1_r = (int16_t)(n >> (32 * i + 0));
+        int64_t elt1_i = (int16_t)(n >> (32 * i + 16));
+        int64_t elt2_a = (int16_t)(m >> (32 * i + 16 * sel_a));
+        int64_t elt2_b = (int16_t)(m >> (32 * i + 16 * sel_b));
+
+        a += elt1_r * elt2_a + elt1_i * elt2_b * sub_i;
+    }
+    return a;
+}
+
+void HELPER(sve2_cdot_zzzz_s)(void *vd, void *vn, void *vm,
+                              void *va, uint32_t desc)
+{
+    int opr_sz = simd_oprsz(desc);
+    int rot = simd_data(desc);
+    int sel_a = rot & 1;
+    int sel_b = sel_a ^ 1;
+    int sub_i = (rot == 0 || rot == 3 ? -1 : 1);
+    uint32_t *d = vd, *n = vn, *m = vm, *a = va;
+
+    for (int e = 0; e < opr_sz / 4; e++) {
+        d[e] = do_cdot_s(n[e], m[e], a[e], sel_a, sel_b, sub_i);
+    }
+}
+
+void HELPER(sve2_cdot_zzzz_d)(void *vd, void *vn, void *vm,
+                              void *va, uint32_t desc)
+{
+    int opr_sz = simd_oprsz(desc);
+    int rot = simd_data(desc);
+    int sel_a = rot & 1;
+    int sel_b = sel_a ^ 1;
+    int sub_i = (rot == 0 || rot == 3 ? -1 : 1);
+    uint64_t *d = vd, *n = vn, *m = vm, *a = va;
+
+    for (int e = 0; e < opr_sz / 8; e++) {
+        d[e] = do_cdot_d(n[e], m[e], a[e], sel_a, sel_b, sub_i);
+    }
+}
+
+void HELPER(sve2_cdot_idx_s)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
+{
+    int opr_sz = simd_oprsz(desc);
+    int rot = extract32(desc, SIMD_DATA_SHIFT, 2);
+    int idx = H4(extract32(desc, SIMD_DATA_SHIFT + 2, 2));
+    int sel_a = rot & 1;
+    int sel_b = sel_a ^ 1;
+    int sub_i = (rot == 0 || rot == 3 ? -1 : 1);
+    uint32_t *d = vd, *n = vn, *m = vm, *a = va;
+
+    for (int seg = 0; seg < opr_sz / 4; seg += 4) {
+        uint32_t seg_m = m[seg + idx];
+        for (int e = 0; e < 4; e++) {
+            d[seg + e] = do_cdot_s(n[seg + e], seg_m, a[seg + e],
+                                   sel_a, sel_b, sub_i);
+        }
+    }
+}
+
+void HELPER(sve2_cdot_idx_d)(void *vd, void *vn, void *vm,
+                             void *va, uint32_t desc)
+{
+    int seg, opr_sz = simd_oprsz(desc);
+    int rot = extract32(desc, SIMD_DATA_SHIFT, 2);
+    int idx = extract32(desc, SIMD_DATA_SHIFT + 2, 2);
+    int sel_a = rot & 1;
+    int sel_b = sel_a ^ 1;
+    int sub_i = (rot == 0 || rot == 3 ? -1 : 1);
+    uint64_t *d = vd, *n = vn, *m = vm, *a = va;
+
+    for (seg = 0; seg < opr_sz / 8; seg += 2) {
+        uint64_t seg_m = m[seg + idx];
+        for (int e = 0; e < 2; e++) {
+            d[seg + e] = do_cdot_d(n[seg + e], seg_m, a[seg + e],
+                                   sel_a, sel_b, sub_i);
+        }
+    }
+}
+
 #define DO_ZZXZ(NAME, TYPE, H, OP) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
 {                                                                       \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR_ROT(CMLA_zzxz_s, gen_helper_sve2_cmla_idx_s)
 DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_h, gen_helper_sve2_sqrdcmlah_idx_h)
 DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_s, gen_helper_sve2_sqrdcmlah_idx_s)
 
+DO_SVE2_RRXR_ROT(CDOT_zzxw_s, gen_helper_sve2_cdot_idx_s)
+DO_SVE2_RRXR_ROT(CDOT_zzxw_d, gen_helper_sve2_cdot_idx_d)
+
 #undef DO_SVE2_RRXR_ROT
 
 /*
@@ -XXX,XX +XXX,XX @@ static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a)
     return true;
 }
 
+static bool trans_CDOT_zzzz(DisasContext *s, arg_CMLA_zzzz *a)
+{
+    if (!dc_isar_feature(aa64_sve2, s) || a->esz < MO_32) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_helper_gvec_4 *fn = (a->esz == MO_32
+                                 ? gen_helper_sve2_cdot_zzzz_s
+                                 : gen_helper_sve2_cdot_zzzz_d);
+        gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->rot);
+    }
+    return true;
+}
+
 static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a)
 {
     static gen_helper_gvec_4 * const fns[] = {
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

We're about to add more variations on this theme.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-65-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/vec_helper.c | 82 ++++++++++-------------------------------
 1 file changed, 20 insertions(+), 62 deletions(-)

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
 /* Integer 8 and 16-bit dot-product.
  *
  * Note that for the loops herein, host endianness does not matter
- * with respect to the ordering of data within the 64-bit lanes.
+ * with respect to the ordering of data within the quad-width lanes.
  * All elements are treated equally, no matter where they are.
  */
 
-void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
-{
-    intptr_t i, opr_sz = simd_oprsz(desc);
-    int32_t *d = vd, *a = va;
-    int8_t *n = vn, *m = vm;
-
-    for (i = 0; i < opr_sz / 4; ++i) {
-        d[i] = (a[i] +
-                n[i * 4 + 0] * m[i * 4 + 0] +
-                n[i * 4 + 1] * m[i * 4 + 1] +
-                n[i * 4 + 2] * m[i * 4 + 2] +
-                n[i * 4 + 3] * m[i * 4 + 3]);
-    }
-    clear_tail(d, opr_sz, simd_maxsz(desc));
+#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i, opr_sz = simd_oprsz(desc);                                \
+    TYPED *d = vd, *a = va;                                               \
+    TYPEN *n = vn;                                                        \
+    TYPEM *m = vm;                                                        \
+    for (i = 0; i < opr_sz / sizeof(TYPED); ++i) {                        \
+        d[i] = (a[i] +                                                    \
+                (TYPED)n[i * 4 + 0] * m[i * 4 + 0] +                      \
+                (TYPED)n[i * 4 + 1] * m[i * 4 + 1] +                      \
+                (TYPED)n[i * 4 + 2] * m[i * 4 + 2] +                      \
+                (TYPED)n[i * 4 + 3] * m[i * 4 + 3]);                      \
+    }                                                                     \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
 
-void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
-{
-    intptr_t i, opr_sz = simd_oprsz(desc);
-    uint32_t *d = vd, *a = va;
-    uint8_t *n = vn, *m = vm;
-
-    for (i = 0; i < opr_sz / 4; ++i) {
-        d[i] = (a[i] +
-                n[i * 4 + 0] * m[i * 4 + 0] +
-                n[i * 4 + 1] * m[i * 4 + 1] +
-                n[i * 4 + 2] * m[i * 4 + 2] +
-                n[i * 4 + 3] * m[i * 4 + 3]);
-    }
-    clear_tail(d, opr_sz, simd_maxsz(desc));
-}
-
-void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
-{
-    intptr_t i, opr_sz = simd_oprsz(desc);
-    int64_t *d = vd, *a = va;
-    int16_t *n = vn, *m = vm;
-
-    for (i = 0; i < opr_sz / 8; ++i) {
-        d[i] = (a[i] +
-                (int64_t)n[i * 4 + 0] * m[i * 4 + 0] +
-                (int64_t)n[i * 4 + 1] * m[i * 4 + 1] +
-                (int64_t)n[i * 4 + 2] * m[i * 4 + 2] +
-                (int64_t)n[i * 4 + 3] * m[i * 4 + 3]);
-    }
-    clear_tail(d, opr_sz, simd_maxsz(desc));
-}
-
-void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
-{
-    intptr_t i, opr_sz = simd_oprsz(desc);
-    uint64_t *d = vd, *a = va;
-    uint16_t *n = vn, *m = vm;
-
-    for (i = 0; i < opr_sz / 8; ++i) {
-        d[i] = (a[i] +
-                (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] +
-                (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] +
-                (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] +
-                (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]);
-    }
-    clear_tail(d, opr_sz, simd_maxsz(desc));
-}
+DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t)
+DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t)
+DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t)
+DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t)
 
 void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm,
                              void *va, uint32_t desc)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

We're about to add more variations on this theme.
Accept the inner loop for the _h variants, rather
than keep it unrolled.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-66-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/vec_helper.c | 160 ++++++++--------------------------------
 1 file changed, 29 insertions(+), 131 deletions(-)

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t)
 DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t)
 DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t)
 
-void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm,
-                             void *va, uint32_t desc)
-{
-    intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
-    intptr_t index = simd_data(desc);
-    int32_t *d = vd, *a = va;
-    int8_t *n = vn;
-    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.
-     */
-    segend = MIN(4, opr_sz_4);
-    i = 0;
-    do {
-        int8_t m0 = m_indexed[i * 4 + 0];
-        int8_t m1 = m_indexed[i * 4 + 1];
-        int8_t m2 = m_indexed[i * 4 + 2];
-        int8_t m3 = m_indexed[i * 4 + 3];
-
-        do {
-            d[i] = (a[i] +
-                    n[i * 4 + 0] * m0 +
-                    n[i * 4 + 1] * m1 +
-                    n[i * 4 + 2] * m2 +
-                    n[i * 4 + 3] * m3);
-        } while (++i < segend);
-        segend = i + 4;
-    } while (i < opr_sz_4);
-
-    clear_tail(d, opr_sz, simd_maxsz(desc));
+#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i = 0, opr_sz = simd_oprsz(desc);                            \
+    intptr_t opr_sz_n = opr_sz / sizeof(TYPED);                           \
+    intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n);                  \
+    intptr_t index = simd_data(desc);                                     \
+    TYPED *d = vd, *a = va;                                               \
+    TYPEN *n = vn;                                                        \
+    TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 4;                       \
+    do {                                                                  \
+        TYPED m0 = m_indexed[i * 4 + 0];                                  \
+        TYPED m1 = m_indexed[i * 4 + 1];                                  \
+        TYPED m2 = m_indexed[i * 4 + 2];                                  \
+        TYPED m3 = m_indexed[i * 4 + 3];                                  \
+        do {                                                              \
+            d[i] = (a[i] +                                                \
+                    n[i * 4 + 0] * m0 +                                   \
+                    n[i * 4 + 1] * m1 +                                   \
+                    n[i * 4 + 2] * m2 +                                   \
+                    n[i * 4 + 3] * m3);                                   \
+        } while (++i < segend);                                           \
+        segend = i + 4;                                                   \
+    } while (i < opr_sz_n);                                               \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
 
-void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm,
-                             void *va, uint32_t desc)
-{
-    intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4;
-    intptr_t index = simd_data(desc);
-    uint32_t *d = vd, *a = va;
-    uint8_t *n = vn;
-    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.
-     */
-    segend = MIN(4, opr_sz_4);
-    i = 0;
-    do {
-        uint8_t m0 = m_indexed[i * 4 + 0];
-        uint8_t m1 = m_indexed[i * 4 + 1];
-        uint8_t m2 = m_indexed[i * 4 + 2];
-        uint8_t m3 = m_indexed[i * 4 + 3];
-
-        do {
-            d[i] = (a[i] +
-                    n[i * 4 + 0] * m0 +
-                    n[i * 4 + 1] * m1 +
-                    n[i * 4 + 2] * m2 +
-                    n[i * 4 + 3] * m3);
-        } while (++i < segend);
-        segend = i + 4;
-    } while (i < opr_sz_4);
-
-    clear_tail(d, opr_sz, simd_maxsz(desc));
-}
-
-void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm,
-                             void *va, uint32_t desc)
-{
-    intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
-    intptr_t index = simd_data(desc);
-    int64_t *d = vd, *a = va;
-    int16_t *n = vn;
-    int16_t *m_indexed = (int16_t *)vm + index * 4;
-
-    /* This is supported by SVE only, so opr_sz is always a multiple of 16.
-     * Process the entire segment all at once, writing back the results
-     * only after we've consumed all of the inputs.
-     */
-    for (i = 0; i < opr_sz_8; i += 2) {
-        int64_t d0, d1;
-
-        d0  = a[i + 0];
-        d0 += n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0];
-        d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1];
-        d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2];
-        d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3];
-
-        d1  = a[i + 1];
-        d1 += n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0];
-        d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1];
-        d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2];
-        d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3];
-
-        d[i + 0] = d0;
-        d[i + 1] = d1;
-    }
-    clear_tail(d, opr_sz, simd_maxsz(desc));
-}
-
-void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm,
-                             void *va, uint32_t desc)
-{
-    intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8;
-    intptr_t index = simd_data(desc);
-    uint64_t *d = vd, *a = va;
-    uint16_t *n = vn;
-    uint16_t *m_indexed = (uint16_t *)vm + index * 4;
-
-    /* This is supported by SVE only, so opr_sz is always a multiple of 16.
-     * Process the entire segment all at once, writing back the results
-     * only after we've consumed all of the inputs.
-     */
-    for (i = 0; i < opr_sz_8; i += 2) {
-        uint64_t d0, d1;
-
-        d0  = a[i + 0];
-        d0 += n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0];
-        d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1];
-        d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2];
-        d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3];
-
-        d1  = a[i + 1];
-        d1 += n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0];
-        d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1];
-        d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2];
-        d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3];
-
-        d[i + 0] = d0;
-        d[i + 1] = d1;
-    }
-    clear_tail(d, opr_sz, simd_maxsz(desc));
-}
+DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4)
+DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, )
+DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, )
 
 void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
                          void *vfpst, uint32_t desc)
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-67-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           |  5 +++++
 target/arm/helper.h        |  4 ++++
 target/arm/sve.decode      |  4 ++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 target/arm/vec_helper.c    |  2 ++
 5 files changed, 31 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-68-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h        |  1 +
 target/arm/sve.decode      |  4 ++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 target/arm/vec_helper.c    |  1 +
 4 files changed, 22 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-69-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve.decode      |  6 ++++++
 target/arm/translate-sve.c | 11 +++++++++++
 2 files changed, 17 insertions(+)

diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ STNT1_zprz      1110010 .. 00 ..... 001 ... ..... ..... \
 # SVE2 32-bit scatter non-temporal store (vector plus scalar)
 STNT1_zprz      1110010 .. 10 ..... 001 ... ..... ..... \
                 @rprr_scatter_store xs=0 esz=2 scale=0
+
+### SVE2 Crypto Extensions
+
+# SVE2 crypto unary operations
+# AESMC and AESIMC
+AESMC           01000101 00 10000011100 decrypt:1 00000 rd:5
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a)
     }
     return true;
 }
+
+static bool trans_AESMC(DisasContext *s, arg_AESMC *a)
+{
+    if (!dc_isar_feature(aa64_sve2_aes, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zz(s, gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt);
+    }
+    return true;
+}
-- 
2.20.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-70-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           |  5 +++++
 target/arm/sve.decode      |  7 +++++++
 target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-71-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           |  5 +++++
 target/arm/sve.decode      |  4 ++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 3 files changed, 25 insertions(+)

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-72-richard.henderson@linaro.org
Message-Id: <20200428144352.9275-1-steplong@quicinc.com>
[rth: rearrange the macros a little and rebase]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    | 10 +++++
 target/arm/sve.decode      |  5 +++
 target/arm/sve_helper.c    | 90 ++++++++++++++++++++++++++++++--------
 target/arm/translate-sve.c | 33 ++++++++++++++
 4 files changed, 119 insertions(+), 19 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-73-richard.henderson@linaro.org
Message-Id: <20200428174332.17162-2-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  5 +++++
 target/arm/sve.decode      |  4 ++++
 target/arm/sve_helper.c    | 20 ++++++++++++++++++++
 target/arm/translate-sve.c | 16 ++++++++++++++++
 4 files changed, 45 insertions(+)

Hi; here's another arm pullreq; main parts here are the
new i.MX 8MM EVK board, and a lot of refactoring.

thanks
-- PMM

The following changes since commit aa15257174da180c6a8a9d58f87319cfe61c5520:

Merge tag 'pbouvier/pr/plugins-20260424' of https://gitlab.com/p-b-o/qemu into staging (2026-04-25 10:22:04 -0400)

are available in the Git repository at:

https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20260427

for you to fetch changes up to 4575da5ecb7a27544aa6da1f78e700e8100ceaea:

target/arm: report register in WFIT syndromes (2026-04-27 11:46:34 +0100)

----------------------------------------------------------------
target-arm queue:
docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list
hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board
target/arm: Build M-profile helper code once only
hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register
hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header
target/arm: Allow 'aarch64=off' to be set for TCG CPUs
target/arm: Allow some sysregs to not have to be an exact match for migration
hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices
hw/arm/fsl-imx6ul: Implement LCDIF display device
target/arm: Refactor syndrome value code to use registerfields
target/arm: Report the register in WFxT syndromes

----------------------------------------------------------------
Alex Bennée (24):
      docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list
      target/arm: migrate basic syndrome helpers to registerfields
      target/arm: migrate system/cp trap syndromes to registerfields
      target/arm: migrate FP/SIMD trap syndromes to registerfields
      target/arm: migrate eret trap syndromes to registerfields
      target/arm: migrate SME trap syndromes to registerfields
      target/arm: migrate PAC trap syndromes to registerfields
      target/arm: migrate BTI trap syndromes to registerfields
      target/arm: migrate BXJ trap syndromes to registerfields
      target/arm: migrate Granule Protection traps to registerfields
      target/arm: migrate fault syndromes to registerfields
      target/arm: migrate debug syndromes to registerfields
      target/arm: migrate wfx syndromes to registerfields
      target/arm: migrate gcs syndromes to registerfields
      target/arm: migrate memory op syndromes to registerfields
      target/arm: migrate check_hcr_el2_trap to use syndrome helper
      target/arm: use syndrome helpers in arm_cpu_do_interrupt_aarch32_hyp
      target/arm: use syndrome helpers to set SAME_EL EC bit
      target/arm: make whpx use syndrome helpers for decode
      target/arm: make hvf use syndrome helpers for decode
      target/arm: use syndrome helpers in merge_syn_data_abort
      target/arm: use syndrome helpers to query VNCR bit
      target/arm: remove old syndrome defines
      target/arm: report register in WFIT syndromes

Eric Auger (7):
      target/arm/cpu: Introduce the infrastructure for cpreg migration tolerances
      target/arm/machine: Handle ToleranceNotOnBothEnds migration tolerances
      target/arm/machine: Handle ToleranceOnlySrcTestValue migration tolerance
      target/arm/cpu64: Mitigate migration failures due to spurious TCR_EL1, PIRE0_EL1 and PIR_EL1
      target/arm/cpu64: Define cpreg migration tolerance for KVM_REG_ARM_VENDOR_HYP_BMAP_2
      target/arm/helper: Define cpreg migration tolerance for DGBDTR_EL0
      Revert "target/arm: Reinstate bogus AArch32 DBGDTRTX register for migration compat"

Gaurav Sharma (15):
      hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board
      hw/misc/imx8mp_analog: Add property to analog device
      hw/arm/fsl-imx8mm: Add Analog device IP to iMX8MM SOC
      hw/arm/fsl-imx8mm: Add Clock Control Module IP to iMX8MM
      hw/arm/fsl-imx8mm: Implemented support for SNVS
      hw/arm/fsl-imx8mm: Adding support for USDHC storage controllers
      hw/arm/fsl-imx8mm: Add PCIe support
      hw/arm/fsl-imx8mm: Add GPIO controllers
      hw/arm/fsl-imx8mm: Adding support for I2C emulation
      hw/arm/fsl-imx8mm: Adding support for SPI controller
      hw/arm/fsl-imx8mm: Adding support for Watchdog Timers
      hw/arm/fsl-imx8mm: Adding support for General Purpose Timers
      hw/arm/fsl-imx8mm: Adding support for ENET ethernet controller
      hw/arm/fsl-imx8mm: Adding support for USB controller
      hw/arm/fsl-imx8mm: Adding functional testing of iMX8MM emulation

Osama Abdelkader (1):
      hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices

Peter Maydell (4):
      hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header
      target/arm: Clear AArch64 ID regs from ARMISARegisters if AArch64 disabled
      target/arm: Allow 'aarch64=off' to be set for TCG CPUs
      tests/functional/aarch64: Add basic test of TCG aarch64=off

Philippe Mathieu-Daudé (9):
      target/arm: Ignore endianness when setting MTE tags
      target/arm: Explode MO_TExx -> MO_TE | MO_xx
      target/arm: Hoist MO_TE into mve_advance_vpt()
      target/arm: Hoist MO_TE into MVE DO_VSTR() macro
      target/arm: Introduce mo_endian() helper
      target/arm: Replace MO_TE -> mo_endian() for MVE helpers
      target/arm: Compile mve_helper.c once
      target/arm: Replace MO_TE -> mo_endian() for Cortex-M helpers
      target/arm: Compile m_helper.c once

Thomas Huth (1):
      hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register

Yucai Liu (2):
      hw/display: Add i.MX6UL LCDIF device model
      hw/arm/fsl-imx6ul: Wire in the LCDIF device model

MAINTAINERS                                       |  16 +-
 docs/system/arm/cpu-features.rst                  |  10 +-
 docs/system/arm/emulation.rst                     |   2 +
 docs/system/arm/{imx8mp-evk.rst => imx8m.rst}     |  49 +-
 docs/system/target-arm.rst                        |   2 +-
 hw/arm/Kconfig                                    |  25 +
 hw/arm/fsl-imx6ul.c                               |  12 +-
 hw/arm/fsl-imx8mm.c                               | 704 ++++++++++++++++++++++
 hw/arm/imx8mm-evk.c                               | 130 ++++
 hw/arm/integratorcp.c                             |   3 -
 hw/arm/meson.build                                |   2 +
 hw/arm/raspi4b.c                                  |  10 +-
 hw/arm/realview.c                                 |   2 +-
 hw/arm/vexpress.c                                 |   2 +-
 hw/arm/virt.c                                     |   1 -
 hw/display/Kconfig                                |   4 +
 hw/display/imx6ul_lcdif.c                         | 453 ++++++++++++++
 hw/display/meson.build                            |   1 +
 hw/misc/arm_sysctl.c                              |   2 +-
 hw/misc/imx8mp_analog.c                           |  12 +-
 hw/timer/imx_gpt.c                                |  26 +
 hw/vmapple/vmapple.c                              |   1 -
 include/hw/arm/fsl-imx6ul.h                       |   4 +-
 include/hw/arm/fsl-imx8mm.h                       | 242 ++++++++
 include/hw/arm/primecell.h                        |  12 -
 include/hw/display/imx6ul_lcdif.h                 |  37 ++
 include/hw/misc/arm_sysctl.h                      |  16 +
 include/hw/misc/imx8mp_analog.h                   |   3 +
 include/hw/timer/imx_gpt.h                        |   2 +
 target/arm/cpu-features.h                         |   5 +
 target/arm/cpu.c                                  | 153 ++++-
 target/arm/cpu.h                                  |   4 +-
 target/arm/cpu64.c                                |  39 ++
 target/arm/debug_helper.c                         |  29 -
 target/arm/helper.c                               |  27 +-
 target/arm/hvf/hvf.c                              |  14 +-
 target/arm/internals.h                            |  60 ++
 target/arm/machine.c                              |  33 +-
 target/arm/syndrome.h                             | 595 ++++++++++++++----
 target/arm/tcg/debug.c                            |   2 +-
 target/arm/tcg/helper-a64.c                       |   2 +-
 target/arm/tcg/helper-defs.h                      |   2 +-
 target/arm/tcg/m_helper.c                         |   8 +-
 target/arm/tcg/meson.build                        |   6 +-
 target/arm/tcg/mve_helper.c                       | 102 ++--
 target/arm/tcg/op_helper.c                        |   7 +-
 target/arm/tcg/tlb_helper.c                       |   6 +-
 target/arm/tcg/translate-a64.c                    |   2 +-
 target/arm/tcg/vfp_helper.c                       |   5 +-
 target/arm/trace-events                           |   2 +
 target/arm/whpx/whpx-all.c                        |  13 +-
 tests/functional/aarch64/meson.build              |   3 +
 tests/functional/aarch64/test_imx8mm_evk.py       |  69 +++
 tests/functional/aarch64/test_virt_aarch64_off.py |  37 ++
 tests/qtest/arm-cpu-features.c                    |   8 +-
 55 files changed, 2743 insertions(+), 275 deletions(-)
 rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%)
 create mode 100644 hw/arm/fsl-imx8mm.c
 create mode 100644 hw/arm/imx8mm-evk.c
 create mode 100644 hw/display/imx6ul_lcdif.c
 create mode 100644 include/hw/arm/fsl-imx8mm.h
 delete mode 100644 include/hw/arm/primecell.h
 create mode 100644 include/hw/display/imx6ul_lcdif.h
 create mode 100644 include/hw/misc/arm_sysctl.h
 create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py
 create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py

From: Alex Bennée <alex.bennee@linaro.org>

This is just a documentation tweak as we already support both.
FEAT_AA32 implies FEAT_AA32EL0. FEAT_AA64 implies FEAT_AA64EL[0123].

This is however useful if you are using emulation.rst as a source of
truth of what QEMU emulates and when cross checking with
Features.json from Arm.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260421093506.616307-1-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/system/arm/emulation.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -XXX,XX +XXX,XX @@ QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7,
 Armv8 and Armv9 versions of the A-profile architecture. It also has support for
 the following architecture extensions:
 
+- FEAT_AA32 (PE Support for AArch32)
 - FEAT_AA32BF16 (AArch32 BFloat16 instructions)
 - FEAT_AA32EL0 (Support for AArch32 at EL0)
 - FEAT_AA32EL1 (Support for AArch32 at EL1)
@@ -XXX,XX +XXX,XX @@ the following architecture extensions:
 - FEAT_AA32EL3 (Support for AArch32 at EL3)
 - FEAT_AA32HPD (AArch32 hierarchical permission disables)
 - FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions)
+- FEAT_AA64 (PE uses AArch64 after last reboot)
 - FEAT_AA64EL0 (Support for AArch64 at EL0)
 - FEAT_AA64EL1 (Support for AArch64 at EL1)
 - FEAT_AA64EL2 (Support for AArch64 at EL2)
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Implemented CPUs, RAM, UARTs and Interrupt Controller
Other peripherals are represented as TYPE_UNIMPLEMENTED_DEVICE
Complete memory map of the SoC is provided.

Set default RAM size to 2GB and default CPU count to 4 to match
the real i.MX8MM EVK hardware configuration.

Documentation is shared with imx8mp-evk to avoid duplication.

Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
[PMM: fixed over-long lines in doc]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS                                   |  11 +-
 docs/system/arm/{imx8mp-evk.rst => imx8m.rst} |  49 ++-
 docs/system/target-arm.rst                    |   2 +-
 hw/arm/Kconfig                                |  12 +
 hw/arm/fsl-imx8mm.c                           | 377 ++++++++++++++++++
 hw/arm/imx8mm-evk.c                           | 112 ++++++
 hw/arm/meson.build                            |   2 +
 include/hw/arm/fsl-imx8mm.h                   | 158 ++++++++
 8 files changed, 709 insertions(+), 14 deletions(-)
 rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%)
 create mode 100644 hw/arm/fsl-imx8mm.c
 create mode 100644 hw/arm/imx8mm-evk.c
 create mode 100644 include/hw/arm/fsl-imx8mm.h

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/pci-host/designware.c
 F: include/hw/pci-host/designware.h
 F: docs/system/arm/mcimx7d-sabre.rst
 
+MCIMX8MM-EVK / iMX8MM
+M: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+L: qemu-arm@nongnu.org
+S: Maintained
+F: hw/arm/fsl-imx8mm.c
+F: hw/arm/imx8mm-evk.c
+F: include/hw/arm/fsl-imx8mm.h
+F: docs/system/arm/imx8m.rst
+
 MCIMX8MP-EVK / i.MX8MP
 M: Bernhard Beschow <shentey@gmail.com>
 L: qemu-arm@nongnu.org
@@ -XXX,XX +XXX,XX @@ F: hw/rtc/rs5c372.c
 F: include/hw/arm/fsl-imx8mp.h
 F: include/hw/misc/imx8mp_*.h
 F: include/hw/pci-host/fsl_imx8m_phy.h
-F: docs/system/arm/imx8mp-evk.rst
+F: docs/system/arm/imx8m.rst
 F: tests/functional/aarch64/test_imx8mp_evk.py
 F: tests/qtest/rs5c372-test.c
 
diff --git a/docs/system/arm/imx8mp-evk.rst b/docs/system/arm/imx8m.rst
similarity index 58%
rename from docs/system/arm/imx8mp-evk.rst
rename to docs/system/arm/imx8m.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/imx8mp-evk.rst
+++ b/docs/system/arm/imx8m.rst
@@ -XXX,XX +XXX,XX @@
-NXP i.MX 8M Plus Evaluation Kit (``imx8mp-evk``)
-================================================
+NXP i.MX 8M Plus and i.MX 8M Mini Evaluation Kits (``imx8mp-evk``, ``imx8mm-evk``)
+==================================================================================
 
-The ``imx8mp-evk`` machine models the i.MX 8M Plus Evaluation Kit, based on an
-i.MX 8M Plus SoC.
+The ``imx8mp-evk`` and ``imx8mm-evk`` machine models the i.MX 8M Plus
+and i.MX 8M Mini Evaluation Kits, based on i.MX 8M Plus and i.MX8M
+Mini SoCs.
 
 Supported devices
 -----------------
 
-The ``imx8mp-evk`` machine implements the following devices:
+The ``imx8mp-evk`` and ``imx8mm-evk`` machines implement the
+following devices:
 
  * Up to 4 Cortex-A53 cores
  * Generic Interrupt Controller (GICv3)
@@ -XXX,XX +XXX,XX @@ The ``imx8mp-evk`` machine implements the following devices:
 Boot options
 ------------
 
-The ``imx8mp-evk`` machine can start a Linux kernel directly using the standard
-``-kernel`` functionality.
+The ``imx8mp-evk`` and ``imx8mm-evk`` machines can start a Linux
+kernel directly using the standard ``-kernel`` functionality.
 
 Direct Linux Kernel Boot
 ''''''''''''''''''''''''
@@ -XXX,XX +XXX,XX @@ is to generate an image with Buildroot. Version 2024.11.1 is tested at the time
 of writing and involves two steps. First run the following commands in the
 toplevel directory of the Buildroot source tree:
 
+For i.MX 8M Plus EVK:
+
 .. code-block:: bash
 
   $ make freescale_imx8mpevk_defconfig
   $ make
 
+For i.MX 8M Mini EVK:
+
+.. code-block:: bash
+
+  $ make freescale_imx8mmevk_defconfig
+  $ make
+
 Once finished successfully there is an ``output/image`` subfolder. Navigate into
 it and resize the SD card image to a power of two:
 
@@ -XXX,XX +XXX,XX @@ it and resize the SD card image to a power of two:
 
 Now that everything is prepared the machine can be started as follows:
 
+For i.MX 8M Plus EVK:
+
 .. code-block:: bash
 
   $ qemu-system-aarch64 -M imx8mp-evk \
@@ -XXX,XX +XXX,XX @@ Now that everything is prepared the machine can be started as follows:
       -append "root=/dev/mmcblk2p2" \
       -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2
 
+For i.MX 8M Mini EVK:
+
+.. code-block:: bash
+
+  $ qemu-system-aarch64 -M imx8mm-evk -smp 4 -m 2G \
+      -display none -serial null -serial stdio \
+      -kernel Image \
+      -dtb imx8mm-evk.dtb \
+      -append "root=/dev/mmcblk2p2" \
+      -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2
 
 KVM Acceleration
 ----------------
@@ -XXX,XX +XXX,XX @@ To enable hardware-assisted acceleration via KVM, append
 ``-accel kvm`` to the command line. While this speeds up performance
 significantly, be aware of the following limitations:
 
-* The ``imx8mp-evk`` machine is not included under the "virtualization use case"
-  of :doc:`QEMU's security policy </system/security>`. This means that you
-  should not trust that it can contain malicious guests, whether it is run
-  using TCG or KVM. If you don't trust your guests and you're relying on QEMU to
-  be the security boundary, you want to choose another machine such as ``virt``.
+* The ``imx8mp-evk`` and ``imx8mm-evk`` machines are not included
+  under the "virtualization use case" of :doc:`QEMU's security
+  policy </system/security>`.  This means that you should not trust that
+  it can contain malicious guests, whether it is run using TCG or KVM.
+  If you don't trust your guests and you're relying on QEMU to be the
+  security boundary, you want to choose another machine such as
+  ``virt``.
 * Rather than Cortex-A53 CPUs, the same CPU type as the host's will be used.
   This is a limitation of KVM and may not work with guests with a tight
   dependency on Cortex-A53.
diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/target-arm.rst
+++ b/docs/system/target-arm.rst
@@ -XXX,XX +XXX,XX @@ Board-specific documentation
    arm/imx25-pdk
    arm/mcimx6ul-evk
    arm/mcimx7d-sabre
-   arm/imx8mp-evk
+   arm/imx8m
    arm/orangepi
    arm/raspi
    arm/collie
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
     depends on TCG
     select FSL_IMX8MP
 
+config FSL_IMX8MM
+    bool
+    select ARM_GIC
+    select IMX
+
+config FSL_IMX8MM_EVK
+    bool
+    default y
+    depends on AARCH64
+    depends on TCG
+    select FSL_IMX8MM
+
 config ARM_SMMUV3_ACCEL
     bool
     depends on ARM_SMMUV3
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * i.MX 8MM SoC Implementation
+ *
+ * Based on hw/arm/fsl-imx6.c
+ *
+ * Copyright (c) 2025, NXP Semiconductors
+ * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * iMX8MM Reference Manual - https://www.nxp.com/products/i.MX8MMINI -> Documentation
+ */
+
+#include "qemu/osdep.h"
+#include "system/address-spaces.h"
+#include "hw/arm/bsa.h"
+#include "hw/arm/fsl-imx8mm.h"
+#include "hw/misc/unimp.h"
+#include "hw/core/boards.h"
+#include "system/kvm.h"
+#include "system/system.h"
+#include "target/arm/cpu.h"
+#include "target/arm/cpu-qom.h"
+#include "target/arm/kvm_arm.h"
+#include "qapi/error.h"
+#include "qobject/qlist.h"
+
+static const struct {
+    hwaddr addr;
+    size_t size;
+    const char *name;
+} fsl_imx8mm_memmap[] = {
+    [FSL_IMX8MM_RAM] = { FSL_IMX8MM_RAM_START, FSL_IMX8MM_RAM_SIZE_MAX, "ram" },
+    [FSL_IMX8MM_DDR_PHY_BROADCAST] = { 0x3dc00000, 4 * MiB, "ddr_phy_broadcast" },
+    [FSL_IMX8MM_DDR_PERF_MON] = { 0x3d800000, 4 * MiB, "ddr_perf_mon" },
+    [FSL_IMX8MM_DDR_CTL] = { 0x3d400000, 4 * MiB, "ddr_ctl" },
+    [FSL_IMX8MM_DDR_PHY] = { 0x3c000000, 16 * MiB, "ddr_phy" },
+    [FSL_IMX8MM_GIC_DIST] = { 0x38800000, 512 * KiB, "gic_dist" },
+    [FSL_IMX8MM_GIC_REDIST] = { 0x38880000, 512 * KiB, "gic_redist" },
+    [FSL_IMX8MM_VPU] = { 0x38340000, 2 * MiB, "vpu" },
+    [FSL_IMX8MM_VPU_BLK_CTRL] = { 0x38330000, 2 * MiB, "vpu_blk_ctrl" },
+    [FSL_IMX8MM_VPU_G2_DECODER] = { 0x38310000, 1 * MiB, "vpu_g2_decoder" },
+    [FSL_IMX8MM_VPU_G1_DECODER] = { 0x38300000, 1 * MiB, "vpu_g1_decoder" },
+    [FSL_IMX8MM_USB2_OTG] = { 0x32e50200, 0x200, "usb2_otg" },
+    [FSL_IMX8MM_USB2] = { 0x32e50000, 0x200, "usb2" },
+    [FSL_IMX8MM_USB1_OTG] = { 0x32e40200, 0x200, "usb1_otg" },
+    [FSL_IMX8MM_USB1] = { 0x32e40000, 0x200, "usb1" },
+    [FSL_IMX8MM_GPU2D] = { 0x38000000, 64 * KiB, "gpu2d" },
+    [FSL_IMX8MM_QSPI1_RX_BUFFER] = { 0x34000000, 32 * MiB, "qspi1_rx_buffer" },
+    [FSL_IMX8MM_PCIE1] = { 0x33800000, 4 * MiB, "pcie1" },
+    [FSL_IMX8MM_QSPI1_TX_BUFFER] = { 0x33008000, 32 * KiB, "qspi1_tx_buffer" },
+    [FSL_IMX8MM_APBH_DMA] = { 0x33000000, 32 * KiB, "apbh_dma" },
+
+    /* AIPS-4 Begin */
+    [FSL_IMX8MM_TZASC] = { 0x32f80000, 64 * KiB, "tzasc" },
+    [FSL_IMX8MM_PCIE_PHY1] = { 0x32f00000, 64 * KiB, "pcie_phy1" },
+    [FSL_IMX8MM_MEDIA_BLK_CTL] = { 0x32e28000, 256, "media_blk_ctl" },
+    [FSL_IMX8MM_LCDIF] = { 0x32e00000, 64 * KiB, "lcdif" },
+    [FSL_IMX8MM_MIPI_DSI] = { 0x32e10000, 64 * KiB, "mipi_dsi" },
+    [FSL_IMX8MM_MIPI_CSI] = { 0x32e30000, 64 * KiB, "mipi_csi" },
+    [FSL_IMX8MM_AIPS4_CONFIGURATION] = { 0x32df0000, 64 * KiB, "aips4_configuration" },
+    /* AIPS-4 End */
+
+    [FSL_IMX8MM_INTERCONNECT] = { 0x32700000, 1 * MiB, "interconnect" },
+
+    /* AIPS-3 Begin */
+    [FSL_IMX8MM_ENET1] = { 0x30be0000, 64 * KiB, "enet1" },
+    [FSL_IMX8MM_SDMA1] = { 0x30bd0000, 64 * KiB, "sdma1" },
+    [FSL_IMX8MM_QSPI] = { 0x30bb0000, 64 * KiB, "qspi" },
+    [FSL_IMX8MM_USDHC3] = { 0x30b60000, 64 * KiB, "usdhc3" },
+    [FSL_IMX8MM_USDHC2] = { 0x30b50000, 64 * KiB, "usdhc2" },
+    [FSL_IMX8MM_USDHC1] = { 0x30b40000, 64 * KiB, "usdhc1" },
+    [FSL_IMX8MM_SEMAPHORE_HS] = { 0x30ac0000, 64 * KiB, "semaphore_hs" },
+    [FSL_IMX8MM_MU_B] = { 0x30ab0000, 64 * KiB, "mu_b" },
+    [FSL_IMX8MM_MU_A] = { 0x30aa0000, 64 * KiB, "mu_a" },
+    [FSL_IMX8MM_UART4] = { 0x30a60000, 64 * KiB, "uart4" },
+    [FSL_IMX8MM_I2C4] = { 0x30a50000, 64 * KiB, "i2c4" },
+    [FSL_IMX8MM_I2C3] = { 0x30a40000, 64 * KiB, "i2c3" },
+    [FSL_IMX8MM_I2C2] = { 0x30a30000, 64 * KiB, "i2c2" },
+    [FSL_IMX8MM_I2C1] = { 0x30a20000, 64 * KiB, "i2c1" },
+    [FSL_IMX8MM_AIPS3_CONFIGURATION] = { 0x309f0000, 64 * KiB, "aips3_configuration" },
+    [FSL_IMX8MM_CAAM] = { 0x30900000, 256 * KiB, "caam" },
+    [FSL_IMX8MM_SPBA1] = { 0x308f0000, 64 * KiB, "spba1" },
+    [FSL_IMX8MM_UART2] = { 0x30890000, 64 * KiB, "uart2" },
+    [FSL_IMX8MM_UART3] = { 0x30880000, 64 * KiB, "uart3" },
+    [FSL_IMX8MM_UART1] = { 0x30860000, 64 * KiB, "uart1" },
+    [FSL_IMX8MM_ECSPI3] = { 0x30840000, 64 * KiB, "ecspi3" },
+    [FSL_IMX8MM_ECSPI2] = { 0x30830000, 64 * KiB, "ecspi2" },
+    [FSL_IMX8MM_ECSPI1] = { 0x30820000, 64 * KiB, "ecspi1" },
+    /* AIPS-3 End */
+
+    /* AIPS-2 Begin */
+    [FSL_IMX8MM_QOSC] = { 0x307f0000, 64 * KiB, "qosc" },
+    [FSL_IMX8MM_PERFMON2] = { 0x307d0000, 64 * KiB, "perfmon2" },
+    [FSL_IMX8MM_PERFMON1] = { 0x307c0000, 64 * KiB, "perfmon1" },
+    [FSL_IMX8MM_GPT4] = { 0x30700000, 64 * KiB, "gpt4" },
+    [FSL_IMX8MM_GPT5] = { 0x306f0000, 64 * KiB, "gpt5" },
+    [FSL_IMX8MM_GPT6] = { 0x306e0000, 64 * KiB, "gpt6" },
+    [FSL_IMX8MM_SYSCNT_CTRL] = { 0x306c0000, 64 * KiB, "syscnt_ctrl" },
+    [FSL_IMX8MM_SYSCNT_CMP] = { 0x306b0000, 64 * KiB, "syscnt_cmp" },
+    [FSL_IMX8MM_SYSCNT_RD] = { 0x306a0000, 64 * KiB, "syscnt_rd" },
+    [FSL_IMX8MM_PWM4] = { 0x30690000, 64 * KiB, "pwm4" },
+    [FSL_IMX8MM_PWM3] = { 0x30680000, 64 * KiB, "pwm3" },
+    [FSL_IMX8MM_PWM2] = { 0x30670000, 64 * KiB, "pwm2" },
+    [FSL_IMX8MM_PWM1] = { 0x30660000, 64 * KiB, "pwm1" },
+    [FSL_IMX8MM_AIPS2_CONFIGURATION] = { 0x305f0000, 64 * KiB, "aips2_configuration" },
+    /* AIPS-2 End */
+
+    /* AIPS-1 Begin */
+    [FSL_IMX8MM_CSU] = { 0x303e0000, 64 * KiB, "csu" },
+    [FSL_IMX8MM_RDC] = { 0x303d0000, 64 * KiB, "rdc" },
+    [FSL_IMX8MM_SEMAPHORE2] = { 0x303c0000, 64 * KiB, "semaphore2" },
+    [FSL_IMX8MM_SEMAPHORE1] = { 0x303b0000, 64 * KiB, "semaphore1" },
+    [FSL_IMX8MM_GPC] = { 0x303a0000, 64 * KiB, "gpc" },
+    [FSL_IMX8MM_SRC] = { 0x30390000, 64 * KiB, "src" },
+    [FSL_IMX8MM_CCM] = { 0x30380000, 64 * KiB, "ccm" },
+    [FSL_IMX8MM_SNVS_HP] = { 0x30370000, 64 * KiB, "snvs_hp" },
+    [FSL_IMX8MM_ANA_PLL] = { 0x30360000, 64 * KiB, "ana_pll" },
+    [FSL_IMX8MM_OCOTP_CTRL] = { 0x30350000, 64 * KiB, "ocotp_ctrl" },
+    [FSL_IMX8MM_IOMUXC_GPR] = { 0x30340000, 64 * KiB, "iomuxc_gpr" },
+    [FSL_IMX8MM_IOMUXC] = { 0x30330000, 64 * KiB, "iomuxc" },
+    [FSL_IMX8MM_GPT3] = { 0x302f0000, 64 * KiB, "gpt3" },
+    [FSL_IMX8MM_GPT2] = { 0x302e0000, 64 * KiB, "gpt2" },
+    [FSL_IMX8MM_GPT1] = { 0x302d0000, 64 * KiB, "gpt1" },
+    [FSL_IMX8MM_SDMA2] = { 0x302c0000, 64 * KiB, "sdma2" },
+    [FSL_IMX8MM_SDMA3] = { 0x302b0000, 64 * KiB, "sdma3" },
+    [FSL_IMX8MM_WDOG3] = { 0x302a0000, 64 * KiB, "wdog3" },
+    [FSL_IMX8MM_WDOG2] = { 0x30290000, 64 * KiB, "wdog2" },
+    [FSL_IMX8MM_WDOG1] = { 0x30280000, 64 * KiB, "wdog1" },
+    [FSL_IMX8MM_ANA_OSC] = { 0x30270000, 64 * KiB, "ana_osc" },
+    [FSL_IMX8MM_ANA_TSENSOR] = { 0x30260000, 64 * KiB, "ana_tsensor" },
+    [FSL_IMX8MM_GPIO5] = { 0x30240000, 64 * KiB, "gpio5" },
+    [FSL_IMX8MM_GPIO4] = { 0x30230000, 64 * KiB, "gpio4" },
+    [FSL_IMX8MM_GPIO3] = { 0x30220000, 64 * KiB, "gpio3" },
+    [FSL_IMX8MM_GPIO2] = { 0x30210000, 64 * KiB, "gpio2" },
+    [FSL_IMX8MM_GPIO1] = { 0x30200000, 64 * KiB, "gpio1" },
+    [FSL_IMX8MM_AIPS1_CONFIGURATION] = { 0x301f0000, 64 * KiB, "aips1_configuration" },
+    [FSL_IMX8MM_SAI6] = { 0x30060000, 64 * KiB, "sai6" },
+    [FSL_IMX8MM_SAI5] = { 0x30050000, 64 * KiB, "sai5" },
+    [FSL_IMX8MM_SAI3] = { 0x30030000, 64 * KiB, "sai3" },
+    [FSL_IMX8MM_SAI2] = { 0x30020000, 64 * KiB, "sai2" },
+    [FSL_IMX8MM_SAI1] = { 0x30010000, 64 * KiB, "sai1" },
+
+    /* AIPS-1 End */
+
+    [FSL_IMX8MM_A53_DAP] = { 0x28000000, 16 * MiB, "a53_dap" },
+    [FSL_IMX8MM_PCIE1_MEM] = { 0x18000000, 128 * MiB, "pcie1_mem" },
+    [FSL_IMX8MM_QSPI_MEM] = { 0x08000000, 256 * MiB, "qspi_mem" },
+    [FSL_IMX8MM_OCRAM] = { 0x00900000, 256 * KiB, "ocram" },
+    [FSL_IMX8MM_TCM_DTCM] = { 0x00800000, 128 * KiB, "tcm_dtcm" },
+    [FSL_IMX8MM_TCM_ITCM] = { 0x007e0000, 128 * KiB, "tcm_itcm" },
+    [FSL_IMX8MM_OCRAM_S] = { 0x00180000, 32 * KiB, "ocram_s" },
+    [FSL_IMX8MM_CAAM_MEM] = { 0x00100000, 32 * KiB, "caam_mem" },
+    [FSL_IMX8MM_BOOT_ROM_PROTECTED] = { 0x0003f000, 4 * KiB, "boot_rom_protected" },
+    [FSL_IMX8MM_BOOT_ROM] = { 0x00000000, 252 * KiB, "boot_rom" },
+};
+
+static void fsl_imx8mm_init(Object *obj)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    FslImx8mmState *s = FSL_IMX8MM(obj);
+    const char *cpu_type = ms->cpu_type ?: ARM_CPU_TYPE_NAME("cortex-a53");
+    int i;
+
+    for (i = 0; i < MIN(ms->smp.cpus, FSL_IMX8MM_NUM_CPUS); i++) {
+        g_autofree char *name = g_strdup_printf("cpu%d", i);
+        object_initialize_child(obj, name, &s->cpu[i], cpu_type);
+    }
+
+    object_initialize_child(obj, "gic", &s->gic, gicv3_class_name());
+
+    for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
+        g_autofree char *name = g_strdup_printf("uart%d", i + 1);
+        object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
+    }
+
+}
+
+static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    FslImx8mmState *s = FSL_IMX8MM(dev);
+    DeviceState *gicdev = DEVICE(&s->gic);
+    int i;
+
+    if (ms->smp.cpus > FSL_IMX8MM_NUM_CPUS) {
+        error_setg(errp, "%s: Only %d CPUs are supported (%d requested)",
+                   TYPE_FSL_IMX8MM, FSL_IMX8MM_NUM_CPUS, ms->smp.cpus);
+        return;
+    }
+
+    /* CPUs */
+    for (i = 0; i < ms->smp.cpus; i++) {
+        /* On uniprocessor, the CBAR is set to 0 */
+        if (ms->smp.cpus > 1 &&
+                object_property_find(OBJECT(&s->cpu[i]), "reset-cbar")) {
+            object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar",
+                                    fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr,
+                                    &error_abort);
+        }
+
+        /*
+         * CNTFID0 base frequency in Hz of system counter
+         */
+        object_property_set_int(OBJECT(&s->cpu[i]), "cntfrq", 8000000,
+                                &error_abort);
+
+        if (object_property_find(OBJECT(&s->cpu[i]), "has_el2")) {
+            object_property_set_bool(OBJECT(&s->cpu[i]), "has_el2",
+                                     !kvm_enabled(), &error_abort);
+        }
+
+        if (object_property_find(OBJECT(&s->cpu[i]), "has_el3")) {
+            object_property_set_bool(OBJECT(&s->cpu[i]), "has_el3",
+                                     !kvm_enabled(), &error_abort);
+        }
+
+        if (i) {
+            /*
+             * Secondary CPUs start in powered-down state (and can be
+             * powered up via the SRC system reset controller)
+             */
+            object_property_set_bool(OBJECT(&s->cpu[i]), "start-powered-off",
+                                     true, &error_abort);
+        }
+
+        if (!qdev_realize(DEVICE(&s->cpu[i]), NULL, errp)) {
+            return;
+        }
+    }
+
+    /* GIC */
+    {
+        SysBusDevice *gicsbd = SYS_BUS_DEVICE(&s->gic);
+        QList *redist_region_count;
+        bool pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL);
+
+        qdev_prop_set_uint32(gicdev, "num-cpu", ms->smp.cpus);
+        qdev_prop_set_uint32(gicdev, "num-irq",
+                             FSL_IMX8MM_NUM_IRQS + GIC_INTERNAL);
+        redist_region_count = qlist_new();
+        qlist_append_int(redist_region_count, ms->smp.cpus);
+        qdev_prop_set_array(gicdev, "redist-region-count", redist_region_count);
+        object_property_set_link(OBJECT(&s->gic), "sysmem",
+                                 OBJECT(get_system_memory()), &error_fatal);
+        if (!sysbus_realize(gicsbd, errp)) {
+            return;
+        }
+        sysbus_mmio_map(gicsbd, 0, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr);
+        sysbus_mmio_map(gicsbd, 1, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_REDIST].addr);
+
+        /*
+         * Wire the outputs from each CPU's generic timer and the GICv3
+         * maintenance interrupt signal to the appropriate GIC PPI inputs, and
+         * the GIC's IRQ/FIQ interrupt outputs to the CPU's inputs.
+         */
+        for (i = 0; i < ms->smp.cpus; i++) {
+            DeviceState *cpudev = DEVICE(&s->cpu[i]);
+            int intidbase = FSL_IMX8MM_NUM_IRQS + i * GIC_INTERNAL;
+            qemu_irq irq;
+
+            /*
+             * Mapping from the output timer irq lines from the CPU to the
+             * GIC PPI inputs.
+             */
+            static const int timer_irqs[] = {
+                [GTIMER_PHYS] = ARCH_TIMER_NS_EL1_IRQ,
+                [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ,
+                [GTIMER_HYP]  = ARCH_TIMER_NS_EL2_IRQ,
+                [GTIMER_SEC]  = ARCH_TIMER_S_EL1_IRQ,
+            };
+
+            for (int j = 0; j < ARRAY_SIZE(timer_irqs); j++) {
+                irq = qdev_get_gpio_in(gicdev, intidbase + timer_irqs[j]);
+                qdev_connect_gpio_out(cpudev, j, irq);
+            }
+
+            irq = qdev_get_gpio_in(gicdev, intidbase + ARCH_GIC_MAINT_IRQ);
+            qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt",
+                                        0, irq);
+
+            irq = qdev_get_gpio_in(gicdev, intidbase + VIRTUAL_PMU_IRQ);
+            qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, irq);
+
+            sysbus_connect_irq(gicsbd, i,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_IRQ));
+            sysbus_connect_irq(gicsbd, i + ms->smp.cpus,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_FIQ));
+            sysbus_connect_irq(gicsbd, i + 2 * ms->smp.cpus,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ));
+            sysbus_connect_irq(gicsbd, i + 3 * ms->smp.cpus,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ));
+
+            if (kvm_enabled()) {
+                if (pmu) {
+                    assert(arm_feature(&s->cpu[i].env, ARM_FEATURE_PMU));
+                    if (kvm_irqchip_in_kernel()) {
+                        kvm_arm_pmu_set_irq(&s->cpu[i], VIRTUAL_PMU_IRQ);
+                    }
+                    kvm_arm_pmu_init(&s->cpu[i]);
+                }
+            }
+        }
+    }
+
+    /* UARTs */
+    for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } serial_table[FSL_IMX8MM_NUM_UARTS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART1].addr, FSL_IMX8MM_UART1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART2].addr, FSL_IMX8MM_UART2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART3].addr, FSL_IMX8MM_UART3_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART4].addr, FSL_IMX8MM_UART4_IRQ },
+        };
+
+        qdev_prop_set_chr(DEVICE(&s->uart[i]), "chardev", serial_hd(i));
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->uart[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart[i]), 0, serial_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0,
+                           qdev_get_gpio_in(gicdev, serial_table[i].irq));
+    }
+
+    /* On-Chip RAM */
+    if (!memory_region_init_ram(&s->ocram, OBJECT(dev), "imx8mm.ocram",
+                                fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].size,
+                                errp)) {
+        return;
+    }
+    memory_region_add_subregion(get_system_memory(),
+                                fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
+                                &s->ocram);
+
+    /* Unimplemented devices */
+    for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
+        switch (i) {
+        case FSL_IMX8MM_GIC_DIST:
+        case FSL_IMX8MM_GIC_REDIST:
+        case FSL_IMX8MM_RAM:
+        case FSL_IMX8MM_OCRAM:
+        case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
+            /* device implemented and treated above */
+            break;
+
+        default:
+            create_unimplemented_device(fsl_imx8mm_memmap[i].name,
+                                        fsl_imx8mm_memmap[i].addr,
+                                        fsl_imx8mm_memmap[i].size);
+            break;
+        }
+    }
+}
+
+static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    dc->realize = fsl_imx8mm_realize;
+
+    dc->desc = "i.MX 8MM SoC";
+}
+
+static const TypeInfo fsl_imx8mm_types[] = {
+    {
+        .name = TYPE_FSL_IMX8MM,
+        .parent = TYPE_SYS_BUS_DEVICE,
+        .instance_size = sizeof(FslImx8mmState),
+        .instance_init = fsl_imx8mm_init,
+        .class_init = fsl_imx8mm_class_init,
+    },
+};
+
+DEFINE_TYPES(fsl_imx8mm_types)
diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/arm/imx8mm-evk.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * NXP i.MX 8MM Evaluation Kit System Emulation
+ *
+ * Copyright (c) 2025, NXP Semiconductors
+ * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "system/address-spaces.h"
+#include "hw/arm/boot.h"
+#include "hw/arm/fsl-imx8mm.h"
+#include "hw/arm/machines-qom.h"
+#include "hw/core/boards.h"
+#include "hw/core/qdev-properties.h"
+#include "system/kvm.h"
+#include "system/qtest.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+#include <libfdt.h>
+
+static void imx8mm_evk_modify_dtb(const struct arm_boot_info *info, void *fdt)
+{
+    int i, offset;
+
+    /* Temporarily disable following nodes until they are implemented */
+    const char *nodes_to_remove[] = {
+        "nxp,imx8mm-fspi",
+        "fsl,imx8mm-mipi-csi",
+        "fsl,imx8mm-mipi-dsim"
+    };
+
+    for (i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) {
+        const char *dev_str = nodes_to_remove[i];
+
+        offset = fdt_node_offset_by_compatible(fdt, -1, dev_str);
+        while (offset >= 0) {
+            fdt_nop_node(fdt, offset);
+            offset = fdt_node_offset_by_compatible(fdt, offset, dev_str);
+        }
+    }
+
+    /* Remove cpu-idle-states property from CPU nodes */
+    offset = fdt_node_offset_by_compatible(fdt, -1, "arm,cortex-a53");
+    while (offset >= 0) {
+        fdt_nop_property(fdt, offset, "cpu-idle-states");
+        offset = fdt_node_offset_by_compatible(fdt, offset, "arm,cortex-a53");
+    }
+
+    if (kvm_enabled()) {
+        /* Use system counter frequency from host CPU to fix time in guest */
+        offset = fdt_node_offset_by_compatible(fdt, -1, "arm,armv8-timer");
+        while (offset >= 0) {
+            fdt_nop_property(fdt, offset, "clock-frequency");
+            offset = fdt_node_offset_by_compatible(fdt, offset, "arm,armv8-timer");
+        }
+    }
+}
+
+static void imx8mm_evk_init(MachineState *machine)
+{
+    static struct arm_boot_info boot_info;
+    FslImx8mmState *s;
+
+    if (machine->ram_size > FSL_IMX8MM_RAM_SIZE_MAX) {
+        error_report("RAM size " RAM_ADDR_FMT " above max supported (%08" PRIx64 ")",
+                     machine->ram_size, FSL_IMX8MM_RAM_SIZE_MAX);
+        exit(1);
+    }
+
+    boot_info = (struct arm_boot_info) {
+        .loader_start = FSL_IMX8MM_RAM_START,
+        .board_id = -1,
+        .ram_size = machine->ram_size,
+        .psci_conduit = QEMU_PSCI_CONDUIT_SMC,
+        .modify_dtb = imx8mm_evk_modify_dtb,
+    };
+
+    s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine),
+                                         "soc", &error_fatal, NULL));
+    sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal);
+
+    memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START,
+                                machine->ram);
+
+    if (!qtest_enabled()) {
+        arm_load_kernel(&s->cpu[0], machine, &boot_info);
+    }
+}
+
+static const char *imx8mm_evk_get_default_cpu_type(const MachineState *ms)
+{
+    if (kvm_enabled()) {
+        return ARM_CPU_TYPE_NAME("host");
+    }
+
+    return ARM_CPU_TYPE_NAME("cortex-a53");
+}
+
+static void imx8mm_evk_machine_init(MachineClass *mc)
+{
+    mc->desc = "NXP i.MX 8MM EVK Board";
+    mc->init = imx8mm_evk_init;
+    mc->max_cpus = FSL_IMX8MM_NUM_CPUS;
+    mc->default_cpus = FSL_IMX8MM_NUM_CPUS;
+    mc->default_ram_size = 2 * GiB;
+    mc->default_ram_id = "imx8mm-evk.ram";
+    mc->get_default_cpu_type = imx8mm_evk_get_default_cpu_type;
+}
+
+DEFINE_MACHINE_AARCH64("imx8mm-evk", imx8mm_evk_machine_init)
diff --git a/hw/arm/meson.build b/hw/arm/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -XXX,XX +XXX,XX @@ arm_common_ss.add(when: 'CONFIG_ARMSSE', if_true: files('armsse.c'))
 arm_common_ss.add(when: 'CONFIG_FSL_IMX7', if_true: files('fsl-imx7.c', 'mcimx7d-sabre.c'))
 arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP', if_true: files('fsl-imx8mp.c'))
 arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP_EVK', if_true: files('imx8mp-evk.c'))
+arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM', if_true: files('fsl-imx8mm.c'))
+arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM_EVK', if_true: files('imx8mm-evk.c'))
 arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c'))
 arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3_ACCEL', if_true: files('smmuv3-accel.c'))
 stub_ss.add(files('smmuv3-accel-stubs.c'))
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * i.MX 8MM SoC Definitions
+ *
+ * Copyright (c) 2025, NXP Semiconductors
+ * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef FSL_IMX8MM_H
+#define FSL_IMX8MM_H
+
+#include "cpu.h"
+#include "hw/char/imx_serial.h"
+#include "hw/intc/arm_gicv3_common.h"
+#include "qom/object.h"
+#include "qemu/units.h"
+
+#define TYPE_FSL_IMX8MM "fsl-imx8mm"
+OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
+
+#define FSL_IMX8MM_RAM_START        0x40000000
+#define FSL_IMX8MM_RAM_SIZE_MAX     (4 * GiB)
+
+enum FslImx8mmConfiguration {
+    FSL_IMX8MM_NUM_CPUS         = 4,
+    FSL_IMX8MM_NUM_IRQS         = 128,
+    FSL_IMX8MM_NUM_UARTS        = 4,
+};
+
+struct FslImx8mmState {
+    SysBusDevice   parent_obj;
+
+    ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
+    GICv3State         gic;
+    IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
+    MemoryRegion ocram;
+};
+
+enum FslImx8mmMemoryRegions {
+    FSL_IMX8MM_A53_DAP,
+    FSL_IMX8MM_AIPS1_CONFIGURATION,
+    FSL_IMX8MM_AIPS2_CONFIGURATION,
+    FSL_IMX8MM_AIPS3_CONFIGURATION,
+    FSL_IMX8MM_AIPS4_CONFIGURATION,
+    FSL_IMX8MM_ANA_OSC,
+    FSL_IMX8MM_ANA_PLL,
+    FSL_IMX8MM_ANA_TSENSOR,
+    FSL_IMX8MM_APBH_DMA,
+    FSL_IMX8MM_BOOT_ROM,
+    FSL_IMX8MM_BOOT_ROM_PROTECTED,
+    FSL_IMX8MM_CAAM,
+    FSL_IMX8MM_CAAM_MEM,
+    FSL_IMX8MM_CCM,
+    FSL_IMX8MM_CSU,
+    FSL_IMX8MM_DDR_CTL,
+    FSL_IMX8MM_DDR_PERF_MON,
+    FSL_IMX8MM_DDR_PHY,
+    FSL_IMX8MM_DDR_PHY_BROADCAST,
+    FSL_IMX8MM_ECSPI1,
+    FSL_IMX8MM_ECSPI2,
+    FSL_IMX8MM_ECSPI3,
+    FSL_IMX8MM_ENET1,
+    FSL_IMX8MM_GIC_DIST,
+    FSL_IMX8MM_GIC_REDIST,
+    FSL_IMX8MM_GPC,
+    FSL_IMX8MM_GPIO1,
+    FSL_IMX8MM_GPIO2,
+    FSL_IMX8MM_GPIO3,
+    FSL_IMX8MM_GPIO4,
+    FSL_IMX8MM_GPIO5,
+    FSL_IMX8MM_GPT1,
+    FSL_IMX8MM_GPT2,
+    FSL_IMX8MM_GPT3,
+    FSL_IMX8MM_GPT4,
+    FSL_IMX8MM_GPT5,
+    FSL_IMX8MM_GPT6,
+    FSL_IMX8MM_GPU2D,
+    FSL_IMX8MM_I2C1,
+    FSL_IMX8MM_I2C2,
+    FSL_IMX8MM_I2C3,
+    FSL_IMX8MM_I2C4,
+    FSL_IMX8MM_INTERCONNECT,
+    FSL_IMX8MM_IOMUXC,
+    FSL_IMX8MM_IOMUXC_GPR,
+    FSL_IMX8MM_MEDIA_BLK_CTL,
+    FSL_IMX8MM_LCDIF,
+    FSL_IMX8MM_MIPI_CSI,
+    FSL_IMX8MM_MIPI_DSI,
+    FSL_IMX8MM_MU_A,
+    FSL_IMX8MM_MU_B,
+    FSL_IMX8MM_OCOTP_CTRL,
+    FSL_IMX8MM_OCRAM,
+    FSL_IMX8MM_OCRAM_S,
+    FSL_IMX8MM_PCIE1,
+    FSL_IMX8MM_PCIE1_MEM,
+    FSL_IMX8MM_PCIE_PHY1,
+    FSL_IMX8MM_PERFMON1,
+    FSL_IMX8MM_PERFMON2,
+    FSL_IMX8MM_PWM1,
+    FSL_IMX8MM_PWM2,
+    FSL_IMX8MM_PWM3,
+    FSL_IMX8MM_PWM4,
+    FSL_IMX8MM_QOSC,
+    FSL_IMX8MM_QSPI,
+    FSL_IMX8MM_QSPI1_RX_BUFFER,
+    FSL_IMX8MM_QSPI1_TX_BUFFER,
+    FSL_IMX8MM_QSPI_MEM,
+    FSL_IMX8MM_RAM,
+    FSL_IMX8MM_RDC,
+    FSL_IMX8MM_SAI1,
+    FSL_IMX8MM_SAI2,
+    FSL_IMX8MM_SAI3,
+    FSL_IMX8MM_SAI5,
+    FSL_IMX8MM_SAI6,
+    FSL_IMX8MM_SDMA1,
+    FSL_IMX8MM_SDMA2,
+    FSL_IMX8MM_SDMA3,
+    FSL_IMX8MM_SEMAPHORE1,
+    FSL_IMX8MM_SEMAPHORE2,
+    FSL_IMX8MM_SEMAPHORE_HS,
+    FSL_IMX8MM_SNVS_HP,
+    FSL_IMX8MM_SPBA1,
+    FSL_IMX8MM_SRC,
+    FSL_IMX8MM_SYSCNT_CMP,
+    FSL_IMX8MM_SYSCNT_CTRL,
+    FSL_IMX8MM_SYSCNT_RD,
+    FSL_IMX8MM_TCM_DTCM,
+    FSL_IMX8MM_TCM_ITCM,
+    FSL_IMX8MM_TZASC,
+    FSL_IMX8MM_UART1,
+    FSL_IMX8MM_UART2,
+    FSL_IMX8MM_UART3,
+    FSL_IMX8MM_UART4,
+    FSL_IMX8MM_USB1,
+    FSL_IMX8MM_USB2,
+    FSL_IMX8MM_USB1_OTG,
+    FSL_IMX8MM_USB2_OTG,
+    FSL_IMX8MM_USDHC1,
+    FSL_IMX8MM_USDHC2,
+    FSL_IMX8MM_USDHC3,
+    FSL_IMX8MM_VPU,
+    FSL_IMX8MM_VPU_BLK_CTRL,
+    FSL_IMX8MM_VPU_G1_DECODER,
+    FSL_IMX8MM_VPU_G2_DECODER,
+    FSL_IMX8MM_WDOG1,
+    FSL_IMX8MM_WDOG2,
+    FSL_IMX8MM_WDOG3,
+};
+
+enum FslImx8mmIrqs {
+    FSL_IMX8MM_UART1_IRQ    = 26,
+    FSL_IMX8MM_UART2_IRQ    = 27,
+    FSL_IMX8MM_UART3_IRQ    = 28,
+    FSL_IMX8MM_UART4_IRQ    = 29,
+};
+
+#endif /* FSL_IMX8MM_H */
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Add configurable properties for register reset values that differ
between i.MX 8M variants (Plus, Mini, etc.). This allows the same
device implementation to be shared across multiple SoCs.

Properties added:
- arm-pll-fdiv-ctl0-reset: ARM PLL divider control reset value

Default value is set to match i.MX 8MP reset value (0x000FA031).
This can be overridden in the variant like iMX8MM with its own
reset value.

Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/misc/imx8mp_analog.c         | 12 +++++++++++-
 include/hw/misc/imx8mp_analog.h |  3 +++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/hw/misc/imx8mp_analog.c b/hw/misc/imx8mp_analog.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx8mp_analog.c
+++ b/hw/misc/imx8mp_analog.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/log.h"
 
 #include "hw/misc/imx8mp_analog.h"
+#include "hw/core/qdev-properties.h"
 #include "migration/vmstate.h"
 
 #define ANALOG_PLL_LOCK BIT(31)
@@ -XXX,XX +XXX,XX @@ static void imx8mp_analog_reset(DeviceState *dev)
     s->analog[ANALOG_VPU_PLL_LOCKD_CTRL] = 0x0010003f;
     s->analog[ANALOG_VPU_PLL_MNIT_CTRL] = 0x00280081;
     s->analog[ANALOG_ARM_PLL_GEN_CTRL] = 0x00000810;
-    s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = 0x000fa031;
+
+    /* Use property value instead of hardcoded */
+    s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = s->arm_pll_fdiv_ctl0_reset;
+
     s->analog[ANALOG_ARM_PLL_LOCKD_CTRL] = 0x0010003f;
     s->analog[ANALOG_ARM_PLL_MNIT_CTRL] = 0x00280081;
     s->analog[ANALOG_SYS_PLL1_GEN_CTRL] = 0x0aaaa810;
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription imx8mp_analog_vmstate = {
     },
 };
 
+static const Property imx8mp_analog_properties[] = {
+    DEFINE_PROP_UINT32("arm-pll-fdiv-ctl0-reset", IMX8MPAnalogState,
+                       arm_pll_fdiv_ctl0_reset, 0x000fa031), /* imx8mp default */
+};
+
 static void imx8mp_analog_class_init(ObjectClass *klass, const void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     device_class_set_legacy_reset(dc, imx8mp_analog_reset);
+    device_class_set_props(dc, imx8mp_analog_properties);
     dc->vmsd  = &imx8mp_analog_vmstate;
     dc->desc  = "i.MX 8M Plus Analog Module";
 }
diff --git a/include/hw/misc/imx8mp_analog.h b/include/hw/misc/imx8mp_analog.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/misc/imx8mp_analog.h
+++ b/include/hw/misc/imx8mp_analog.h
@@ -XXX,XX +XXX,XX @@ struct IMX8MPAnalogState {
     } mmio;
 
     uint32_t analog[ANALOG_MAX];
+
+    /* Property for variant-specific reset values */
+    uint32_t arm_pll_fdiv_ctl0_reset;
 };
 
 #endif /* IMX8MP_ANALOG_H */
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Add the Analog IP to i.MX8MM SoC. iMX8MM and i.MX8MP uses
the same Analog IP so the analog ip source will be shared.

The ARM PLL divider control register (arm-pll-fdiv-ctl0) has
a different reset value on i.MX8MM (0x000fa030) compared to
i.MX8MP (0x000fa031). So iMX8MM will be overriding this property
with its own reset-value.

Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 12 ++++++++++++
 include/hw/arm/fsl-imx8mm.h |  2 ++
 3 files changed, 15 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
 config FSL_IMX8MM
     bool
     select ARM_GIC
+    select FSL_IMX8MP_ANALOG
     select IMX
 
 config FSL_IMX8MM_EVK
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
 
     object_initialize_child(obj, "gic", &s->gic, gicv3_class_name());
 
+    object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG);
+
     for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
         g_autofree char *name = g_strdup_printf("uart%d", i + 1);
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         }
     }
 
+    /* Analog */
+    object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset",
+                            0x000fa030, &error_abort);
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->analog), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->analog), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_ANA_PLL].addr);
+
     /* UARTs */
     for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     /* Unimplemented devices */
     for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
         switch (i) {
+        case FSL_IMX8MM_ANA_PLL:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "cpu.h"
 #include "hw/char/imx_serial.h"
 #include "hw/intc/arm_gicv3_common.h"
+#include "hw/misc/imx8mp_analog.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMX8MPAnalogState  analog;
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
 };
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Add the Clock Control Module (CCM) device to i.MX8MM SoC.
The CCM implementation is shared with i.MX8MP as the register
layout is identical between the two variants.Hence iMX8MM will
be using the source of iMX8MP CCM.

Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 10 ++++++++++
 include/hw/arm/fsl-imx8mm.h |  2 ++
 3 files changed, 13 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     bool
     select ARM_GIC
     select FSL_IMX8MP_ANALOG
+    select FSL_IMX8MP_CCM
     select IMX
 
 config FSL_IMX8MM_EVK
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
 
     object_initialize_child(obj, "gic", &s->gic, gicv3_class_name());
 
+    object_initialize_child(obj, "ccm", &s->ccm, TYPE_IMX8MP_CCM);
+
     object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG);
 
     for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         }
     }
 
+    /* CCM */
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->ccm), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_CCM].addr);
+
     /* Analog */
     object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset",
                             0x000fa030, &error_abort);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
         switch (i) {
         case FSL_IMX8MM_ANA_PLL:
+        case FSL_IMX8MM_CCM:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/char/imx_serial.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/misc/imx8mp_analog.h"
+#include "hw/misc/imx8mp_ccm.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

SNVS contains an RTC which allows Linux to deal correctly with time

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of SD/MMC cards through a virtual SDHCI interface
The emulated SDHCI controller allows guest OS to use emulated storage as
a standard block device.
This will allow running the images such as those generated
by Buildroot.

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 25 +++++++++++++++++++++++++
 hw/arm/imx8mm-evk.c         | 17 +++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  7 +++++++
 4 files changed, 50 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
+    select SDHCI
 
 config FSL_IMX8MM_EVK
     bool
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
+        g_autofree char *name = g_strdup_printf("usdhc%d", i + 1);
+        object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
+    }
 }
 
 static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* USDHCs */
+    for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } usdhc_table[FSL_IMX8MM_NUM_USDHCS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC1].addr, FSL_IMX8MM_USDHC1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC2].addr, FSL_IMX8MM_USDHC2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC3].addr, FSL_IMX8MM_USDHC3_IRQ },
+        };
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->usdhc[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->usdhc[i]), 0, usdhc_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->usdhc[i]), 0,
+                           qdev_get_gpio_in(gicdev, usdhc_table[i].irq));
+    }
+
     /* SNVS */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_OCRAM:
         case FSL_IMX8MM_SNVS_HP:
         case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
+        case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3:
             /* device implemented and treated above */
             break;
 
diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/imx8mm-evk.c
+++ b/hw/arm/imx8mm-evk.c
@@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine)
     memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START,
                                 machine->ram);
 
+    for (int i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
+        BusState *bus;
+        DeviceState *carddev;
+        BlockBackend *blk;
+        DriveInfo *di = drive_get(IF_SD, i, 0);
+
+        if (!di) {
+            continue;
+        }
+
+        blk = blk_by_legacy_dinfo(di);
+        bus = qdev_get_child_bus(DEVICE(&s->usdhc[i]), "sd-bus");
+        carddev = qdev_new(TYPE_SD_CARD);
+        qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal);
+        qdev_realize_and_unref(carddev, bus, &error_fatal);
+    }
+
     if (!qtest_enabled()) {
         arm_load_kernel(&s->cpu[0], machine, &boot_info);
     }
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
+#include "hw/sd/sdhci.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
+    FSL_IMX8MM_NUM_USDHCS       = 3,
 };
 
 struct FslImx8mmState {
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX7SNVSState      snvs;
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
+    SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmMemoryRegions {
 };
 
 enum FslImx8mmIrqs {
+    FSL_IMX8MM_USDHC1_IRQ   = 22,
+    FSL_IMX8MM_USDHC2_IRQ   = 23,
+    FSL_IMX8MM_USDHC3_IRQ   = 24,
+
     FSL_IMX8MM_UART1_IRQ    = 26,
     FSL_IMX8MM_UART2_IRQ    = 27,
     FSL_IMX8MM_UART3_IRQ    = 28,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

This enables support for Designware PCI Express Controller emulation
It provides a controlled environment to debug the linux pci subsystem

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  3 +++
 hw/arm/fsl-imx8mm.c         | 30 ++++++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h | 10 ++++++++++
 3 files changed, 43 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
 
 config FSL_IMX8MM
     bool
+    imply PCI_DEVICES
     select ARM_GIC
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
     select SDHCI
+    select PCI_EXPRESS_DESIGNWARE
+    select PCI_EXPRESS_FSL_IMX8M_PHY
 
 config FSL_IMX8MM_EVK
     bool
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         g_autofree char *name = g_strdup_printf("usdhc%d", i + 1);
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
     }
+
+    object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
+    object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
+                            TYPE_FSL_IMX8M_PCIE_PHY);
 }
 
 static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0,
                     fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr);
 
+    /* PCIe */
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_PCIE1].addr);
+
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTA_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTB_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTC_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTD_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 4,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_MSI_IRQ));
+
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie_phy), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie_phy), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_PCIE_PHY1].addr);
+
     /* Unimplemented devices */
     for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
         switch (i) {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_CCM:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
+        case FSL_IMX8MM_PCIE1:
+        case FSL_IMX8MM_PCIE_PHY1:
         case FSL_IMX8MM_RAM:
         case FSL_IMX8MM_OCRAM:
         case FSL_IMX8MM_SNVS_HP:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
+#include "hw/pci-host/designware.h"
+#include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
 #include "qom/object.h"
 #include "qemu/units.h"
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
+    DesignwarePCIEHost pcie;
+    FslImx8mPciePhyState   pcie_phy;
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART2_IRQ    = 27,
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
+
+    FSL_IMX8MM_PCI_INTA_IRQ = 122,
+    FSL_IMX8MM_PCI_INTB_IRQ = 123,
+    FSL_IMX8MM_PCI_INTC_IRQ = 124,
+    FSL_IMX8MM_PCI_INTD_IRQ = 125,
+    FSL_IMX8MM_PCI_MSI_IRQ  = 127,
 };
 
 #endif /* FSL_IMX8MM_H */
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Enabled GPIO controller emulation
Also updated the GPIO IRQ lines of iMX8MM

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/fsl-imx8mm.c         | 54 +++++++++++++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h | 14 ++++++++++
 2 files changed, 68 insertions(+)

diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
+        g_autofree char *name = g_strdup_printf("gpio%d", i + 1);
+        object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO);
+    }
+
     for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
         g_autofree char *name = g_strdup_printf("usdhc%d", i + 1);
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* GPIOs */
+    for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq_low;
+            unsigned int irq_high;
+        } gpio_table[FSL_IMX8MM_NUM_GPIOS] = {
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO1].addr,
+                FSL_IMX8MM_GPIO1_LOW_IRQ,
+                FSL_IMX8MM_GPIO1_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO2].addr,
+                FSL_IMX8MM_GPIO2_LOW_IRQ,
+                FSL_IMX8MM_GPIO2_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO3].addr,
+                FSL_IMX8MM_GPIO3_LOW_IRQ,
+                FSL_IMX8MM_GPIO3_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO4].addr,
+                FSL_IMX8MM_GPIO4_LOW_IRQ,
+                FSL_IMX8MM_GPIO4_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO5].addr,
+                FSL_IMX8MM_GPIO5_LOW_IRQ,
+                FSL_IMX8MM_GPIO5_HIGH_IRQ
+            },
+        };
+        object_property_set_bool(OBJECT(&s->gpio[i]), "has-edge-sel", true,
+                                 &error_abort);
+        object_property_set_bool(OBJECT(&s->gpio[i]), "has-upper-pin-irq",
+                                 true, &error_abort);
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpio[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpio[i]), 0, gpio_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0,
+                           qdev_get_gpio_in(gicdev, gpio_table[i].irq_low));
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1,
+                           qdev_get_gpio_in(gicdev, gpio_table[i].irq_high));
+    }
+
     /* USDHCs */
     for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_CCM:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
+        case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 
 #include "cpu.h"
 #include "hw/char/imx_serial.h"
+#include "hw/gpio/imx_gpio.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
 
 enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
+    FSL_IMX8MM_NUM_GPIOS        = 5,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
     FSL_IMX8MM_NUM_USDHCS       = 3,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMXGPIOState       gpio[FSL_IMX8MM_NUM_GPIOS];
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMX7SNVSState      snvs;
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
 
+    FSL_IMX8MM_GPIO1_LOW_IRQ  = 64,
+    FSL_IMX8MM_GPIO1_HIGH_IRQ = 65,
+    FSL_IMX8MM_GPIO2_LOW_IRQ  = 66,
+    FSL_IMX8MM_GPIO2_HIGH_IRQ = 67,
+    FSL_IMX8MM_GPIO3_LOW_IRQ  = 68,
+    FSL_IMX8MM_GPIO3_HIGH_IRQ = 69,
+    FSL_IMX8MM_GPIO4_LOW_IRQ  = 70,
+    FSL_IMX8MM_GPIO4_HIGH_IRQ = 71,
+    FSL_IMX8MM_GPIO5_LOW_IRQ  = 72,
+    FSL_IMX8MM_GPIO5_HIGH_IRQ = 73,
+
     FSL_IMX8MM_PCI_INTA_IRQ = 122,
     FSL_IMX8MM_PCI_INTB_IRQ = 123,
     FSL_IMX8MM_PCI_INTC_IRQ = 124,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

This can be used to test and debug I2C device drivers.
Added I2C interrupts

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  2 ++
 hw/arm/fsl-imx8mm.c         | 27 +++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  8 ++++++++
 3 files changed, 37 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
 config FSL_IMX8MM
     bool
     imply PCI_DEVICES
+    imply I2C_DEVICES
     select ARM_GIC
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
+    select IMX_I2C
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
+        g_autofree char *name = g_strdup_printf("i2c%d", i + 1);
+        object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C);
+    }
+
     for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
         g_autofree char *name = g_strdup_printf("gpio%d", i + 1);
         object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* I2Cs */
+    for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } i2c_table[FSL_IMX8MM_NUM_I2CS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C1].addr, FSL_IMX8MM_I2C1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C2].addr, FSL_IMX8MM_I2C2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C3].addr, FSL_IMX8MM_I2C3_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C4].addr, FSL_IMX8MM_I2C4_IRQ },
+        };
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->i2c[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, i2c_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0,
+                           qdev_get_gpio_in(gicdev, i2c_table[i].irq));
+    }
+
     /* GPIOs */
     for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
+        case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "cpu.h"
 #include "hw/char/imx_serial.h"
 #include "hw/gpio/imx_gpio.h"
+#include "hw/i2c/imx_i2c.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
 enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
     FSL_IMX8MM_NUM_GPIOS        = 5,
+    FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
     FSL_IMX8MM_NUM_USDHCS       = 3,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMX7SNVSState      snvs;
+    IMXI2CState        i2c[FSL_IMX8MM_NUM_I2CS];
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
 
+    FSL_IMX8MM_I2C1_IRQ     = 35,
+    FSL_IMX8MM_I2C2_IRQ     = 36,
+    FSL_IMX8MM_I2C3_IRQ     = 37,
+    FSL_IMX8MM_I2C4_IRQ     = 38,
+
     FSL_IMX8MM_GPIO1_LOW_IRQ  = 64,
     FSL_IMX8MM_GPIO1_HIGH_IRQ = 65,
     FSL_IMX8MM_GPIO2_LOW_IRQ  = 66,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of ECSPI in iMX8MM
Added SPI IRQ lines

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/fsl-imx8mm.c         | 26 ++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  7 +++++++
 2 files changed, 33 insertions(+)

diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
+        g_autofree char *name = g_strdup_printf("spi%d", i + 1);
+        object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI);
+    }
+
     object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
     object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
                             TYPE_FSL_IMX8M_PCIE_PHY);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                            qdev_get_gpio_in(gicdev, usdhc_table[i].irq));
     }
 
+    /* ECSPIs */
+    for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } spi_table[FSL_IMX8MM_NUM_ECSPIS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI1].addr, FSL_IMX8MM_ECSPI1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI2].addr, FSL_IMX8MM_ECSPI2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI3].addr, FSL_IMX8MM_ECSPI3_IRQ },
+        };
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->spi[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, spi_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0,
+                           qdev_get_gpio_in(gicdev, spi_table[i].irq));
+    }
+
     /* SNVS */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
+        case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3:
         case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci-host/designware.h"
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
+#include "hw/ssi/imx_spi.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
 
 enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
+    FSL_IMX8MM_NUM_ECSPIS       = 3,
     FSL_IMX8MM_NUM_GPIOS        = 5,
     FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMX7SNVSState      snvs;
+    IMXSPIState        spi[FSL_IMX8MM_NUM_ECSPIS];
     IMXI2CState        i2c[FSL_IMX8MM_NUM_I2CS];
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
 
+    FSL_IMX8MM_ECSPI1_IRQ   = 31,
+    FSL_IMX8MM_ECSPI2_IRQ   = 32,
+    FSL_IMX8MM_ECSPI3_IRQ   = 33,
+
     FSL_IMX8MM_I2C1_IRQ     = 35,
     FSL_IMX8MM_I2C2_IRQ     = 36,
     FSL_IMX8MM_I2C3_IRQ     = 37,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of WDT in iMX8MM
Added WDT IRQ lines

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 28 ++++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  7 +++++++
 3 files changed, 36 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
+    select WDT_IMX2
 
 config FSL_IMX8MM_EVK
     bool
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) {
+        g_autofree char *name = g_strdup_printf("wdt%d", i);
+        object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT);
+    }
+
     object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
     object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
                             TYPE_FSL_IMX8M_PCIE_PHY);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0,
                     fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr);
 
+    /* Watchdogs */
+    for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } wdog_table[FSL_IMX8MM_NUM_WDTS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG1].addr, FSL_IMX8MM_WDOG1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG2].addr, FSL_IMX8MM_WDOG2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG3].addr, FSL_IMX8MM_WDOG3_IRQ },
+        };
+
+        object_property_set_bool(OBJECT(&s->wdt[i]), "pretimeout-support",
+                                 true, &error_abort);
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->wdt[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, wdog_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0,
+                           qdev_get_gpio_in(gicdev, wdog_table[i].irq));
+    }
+
     /* PCIe */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_SNVS_HP:
         case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
         case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3:
+        case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3:
             /* device implemented and treated above */
             break;
 
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
 #include "hw/ssi/imx_spi.h"
+#include "hw/watchdog/wdt_imx2.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
     FSL_IMX8MM_NUM_USDHCS       = 3,
+    FSL_IMX8MM_NUM_WDTS         = 3,
 };
 
 struct FslImx8mmState {
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
+    IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
 };
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_GPIO5_LOW_IRQ  = 72,
     FSL_IMX8MM_GPIO5_HIGH_IRQ = 73,
 
+    FSL_IMX8MM_WDOG1_IRQ    = 78,
+    FSL_IMX8MM_WDOG2_IRQ    = 79,
+    FSL_IMX8MM_WDOG3_IRQ    = 10,
+
     FSL_IMX8MM_PCI_INTA_IRQ = 122,
     FSL_IMX8MM_PCI_INTB_IRQ = 123,
     FSL_IMX8MM_PCI_INTC_IRQ = 124,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of GPT in iMX8MM
Added GPT IRQ lines

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 54 +++++++++++++++++++++++++++++++++++++
 hw/timer/imx_gpt.c          | 26 ++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h | 11 ++++++++
 include/hw/timer/imx_gpt.h  |  2 ++
 5 files changed, 94 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select FSL_IMX8MP_CCM
     select IMX
     select IMX_I2C
+    select OR_IRQ
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) {
+        g_autofree char *name = g_strdup_printf("gpt%d", i + 1);
+        object_initialize_child(obj, name, &s->gpt[i], TYPE_IMX8MM_GPT);
+    }
+    object_initialize_child(obj, "gpt5-gpt6-irq", &s->gpt5_gpt6_irq,
+                            TYPE_OR_IRQ);
+
     for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
         g_autofree char *name = g_strdup_printf("i2c%d", i + 1);
         object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* GPTs */
+    object_property_set_int(OBJECT(&s->gpt5_gpt6_irq), "num-lines", 2,
+                            &error_abort);
+    if (!qdev_realize(DEVICE(&s->gpt5_gpt6_irq), NULL, errp)) {
+        return;
+    }
+
+    qdev_connect_gpio_out(DEVICE(&s->gpt5_gpt6_irq), 0,
+                          qdev_get_gpio_in(gicdev, FSL_IMX8MM_GPT5_GPT6_IRQ));
+
+    for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) {
+        hwaddr gpt_addrs[FSL_IMX8MM_NUM_GPTS] = {
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT1].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT2].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT3].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT4].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT5].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT6].addr,
+        };
+
+        s->gpt[i].ccm = IMX_CCM(&s->ccm);
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpt[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpt[i]), 0, gpt_addrs[i]);
+
+        if (i < FSL_IMX8MM_NUM_GPTS - 2) {
+            static const unsigned int gpt_irqs[FSL_IMX8MM_NUM_GPTS - 2] = {
+                FSL_IMX8MM_GPT1_IRQ,
+                FSL_IMX8MM_GPT2_IRQ,
+                FSL_IMX8MM_GPT3_IRQ,
+                FSL_IMX8MM_GPT4_IRQ,
+            };
+
+            sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0,
+                               qdev_get_gpio_in(gicdev, gpt_irqs[i]));
+        } else {
+            int irq = i - FSL_IMX8MM_NUM_GPTS + 2;
+
+            sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0,
+                               qdev_get_gpio_in(DEVICE(&s->gpt5_gpt6_irq), irq));
+        }
+    }
+
     /* I2Cs */
     for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
+        case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6:
         case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3:
         case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/imx_gpt.c
+++ b/hw/timer/imx_gpt.c
@@ -XXX,XX +XXX,XX @@
  * Originally written by Hans Jiang
  * Updated by Peter Chubb
  * Updated by Jean-Christophe Dubois <jcd@tribudubois.net>
+ * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com>
  *
  * This code is licensed under GPL version 2 or later.  See
  * the COPYING file in the top-level directory.
@@ -XXX,XX +XXX,XX @@ static const IMXClk imx8mp_gpt_clocks[] = {
     CLK_NONE,      /* 111 not defined */
 };
 
+static const IMXClk imx8mm_gpt_clocks[] = {
+    CLK_NONE,      /* 000 No clock source */
+    CLK_IPG,       /* 001 ipg_clk, 532MHz */
+    CLK_IPG_HIGH,  /* 010 ipg_clk_highfreq */
+    CLK_EXT,       /* 011 External clock */
+    CLK_32k,       /* 100 ipg_clk_32k */
+    CLK_HIGH,      /* 101 ipg_clk_16M */
+    CLK_NONE,      /* 110 not defined */
+    CLK_NONE,      /* 111 not defined */
+};
+
 /* Must be called from within ptimer_transaction_begin/commit block */
 static void imx_gpt_set_freq(IMXGPTState *s)
 {
@@ -XXX,XX +XXX,XX @@ static void imx8mp_gpt_init(Object *obj)
     s->clocks = imx8mp_gpt_clocks;
 }
 
+static void imx8mm_gpt_init(Object *obj)
+{
+    IMXGPTState *s = IMX_GPT(obj);
+
+    s->clocks = imx8mm_gpt_clocks;
+}
+
 static const TypeInfo imx25_gpt_info = {
     .name = TYPE_IMX25_GPT,
     .parent = TYPE_SYS_BUS_DEVICE,
@@ -XXX,XX +XXX,XX @@ static const TypeInfo imx8mp_gpt_info = {
     .instance_init = imx8mp_gpt_init,
 };
 
+static const TypeInfo imx8mm_gpt_info = {
+    .name = TYPE_IMX8MM_GPT,
+    .parent = TYPE_IMX25_GPT,
+    .instance_init = imx8mm_gpt_init,
+};
+
 static void imx_gpt_register_types(void)
 {
     type_register_static(&imx25_gpt_info);
@@ -XXX,XX +XXX,XX @@ static void imx_gpt_register_types(void)
     type_register_static(&imx6ul_gpt_info);
     type_register_static(&imx7_gpt_info);
     type_register_static(&imx8mp_gpt_info);
+    type_register_static(&imx8mm_gpt_info);
 }
 
 type_init(imx_gpt_register_types)
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
+#include "hw/or-irq.h"
 #include "hw/pci-host/designware.h"
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
 #include "hw/ssi/imx_spi.h"
+#include "hw/timer/imx_gpt.h"
 #include "hw/watchdog/wdt_imx2.h"
 #include "qom/object.h"
 #include "qemu/units.h"
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
     FSL_IMX8MM_NUM_ECSPIS       = 3,
     FSL_IMX8MM_NUM_GPIOS        = 5,
+    FSL_IMX8MM_NUM_GPTS         = 6,
     FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMXGPTState        gpt[FSL_IMX8MM_NUM_GPTS];
     IMXGPIOState       gpio[FSL_IMX8MM_NUM_GPIOS];
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
+    OrIRQState         gpt5_gpt6_irq;
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_I2C3_IRQ     = 37,
     FSL_IMX8MM_I2C4_IRQ     = 38,
 
+    FSL_IMX8MM_GPT1_IRQ      = 55,
+    FSL_IMX8MM_GPT2_IRQ      = 54,
+    FSL_IMX8MM_GPT3_IRQ      = 53,
+    FSL_IMX8MM_GPT4_IRQ      = 52,
+    FSL_IMX8MM_GPT5_GPT6_IRQ = 51,
+
     FSL_IMX8MM_GPIO1_LOW_IRQ  = 64,
     FSL_IMX8MM_GPIO1_HIGH_IRQ = 65,
     FSL_IMX8MM_GPIO2_LOW_IRQ  = 66,
diff --git a/include/hw/timer/imx_gpt.h b/include/hw/timer/imx_gpt.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/timer/imx_gpt.h
+++ b/include/hw/timer/imx_gpt.h
@@ -XXX,XX +XXX,XX @@
  * Originally written by Hans Jiang
  * Updated by Peter Chubb
  * Updated by Jean-Christophe Dubois <jcd@tribudubois.net>
+ * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -XXX,XX +XXX,XX @@
 #define TYPE_IMX6UL_GPT "imx6ul.gpt"
 #define TYPE_IMX7_GPT "imx7.gpt"
 #define TYPE_IMX8MP_GPT "imx8mp.gpt"
+#define TYPE_IMX8MM_GPT "imx8mm.gpt"
 
 #define TYPE_IMX_GPT TYPE_IMX25_GPT
 
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of ENET ethernet controller in iMX8MM
Enables testing and debugging of network dependent drivers
Added ENET MAC IRQ lines

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 24 ++++++++++++++++++++++++
 hw/arm/imx8mm-evk.c         |  1 +
 include/hw/arm/fsl-imx8mm.h | 10 +++++++++-
 4 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
+    select IMX_FEC
     select IMX_I2C
     select OR_IRQ
     select SDHCI
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT);
     }
 
+    object_initialize_child(obj, "eth0", &s->enet, TYPE_IMX_ENET);
+
     object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
     object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
                             TYPE_FSL_IMX8M_PCIE_PHY);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                            qdev_get_gpio_in(gicdev, spi_table[i].irq));
     }
 
+    /* ENET1 */
+    object_property_set_uint(OBJECT(&s->enet), "phy-num", s->phy_num,
+                             &error_abort);
+    object_property_set_uint(OBJECT(&s->enet), "tx-ring-num", 3, &error_abort);
+    qemu_configure_nic_device(DEVICE(&s->enet), true, NULL);
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->enet), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->enet), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_ENET1].addr);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 0,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_ENET1_MAC_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 1,
+                       qdev_get_gpio_in(gicdev, FSL_IMX6_ENET1_MAC_1588_IRQ));
+
     /* SNVS */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
         case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6:
         case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3:
+        case FSL_IMX8MM_ENET1:
         case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     }
 }
 
+static const Property fsl_imx8mm_properties[] = {
+    DEFINE_PROP_UINT32("fec1-phy-num", FslImx8mmState, phy_num, 0),
+    DEFINE_PROP_BOOL("fec1-phy-connected", FslImx8mmState, phy_connected, true),
+};
+
 static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
 
+    device_class_set_props(dc, fsl_imx8mm_properties);
     dc->realize = fsl_imx8mm_realize;
 
     dc->desc = "i.MX 8MM SoC";
diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/imx8mm-evk.c
+++ b/hw/arm/imx8mm-evk.c
@@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine)
 
     s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine),
                                          "soc", &error_fatal, NULL));
+    object_property_set_uint(OBJECT(s), "fec1-phy-num", 1, &error_fatal);
     sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal);
 
     memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START,
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
-#include "hw/or-irq.h"
+#include "hw/net/imx_fec.h"
+#include "hw/core/or-irq.h"
 #include "hw/pci-host/designware.h"
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXI2CState        i2c[FSL_IMX8MM_NUM_I2CS];
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
+    IMXFECState        enet;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
     IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
     OrIRQState         gpt5_gpt6_irq;
+
+    uint32_t           phy_num;
+    bool               phy_connected;
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_WDOG2_IRQ    = 79,
     FSL_IMX8MM_WDOG3_IRQ    = 10,
 
+    FSL_IMX8MM_ENET1_MAC_IRQ    = 118,
+    FSL_IMX6_ENET1_MAC_1588_IRQ = 121,
+
     FSL_IMX8MM_PCI_INTA_IRQ = 122,
     FSL_IMX8MM_PCI_INTB_IRQ = 123,
     FSL_IMX8MM_PCI_INTC_IRQ = 124,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of USB on iMX8MM
Enables testing and debugging of USB drivers

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 27 +++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  6 ++++++
 3 files changed, 34 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
+    select USB_DWC3
     select WDT_IMX2
 
 config FSL_IMX8MM_EVK
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) {
+        g_autofree char *name = g_strdup_printf("usb%d", i);
+        object_initialize_child(obj, name, &s->usb[i], TYPE_USB_DWC3);
+    }
+
     for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
         g_autofree char *name = g_strdup_printf("spi%d", i + 1);
         object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                            qdev_get_gpio_in(gicdev, usdhc_table[i].irq));
     }
 
+    /* USBs */
+    for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } usb_table[FSL_IMX8MM_NUM_USBS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USB1].addr, FSL_IMX8MM_USB1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USB2].addr, FSL_IMX8MM_USB2_IRQ },
+        };
+
+        qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p2", 1);
+        qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p3", 1);
+        qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "slots", 2);
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->usb[i]), errp)) {
+            return;
+        }
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, usb_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i].sysbus_xhci), 0,
+                           qdev_get_gpio_in(gicdev, usb_table[i].irq));
+    }
+
     /* ECSPIs */
     for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_OCRAM:
         case FSL_IMX8MM_SNVS_HP:
         case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
+        case FSL_IMX8MM_USB1 ... FSL_IMX8MM_USB2:
         case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3:
         case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3:
             /* device implemented and treated above */
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/sd/sdhci.h"
 #include "hw/ssi/imx_spi.h"
 #include "hw/timer/imx_gpt.h"
+#include "hw/usb/hcd-dwc3.h"
 #include "hw/watchdog/wdt_imx2.h"
 #include "qom/object.h"
 #include "qemu/units.h"
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
+    FSL_IMX8MM_NUM_USBS         = 2,
     FSL_IMX8MM_NUM_USDHCS       = 3,
     FSL_IMX8MM_NUM_WDTS         = 3,
 };
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXFECState        enet;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
     IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
+    USBDWC3            usb[FSL_IMX8MM_NUM_USBS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
     OrIRQState         gpt5_gpt6_irq;
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_I2C3_IRQ     = 37,
     FSL_IMX8MM_I2C4_IRQ     = 38,
 
+    FSL_IMX8MM_USB1_IRQ     = 40,
+    FSL_IMX8MM_USB2_IRQ     = 41,
+
     FSL_IMX8MM_GPT1_IRQ      = 55,
     FSL_IMX8MM_GPT2_IRQ      = 54,
     FSL_IMX8MM_GPT3_IRQ      = 53,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Added script that would validate the iMX8MM emulation by checking the
linux console log. If it succeeds, it will return:-

ok 1 test_imx8mm_evk.Imx8mmEvkMachine.test_aarch64_imx8mm_evk_usdhc

Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
[PMM: Add missing blank lines that flake8 wants]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS                                 |  1 +
 tests/functional/aarch64/meson.build        |  2 +
 tests/functional/aarch64/test_imx8mm_evk.py | 69 +++++++++++++++++++++
 3 files changed, 72 insertions(+)
 create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/arm/fsl-imx8mm.c
 F: hw/arm/imx8mm-evk.c
 F: include/hw/arm/fsl-imx8mm.h
 F: docs/system/arm/imx8m.rst
+F: tests/functional/aarch64/test_imx8mm_evk.py
 
 MCIMX8MP-EVK / i.MX8MP
 M: Bernhard Beschow <shentey@gmail.com>
diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/tests/functional/aarch64/meson.build
+++ b/tests/functional/aarch64/meson.build
@@ -XXX,XX +XXX,XX @@ test_aarch64_timeouts = {
   'aspeed_ast2700a2' : 600,
   'aspeed_ast2700fc' : 600,
   'device_passthrough' : 720,
+  'imx8mm_evk' : 240,
   'imx8mp_evk' : 240,
   'raspi4' : 480,
   'reverse_debug' : 180,
@@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [
   'aspeed_ast2700fc',
   'device_passthrough',
   'hotplug_pci',
+  'imx8mm_evk',
   'imx8mp_evk',
   'kvm',
   'multiprocess',
diff --git a/tests/functional/aarch64/test_imx8mm_evk.py b/tests/functional/aarch64/test_imx8mm_evk.py
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/functional/aarch64/test_imx8mm_evk.py
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Functional test that boots a Linux kernel and checks the console
+#
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+from qemu_test import LinuxKernelTest, Asset
+
+
+class Imx8mmEvkMachine(LinuxKernelTest):
+
+    ASSET_IMAGE = Asset(
+        ('https://cloud.debian.org/images/cloud/bookworm/20231210-1590/'
+         'debian-12-generic-arm64-20231210-1590.tar.xz'),
+        '7ebf1577b32d5af6204df74b54ca2e4675de9b5a9fa14f3ff70b88eeb7b3b359')
+
+    KERNEL_OFFSET = 0x51000000
+    KERNEL_SIZE = 32622528
+    INITRD_OFFSET = 0x76000000
+    INITRD_SIZE = 30987766
+    DTB_OFFSET = 0x64DB5000
+    DTB_SIZE = 36812
+
+    def extract(self, in_path, out_path, offset, size):
+        try:
+            with open(in_path, "rb") as source:
+                source.seek(offset)
+                data = source.read(size)
+            with open(out_path, "wb") as target:
+                target.write(data)
+        except (IOError, ValueError) as e:
+            self.log.error(f"Failed to extract {out_path}: {e}")
+            raise
+
+    def setUp(self):
+        super().setUp()
+
+        self.image_path = self.scratch_file("disk.raw")
+        self.kernel_path = self.scratch_file("linux")
+        self.initrd_path = self.scratch_file("initrd.zstd")
+        self.dtb_path = self.scratch_file("imx8mm-evk.dtb")
+
+        self.archive_extract(self.ASSET_IMAGE)
+        self.extract(self.image_path, self.kernel_path,
+                     self.KERNEL_OFFSET, self.KERNEL_SIZE)
+        self.extract(self.image_path, self.initrd_path,
+                     self.INITRD_OFFSET, self.INITRD_SIZE)
+        self.extract(self.image_path, self.dtb_path,
+                     self.DTB_OFFSET, self.DTB_SIZE)
+
+    def test_aarch64_imx8mm_evk_usdhc(self):
+        self.require_accelerator("tcg")
+        self.set_machine('imx8mm-evk')
+        self.vm.set_console(console_index=1)
+        self.vm.add_args('-m', '2G',
+                         '-smp', '4',
+                         '-kernel', self.kernel_path,
+                         '-initrd', self.initrd_path,
+                         '-dtb', self.dtb_path,
+                         '-append', 'root=/dev/mmcblk2p1',
+                         '-drive', f'file={self.image_path},if=sd,bus=2,'
+                                    'format=raw,id=mmcblk2,snapshot=on')
+
+        self.vm.launch()
+        self.wait_for_console_pattern('Welcome to ')
+
+
+if __name__ == '__main__':
+    LinuxKernelTest.main()
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

As mentioned by Richard in [*]:

We don't actually need any specific endianness here, because
  every byte has the same value.  So we could simply drop MO_TE.
  That would produce a store in host-endianness, which will be
  fractionally more efficient on some hosts.

[*] https://lore.kernel.org/qemu-devel/d64d3576-9188-4e74-afdc-3492c9feb8e0@linaro.org/

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260414005348.4767-2-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-a64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -XXX,XX +XXX,XX @@ static uint64_t set_step_tags(CPUARMState *env, uint64_t toaddr,
          * the page dirty and will use the fast path.
          */
         uint64_t repldata = data * 0x0101010101010101ULL;
-        MemOpIdx oi16 = make_memop_idx(MO_TE | MO_128, memidx);
+        MemOpIdx oi16 = make_memop_idx(MO_128, memidx);
         cpu_st16_mmu(env, toaddr, int128_make128(repldata, repldata), oi16, ra);
         mte_mops_set_tags(env, toaddr, 16, *mtedesc);
         return 16;
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Extract the implicit MO_TE definition in order to replace
it in the next commit.

Mechanical change using:

$ for n in UW UL UQ UO SW SL SQ; do \
      sed -i -e "s/MO_TE$n/MO_TE | MO_$n/" \
           $(git grep -l MO_TE$n target/arm); \
    done

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-3-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c   |  6 +--
 target/arm/tcg/mve_helper.c | 79 ++++++++++++++++++++-----------------
 2 files changed, 45 insertions(+), 40 deletions(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
 
     /* Note that these stores can throw exceptions on MPU faults */
     ARMMMUIdx mmu_idx = arm_mmu_idx(env);
-    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+    MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN,
                                  arm_to_core_mmu_idx(mmu_idx));
     cpu_stl_mmu(env, sp, nextinst, oi, GETPC());
     cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC());
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
     bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK;
     uintptr_t ra = GETPC();
     ARMMMUIdx mmu_idx = arm_mmu_idx(env);
-    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+    MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN,
                                  arm_to_core_mmu_idx(mmu_idx));
 
     assert(env->v7m.secure);
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
     ARMCPU *cpu = env_archcpu(env);
     uintptr_t ra = GETPC();
     ARMMMUIdx mmu_idx = arm_mmu_idx(env);
-    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+    MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN,
                                  arm_to_core_mmu_idx(mmu_idx));
 
     /* fptr is the value of Rn, the frame pointer we load the FP regs from */
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
     }
 
 DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t)
-DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t)
-DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t)
+DO_VLDR(vldrh, MO_TE | MO_UW, 2, uint16_t, ldw, 2, uint16_t)
+DO_VLDR(vldrw, MO_TE | MO_UL, 4, uint32_t, ldl, 4, uint32_t)
 
 DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t)
-DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t)
-DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t)
+DO_VSTR(vstrh, MO_TE | MO_UW, 2, stw, 2, uint16_t)
+DO_VSTR(vstrw, MO_TE | MO_UL, 4, stl, 4, uint32_t)
 
 DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t)
 DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t)
 DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t)
 DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t)
-DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t)
-DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t)
+DO_VLDR(vldrh_sw, MO_TE | MO_SW, 2, int16_t, ldw, 4, int32_t)
+DO_VLDR(vldrh_uw, MO_TE | MO_UW, 2, uint16_t, ldw, 4, uint32_t)
 
 DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t)
 DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t)
-DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
+DO_VSTR(vstrh_w, MO_TE | MO_UW, 2, stw, 4, int32_t)
 
 #undef DO_VLDR
 #undef DO_VSTR
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
 
 DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4,
+           int32_t, uint32_t, ADDR_ADD, false)
 
 DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
+           uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
+           uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
+           uint32_t, uint32_t, ADDR_ADD, false)
 DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4,
            int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2,
+DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
            uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
            uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4,
+DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
            uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false)
 DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false)
 
-DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
+DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
+           uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
-DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true)
+DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
 
 /*
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-4-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-5-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 43 +++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 23 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
+        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
+        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
 
 DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4,
-           int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false)
 
 DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
-           uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
-           uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
-           uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
 DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_sw, MO_SW, int16_t, ldw, 4,
            int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
+DO_VLDR_SG(vldrh_sg_os_uh, MO_UW, uint16_t, ldw, 2,
            uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_uw, MO_UW, uint16_t, ldw, 4,
            uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
+DO_VLDR_SG(vldrw_sg_os_uw, MO_UL, uint32_t, ldl, 4,
            uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrw_sg_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, false)
 DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false)
 
-DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
+DO_VSTR_SG(vstrh_sg_os_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrh_sg_os_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrw_sg_os_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
-           uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
-DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true)
+DO_VSTR_SG(vstrw_sg_wb_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
 
 /*
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-6-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/internals.h      | 6 ++++++
 target/arm/tcg/mve_helper.c | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/target/arm/internals.h b/target/arm/internals.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -XXX,XX +XXX,XX @@
 #include "exec/hwaddr.h"
 #include "exec/vaddr.h"
 #include "exec/breakpoint.h"
+#include "exec/memop.h"
 #include "accel/tcg/tb-cpu-state.h"
 #include "hw/core/registerfields.h"
 #include "tcg/tcg-gvec-desc.h"
@@ -XXX,XX +XXX,XX @@
 #define BANK_HYP    6
 #define BANK_MON    7
 
+static inline MemOp mo_endian(CPUARMState *env)
+{
+    return EX_TBFLAG_ANY(env->hflags, BE_DATA) ? MO_BE : MO_LE;
+}
+
 static inline int arm_env_mmu_index(CPUARMState *env)
 {
     return EX_TBFLAG_ANY(env->hflags, MMUIDX);
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-7-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 47 +++++++++++++++++++++++--------------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned b, e;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         /*                                                              \
          * R_SXTM allows the dest reg to become UNKNOWN for abandoned   \
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
         uint16_t mask = mve_element_mask(env);                          \
         unsigned b, e;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         for (b = 0, e = 0; b < 16; b += ESIZE, e++) {                   \
             if (mask & (1 << b)) {                                      \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-8-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/meson.build  | 3 ++-
 target/arm/tcg/mve_helper.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c'))
 arm_ss.add(files(
   'cpu32.c',
   'm_helper.c',
-  'mve_helper.c',
 ))
 
 arm_ss.add(when: 'TARGET_AARCH64', if_true: files(
@@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add(
   'debug.c',
   'hflags.c',
   'gengvec.c',
+  'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
   'psci.c',
@@ -XXX,XX +XXX,XX @@ arm_user_ss.add(
   'debug.c',
   'gengvec.c',
   'hflags.c',
+  'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
   'tlb_helper.c',
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "helper-mve.h"
 #include "internals.h"
 #include "vec_internal.h"
-#include "accel/tcg/cpu-ldst.h"
+#include "accel/tcg/cpu-ldst-common.h"
 #include "tcg/tcg.h"
 #include "fpu/softfloat.h"
 #include "crypto/clmul.h"
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-9-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-10-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c  | 2 +-
 target/arm/tcg/meson.build | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/log.h"
 #include "exec/page-protection.h"
 #ifdef CONFIG_TCG
-#include "accel/tcg/cpu-ldst.h"
+#include "accel/tcg/cpu-ldst-common.h"
 #include "semihosting/common-semi.h"
 #endif
 #if !defined(CONFIG_USER_ONLY)
diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c'))
 
 arm_ss.add(files(
   'cpu32.c',
-  'm_helper.c',
 ))
 
 arm_ss.add(when: 'TARGET_AARCH64', if_true: files(
@@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add(
   'debug.c',
   'hflags.c',
   'gengvec.c',
+  'm_helper.c',
   'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
@@ -XXX,XX +XXX,XX @@ arm_user_ss.add(
   'debug.c',
   'gengvec.c',
   'hflags.c',
+  'm_helper.c',
   'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
-- 
2.43.0

From: Thomas Huth <thuth@redhat.com>

When writing to this register, QEMU currently aborts:

$ echo "readl 0x10000018" | ./qemu-system-arm -audiodev none,id=snd0 \
    -M integratorcp,accel=qtest,audiodev=snd0 -display none -qtest stdio
 [I 0.000000] OPENED
 [R +0.001907] readl 0x10000018
 qemu: hardware error: integratorcm_read: CM_LMBUSCNT
 [...]
 Aborted                    (core dumped)

This is bad, a guest should ideally never be able to kill QEMU like this.

Now, according to the "Intergrator/CP User Guide" from:

https://developer.arm.com/documentation/dui0159/b/porting-integrator-ap-and-im-pd1/registers

"The Integrator/AP CM_LMBUSCNT has been removed."

That means this register does not seem to be implemented on real CP boards
at all, only for older AP boards. Thus it should be fine if we simply
ignore this register in QEMU and handle it like all other unimplemented
registers in the "default" handler of the case statement.

Resolves: https://gitlab.com/qemu-project/qemu/-/work_items/3407
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260420064933.64765-1-thuth@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/integratorcp.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/integratorcp.c
+++ b/hw/arm/integratorcp.c
@@ -XXX,XX +XXX,XX @@ static uint64_t integratorcm_read(void *opaque, hwaddr offset,
         } else {
             return s->cm_lock;
         }
-    case 6: /* CM_LMBUSCNT */
-        /* ??? High frequency timer.  */
-        hw_error("integratorcm_read: CM_LMBUSCNT");
     case 7: /* CM_AUXOSC */
         return s->cm_auxosc;
     case 8: /* CM_SDRAM */
-- 
2.43.0

include/hw/arm/primecell.h used to be more expansive, but now the
only thing it defines is the ARM_SYSCTL_GPIO_* constants for the GPIO
lines for the arm-sysctl system-control device used on the Realview,
Versatile and Versatile Express boards.

Replace it with a header file specific to that device.

virt.c and vmapple.c included primecell.h despite not using the
constants it defined; there we can simply drop the include entirely.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260416172627.690396-1-peter.maydell@linaro.org
---
 MAINTAINERS                  |  2 +-
 hw/arm/realview.c            |  2 +-
 hw/arm/vexpress.c            |  2 +-
 hw/arm/virt.c                |  1 -
 hw/misc/arm_sysctl.c         |  2 +-
 hw/vmapple/vmapple.c         |  1 -
 include/hw/arm/primecell.h   | 12 ------------
 include/hw/misc/arm_sysctl.h | 16 ++++++++++++++++
 8 files changed, 20 insertions(+), 18 deletions(-)
 delete mode 100644 include/hw/arm/primecell.h
 create mode 100644 include/hw/misc/arm_sysctl.h

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/ssi/pl022.c
 F: include/hw/ssi/pl022.h
 F: hw/rtc/pl031.c
 F: include/hw/rtc/pl031.h
-F: include/hw/arm/primecell.h
 F: hw/timer/cmsdk-apb-timer.c
 F: include/hw/timer/cmsdk-apb-timer.h
 F: tests/qtest/cmsdk-apb-timer-test.c
@@ -XXX,XX +XXX,XX @@ F: hw/*/versatile*
 F: hw/i2c/arm_sbcon_i2c.c
 F: include/hw/i2c/arm_sbcon_i2c.h
 F: hw/misc/arm_sysctl.c
+F: include/hw/misc/arm_sysctl.h
 F: docs/system/arm/versatile.rst
 
 Virt
diff --git a/hw/arm/realview.c b/hw/arm/realview.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/realview.c
+++ b/hw/arm/realview.c
@@ -XXX,XX +XXX,XX @@
 #include "target/arm/cpu.h"
 #include "hw/core/sysbus.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/arm/machines-qom.h"
 #include "hw/core/split-irq.h"
+#include "hw/misc/arm_sysctl.h"
 #include "hw/net/lan9118.h"
 #include "hw/net/smc91c111.h"
 #include "hw/pci/pci.h"
diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/vexpress.c
+++ b/hw/arm/vexpress.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/datadir.h"
 #include "hw/core/sysbus.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/arm/machines-qom.h"
+#include "hw/misc/arm_sysctl.h"
 #include "hw/net/lan9118.h"
 #include "hw/i2c/i2c.h"
 #include "net/net.h"
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -XXX,XX +XXX,XX @@
 #include "monitor/qdev.h"
 #include "hw/core/sysbus.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/arm/virt.h"
 #include "hw/arm/machines-qom.h"
 #include "hw/block/flash.h"
diff --git a/hw/misc/arm_sysctl.c b/hw/misc/arm_sysctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/arm_sysctl.c
+++ b/hw/misc/arm_sysctl.c
@@ -XXX,XX +XXX,XX @@
 #include "system/runstate.h"
 #include "qemu/bitops.h"
 #include "hw/core/sysbus.h"
+#include "hw/misc/arm_sysctl.h"
 #include "migration/vmstate.h"
-#include "hw/arm/primecell.h"
 #include "qemu/log.h"
 #include "qemu/module.h"
 #include "qom/object.h"
diff --git a/hw/vmapple/vmapple.c b/hw/vmapple/vmapple.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/vmapple/vmapple.c
+++ b/hw/vmapple/vmapple.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/core/sysbus.h"
 #include "hw/usb/usb.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/char/pl011.h"
 #include "hw/intc/arm_gic.h"
 #include "hw/intc/arm_gicv3_common.h"
diff --git a/include/hw/arm/primecell.h b/include/hw/arm/primecell.h
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/include/hw/arm/primecell.h
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-#ifndef PRIMECELL_H
-#define PRIMECELL_H
-
-/* Declarations for ARM PrimeCell based periperals.  */
-/* Also includes some devices that are currently only used by the
-   ARM boards.  */
-
-/* arm_sysctl GPIO lines */
-#define ARM_SYSCTL_GPIO_MMC_WPROT 0
-#define ARM_SYSCTL_GPIO_MMC_CARDIN 1
-
-#endif
diff --git a/include/hw/misc/arm_sysctl.h b/include/hw/misc/arm_sysctl.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/misc/arm_sysctl.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Status and system control registers for ARM RealView/Versatile boards.
+ *
+ * Copyright (c) Linaro Ltd
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef HW_MISC_ARM_SYSCTL_H
+#define HW_MISC_ARM_SYSCTL_H
+
+/* arm_sysctl inbound GPIO lines */
+#define ARM_SYSCTL_GPIO_MMC_WPROT 0
+#define ARM_SYSCTL_GPIO_MMC_CARDIN 1
+
+#endif
-- 
2.43.0

If we create a normally-AArch64 CPU and configure it with
aarch64=off, this will by default leave all the AArch64 ID register
values in its ARMISARegisters struct untouched.  That in turn means
that tests of cpu_isar_feature(aa64_something, cpu) will return true.

Until now we have had a design policy that you shouldn't check an
aa64_ feature unless you know that the CPU has AArch64; but this is
quite fragile as it's easy to forget and only causes a problem in the
corner case where AArch64 was turned off.  In particular, when we
extend the ability to disable AArch64 from only KVM to also TCG there
are many more aa64 feature check points which we would otherwise have
to audit for whether they needed to be guarded with a check on
ARM_FEATURE_AARCH64.

Instead, make the CPU realize function zero out all the 64-bit ID
registers if a TCG CPU doesn't have AArch64; this will make aa64_
feature tests generally return false.

We only do this for TCG because only TCG really needs it, and for
KVM it might be confusing to have QEMU's idea of the ID registers
be different from KVM's.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260416165353.589569-2-peter.maydell@linaro.org
---
 target/arm/cpu.c | 35 +++++++++++++++++++++++++++++++++++
 target/arm/cpu.h |  3 ++-
 2 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp)
     }
 }
 
+static void arm_clear_aarch64_idregs(ARMCPU *cpu)
+{
+    /* Zero out all the AArch64 ID registers in ARMISARegisters */
+    SET_IDREG(&cpu->isar, ID_AA64ISAR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64ISAR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64ISAR2, 0);
+    SET_IDREG(&cpu->isar, ID_AA64PFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64PFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64PFR2, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR2, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR3, 0);
+    SET_IDREG(&cpu->isar, ID_AA64DFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64DFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64AFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64AFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64ZFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64SMFR0, 0);
+}
+
 static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
     }
 #endif
 
+    /*
+     * A TCG aarch64=off CPU has no AArch64 at all, so we clear out the
+     * ID registers to avoid cpu_isar_feature(aa64_something, cpu) tests
+     * incorrectly returning true. We don't do this for other accelerators
+     * (which in practice means "for KVM", since no others have AArch32
+     * guest support) because from KVM's point of view the AArch64 ID
+     * registers still exist and must have their correct values. So we
+     * avoid clearing them out so that we don't have QEMU and KVM with
+     * different ideas of the ID registers.
+     */
+    if (tcg_enabled() && !arm_feature(env, ARM_FEATURE_AARCH64)) {
+        arm_clear_aarch64_idregs(cpu);
+    }
+
 #ifdef CONFIG_USER_ONLY
     /*
      * User mode relies on IC IVAU instructions to catch modification of
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
      * Note that if you add an ID register to the ARMISARegisters struct
      * you need to also update the 32-bit and 64-bit versions of the
      * kvm_arm_get_host_cpu_features() function to correctly populate the
-     * field by reading the value from the KVM vCPU.
+     * field by reading the value from the KVM vCPU. If it is an AArch64
+     * ID register then you also must update arm_clear_aarch64_idregs().
      */
     struct ARMISARegisters {
         uint32_t mvfr0;
-- 
2.43.0

Allow the 'aarch64=off' property, which is currently KVM-only, to
be set for TCG CPUs also.

Note that we don't permit it on the qemu-aarch64 user-mode binary:
this makes no sense as that executable can only handle AArch64
syscalls (and it would also assert at startup since it doesn't
compile in the A32-specific GDB xml files like arm-neon.xml).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Clément Chigot <chigot@adacore.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260416165353.589569-3-peter.maydell@linaro.org
---
 docs/system/arm/cpu-features.rst | 10 +++++----
 target/arm/cpu-features.h        |  5 +++++
 target/arm/cpu.c                 | 36 ++++++++++++++++++++++++++++----
 tests/qtest/arm-cpu-features.c   |  8 ++-----
 4 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/cpu-features.rst
+++ b/docs/system/arm/cpu-features.rst
@@ -XXX,XX +XXX,XX @@ not implement ARMv8-A, will not have the ``aarch64`` CPU property.
 QEMU's support may be limited for some CPU features, only partially
 supporting the feature or only supporting the feature under certain
 configurations.  For example, the ``aarch64`` CPU feature, which, when
-disabled, enables the optional AArch32 CPU feature, is only supported
-when using the KVM accelerator and when running on a host CPU type that
-supports the feature.  While ``aarch64`` currently only works with KVM,
-it could work with TCG.  CPU features that are specific to KVM are
+disabled, enables the optional AArch32 CPU feature, can only be set to
+``off`` on the TCG and KVM accelerators, and it cannot be set to
+``off`` under KVM unless running on a host CPU type that supports
+running guests in AArch32.
+
+CPU features that are inherently specific to KVM are
 prefixed with "kvm-" and are described in "KVM VCPU Features".
 
 CPU Feature Probing
diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL2) >= 2;
 }
 
+static inline bool isar_feature_aa64_aa32_el3(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL3) >= 2;
+}
+
 static inline bool isar_feature_aa64_ras(const ARMISARegisters *id)
 {
     return FIELD_EX64_IDREG(id, ID_AA64PFR0, RAS) != 0;
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp)
      * uniform execution state like do_interrupt.
      */
     if (value == false) {
-        if (!kvm_enabled() || !kvm_arm_aarch32_supported()) {
-            error_setg(errp, "'aarch64' feature cannot be disabled "
-                             "unless KVM is enabled and 32-bit EL1 "
-                             "is supported");
+        if (kvm_enabled()) {
+            if (!kvm_arm_aarch32_supported()) {
+                error_setg(errp, "'aarch64' feature cannot be disabled for KVM "
+                           "because this host does not support 32-bit EL1");
+                return;
+            }
+        } else if (tcg_enabled()) {
+#ifdef CONFIG_USER_ONLY
+            error_setg(errp, "'aarch64' feature cannot be disabled for "
+                       "usermode emulator qemu-aarch64; use qemu-arm instead");
+            return;
+#else
+            bool aa32_at_highest_el;
+            if (arm_feature(&cpu->env, ARM_FEATURE_EL3)) {
+                aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el3, cpu);
+            } else if (arm_feature(&cpu->env, ARM_FEATURE_EL2)) {
+                aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el2, cpu);
+            } else {
+                aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el1, cpu);
+            }
+
+            if (!aa32_at_highest_el) {
+                error_setg(errp, "'aarch64' feature cannot be disabled for "
+                           "this TCG CPU because it does not support 32-bit "
+                           "execution at its highest implemented exception "
+                           "level");
+                return;
+            }
+#endif
+        } else {
+            error_setg(errp, "'aarch64' feature cannot be disabled for "
+                       "this accelerator");
             return;
         }
         unset_feature(&cpu->env, ARM_FEATURE_AARCH64);
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data)
         sve_tests_default(qts, "max");
         pauth_tests_default(qts, "max");
 
-        /* Test that features that depend on KVM generate errors without. */
-        assert_error(qts, "max",
-                     "'aarch64' feature cannot be disabled "
-                     "unless KVM is enabled and 32-bit EL1 "
-                     "is supported",
-                     "{ 'aarch64': false }");
+        /* TCG allows us to turn off AArch64 on the 'max' CPU type */
+        assert_set_feature(qts, "max", "aarch64", false);
     }
 
     qtest_quit(qts);
-- 
2.43.0

Add a basic test of the TCG 'aarch64=off' functionality; this is the
same as our existing arm/test_virt test, but it runs the AArch32
guest kernel on qemu-system-aarch64 with -cpu max,aarch64=off.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260416165353.589569-4-peter.maydell@linaro.org
---
 tests/functional/aarch64/meson.build          |  1 +
 .../aarch64/test_virt_aarch64_off.py          | 37 +++++++++++++++++++
 2 files changed, 38 insertions(+)
 create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py

diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/tests/functional/aarch64/meson.build
+++ b/tests/functional/aarch64/meson.build
@@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [
   'tcg_plugins',
   'tuxrun',
   'virt',
+  'virt_aarch64_off',
   'virt_gpu',
   'virt_vbsa',
   'xen',
diff --git a/tests/functional/aarch64/test_virt_aarch64_off.py b/tests/functional/aarch64/test_virt_aarch64_off.py
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/functional/aarch64/test_virt_aarch64_off.py
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Functional test that boots an AArch32 Linux kernel and checks the console
+# on a TCG aarch64 CPU with aarch64=off. This is the same image etc
+# as we use in tests/functional/arm/test_virt.py.
+#
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+from qemu_test import LinuxKernelTest, Asset
+
+class ArmVirtMachine(LinuxKernelTest):
+
+    ASSET_KERNEL = Asset(
+        ('https://archives.fedoraproject.org/pub/archive/fedora/linux/'
+         'releases/29/Everything/armhfp/os/images/pxeboot/vmlinuz'),
+        '18dd5f1a9a28bd539f9d047f7c0677211bae528e8712b40ca5a229a4ad8e2591')
+
+    def test_arm_virt(self):
+        self.set_machine('virt')
+        # KVM aarch64=off requires a host CPU that supports it, so
+        # restrict the test to TCG only
+        self.require_accelerator('tcg')
+        self.vm.add_args('-cpu', 'max,aarch64=off')
+
+        kernel_path = self.ASSET_KERNEL.fetch()
+
+        self.vm.set_console()
+        kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
+                               'console=ttyAMA0')
+        self.vm.add_args('-kernel', kernel_path,
+                         '-append', kernel_command_line)
+        self.vm.launch()
+        console_pattern = 'Kernel command line: %s' % kernel_command_line
+        self.wait_for_console_pattern(console_pattern)
+
+if __name__ == '__main__':
+    LinuxKernelTest.main()
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

We introduce a datatype for a tolerance with respect to a given
cpreg migration issue. The tolerance applies to a given cpreg kvm index,
and can be of different types:
a) mismatch in cpreg indexes
- ToleranceNotOnBothEnds (cpreg index is allowed to be only present
  on one end)
- ToleranceOnlySrcTestValue (cpreg index is allowed to be only
  present in source if its value @mask field matches @value)
b) mismatch in cpreg values
- ToleranceDiffInMask (value differences are allowed only within a mask)
- ToleranceFieldLT (incoming field value must be less than a given value)
- ToleranceFieldGT (incoming field value must be greater than a given value)

A QLIST of such tolerances can be populated using a new helper:
arm_register_cpreg_mig_tolerance() and arm_cpu_match_cpreg_mig_tolerance()
allows to check whether a tolerance exists for a given kvm index and its
criterion is matched.

callers for those helpers will be introduced in subsequent patches.

Only registration of migration tolerances related to cpreg index
mismatch is currently allowed.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20260420140552.104369-2-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.c       | 82 ++++++++++++++++++++++++++++++++++++++++++
 target/arm/cpu.h       |  1 +
 target/arm/internals.h | 54 ++++++++++++++++++++++++++++
 3 files changed, 137 insertions(+)

diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook,
     QLIST_INSERT_HEAD(&cpu->el_change_hooks, entry, node);
 }
 
+static ARMCPRegMigTolerance *find_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx)
+{
+    ARMCPRegMigTolerance *t;
+    QLIST_FOREACH(t, &cpu->cpreg_mig_tolerances, node) {
+        if (t->kvmidx == kvmidx)  {
+            return t;
+        }
+    }
+    return NULL;
+}
+
+void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                      uint64_t mask, uint64_t value,
+                                      ARMCPRegMigToleranceType type)
+{
+    ARMCPRegMigTolerance *entry;
+
+    /* make sure the kvmidx has not tolerance already registered */
+    assert(!find_mig_tolerance(cpu, kvmidx));
+
+    assert(type == ToleranceNotOnBothEnds ||
+           type == ToleranceOnlySrcTestValue);
+
+    entry = g_new0(ARMCPRegMigTolerance, 1);
+
+    entry->kvmidx = kvmidx;
+    entry->mask = mask;
+    entry->value = value;
+    entry->type = type;
+
+    QLIST_INSERT_HEAD(&cpu->cpreg_mig_tolerances, entry, node);
+}
+
+bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                       uint64_t vmstate_value, uint64_t local_value,
+                                       ARMCPRegMigToleranceType type)
+{
+    ARMCPRegMigTolerance *t = find_mig_tolerance(cpu, kvmidx);
+    uint64_t diff, diff_outside_mask, field;
+
+    if (!t || t->type != type) {
+        return false;
+    }
+
+    if (type == ToleranceNotOnBothEnds) {
+        return true;
+    }
+
+    if (type == ToleranceOnlySrcTestValue &&
+        ((vmstate_value & t->mask) == t->value)) {
+        return true;
+    }
+
+    /* Need to check the mask */
+    diff = vmstate_value ^ local_value;
+    diff_outside_mask = diff & ~t->mask;
+
+    if (diff_outside_mask) {
+        /* there are differences outside of the mask */
+        return false;
+    }
+    if (type == ToleranceDiffInMask) {
+        /* differences only in the field, tolerance matched */
+        return true;
+    }
+    /* need to compare field value against authorized ones */
+    field = vmstate_value & t->mask;
+    if (type == ToleranceFieldLT && (field < t->value)) {
+        return true;
+    }
+    if (type == ToleranceFieldGT && (field > t->value)) {
+        return true;
+    }
+    return false;
+}
+
 static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque)
 {
     /* Reset a single ARMCPRegInfo register */
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj)
 
     QLIST_INIT(&cpu->pre_el_change_hooks);
     QLIST_INIT(&cpu->el_change_hooks);
+    QLIST_INIT(&cpu->cpreg_mig_tolerances);
 
 #ifdef CONFIG_USER_ONLY
 # ifdef TARGET_AARCH64
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
     ARMELChangeHook *hook, *next;
+    ARMCPRegMigTolerance *t, *n;
 
     g_hash_table_destroy(cpu->cp_regs);
 
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj)
         QLIST_REMOVE(hook, node);
         g_free(hook);
     }
+    QLIST_FOREACH_SAFE(t, &cpu->cpreg_mig_tolerances, node, n) {
+        QLIST_REMOVE(t, node);
+        g_free(t);
+    }
 #ifndef CONFIG_USER_ONLY
     if (cpu->pmu_timer) {
         timer_free(cpu->pmu_timer);
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
 
     QLIST_HEAD(, ARMELChangeHook) pre_el_change_hooks;
     QLIST_HEAD(, ARMELChangeHook) el_change_hooks;
+    QLIST_HEAD(, ARMCPRegMigTolerance) cpreg_mig_tolerances;
 
     int32_t node_id; /* NUMA node this CPU belongs to */
 
diff --git a/target/arm/internals.h b/target/arm/internals.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -XXX,XX +XXX,XX @@ int compare_u64(const void *a, const void *b);
 /* Used in FEAT_MEC to set the MECIDWidthm1 field in the MECIDR_EL2 register. */
 #define MECID_WIDTH 16
 
+typedef enum {
+    ToleranceNotOnBothEnds,
+    ToleranceOnlySrcTestValue,
+    ToleranceDiffInMask,
+    ToleranceFieldLT,
+    ToleranceFieldGT,
+} ARMCPRegMigToleranceType;
+
+typedef struct ARMCPRegMigTolerance {
+    uint64_t kvmidx;
+    uint64_t mask;
+    uint64_t value;
+    ARMCPRegMigToleranceType type;
+    QLIST_ENTRY(ARMCPRegMigTolerance) node;
+} ARMCPRegMigTolerance;
+
+/**
+ * arm_register_cpreg_mig_tolerance:
+ * Register a migration tolerance wrt one given cpreg identified by its
+ * @kvmidx. Calling this function twice for the same @kvmidx is a
+ * programming error and will cause an assertion failure.
+ *
+ * @cpu: vcpu to apply the migration tolerance on
+ * @kvmidx: kvm index of the cpreg the tolerance applies to
+ * @mask: bitmask where a difference is tolerated
+ *        (relevant with ToleranceDiffInMask)
+ * @value: value the bitmask field is compared with
+ *        (relevant with ToleranceFieldLT and ToleranceFieldGT)
+ * @type: type of the migration tolerance:
+ * - ToleranceNotOnBothEnds (cpreg index is allowed to be only present
+ *   on one end)
+ * - ToleranceOnlySrcTestValue (cpreg index is allowed to be only
+ *   present in source if its value @mask field matches @value)
+ * - ToleranceDiffInMask (mismatch in cpreg values are only tolerated
+ *   if differences are within @mask)
+ * - ToleranceFieldLT (mismatch in cpreg values are only tolerated
+ *   if incoming @bitmask field value is less than @value)
+ * - ToleranceFieldGT (mismatch in cpreg values are only tolerated
+ *   if incoming @bitmask field value is greater than @value)
+ */
+void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                      uint64_t mask, uint64_t value,
+                                      ARMCPRegMigToleranceType type);
+
+/**
+ * arm_cpu_match_cpreg_mig_tolerance:
+ * Check whether a tolerance of type @type exists for a given @kvmidx
+ * and the tolerance criterion is satisfied
+ */
+bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                       uint64_t vmstate_value, uint64_t local_value,
+                                       ARMCPRegMigToleranceType type);
+
+
 #endif
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

If there is a mismatch between the cpreg indexes found on both ends,
check whether a tolerance was registered for the given kvmidx. If any,
silence warning/errors.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-3-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/machine.c    | 21 +++++++++++++++------
 target/arm/trace-events |  2 ++
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/target/arm/machine.c b/target/arm/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx
 {
     g_autofree gchar *name = print_register_name(kvmidx);
 
+    if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
+                                          0, 0, ToleranceNotOnBothEnds)) {
+        trace_tolerate_cpreg_missing_in_incoming_stream(name);
+        return;
+    }
     warn_report("%s: %s "
                 "expected by the destination but not in the incoming stream: "
                  "skip it", __func__, name);
 }
 
 /*
- * Handle the situation where @kvmidx is in the incoming stream
- * but not on destination. This currently fails the migration but
- * we plan to accomodate some exceptions, hence the boolean returned value.
+ * Handle the situation where @kvmidx is in the incoming
+ * stream but not on destination. This fails the migration if
+ * no cpreg mig tolerance is matched for this @kvmidx
+ * Return true if the migration should eventually fail
  */
 static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx)
 {
     g_autofree gchar *name = print_register_name(kvmidx);
-    bool fail = true;
 
+    if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
+                                          0, 0, ToleranceNotOnBothEnds)) {
+        trace_tolerate_cpreg_only_in_incoming_stream(name);
+        return false;
+    }
     error_report("%s: %s in the incoming stream but unknown on the "
                  "destination: fail migration", __func__, name);
-
-    return fail;
+    return true;
 }
 
 static int cpu_post_load(void *opaque, int version_id)
diff --git a/target/arm/trace-events b/target/arm/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/trace-events
+++ b/target/arm/trace-events
@@ -XXX,XX +XXX,XX @@ arm_psci_call(uint64_t x0, uint64_t x1, uint64_t x2, uint64_t x3, uint32_t cpuid
 
 # machine.c
 cpu_post_load(uint32_t cpreg_vmstate_array_len, uint32_t cpreg_array_len) "cpreg_vmstate_array_len=%d cpreg_array_len=%d"
+tolerate_cpreg_missing_in_incoming_stream(char *name) "%s is missing in incoming stream but this is explicitly tolerated"
+tolerate_cpreg_only_in_incoming_stream(char *name) "%s is in incoming stream but not on destination but this is explicitly tolerated"
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

Pass the value of the incoming register to
handle_cpreg_only_in_incoming_stream and check whether there is
a matching ToleranceOnlySrcTestValue tolerance.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20260420140552.104369-4-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/machine.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/target/arm/machine.c b/target/arm/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx
  * no cpreg mig tolerance is matched for this @kvmidx
  * Return true if the migration should eventually fail
  */
-static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx)
+static bool
+handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx, uint64_t value)
 {
     g_autofree gchar *name = print_register_name(kvmidx);
 
     if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
-                                          0, 0, ToleranceNotOnBothEnds)) {
+                                          0, 0, ToleranceNotOnBothEnds) ||
+        arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
+                                          value, 0, ToleranceOnlySrcTestValue)) {
         trace_tolerate_cpreg_only_in_incoming_stream(name);
         return false;
     }
@@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id)
         }
         if (cpu->cpreg_vmstate_indexes[v] < cpu->cpreg_indexes[i]) {
             fail = handle_cpreg_only_in_incoming_stream(cpu,
-                                                        cpu->cpreg_vmstate_indexes[v++]);
+                                                        cpu->cpreg_vmstate_indexes[v],
+                                                        cpu->cpreg_vmstate_values[v]);
+            v++;
             continue;
         }
         /* matching register, copy the value over */
@@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id)
      */
     for ( ; v < cpu->cpreg_vmstate_array_len; v++) {
         fail = handle_cpreg_only_in_incoming_stream(cpu,
-                                                    cpu->cpreg_vmstate_indexes[v]);
+                                                    cpu->cpreg_vmstate_indexes[v],
+                                                    cpu->cpreg_vmstate_values[v]);
     }
     if (fail) {
         return -1;
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

Before linux v6.13 those registers were erroneously unconditionally
exposed and this was fixed by commits:
- 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace when
                 disabled for guests")
- a68cddbe47ef ("KVM: arm64: Hide S1PIE registers from userspace
                 when disabled for guests")
in v6.13.

This means if we migrate from an old kernel host to a >= 6.13 kernel
host, migration currently fails.

Declare cpreg migration tolerance for those registers.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-5-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu64.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj)
     define_cortex_a72_a57_a53_cp_reginfo(cpu);
 }
 
+#if defined(CONFIG_KVM)
+static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu)
+{
+    /*
+     * Registers that may be in the incoming stream and not exposed
+     * on the destination
+     */
+
+    /*
+     * TCR_EL1 was erroneously unconditionnally exposed before linux v6.13.
+     * See commit 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace
+     * when disabled for guests")
+     */
+    arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 2, 0, 3),
+                                     0, 0, ToleranceNotOnBothEnds);
+    /*
+     * PIRE0_EL1 and PIR_EL1 were erroneously unconditionnally exposed
+     * before linux v6.13. See commit a68cddbe47ef ("KVM: arm64: Hide
+     * S1PIE registers from userspace when disabled for guests")
+     */
+    arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 2),
+                                     0, 0, ToleranceNotOnBothEnds);
+    arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3),
+                                     0, 0, ToleranceNotOnBothEnds);
+}
+#endif
+
 static void aarch64_host_initfn(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
@@ -XXX,XX +XXX,XX @@ static void aarch64_host_initfn(Object *obj)
 #endif
 
 #if defined(CONFIG_KVM)
+    kvm_arm_set_cpreg_mig_tolerances(cpu);
     kvm_arm_set_cpu_features_from_host(cpu);
     aarch64_add_sve_properties(obj);
 #elif defined(CONFIG_HVF)
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed
from v6.15 onwards. Backward migration from a >= v6.15 to an older
kernel would fail without cpreg migration tolerance definition
for this register. If the register is present on source but not
on destination, its value must be checked to make sure it matches
the reset value, ie. 0, meaning no service is exposed to the guest,
hence the choice of a ToleranceOnlySrcTestValue migration
tolerance.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-6-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu64.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@ static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu)
                                      0, 0, ToleranceNotOnBothEnds);
     arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3),
                                      0, 0, ToleranceNotOnBothEnds);
+
+    /*
+     * KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed
+     * from v6.15 onwards. Backward migration from a >= v6.15 to an older
+     * kernel would fail without cpreg migration tolerance definition.
+     * If the register is present on source but not on destination, make
+     * sure it has its reset value, ie. 0, meaning no service is exposed
+     * to the guest.
+     */
+    arm_register_cpreg_mig_tolerance(cpu, KVM_REG_ARM_FW_FEAT_BMAP_REG(3),
+                                     UINT64_MAX, 0, ToleranceOnlySrcTestValue);
 }
 #endif
 
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

We want to remove AArch32 DBGDTRTX which was erroneously exposed.
This was attempted by 655659a74a36b ("target/arm: Correct encoding
of Debug Communications Channel registers") but it was discovered
that the removal of this debug register broke forward migration on
TCG. Now we have the cpreg migration tolerance infrastructure, we
can declare one for the DBGDTRTX. This allow to revert the reinstate
patch.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-7-eric.auger@redhat.com
[PMM: revised comment, included note about when we can drop
 the workaround]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu)
             .fgt = FGT_CLIDR_EL1,
             .resetvalue = GET_IDREG(isar, CLIDR)
         };
+        uint64_t dbgtr_el0_kvmidx =
+            cpreg_to_kvm_id(ENCODE_CP_REG(14, 0, 1, 0, 5, 3, 0));
+
         define_one_arm_cp_reg(cpu, &clidr);
         define_arm_cp_regs(cpu, v7_cp_reginfo);
         define_debug_regs(cpu);
+        /*
+         * We used to incorrectly expose a non-existent AArch32 "DBGDTRTX"
+         * register with this encoding. This has been fixed by commit
+         * 655659a74a36 ("target/arm: Correct encoding of Debug
+         * Communications Channel registers") by the introduction of correct
+         * separate cpreg definitions for AA64 and AA32 versions. However,
+         * the old cpreg definition couldn't be removed without breaking
+         * migration, so commit 4f2b82f604 reinstated the bogus encoding
+         * for migration data only.
+         *
+         * Now that we have migration tolerance infrastructure, we can use
+         * this to allow forward migration from the buggy QEMU versions,
+         * accepting and ignoring the bogus register if it is in the
+         * source data. QEMU 11.0 was the last version that sent the
+         * bogus encoding, so this workaround can be removed at the point
+         * where we no longer care about migration from that version
+         * (i.e. when we remove the "virt-11.0" machine type).
+         */
+        arm_register_cpreg_mig_tolerance(cpu, dbgtr_el0_kvmidx,
+                                         0, 0, ToleranceNotOnBothEnds);
     } else {
         define_arm_cp_regs(cpu, not_v7_cp_reginfo);
     }
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

This reverts commit 4f2b82f60431 ("target/arm: Reinstate bogus AArch32
DBGDTRTX register for migration compat). We don't need that commit
anymore as the AArch32 DBGDTRTX register is declared to
be safe to ignore in the incoming migration stream.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-8-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/debug_helper.c | 29 -----------------------------
 1 file changed, 29 deletions(-)

diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -XXX,XX +XXX,XX @@ static void dbgclaimclr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     env->cp15.dbgclaim &= ~(value & 0xFF);
 }
 
-static CPAccessResult access_bogus(CPUARMState *env, const ARMCPRegInfo *ri,
-                                   bool isread)
-{
-    /* Always UNDEF, as if this cpreg didn't exist */
-    return CP_ACCESS_UNDEFINED;
-}
-
 static const ARMCPRegInfo debug_cp_reginfo[] = {
     /*
      * DBGDRAR, DBGDSAR: always RAZ since we don't implement memory mapped
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_cp_reginfo[] = {
       .opc0 = 2, .opc1 = 3, .crn = 0, .crm = 4, .opc2 = 0,
       .access = PL0_RW, .accessfn = access_tdcc,
       .type = ARM_CP_CONST, .resetvalue = 0 },
-    /*
-     * This is not a real AArch32 register. We used to incorrectly expose
-     * this due to a QEMU bug; to avoid breaking migration compatibility we
-     * need to continue to provide it so that we don't fail the inbound
-     * migration when it tells us about a sysreg that we don't have.
-     * We set an always-fails .accessfn, which means that the guest doesn't
-     * actually see this register (it will always UNDEF, identically to if
-     * there were no cpreg definition for it other than that we won't print
-     * a LOG_UNIMP message about it), and we set the ARM_CP_NO_GDB flag so the
-     * gdbstub won't see it either.
-     * (We can't just set .access = 0, because add_cpreg_to_hashtable()
-     * helpfully ignores cpregs which aren't accessible to the highest
-     * implemented EL.)
-     *
-     * TODO: implement a system for being able to describe "this register
-     * can be ignored if it appears in the inbound stream"; then we can
-     * remove this temporary hack.
-     */
-    { .name = "BOGUS_DBGDTR_EL0", .state = ARM_CP_STATE_AA32,
-      .cp = 14, .opc1 = 3, .crn = 0, .crm = 5, .opc2 = 0,
-      .access = PL0_RW, .accessfn = access_bogus,
-      .type = ARM_CP_CONST | ARM_CP_NO_GDB, .resetvalue = 0 },
     /*
      * OSECCR_EL1 provides a mechanism for an operating system
      * to access the contents of EDECCR. EDECCR is not implemented though,
-- 
2.43.0

From: Osama Abdelkader <osama.abdelkader@gmail.com>

fdt_node_offset_by_compatible(fdt, -1, compat) only finds the first match.
If the blob has more than one node with the same compatible string, extra
nodes will remain active. Remove all the matching nodes, using the same
loop as imx8mp-evk.c does for this purpose.

Signed-off-by: Osama Abdelkader <osama.abdelkader@gmail.com>
Message-id: 20260420162114.308519-1-osama.abdelkader@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/raspi4b.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/hw/arm/raspi4b.c b/hw/arm/raspi4b.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/raspi4b.c
+++ b/hw/arm/raspi4b.c
@@ -XXX,XX +XXX,XX @@ static void raspi4_modify_dtb(const struct arm_boot_info *info, void *fdt)
 
     for (int i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) {
         const char *dev_str = nodes_to_remove[i];
+        int offset;
 
-        int offset = fdt_node_offset_by_compatible(fdt, -1, dev_str);
-        if (offset >= 0) {
-            if (!fdt_nop_node(fdt, offset)) {
-                warn_report("bcm2711 dtc: %s has been disabled!", dev_str);
+        offset = fdt_node_offset_by_compatible(fdt, -1, dev_str);
+        while (offset >= 0) {
+            if (fdt_nop_node(fdt, offset) == 0) {
+                warn_report("bcm2711 dtb: %s has been disabled!", dev_str);
             }
+            offset = fdt_node_offset_by_compatible(fdt, offset, dev_str);
         }
     }
 
-- 
2.43.0

From: Yucai Liu <1486344514@qq.com>

Implement a basic i.MX6UL LCDIF controller model with MMIO registers,
frame-done interrupt behavior, and framebuffer-backed display updates
for RGB565 and XRGB8888 input formats.

Place the LCDIF device under hw/display and build it via a dedicated
CONFIG_IMX6UL_LCDIF symbol. Model register fields with
registerfields.h helpers and provide migration support via vmstate.

Signed-off-by: Yucai Liu <1486344514@qq.com>
Message-id: 20260412110240.93116-2-yangyanglan718@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS                       |   2 +
 hw/display/Kconfig                |   4 +
 hw/display/imx6ul_lcdif.c         | 453 ++++++++++++++++++++++++++++++
 hw/display/meson.build            |   1 +
 include/hw/display/imx6ul_lcdif.h |  37 +++
 5 files changed, 497 insertions(+)
 create mode 100644 hw/display/imx6ul_lcdif.c
 create mode 100644 include/hw/display/imx6ul_lcdif.h

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org
 S: Odd Fixes
 F: hw/arm/mcimx6ul-evk.c
 F: hw/arm/fsl-imx6ul.c
+F: hw/display/imx6ul_lcdif.c
 F: hw/misc/imx6ul_ccm.c
 F: include/hw/arm/fsl-imx6ul.h
+F: include/hw/display/imx6ul_lcdif.h
 F: include/hw/misc/imx6ul_ccm.h
 F: docs/system/arm/mcimx6ul-evk.rst
 
diff --git a/hw/display/Kconfig b/hw/display/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/Kconfig
+++ b/hw/display/Kconfig
@@ -XXX,XX +XXX,XX @@ config PL110
     bool
     select FRAMEBUFFER
 
+config IMX6UL_LCDIF
+    bool
+    select FRAMEBUFFER
+
 config SII9022
     bool
     depends on I2C
diff --git a/hw/display/imx6ul_lcdif.c b/hw/display/imx6ul_lcdif.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/display/imx6ul_lcdif.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * i.MX6UL LCDIF controller
+ *
+ * Copyright (c) 2026 Yucai Liu <1486344514@qq.com>
+ */
+
+#include "qemu/osdep.h"
+#include "hw/display/imx6ul_lcdif.h"
+#include "hw/core/irq.h"
+#include "hw/core/registerfields.h"
+#include "hw/display/framebuffer.h"
+#include "migration/vmstate.h"
+#include "system/address-spaces.h"
+#include "qemu/module.h"
+#include "qemu/units.h"
+#include "ui/pixel_ops.h"
+
+#define LCDIF_MMIO_SIZE             (16 * KiB)
+#define LCDIF_RESET_CTRL1           0x000f0000
+
+REG32(CTRL, 0x00)
+    FIELD(CTRL, RUN, 0, 1)
+    FIELD(CTRL, WORD_LENGTH, 8, 2)
+REG32(CTRL1, 0x10)
+    FIELD(CTRL1, CUR_FRAME_DONE_IRQ, 9, 1)
+    FIELD(CTRL1, CUR_FRAME_DONE_IRQ_EN, 13, 1)
+    FIELD(CTRL1, BYTE_PACKING_FORMAT, 16, 4)
+REG32(V4_TRANSFER_COUNT, 0x30)
+    FIELD(V4_TRANSFER_COUNT, H_COUNT, 0, 16)
+    FIELD(V4_TRANSFER_COUNT, V_COUNT, 16, 16)
+REG32(V4_CUR_BUF, 0x40)
+REG32(V4_NEXT_BUF, 0x50)
+REG32(AS_NEXT_BUF, 0x230)
+
+#define REG_SET                     0x4
+#define REG_CLR                     0x8
+#define REG_TOG                     0xc
+
+#define CTRL_WORD_LENGTH_16         0
+#define CTRL_WORD_LENGTH_24         3
+
+#define FRAME_PERIOD_NS             (16 * 1000 * 1000ULL)
+
+enum IMX6ULLCDIFReg {
+    IMX6UL_LCDIF_REG_CTRL = A_CTRL >> 4,
+    IMX6UL_LCDIF_REG_CTRL1 = A_CTRL1 >> 4,
+    IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT = A_V4_TRANSFER_COUNT >> 4,
+    IMX6UL_LCDIF_REG_V4_CUR_BUF = A_V4_CUR_BUF >> 4,
+    IMX6UL_LCDIF_REG_V4_NEXT_BUF = A_V4_NEXT_BUF >> 4,
+    IMX6UL_LCDIF_REG_AS_NEXT_BUF = A_AS_NEXT_BUF >> 4,
+};
+
+static inline bool imx6ul_lcdif_reg_exists(hwaddr reg)
+{
+    return (reg >> 4) < IMX6UL_LCDIF_REGS_NUM;
+}
+
+static inline bool imx6ul_lcdif_reg_has_setclr(hwaddr reg)
+{
+    switch (reg) {
+    case A_CTRL:
+    case A_CTRL1:
+        return true;
+    default:
+        return false;
+    }
+}
+
+static inline bool imx6ul_lcdif_is_running(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL];
+
+    return FIELD_EX32(ctrl, CTRL, RUN);
+}
+
+static inline bool imx6ul_lcdif_frame_done_pending(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1];
+
+    return FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ);
+}
+
+static void imx6ul_lcdif_schedule_frame(IMX6ULLCDIFState *s)
+{
+    int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+
+    timer_mod(s->frame_timer, now + FRAME_PERIOD_NS);
+}
+
+static void imx6ul_lcdif_maybe_schedule_frame(IMX6ULLCDIFState *s)
+{
+    if (imx6ul_lcdif_is_running(s) && !imx6ul_lcdif_frame_done_pending(s)) {
+        imx6ul_lcdif_schedule_frame(s);
+    } else {
+        timer_del(s->frame_timer);
+    }
+}
+
+static void imx6ul_lcdif_update_irq(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1];
+    bool level = FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ_EN) &&
+                 FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ);
+
+    qemu_set_irq(s->irq, level);
+}
+
+static void imx6ul_lcdif_frame_done(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1];
+
+    ctrl1 = FIELD_DP32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ, 1);
+    s->regs[IMX6UL_LCDIF_REG_CTRL1] = ctrl1;
+    imx6ul_lcdif_update_irq(s);
+}
+
+static void imx6ul_lcdif_draw_line_rgb565(void *opaque, uint8_t *dst,
+                                          const uint8_t *src, int width,
+                                          int dststep)
+{
+    uint32_t *dst32 = (uint32_t *)dst;
+    int i;
+
+    for (i = 0; i < width; i++) {
+        uint16_t pixel = lduw_le_p(src);
+        uint8_t r = ((pixel >> 11) & 0x1f) << 3;
+        uint8_t g = ((pixel >> 5) & 0x3f) << 2;
+        uint8_t b = (pixel & 0x1f) << 3;
+
+        *dst32++ = rgb_to_pixel32(r, g, b);
+        src += 2;
+    }
+}
+
+static void imx6ul_lcdif_draw_line_xrgb8888(void *opaque, uint8_t *dst,
+                                            const uint8_t *src, int width,
+                                            int dststep)
+{
+    uint32_t *dst32 = (uint32_t *)dst;
+    int i;
+
+    for (i = 0; i < width; i++) {
+        uint32_t pixel = ldl_le_p(src);
+        uint8_t r = (pixel >> 16) & 0xff;
+        uint8_t g = (pixel >> 8) & 0xff;
+        uint8_t b = pixel & 0xff;
+
+        *dst32++ = rgb_to_pixel32(r, g, b);
+        src += 4;
+    }
+}
+
+static void imx6ul_lcdif_update_display(void *opaque)
+{
+    IMX6ULLCDIFState *s = opaque;
+    DisplaySurface *surface = qemu_console_surface(s->con);
+    uint32_t transfer_count = s->regs[IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT];
+    uint32_t width = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, H_COUNT);
+    uint32_t height = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, V_COUNT);
+    uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL];
+    uint32_t frame_base = s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF];
+    drawfn fn;
+    int first = 0;
+    int last = 0;
+    int src_width;
+
+    if (!imx6ul_lcdif_is_running(s) || width == 0 || height == 0) {
+        return;
+    }
+
+    switch (FIELD_EX32(ctrl, CTRL, WORD_LENGTH)) {
+    case CTRL_WORD_LENGTH_16:
+        s->src_bpp = 2;
+        fn = imx6ul_lcdif_draw_line_rgb565;
+        break;
+    case CTRL_WORD_LENGTH_24:
+        s->src_bpp = 4;
+        fn = imx6ul_lcdif_draw_line_xrgb8888;
+        break;
+    default:
+        return;
+    }
+
+    if (surface_width(surface) != width || surface_height(surface) != height) {
+        qemu_console_resize(s->con, width, height);
+        surface = qemu_console_surface(s->con);
+        s->invalidate = true;
+    }
+
+    src_width = width * s->src_bpp;
+    if (s->invalidate || s->fb_base != frame_base ||
+        s->src_width != src_width || s->rows != height) {
+        framebuffer_update_memory_section(&s->fbsection, get_system_memory(),
+                                          frame_base, height, src_width);
+        s->fb_base = frame_base;
+        s->src_width = src_width;
+        s->rows = height;
+    }
+
+    framebuffer_update_display(surface, &s->fbsection, width, height,
+                               src_width, surface_stride(surface), 0,
+                               s->invalidate, fn, s, &first, &last);
+    if (first >= 0) {
+        dpy_gfx_update(s->con, 0, first, width, last - first + 1);
+    }
+
+    s->invalidate = false;
+}
+
+static void imx6ul_lcdif_invalidate_display(void *opaque)
+{
+    IMX6ULLCDIFState *s = opaque;
+
+    s->invalidate = true;
+}
+
+static const GraphicHwOps imx6ul_lcdif_graphic_ops = {
+    .invalidate = imx6ul_lcdif_invalidate_display,
+    .gfx_update = imx6ul_lcdif_update_display,
+};
+
+static void imx6ul_lcdif_frame_timer_cb(void *opaque)
+{
+    IMX6ULLCDIFState *s = opaque;
+
+    if (!imx6ul_lcdif_is_running(s) || imx6ul_lcdif_frame_done_pending(s)) {
+        return;
+    }
+
+    imx6ul_lcdif_frame_done(s);
+}
+
+static uint64_t imx6ul_lcdif_read(void *opaque, hwaddr offset, unsigned size)
+{
+    IMX6ULLCDIFState *s = opaque;
+    hwaddr reg = offset & ~0xf;
+    uint32_t idx;
+
+    assert(size == 4);
+    assert(!(offset & 0x3));
+    assert(offset < LCDIF_MMIO_SIZE);
+
+    idx = reg >> 4;
+    if (idx >= ARRAY_SIZE(s->regs)) {
+        return 0;
+    }
+
+    return s->regs[idx];
+}
+
+static void imx6ul_lcdif_write(void *opaque, hwaddr offset,
+                               uint64_t value, unsigned size)
+{
+    IMX6ULLCDIFState *s = opaque;
+    hwaddr reg = offset & ~0xf;
+    uint32_t idx;
+    uint32_t oldv;
+
+    assert(size == 4);
+    assert(!(offset & 0x3));
+    assert(offset < LCDIF_MMIO_SIZE);
+
+    if (!imx6ul_lcdif_reg_exists(reg)) {
+        return;
+    }
+
+    idx = reg >> 4;
+    oldv = s->regs[idx];
+
+    switch (offset & 0xf) {
+    case 0:
+        s->regs[idx] = (uint32_t)value;
+        break;
+    case REG_SET:
+        if (!imx6ul_lcdif_reg_has_setclr(reg)) {
+            return;
+        }
+        s->regs[idx] = oldv | (uint32_t)value;
+        break;
+    case REG_CLR:
+        if (!imx6ul_lcdif_reg_has_setclr(reg)) {
+            return;
+        }
+        s->regs[idx] = oldv & ~(uint32_t)value;
+        break;
+    case REG_TOG:
+        if (!imx6ul_lcdif_reg_has_setclr(reg)) {
+            return;
+        }
+        s->regs[idx] = oldv ^ (uint32_t)value;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    switch (reg) {
+    case A_CTRL:
+        if (!FIELD_EX32(oldv, CTRL, RUN) &&
+            FIELD_EX32(s->regs[idx], CTRL, RUN)) {
+            s->invalidate = true;
+            graphic_hw_invalidate(s->con);
+            imx6ul_lcdif_maybe_schedule_frame(s);
+            break;
+        }
+        if (FIELD_EX32(oldv, CTRL, RUN) &&
+            !FIELD_EX32(s->regs[idx], CTRL, RUN)) {
+            timer_del(s->frame_timer);
+        }
+        break;
+    case A_CTRL1:
+        if (FIELD_EX32(oldv, CTRL1, CUR_FRAME_DONE_IRQ) &&
+            !FIELD_EX32(s->regs[idx], CTRL1, CUR_FRAME_DONE_IRQ)) {
+            imx6ul_lcdif_maybe_schedule_frame(s);
+        }
+        break;
+    case A_V4_TRANSFER_COUNT:
+        s->invalidate = true;
+        graphic_hw_invalidate(s->con);
+        break;
+    case A_V4_CUR_BUF:
+        s->invalidate = true;
+        graphic_hw_invalidate(s->con);
+        break;
+    case A_V4_NEXT_BUF:
+        s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF] = s->regs[idx];
+        imx6ul_lcdif_frame_done(s);
+        s->invalidate = true;
+        graphic_hw_invalidate(s->con);
+        imx6ul_lcdif_maybe_schedule_frame(s);
+        return;
+    case A_AS_NEXT_BUF:
+        imx6ul_lcdif_frame_done(s);
+        imx6ul_lcdif_maybe_schedule_frame(s);
+        return;
+    default:
+        break;
+    }
+
+    imx6ul_lcdif_update_irq(s);
+}
+
+static const MemoryRegionOps imx6ul_lcdif_ops = {
+    .read = imx6ul_lcdif_read,
+    .write = imx6ul_lcdif_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+        .unaligned = false,
+    },
+};
+
+static void imx6ul_lcdif_reset(DeviceState *dev)
+{
+    IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev);
+
+    memset(s->regs, 0, sizeof(s->regs));
+    s->regs[IMX6UL_LCDIF_REG_CTRL1] = LCDIF_RESET_CTRL1;
+    s->fb_base = 0;
+    s->src_width = 0;
+    s->rows = 0;
+    s->src_bpp = 0;
+    s->invalidate = true;
+    timer_del(s->frame_timer);
+    imx6ul_lcdif_update_irq(s);
+}
+
+static int imx6ul_lcdif_post_load(void *opaque, int version_id)
+{
+    IMX6ULLCDIFState *s = opaque;
+
+    s->fb_base = 0;
+    s->src_width = 0;
+    s->rows = 0;
+    s->src_bpp = 0;
+    s->invalidate = true;
+
+    imx6ul_lcdif_update_irq(s);
+    if (imx6ul_lcdif_is_running(s) &&
+        !imx6ul_lcdif_frame_done_pending(s) &&
+        !timer_pending(s->frame_timer)) {
+        imx6ul_lcdif_schedule_frame(s);
+    }
+
+    return 0;
+}
+
+static const VMStateDescription vmstate_imx6ul_lcdif = {
+    .name = TYPE_IMX6UL_LCDIF,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .post_load = imx6ul_lcdif_post_load,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT32_ARRAY(regs, IMX6ULLCDIFState, IMX6UL_LCDIF_REGS_NUM),
+        VMSTATE_TIMER_PTR(frame_timer, IMX6ULLCDIFState),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static void imx6ul_lcdif_realize(DeviceState *dev, Error **errp)
+{
+    IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev);
+
+    s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                  imx6ul_lcdif_frame_timer_cb, s);
+    s->invalidate = true;
+    memory_region_init_io(&s->iomem, OBJECT(dev), &imx6ul_lcdif_ops, s,
+                          TYPE_IMX6UL_LCDIF, LCDIF_MMIO_SIZE);
+    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem);
+    sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq);
+    s->con = graphic_console_init(dev, 0, &imx6ul_lcdif_graphic_ops, s);
+}
+
+static void imx6ul_lcdif_unrealize(DeviceState *dev)
+{
+    IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev);
+
+    timer_del(s->frame_timer);
+    timer_free(s->frame_timer);
+    s->frame_timer = NULL;
+
+    if (s->con) {
+        graphic_console_close(s->con);
+        s->con = NULL;
+    }
+}
+
+static void imx6ul_lcdif_class_init(ObjectClass *klass, const void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->realize = imx6ul_lcdif_realize;
+    dc->unrealize = imx6ul_lcdif_unrealize;
+    dc->vmsd = &vmstate_imx6ul_lcdif;
+    device_class_set_legacy_reset(dc, imx6ul_lcdif_reset);
+    dc->desc = "i.MX6UL LCDIF";
+}
+
+static const TypeInfo imx6ul_lcdif_info = {
+    .name = TYPE_IMX6UL_LCDIF,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(IMX6ULLCDIFState),
+    .class_init = imx6ul_lcdif_class_init,
+};
+
+static void imx6ul_lcdif_register_types(void)
+{
+    type_register_static(&imx6ul_lcdif_info);
+}
+
+type_init(imx6ul_lcdif_register_types)
diff --git a/hw/display/meson.build b/hw/display/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/meson.build
+++ b/hw/display/meson.build
@@ -XXX,XX +XXX,XX @@ system_ss.add(when: ['CONFIG_VGA_CIRRUS', 'CONFIG_VGA_ISA'], if_true: files('cir
 system_ss.add(when: 'CONFIG_G364FB', if_true: files('g364fb.c'))
 system_ss.add(when: 'CONFIG_JAZZ_LED', if_true: files('jazz_led.c'))
 system_ss.add(when: 'CONFIG_PL110', if_true: files('pl110.c'))
+system_ss.add(when: 'CONFIG_IMX6UL_LCDIF', if_true: files('imx6ul_lcdif.c'))
 system_ss.add(when: 'CONFIG_SII9022', if_true: files('sii9022.c'))
 system_ss.add(when: 'CONFIG_SSD0303', if_true: files('ssd0303.c'))
 system_ss.add(when: 'CONFIG_SSD0323', if_true: files('ssd0323.c'))
diff --git a/include/hw/display/imx6ul_lcdif.h b/include/hw/display/imx6ul_lcdif.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/display/imx6ul_lcdif.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * i.MX6UL LCDIF controller
+ *
+ * Copyright (c) 2026 Yucai Liu <1486344514@qq.com>
+ */
+
+#ifndef IMX6UL_LCDIF_H
+#define IMX6UL_LCDIF_H
+
+#include "hw/core/sysbus.h"
+#include "qom/object.h"
+#include "qemu/timer.h"
+#include "ui/console.h"
+
+#define TYPE_IMX6UL_LCDIF "imx6ul-lcdif"
+#define IMX6UL_LCDIF_REGS_NUM ((0x230 >> 4) + 1)
+OBJECT_DECLARE_SIMPLE_TYPE(IMX6ULLCDIFState, IMX6UL_LCDIF)
+
+struct IMX6ULLCDIFState {
+    SysBusDevice parent_obj;
+
+    MemoryRegion iomem;
+    MemoryRegionSection fbsection;
+    qemu_irq irq;
+    QemuConsole *con;
+    QEMUTimer *frame_timer;
+    uint32_t fb_base;
+    uint32_t src_width;
+    uint32_t rows;
+    uint8_t src_bpp;
+    bool invalidate;
+    uint32_t regs[IMX6UL_LCDIF_REGS_NUM];
+};
+
+#endif /* IMX6UL_LCDIF_H */
-- 
2.43.0

From: Yucai Liu <1486344514@qq.com>

Instantiate LCDIF as a child object of the i.MX6UL SoC in init and
realize it in the SoC realize path before MMIO/IRQ hookup.

Also make FSL_IMX6UL select CONFIG_IMX6UL_LCDIF and map the LCDIF
region with a 16 KiB size to match the SoC memory map.

Signed-off-by: Yucai Liu <1486344514@qq.com>
Message-id: 20260412110240.93116-3-yangyanglan718@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx6ul.c         | 12 ++++++++++--
 include/hw/arm/fsl-imx6ul.h |  4 +++-
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX6UL
     imply I2C_DEVICES
     select A15MPCORE
     select IMX
+    select IMX6UL_LCDIF
     select IMX_FEC
     select IMX_I2C
     select IMX_USBPHY
diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx6ul.c
+++ b/hw/arm/fsl-imx6ul.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "hw/arm/fsl-imx6ul.h"
+#include "hw/display/imx6ul_lcdif.h"
 #include "hw/misc/unimp.h"
 #include "hw/usb/imx-usb-phy.h"
 #include "hw/core/boards.h"
@@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj)
         object_initialize_child(obj, name, &s->usb[i], TYPE_CHIPIDEA);
     }
 
+    /*
+     * LCDIF
+     */
+    object_initialize_child(obj, "lcdif", &s->lcdif, TYPE_IMX6UL_LCDIF);
+
     /*
      * SDHCIs
      */
@@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp)
     /*
      * LCD
      */
-    create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR,
-                                FSL_IMX6UL_LCDIF_SIZE);
+    sysbus_realize(SYS_BUS_DEVICE(&s->lcdif), &error_abort);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->lcdif), 0, FSL_IMX6UL_LCDIF_ADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->lcdif), 0,
+                       qdev_get_gpio_in(gic, FSL_IMX6UL_LCDIF_IRQ));
 
     /*
      * CSU
diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx6ul.h
+++ b/include/hw/arm/fsl-imx6ul.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/net/imx_fec.h"
 #include "hw/usb/chipidea.h"
 #include "hw/usb/imx-usb-phy.h"
+#include "hw/display/imx6ul_lcdif.h"
 #include "system/memory.h"
 #include "target/arm/cpu.h"
 #include "qom/object.h"
@@ -XXX,XX +XXX,XX @@ struct FslIMX6ULState {
     IMX2WdtState       wdt[FSL_IMX6UL_NUM_WDTS];
     IMXUSBPHYState     usbphy[FSL_IMX6UL_NUM_USB_PHYS];
     ChipideaState      usb[FSL_IMX6UL_NUM_USBS];
+    IMX6ULLCDIFState   lcdif;
     MemoryRegion       rom;
     MemoryRegion       caam;
     MemoryRegion       ocram;
@@ -XXX,XX +XXX,XX @@ enum FslIMX6ULMemoryMap {
     FSL_IMX6UL_PXP_SIZE             = (16 * KiB),
 
     FSL_IMX6UL_LCDIF_ADDR           = 0x021C8000,
-    FSL_IMX6UL_LCDIF_SIZE           = 0x100,
+    FSL_IMX6UL_LCDIF_SIZE           = (16 * KiB),
 
     FSL_IMX6UL_CSI_ADDR             = 0x021C4000,
     FSL_IMX6UL_CSI_SIZE             = 0x100,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

We have a registerfields interface which we can use for defining
fields alongside helpers to access them. Define the basic syndrome
layout and convert the helpers that take the imm16 data directly.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-2-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 75 ++++++++++++++++++++++++++++++++-----------
 1 file changed, 57 insertions(+), 18 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@
 #ifndef TARGET_ARM_SYNDROME_H
 #define TARGET_ARM_SYNDROME_H
 
-#include "qemu/bitops.h"
+#include "hw/core/registerfields.h"
 
 /* Valid Syndrome Register EC field values */
 enum arm_exception_class {
@@ -XXX,XX +XXX,XX @@ enum arm_exception_class {
     EC_AA64_BKPT              = 0x3c,
 };
 
+/* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */
+FIELD(SYNDROME, EC, 26, 6)
+FIELD(SYNDROME, IL, 25, 1)
+FIELD(SYNDROME, ISS, 0, 25)
+
 typedef enum {
     SME_ET_AccessTrap,
     SME_ET_Streaming,
@@ -XXX,XX +XXX,XX @@ typedef enum {
 
 static inline uint32_t syn_get_ec(uint32_t syn)
 {
-    return syn >> ARM_EL_EC_SHIFT;
+    return FIELD_EX32(syn, SYNDROME, EC);
 }
 
 static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec)
 {
-    return deposit32(syn, ARM_EL_EC_SHIFT, ARM_EL_EC_LENGTH, ec);
+    return FIELD_DP32(syn, SYNDROME, EC, ec);
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec)
  */
 static inline uint32_t syn_uncategorized(void)
 {
-    return (EC_UNCATEGORIZED << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_UNCATEGORIZED);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
+FIELD(ISS_IMM16, IMM16, 0, 16)
+
 static inline uint32_t syn_aa64_svc(uint32_t imm16)
 {
-    return (EC_AA64_SVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_SVC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa64_hvc(uint32_t imm16)
 {
-    return (EC_AA64_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_HVC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa64_smc(uint32_t imm16)
 {
-    return (EC_AA64_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_SMC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit)
 {
-    return (EC_AA32_SVC << ARM_EL_EC_SHIFT) | (imm16 & 0xffff)
-        | (is_16bit ? 0 : ARM_EL_IL);
+    uint32_t res = syn_set_ec(0, EC_AA32_SVC);
+    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_hvc(uint32_t imm16)
 {
-    return (EC_AA32_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA32_HVC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_smc(void)
 {
-    return (EC_AA32_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_AA32_SMC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_aa64_bkpt(uint32_t imm16)
 {
-    return (EC_AA64_BKPT << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_BKPT);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit)
 {
-    return (EC_AA32_BKPT << ARM_EL_EC_SHIFT) | (imm16 & 0xffff)
-        | (is_16bit ? 0 : ARM_EL_IL);
+    uint32_t res = syn_set_ec(0, EC_AA32_BKPT);
+    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2,
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit)
 
 static inline uint32_t syn_sve_access_trap(void)
 {
-    return (EC_SVEACCESSTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_SVEACCESSTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
 
 static inline uint32_t syn_illegalstate(void)
 {
-    return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_ILLEGALSTATE);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_pcalignment(void)
 {
-    return (EC_PCALIGNMENT << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_PCALIGNMENT);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn)
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gcs_gcsstr(int ra, int rn)
 
 static inline uint32_t syn_serror(uint32_t extra)
 {
-    return (EC_SERROR << ARM_EL_EC_SHIFT) | ARM_EL_IL | extra;
+    uint32_t res = syn_set_ec(0, EC_SERROR);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, SYNDROME, ISS, extra);
+    return res;
 }
 
 static inline uint32_t syn_mop(bool is_set, bool is_setg, int options,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Migrate syn_aa64_sysregtrap and co-processor register trap syndromes
to the registerfields API. The co-processor syndromes are split
between single and duel register moves.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-3-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 124 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 102 insertions(+), 22 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ enum arm_exception_class {
 
 /* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */
 FIELD(SYNDROME, EC, 26, 6)
-FIELD(SYNDROME, IL, 25, 1)
+FIELD(SYNDROME, IL, 25, 1) /* IL=1 for 32 bit instructions */
 FIELD(SYNDROME, ISS, 0, 25)
 
 typedef enum {
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_smc(uint32_t imm16)
 static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit)
 {
     uint32_t res = syn_set_ec(0, EC_AA32_SVC);
-    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
     res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
     return res;
 }
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_bkpt(uint32_t imm16)
 static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit)
 {
     uint32_t res = syn_set_ec(0, EC_AA32_BKPT);
-    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
     res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
     return res;
 }
 
+/*
+ * ISS encoding for an exception from MSR, MRS, or System instruction
+ * in AArch64 state.
+ */
+FIELD(SYSREG_ISS, ISREAD, 0, 1) /* Direction, 1 is read */
+FIELD(SYSREG_ISS, CRM, 1, 4)
+FIELD(SYSREG_ISS, RT, 5, 5)
+FIELD(SYSREG_ISS, CRN, 10, 4)
+FIELD(SYSREG_ISS, OP1, 14, 3)
+FIELD(SYSREG_ISS, OP2, 17, 3)
+FIELD(SYSREG_ISS, OP0, 20, 2)
+
 static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2,
                                            int crn, int crm, int rt,
                                            int isread)
 {
-    return (EC_SYSTEMREGISTERTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL
-        | (op0 << 20) | (op2 << 17) | (op1 << 14) | (crn << 10) | (rt << 5)
-        | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_SYSTEMREGISTERTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, SYSREG_ISS, OP0, op0);
+    res = FIELD_DP32(res, SYSREG_ISS, OP2, op2);
+    res = FIELD_DP32(res, SYSREG_ISS, OP1, op1);
+    res = FIELD_DP32(res, SYSREG_ISS, CRN, crn);
+    res = FIELD_DP32(res, SYSREG_ISS, RT, rt);
+    res = FIELD_DP32(res, SYSREG_ISS, CRM, crm);
+    res = FIELD_DP32(res, SYSREG_ISS, ISREAD, isread);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from an MCR or MRC access
+ * (move to/from co-processor)
+ */
+FIELD(COPROC_ISS, ISREAD, 0, 1)
+FIELD(COPROC_ISS, CRM, 1, 4)
+FIELD(COPROC_ISS, RT, 5, 5)
+FIELD(COPROC_ISS, CRN, 10, 4)
+FIELD(COPROC_ISS, OP1, 14, 3)
+FIELD(COPROC_ISS, OP2, 17, 3)
+FIELD(COPROC_ISS, COND, 20, 4)
+FIELD(COPROC_ISS, CV, 24, 1)
+
 static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2,
                                         int crn, int crm, int rt, int isread,
                                         bool is_16bit)
 {
-    return (EC_CP14RTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14)
-        | (crn << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP14RTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_ISS, OP2, opc2);
+    res = FIELD_DP32(res, COPROC_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_ISS, CRN, crn);
+    res = FIELD_DP32(res, COPROC_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread);
+
+    return res;
 }
 
 static inline uint32_t syn_cp15_rt_trap(int cv, int cond, int opc1, int opc2,
                                         int crn, int crm, int rt, int isread,
                                         bool is_16bit)
 {
-    return (EC_CP15RTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14)
-        | (crn << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP15RTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_ISS, OP2, opc2);
+    res = FIELD_DP32(res, COPROC_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_ISS, CRN, crn);
+    res = FIELD_DP32(res, COPROC_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from an MCRR or MRRC access
+ * (move to/from co-processor with 2 regs)
+ */
+FIELD(COPROC_R2_ISS, ISREAD, 0, 1)
+FIELD(COPROC_R2_ISS, CRM, 1, 4)
+FIELD(COPROC_R2_ISS, RT, 5, 5)
+FIELD(COPROC_R2_ISS, RT2, 10, 5)
+FIELD(COPROC_R2_ISS, OP1, 16, 4)
+FIELD(COPROC_R2_ISS, COND, 20, 4)
+FIELD(COPROC_R2_ISS, CV, 24, 1)
+
 static inline uint32_t syn_cp14_rrt_trap(int cv, int cond, int opc1, int crm,
                                          int rt, int rt2, int isread,
                                          bool is_16bit)
 {
-    return (EC_CP14RRTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc1 << 16)
-        | (rt2 << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP14RRTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread);
+
+    return res;
 }
 
 static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm,
                                          int rt, int rt2, int isread,
                                          bool is_16bit)
 {
-    return (EC_CP15RRTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc1 << 16)
-        | (rt2 << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP15RRTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread);
+
+    return res;
 }
 
 static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

The syn_simd_access trap was never used so remove it. We should only
see the COPROC encoding on v7 architectures.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-4-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm,
     return res;
 }
 
+/*
+ * ISS encoding for an exception from an access to a register of
+ * instruction resulting from the FPEN or TFP traps.
+ */
+FIELD(FP_ISS, COPROC, 0, 4) /* ARMv7 only */
+FIELD(FP_ISS, COND, 20, 4)
+FIELD(FP_ISS, CV, 24, 1)
+
 static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit,
                                           int coproc)
 {
     /* AArch32 FP trap or any AArch64 FP/SIMD trap: TA == 0 */
-    return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | coproc;
-}
+    uint32_t res = syn_set_ec(0, EC_ADVSIMDFPACCESSTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
 
-static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit)
-{
-    /* AArch32 SIMD trap: TA == 1 coproc == 0 */
-    return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (1 << 5);
+    res = FIELD_DP32(res, FP_ISS, CV, cv);
+    res = FIELD_DP32(res, FP_ISS, COND, cond);
+    res = FIELD_DP32(res, FP_ISS, COPROC, coproc);
+
+    return res;
 }
 
 static inline uint32_t syn_sve_access_trap(void)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

For simplicity keep the OP as a two bit field rather than the two
interlinked fields in the docs (ERET/ERETA).

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-5-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_sve_access_trap(void)
 }
 
 /*
+ * ISS encoding for an exception from an ERET, ERETAA or ERETAB
+ * instructions.
+ *
  * eret_op is bits [1:0] of the ERET instruction, so:
  * 0 for ERET, 2 for ERETAA, 3 for ERETAB.
  */
+FIELD(ERET_ISS, OP, 0, 2)
+
 static inline uint32_t syn_erettrap(int eret_op)
 {
-    return (EC_ERETTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | eret_op;
+    uint32_t res = syn_set_ec(0, EC_ERETTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ERET_ISS, OP, eret_op);
+
+    return res;
 }
 
 static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-6-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_erettrap(int eret_op)
     return res;
 }
 
+/*
+ * ISS encoding for an exception due to SME functionality
+ */
+FIELD(SME_ISS, SMTC, 0, 2)
+
 static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit)
 {
-    return (EC_SMETRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL) | etype;
+    uint32_t res = syn_set_ec(0, EC_SMETRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+    res = FIELD_DP32(res, SME_ISS, SMTC, etype);
+
+    return res;
 }
 
 static inline uint32_t syn_pacfail(bool data, int keynumber)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

syn_pactrap is fairly simple as the ISS is all RES0.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-7-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit)
     return res;
 }
 
+/*
+ * ISS encoding for a PAC Fail exceptions
+ */
+FIELD(PACFAIL_ISS, BnA, 0, 1) /* B key or A key */
+FIELD(PACFAIL_ISS, DnI, 1, 1) /* Data or Instruction */
+
 static inline uint32_t syn_pacfail(bool data, int keynumber)
 {
-    int error_code = (data << 1) | keynumber;
-    return (EC_PACFAIL << ARM_EL_EC_SHIFT) | ARM_EL_IL | error_code;
+    uint32_t res = syn_set_ec(0, EC_PACFAIL);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, PACFAIL_ISS, DnI, data);
+    res = FIELD_DP32(res, PACFAIL_ISS, BnA, keynumber);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a trapped Pointer
+ * Authentication instruction is RES0
+ */
 static inline uint32_t syn_pactrap(void)
 {
-    return (EC_PACTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_PACTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_btitrap(int btype)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-8-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pactrap(void)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from a Branch Target Identification
+ * instruction.
+ */
+FIELD(BTI_ISS, BTYPE, 0, 2)
+
 static inline uint32_t syn_btitrap(int btype)
 {
-    return (EC_BTITRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | btype;
+    uint32_t res = syn_set_ec(0, EC_BTITRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, BTI_ISS, BTYPE, btype);
+    return res;
 }
 
 static inline uint32_t syn_bxjtrap(int cv, int cond, int rm)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

This is an Armv7 specific syndrome for chips with Jazelle
functionality.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-9-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_btitrap(int btype)
     return res;
 }
 
+/*
+ * ISS encoding for trapped BXJ execution
+ *
+ * This is an Armv7 encoding.
+ */
+FIELD(BXJ_ISS, RM, 0, 4)
+/* bits 4:19 are Reserved, UNK/SBZP */
+FIELD(BXJ_ISS, COND, 20, 4)
+FIELD(BXJ_ISS, CV, 24, 1)
+
 static inline uint32_t syn_bxjtrap(int cv, int cond, int rm)
 {
-    return (EC_BXJTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-        (cv << 24) | (cond << 20) | rm;
+    uint32_t res = syn_set_ec(0, EC_BXJTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, BXJ_ISS, CV, cv);
+    res = FIELD_DP32(res, BXJ_ISS, COND, cond);
+    res = FIELD_DP32(res, BXJ_ISS, RM, rm);
+
+    return res;
 }
 
 static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-10-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_bxjtrap(int cv, int cond, int rm)
     return res;
 }
 
+/*
+ * ISS encoding for a Granule Protection Check exception
+ *
+ * These are only reported to EL3
+ */
+FIELD(GPC_ISS, xFSC, 0, 6)
+FIELD(GPC_ISS, WnR, 6, 1) /* Write not Read */
+FIELD(GPC_ISS, S1PTW, 7, 1)
+FIELD(GPC_ISS, CM, 8, 1)
+FIELD(GPC_ISS, VNCR, 13, 1)
+FIELD(GPC_ISS, GPCSC, 14, 6)
+FIELD(GPC_ISS, InD, 20, 1) /* Instruction not Data access */
+FIELD(GPC_ISS, S2PTW, 21, 1)
+
 static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr,
                                int cm, int s1ptw, int wnr, int fsc)
 {
-    return (EC_GPC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (s2ptw << 21)
-        | (ind << 20) | (gpcsc << 14) | (vncr << 13) | (cm << 8)
-        | (s1ptw << 7) | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_GPC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GPC_ISS, S2PTW, s2ptw);
+    res = FIELD_DP32(res, GPC_ISS, InD, ind);
+    res = FIELD_DP32(res, GPC_ISS, GPCSC, gpcsc);
+    res = FIELD_DP32(res, GPC_ISS, VNCR, vncr);
+    res = FIELD_DP32(res, GPC_ISS, CM, cm);
+    res = FIELD_DP32(res, GPC_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, GPC_ISS, WnR, wnr);
+    res = FIELD_DP32(res, GPC_ISS, xFSC, fsc);
+
+    return res;
 }
 
 static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Migrate syn_insn_abort and syn_data_abort_* to the registerfields API.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260422125250.1303100-11-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 87 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 74 insertions(+), 13 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr,
     return res;
 }
 
+/*
+ * ISS encoding for an exception from an Instruction Abort
+ *
+ * (aka instruction abort)
+ */
+FIELD(IABORT_ISS, IFSC, 0, 6)
+FIELD(IABORT_ISS, S1PTW, 7, 1)
+FIELD(IABORT_ISS, EA, 9, 1)
+FIELD(IABORT_ISS, FnV, 10, 1) /* FAR not Valid */
+FIELD(IABORT_ISS, SET, 11, 2)
+FIELD(IABORT_ISS, PFV, 14, 1)
+FIELD(IABORT_ISS, TopLevel, 21, 1) /* FEAT_THE */
+
 static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc)
 {
-    return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc;
+    uint32_t res = syn_set_ec(0, EC_INSNABORT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, IABORT_ISS, EA, ea);
+    res = FIELD_DP32(res, IABORT_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, IABORT_ISS, IFSC, fsc);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a Data Abort
+ */
+FIELD(DABORT_ISS, DFSC, 0, 6)
+FIELD(DABORT_ISS, WNR, 6, 1)
+FIELD(DABORT_ISS, S1PTW, 7, 1)
+FIELD(DABORT_ISS, CM, 8, 1)
+FIELD(DABORT_ISS, EA, 9, 1)
+FIELD(DABORT_ISS, FnV, 10, 1)
+FIELD(DABORT_ISS, LST, 11, 2)
+FIELD(DABORT_ISS, VNCR, 13, 1)
+FIELD(DABORT_ISS, AR, 14, 1)
+FIELD(DABORT_ISS, SF, 15, 1)
+FIELD(DABORT_ISS, SRT, 16, 5)
+FIELD(DABORT_ISS, SSE, 21, 1)
+FIELD(DABORT_ISS, SAS, 22, 2)
+FIELD(DABORT_ISS, ISV, 24, 1)
+
 static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv,
                                              int ea, int cm, int s1ptw,
                                              int wnr, int fsc)
 {
-    return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-           | ARM_EL_IL
-           | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7)
-           | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, DABORT_ISS, FnV, fnv);
+    res = FIELD_DP32(res, DABORT_ISS, EA, ea);
+    res = FIELD_DP32(res, DABORT_ISS, CM, cm);
+    res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, DABORT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc);
+
+    return res;
 }
 
 static inline uint32_t syn_data_abort_with_iss(int same_el,
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el,
                                                int wnr, int fsc,
                                                bool is_16bit)
 {
-    return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-           | (is_16bit ? 0 : ARM_EL_IL)
-           | ARM_EL_ISV | (sas << 22) | (sse << 21) | (srt << 16)
-           | (sf << 15) | (ar << 14)
-           | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, DABORT_ISS, ISV, 1);
+    res = FIELD_DP32(res, DABORT_ISS, SAS, sas);
+    res = FIELD_DP32(res, DABORT_ISS, SSE, sse);
+    res = FIELD_DP32(res, DABORT_ISS, SRT, srt);
+    res = FIELD_DP32(res, DABORT_ISS, SF, sf);
+    res = FIELD_DP32(res, DABORT_ISS, AR, ar);
+    res = FIELD_DP32(res, DABORT_ISS, EA, ea);
+    res = FIELD_DP32(res, DABORT_ISS, CM, cm);
+    res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, DABORT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc);
+
+    return res;
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el,
  */
 static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc)
 {
-    return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (1 << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | ARM_EL_VNCR | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_DATAABORT_SAME_EL);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, DABORT_ISS, VNCR, 1);
+    res = FIELD_DP32(res, DABORT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc);
+
+    return res;
 }
 
 static inline uint32_t syn_swstep(int same_el, int isv, int ex)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Migrate syn_swstep, syn_watchpoint and syn_breakpoint to the
registerfields API.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-12-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 54 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 48 insertions(+), 6 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from a Software Step exception.
+ */
+FIELD(SOFTSTEP_ISS, IFSC, 0, 6)
+FIELD(SOFTSTEP_ISS, EX, 6, 1)
+FIELD(SOFTSTEP_ISS, ISV, 24, 1)
+
 static inline uint32_t syn_swstep(int same_el, int isv, int ex)
 {
-    return (EC_SOFTWARESTEP << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | (isv << 24) | (ex << 6) | 0x22;
+    uint32_t res = syn_set_ec(0, EC_SOFTWARESTEP + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, SOFTSTEP_ISS, ISV, isv);
+    res = FIELD_DP32(res, SOFTSTEP_ISS, EX, ex);
+    res = FIELD_DP32(res, SOFTSTEP_ISS, IFSC, 0x22);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a Watchpoint exception
+ */
+FIELD(WATCHPOINT_ISS, DFSC, 0, 6)
+FIELD(WATCHPOINT_ISS, WNR, 6, 1)
+FIELD(WATCHPOINT_ISS, CM, 8, 1)
+FIELD(WATCHPOINT_ISS, FnV, 10, 1)
+FIELD(WATCHPOINT_ISS, VNCR, 13, 1) /* FEAT_NV2 */
+FIELD(WATCHPOINT_ISS, FnP, 15, 1)
+FIELD(WATCHPOINT_ISS, WPF, 16, 1)
+/* bellow mandatory from FEAT_Debugv8p9 */
+FIELD(WATCHPOINT_ISS, WPTV, 17, 1) /* FEAT_Debugv8p2 - WPT valid */
+FIELD(WATCHPOINT_ISS, WPT, 18, 6) /* FEAT_Debugv8p2 - missing WP number */
+
 static inline uint32_t syn_watchpoint(int same_el, int cm, int wnr)
 {
-    return (EC_WATCHPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | (cm << 8) | (wnr << 6) | 0x22;
+    uint32_t res = syn_set_ec(0, EC_WATCHPOINT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, WATCHPOINT_ISS, CM, cm);
+    res = FIELD_DP32(res, WATCHPOINT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, WATCHPOINT_ISS, DFSC, 0x22);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a Breakpoint or a Vector Catch
+ * debug exception.
+ */
+FIELD(BREAKPOINT_ISS, IFSC, 0, 6)
+
 static inline uint32_t syn_breakpoint(int same_el)
 {
-    return (EC_BREAKPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | 0x22;
+    uint32_t res = syn_set_ec(0, EC_BREAKPOINT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, BREAKPOINT_ISS, IFSC, 0x22);
+
+    return res;
 }
 
 static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

This will help later when we expand the fields we report.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-13-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_breakpoint(int same_el)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from a WF* instruction
+ */
+FIELD(WFX_ISS, TI, 0, 2)
+FIELD(WFX_ISS, RV, 2, 1)
+FIELD(WFX_ISS, RN, 5, 5)
+FIELD(WFX_ISS, COND, 20, 4)
+FIELD(WFX_ISS, CV, 24, 1)
+
 static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
 {
-    return (EC_WFX_TRAP << ARM_EL_EC_SHIFT) |
-           (is_16bit ? 0 : (1 << ARM_EL_IL_SHIFT)) |
-           (cv << 24) | (cond << 20) | ti;
+    uint32_t res = syn_set_ec(0, EC_WFX_TRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, WFX_ISS, CV, cv);
+    res = FIELD_DP32(res, WFX_ISS, COND, cond);
+    res = FIELD_DP32(res, WFX_ISS, TI, ti);
+
+    return res;
 }
 
 static inline uint32_t syn_illegalstate(void)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Tweak arg names to make it clear raddr is the data address register
number.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-14-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 39 +++++++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 6 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pcalignment(void)
     return res;
 }
 
+/*
+ * ISS encoding for a GCS exception
+ *
+ * Field validity depends on EXTYPE
+ */
+FIELD(GCS_ISS, IT, 0, 5)
+FIELD(GCS_ISS, RN, 5, 5) /* only for non EXLOCK exceptions */
+FIELD(GCS_ISS, RADDR, 10, 5) /* only for GCSSTR/GCSSTTR traps */
+FIELD(GCS_ISS, EXTYPE, 20, 4)
+
 static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn)
 {
-    return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-            (GCS_ET_DataCheck << 20) | (rn << 5) | it);
+    uint32_t res = syn_set_ec(0, EC_GCS);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_DataCheck);
+    res = FIELD_DP32(res, GCS_ISS, RN, rn);
+    res = FIELD_DP32(res, GCS_ISS, IT, it);
+
+    return res;
 }
 
 static inline uint32_t syn_gcs_exlock(void)
 {
-    return (EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | (GCS_ET_EXLOCK << 20);
+    uint32_t res = syn_set_ec(0, EC_GCS);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_EXLOCK);
+
+    return res;
 }
 
-static inline uint32_t syn_gcs_gcsstr(int ra, int rn)
+static inline uint32_t syn_gcs_gcsstr(int raddr, int rn)
 {
-    return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-            (GCS_ET_GCSSTR_GCSSTTR << 20) | (ra << 10) | (rn << 5));
+    uint32_t res = syn_set_ec(0, EC_GCS);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_GCSSTR_GCSSTTR);
+    res = FIELD_DP32(res, GCS_ISS, RADDR, raddr);
+    res = FIELD_DP32(res, GCS_ISS, RN, rn);
+
+    return res;
 }
 
 static inline uint32_t syn_serror(uint32_t extra)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-15-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_serror(uint32_t extra)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from the Memory Copy and Memory Set
+ * instructions.
+ */
+FIELD(MOP_ISS, SIZEREG, 0, 5)
+FIELD(MOP_ISS, SRCREG, 5, 5)
+FIELD(MOP_ISS, DESTREG, 10, 5)
+FIELD(MOP_ISS, FORMATOPT, 16, 2)
+FIELD(MOP_ISS, OPT_A, 16, 1)
+FIELD(MOP_ISS, WRONG_OPT, 17, 1)
+FIELD(MOP_ISS, EPILOGUE, 18, 1)
+FIELD(MOP_ISS, OPTIONS, 19, 4)
+FIELD(MOP_ISS, IS_SETG, 23, 1)
+FIELD(MOP_ISS, MEMINST, 24, 1)
+
 static inline uint32_t syn_mop(bool is_set, bool is_setg, int options,
                                bool epilogue, bool wrong_option, bool option_a,
                                int destreg, int srcreg, int sizereg)
 {
-    return (EC_MOP << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-        (is_set << 24) | (is_setg << 23) | (options << 19) |
-        (epilogue << 18) | (wrong_option << 17) | (option_a << 16) |
-        (destreg << 10) | (srcreg << 5) | sizereg;
+    uint32_t res = syn_set_ec(0, EC_MOP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, MOP_ISS, MEMINST, is_set);
+    res = FIELD_DP32(res, MOP_ISS, IS_SETG, is_setg);
+    res = FIELD_DP32(res, MOP_ISS, OPTIONS, options);
+    res = FIELD_DP32(res, MOP_ISS, EPILOGUE, epilogue);
+    res = FIELD_DP32(res, MOP_ISS, WRONG_OPT, wrong_option);
+    res = FIELD_DP32(res, MOP_ISS, OPT_A, option_a);
+    res = FIELD_DP32(res, MOP_ISS, DESTREG, destreg);
+    res = FIELD_DP32(res, MOP_ISS, SRCREG, srcreg);
+    res = FIELD_DP32(res, MOP_ISS, SIZEREG, sizereg);
+
+    return res;
 }
 
 
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

It shares the same COPROC_ISS encoding as the other CP traps although
not all the fields are used.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-16-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h       | 16 ++++++++++++++++
 target/arm/tcg/vfp_helper.c |  5 +----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ FIELD(COPROC_ISS, OP2, 17, 3)
 FIELD(COPROC_ISS, COND, 20, 4)
 FIELD(COPROC_ISS, CV, 24, 1)
 
+static inline uint32_t syn_cp10_rt_trap(int cv, int cond, int opc1,
+                                        int crn, int rt, int isread)
+{
+    uint32_t res = syn_set_ec(0, EC_FPIDTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, COPROC_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_ISS, CRN, crn);
+    res = FIELD_DP32(res, COPROC_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread);
+
+    return res;
+}
+
 static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2,
                                         int crn, int crm, int rt, int isread,
                                         bool is_16bit)
diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vfp_helper.c
+++ b/target/arm/tcg/vfp_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(check_hcr_el2_trap)(CPUARMState *env, uint32_t rt, uint32_t reg)
         g_assert_not_reached();
     }
 
-    syndrome = ((EC_FPIDTRAP << ARM_EL_EC_SHIFT)
-                | ARM_EL_IL
-                | (1 << 24) | (0xe << 20) | (7 << 14)
-                | (reg << 10) | (rt << 5) | 1);
+    syndrome = syn_cp10_rt_trap(1, 0xe, 7, reg, rt, 1);
 
     raise_exception(env, EXCP_HYP_TRAP, syndrome, 2);
 }
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

One more step towards dropping the old #defines.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-17-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs)
              */
             if (cs->exception_index == EXCP_PREFETCH_ABORT ||
                 (cs->exception_index == EXCP_DATA_ABORT &&
-                 !(env->exception.syndrome & ARM_EL_ISV)) ||
+                 !FIELD_EX32(env->exception.syndrome, SYNDROME, IL)) ||
                 syn_get_ec(env->exception.syndrome) == EC_UNCATEGORIZED) {
-                env->exception.syndrome &= ~ARM_EL_IL;
+                env->exception.syndrome = FIELD_DP32(env->exception.syndrome, SYNDROME, IL, 0);
             }
         }
         env->cp15.esr_el[2] = env->exception.syndrome;
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

This removes the last use of ARM_EL_EC_SHIFT.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-18-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h  | 1 -
 target/arm/tcg/debug.c | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
 } GCSInstructionType;
 
 #define ARM_EL_EC_LENGTH 6
-#define ARM_EL_EC_SHIFT 26
 #define ARM_EL_IL_SHIFT 25
 #define ARM_EL_ISV_SHIFT 24
 #define ARM_EL_IL (1 << ARM_EL_IL_SHIFT)
diff --git a/target/arm/tcg/debug.c b/target/arm/tcg/debug.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/debug.c
+++ b/target/arm/tcg/debug.c
@@ -XXX,XX +XXX,XX @@ raise_exception_debug(CPUARMState *env, uint32_t excp, uint32_t syndrome)
      * Similarly for watchpoint and breakpoint matches.
      */
     assert(debug_el >= cur_el);
-    syndrome |= (debug_el == cur_el) << ARM_EL_EC_SHIFT;
+    syndrome |= (debug_el == cur_el) << R_SYNDROME_EC_SHIFT;
     raise_exception(env, excp, syndrome, debug_el);
 }
 
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Rather than open coding a bunch of shifts and masks we can use the
syndrome definitions. While we are at it assert it really is a
EC_DATAABORT.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-19-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/whpx/whpx-all.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/target/arm/whpx/whpx-all.c b/target/arm/whpx/whpx-all.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/whpx/whpx-all.c
+++ b/target/arm/whpx/whpx-all.c
@@ -XXX,XX +XXX,XX @@ static int whpx_handle_mmio(CPUState *cpu, WHV_MEMORY_ACCESS_CONTEXT *ctx)
 {
     uint64_t syndrome = ctx->Syndrome;
 
-    bool isv = syndrome & ARM_EL_ISV;
-    bool iswrite = (syndrome >> 6) & 1;
-    bool sse = (syndrome >> 21) & 1;
-    uint32_t sas = (syndrome >> 22) & 3;
+    bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV);
+    bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR);
+    bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE);
+    uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS);
     uint32_t len = 1 << sas;
-    uint32_t srt = (syndrome >> 16) & 0x1f;
-    uint32_t cm = (syndrome >> 8) & 0x1;
+    uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT);
+    uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM);
     uint64_t val = 0;
 
+    assert(syn_get_ec(syndrome) == EC_DATAABORT);
     assert(!cm);
     assert(isv);
 
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Rather than open coding a bunch of shifts and masks we can use the
syndrome definitions.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260422125250.1303100-20-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/hvf/hvf.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/hvf/hvf.c
+++ b/target/arm/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@ static int hvf_handle_exception(CPUState *cpu, hv_vcpu_exit_exception_t *excp)
         break;
     }
     case EC_DATAABORT: {
-        bool isv = syndrome & ARM_EL_ISV;
-        bool iswrite = (syndrome >> 6) & 1;
-        bool s1ptw = (syndrome >> 7) & 1;
-        bool sse = (syndrome >> 21) & 1;
-        uint32_t sas = (syndrome >> 22) & 3;
+        bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV);
+        bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR);
+        bool s1ptw = FIELD_EX32(syndrome, DABORT_ISS, S1PTW);
+        bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE);
+        uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS);
         uint32_t len = 1 << sas;
-        uint32_t srt = (syndrome >> 16) & 0x1f;
-        uint32_t cm = (syndrome >> 8) & 0x1;
+        uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT);
+        uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM);
         uint64_t val = 0;
         uint64_t ipa = excp->physical_address;
         AddressSpace *as = cpu_get_address_space(cpu, ARMASIdx_NS);
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

One more step to removing the old defines.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-21-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/tlb_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

From: Alex Bennée <alex.bennee@linaro.org>

These are only valid for data abort syndromes.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-22-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/tlb_helper.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/tlb_helper.c
+++ b/target/arm/tcg/tlb_helper.c
@@ -XXX,XX +XXX,XX @@ static inline uint64_t merge_syn_data_abort(uint32_t template_syn,
      * ST64BV, or ST64BV0 insns report syndrome info even for stage-1
      * faults and regardless of the target EL.
      */
-    if (template_syn & ARM_EL_VNCR) {
+    if (FIELD_EX32(template_syn, DABORT_ISS, VNCR)) {
         /*
          * FEAT_NV2 faults on accesses via VNCR_EL2 are a special case:
          * they are always reported as "same EL", even though we are going
@@ -XXX,XX +XXX,XX @@ void arm_deliver_fault(ARMCPU *cpu, vaddr addr,
      * because we masked that out in disas_set_insn_syndrome())
      */
     bool is_vncr = (access_type != MMU_INST_FETCH) &&
-        (env->exception.syndrome & ARM_EL_VNCR);
+        FIELD_EX32(env->exception.syndrome, DABORT_ISS, VNCR);
 
     if (is_vncr) {
         /* FEAT_NV2 faults on accesses via VNCR_EL2 go to EL2 */
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Now everything is defined with registerfields we can drop the old
defines.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-23-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     GCS_IT_GCSPOPX = 9,
 } GCSInstructionType;
 
-#define ARM_EL_EC_LENGTH 6
-#define ARM_EL_IL_SHIFT 25
-#define ARM_EL_ISV_SHIFT 24
-#define ARM_EL_IL (1 << ARM_EL_IL_SHIFT)
-#define ARM_EL_ISV (1 << ARM_EL_ISV_SHIFT)
-
-/* In the Data Abort syndrome */
-#define ARM_EL_VNCR (1 << 13)
-
 static inline uint32_t syn_get_ec(uint32_t syn)
 {
     return FIELD_EX32(syn, SYNDROME, EC);
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Pass the register number (rd) to the wfit helper and report it in the
syndrome ISS.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-24-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h          | 11 ++++++++++-
 target/arm/tcg/helper-defs.h   |  2 +-
 target/arm/tcg/op_helper.c     |  7 ++++---
 target/arm/tcg/translate-a64.c |  2 +-
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ FIELD(WFX_ISS, RN, 5, 5)
 FIELD(WFX_ISS, COND, 20, 4)
 FIELD(WFX_ISS, CV, 24, 1)
 
-static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
+typedef enum {
+    WFI = 0b00,
+    WFE = 0b01,
+    WFIT = 0b10,
+    WFET = 0xb11
+} wfx_ti;
+
+static inline uint32_t syn_wfx(int cv, int cond, int rn, bool rv, wfx_ti ti, bool is_16bit)
 {
     uint32_t res = syn_set_ec(0, EC_WFX_TRAP);
     res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
     res = FIELD_DP32(res, WFX_ISS, CV, cv);
     res = FIELD_DP32(res, WFX_ISS, COND, cond);
     res = FIELD_DP32(res, WFX_ISS, TI, ti);
+    res = FIELD_DP32(res, WFX_ISS, RN, rn);
+    res = FIELD_DP32(res, WFX_ISS, RV, rv);
 
     return res;
 }
diff --git a/target/arm/tcg/helper-defs.h b/target/arm/tcg/helper-defs.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-defs.h
+++ b/target/arm/tcg/helper-defs.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(exception_pc_alignment, noreturn, env, vaddr)
 DEF_HELPER_1(setend, void, env)
 DEF_HELPER_2(wfi, void, env, i32)
 DEF_HELPER_1(wfe, void, env)
-DEF_HELPER_2(wfit, void, env, i64)
+DEF_HELPER_2(wfit, void, env, i32)
 DEF_HELPER_1(yield, void, env)
 DEF_HELPER_1(pre_hvc, void, env)
 DEF_HELPER_2(pre_smc, void, env, i32)
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len)
             env->regs[15] -= insn_len;
         }
 
-        raise_exception(env, excp, syn_wfx(1, 0xe, 0, insn_len == 2),
+        raise_exception(env, excp, syn_wfx(1, 0xe, 0, false, WFI, insn_len == 2),
                         target_el);
     }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len)
 #endif
 }
 
-void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
+void HELPER(wfit)(CPUARMState *env, uint32_t rd)
 {
 #ifdef CONFIG_USER_ONLY
     /*
@@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
     int target_el = check_wfx_trap(env, false, &excp);
     /* The WFIT should time out when CNTVCT_EL0 >= the specified value. */
     uint64_t cntval = gt_get_countervalue(env);
+    uint64_t timeout = env->xregs[rd];
     /*
      * We want the value that we would get if we read CNTVCT_EL0 from
      * the current exception level, so the direct_access offset, not
@@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
 
     if (target_el) {
         env->pc -= 4;
-        raise_exception(env, excp, syn_wfx(1, 0xe, 2, false), target_el);
+        raise_exception(env, excp, syn_wfx(1, 0xe, rd, true, WFIT, false), target_el);
     }
 
     if (uadd64_overflow(timeout, offset, &nexttick)) {
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool trans_WFIT(DisasContext *s, arg_WFIT *a)
     }
 
     gen_a64_update_pc(s, 4);
-    gen_helper_wfit(tcg_env, cpu_reg(s, a->rd));
+    gen_helper_wfit(tcg_env, tcg_constant_i32(a->rd));
     /* Go back to the main loop to check for interrupts */
     s->base.is_jmp = DISAS_EXIT;
     return true;
-- 
2.43.0