Series comparison

The following changes since commit c88f1ffc19e38008a1c33ae039482a860aa7418c:

Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging (2020-05-08 14:29:18 +0100)

are available in the Git repository at:

https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200511

for you to fetch changes up to 7e17d50ebd359ee5fa3d65d7fdc0fe0336d60694:

target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed) (2020-05-11 14:22:54 +0100)

----------------------------------------------------------------
target-arm queue:
 aspeed: Add boot stub for smp booting
 target/arm: Drop access_el3_aa32ns_aa64any()
 aspeed: Support AST2600A1 silicon revision
 aspeed: sdmc: Implement AST2600 locking behaviour
 nrf51: Tracing cleanups
 target/arm: Improve handling of SVE loads and stores
 target/arm: Don't show TCG-only CPUs in KVM-only QEMU builds
 hw/arm/musicpal: Map the UART devices unconditionally
 target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)
 target/arm: Use tcg_gen_gvec_5_ptr for sve FMLA/FCMLA

----------------------------------------------------------------
Edgar E. Iglesias (1):
      target/arm: Drop access_el3_aa32ns_aa64any()

Joel Stanley (3):
      aspeed: Add boot stub for smp booting
      aspeed: Support AST2600A1 silicon revision
      aspeed: sdmc: Implement AST2600 locking behaviour

Philippe Mathieu-Daudé (8):
      hw/arm/nrf51: Add NRF51_PERIPHERAL_SIZE definition
      hw/timer/nrf51_timer: Display timer ID in trace events
      hw/timer/nrf51_timer: Add trace event of counter value update
      target/arm/kvm: Inline set_feature() calls
      target/arm/cpu: Use ARRAY_SIZE() to iterate over ARMCPUInfo[]
      target/arm/cpu: Restrict v8M IDAU interface to Aarch32 CPUs
      target/arm: Restrict TCG cpus to TCG accel
      hw/arm/musicpal: Map the UART devices unconditionally

Richard Henderson (21):
      exec: Add block comments for watchpoint routines
      exec: Fix cpu_watchpoint_address_matches address length
      accel/tcg: Add block comment for probe_access
      accel/tcg: Adjust probe_access call to page_check_range
      accel/tcg: Add probe_access_flags
      accel/tcg: Add endian-specific cpu_{ld, st}* operations
      target/arm: Use cpu_*_data_ra for sve_ldst_tlb_fn
      target/arm: Drop manual handling of set/clear_helper_retaddr
      target/arm: Add sve infrastructure for page lookup
      target/arm: Adjust interface of sve_ld1_host_fn
      target/arm: Use SVEContLdSt in sve_ld1_r
      target/arm: Handle watchpoints in sve_ld1_r
      target/arm: Use SVEContLdSt for multi-register contiguous loads
      target/arm: Update contiguous first-fault and no-fault loads
      target/arm: Use SVEContLdSt for contiguous stores
      target/arm: Reuse sve_probe_page for gather first-fault loads
      target/arm: Reuse sve_probe_page for scatter stores
      target/arm: Reuse sve_probe_page for gather loads
      target/arm: Remove sve_memopidx
      target/arm: Use tcg_gen_gvec_5_ptr for sve FMLA/FCMLA
      target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)

Thomas Huth (1):
      target/arm: Make set_feature() available for other files

From: Joel Stanley <joel@jms.id.au>

This is a boot stub that is similar to the code u-boot runs, allowing
the kernel to boot the secondary CPU.

u-boot works as follows:

1. Initialises the SMP mailbox area in the SCU at 0x1e6e2180 with default values

2. Copies a stub named 'mailbox_insn' from flash to the SCU, just above the
    mailbox area

3. Sets AST_SMP_MBOX_FIELD_READY to a magic value to indicate the
    secondary can begin execution from the stub

4. The stub waits until the AST_SMP_MBOX_FIELD_GOSIGN register is set to
    a magic value

5. Jumps to the address in AST_SMP_MBOX_FIELD_ENTRY, starting Linux

Linux indicates it is ready by writing the address of its entrypoint
function to AST_SMP_MBOX_FIELD_ENTRY and the 'go' magic number to
AST_SMP_MBOX_FIELD_GOSIGN. The secondary CPU sees this at step 4 and
breaks out of it's loop.

To be compatible, a fixed qemu stub is loaded into the mailbox area. As
qemu can ensure the stub is loaded before execution starts, we do not
need to emulate the AST_SMP_MBOX_FIELD_READY behaviour of u-boot. The
secondary CPU's program counter points to the beginning of the stub,
allowing qemu to start secondaries at step four.

Reboot behaviour is preserved by resetting AST_SMP_MBOX_FIELD_GOSIGN
when the secondaries are reset.

This is only configured when the system is booted with -kernel and qemu
does not execute u-boot first.

Reviewed-by: Cédric Le Goater <clg@kaod.org>
Tested-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/aspeed.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/aspeed.c
+++ b/hw/arm/aspeed.c
@@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps max_ram_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
+#define AST_SMP_MAILBOX_BASE            0x1e6e2180
+#define AST_SMP_MBOX_FIELD_ENTRY        (AST_SMP_MAILBOX_BASE + 0x0)
+#define AST_SMP_MBOX_FIELD_GOSIGN       (AST_SMP_MAILBOX_BASE + 0x4)
+#define AST_SMP_MBOX_FIELD_READY        (AST_SMP_MAILBOX_BASE + 0x8)
+#define AST_SMP_MBOX_FIELD_POLLINSN     (AST_SMP_MAILBOX_BASE + 0xc)
+#define AST_SMP_MBOX_CODE               (AST_SMP_MAILBOX_BASE + 0x10)
+#define AST_SMP_MBOX_GOSIGN             0xabbaab00
+
+static void aspeed_write_smpboot(ARMCPU *cpu,
+                                 const struct arm_boot_info *info)
+{
+    static const uint32_t poll_mailbox_ready[] = {
+        /*
+         * r2 = per-cpu go sign value
+         * r1 = AST_SMP_MBOX_FIELD_ENTRY
+         * r0 = AST_SMP_MBOX_FIELD_GOSIGN
+         */
+        0xee100fb0,  /* mrc     p15, 0, r0, c0, c0, 5 */
+        0xe21000ff,  /* ands    r0, r0, #255          */
+        0xe59f201c,  /* ldr     r2, [pc, #28]         */
+        0xe1822000,  /* orr     r2, r2, r0            */
+
+        0xe59f1018,  /* ldr     r1, [pc, #24]         */
+        0xe59f0018,  /* ldr     r0, [pc, #24]         */
+
+        0xe320f002,  /* wfe                           */
+        0xe5904000,  /* ldr     r4, [r0]              */
+        0xe1520004,  /* cmp     r2, r4                */
+        0x1afffffb,  /* bne     <wfe>                 */
+        0xe591f000,  /* ldr     pc, [r1]              */
+        AST_SMP_MBOX_GOSIGN,
+        AST_SMP_MBOX_FIELD_ENTRY,
+        AST_SMP_MBOX_FIELD_GOSIGN,
+    };
+
+    rom_add_blob_fixed("aspeed.smpboot", poll_mailbox_ready,
+                       sizeof(poll_mailbox_ready),
+                       info->smp_loader_start);
+}
+
+static void aspeed_reset_secondary(ARMCPU *cpu,
+                                   const struct arm_boot_info *info)
+{
+    AddressSpace *as = arm_boot_address_space(cpu, info);
+    CPUState *cs = CPU(cpu);
+
+    /* info->smp_bootreg_addr */
+    address_space_stl_notdirty(as, AST_SMP_MBOX_FIELD_GOSIGN, 0,
+                               MEMTXATTRS_UNSPECIFIED, NULL);
+    cpu_set_pc(cs, info->smp_loader_start);
+}
+
 #define FIRMWARE_ADDR 0x0
 
 static void write_boot_rom(DriveInfo *dinfo, hwaddr addr, size_t rom_size,
@@ -XXX,XX +XXX,XX @@ static void aspeed_machine_init(MachineState *machine)
         }
     }
 
+    if (machine->kernel_filename && bmc->soc.num_cpus > 1) {
+        /* With no u-boot we must set up a boot stub for the secondary CPU */
+        MemoryRegion *smpboot = g_new(MemoryRegion, 1);
+        memory_region_init_ram(smpboot, OBJECT(bmc), "aspeed.smpboot",
+                               0x80, &error_abort);
+        memory_region_add_subregion(get_system_memory(),
+                                    AST_SMP_MAILBOX_BASE, smpboot);
+
+        aspeed_board_binfo.write_secondary_boot = aspeed_write_smpboot;
+        aspeed_board_binfo.secondary_cpu_reset_hook = aspeed_reset_secondary;
+        aspeed_board_binfo.smp_loader_start = AST_SMP_MBOX_CODE;
+    }
+
     aspeed_board_binfo.ram_size = ram_size;
     aspeed_board_binfo.loader_start = sc->memmap[ASPEED_SDRAM];
     aspeed_board_binfo.nb_cpus = bmc->soc.num_cpus;
-- 
2.20.1

From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>

Calling access_el3_aa32ns() works for AArch32 only cores
but it does not handle 32-bit EL2 on top of 64-bit EL3
for mixed 32/64-bit cores.

Merge access_el3_aa32ns_aa64any() into access_el3_aa32ns()
and only use the latter.

Fixes: 68e9c2fe65 ("target-arm: Add VTCR_EL2")
Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Message-id: 20200505141729.31930-2-edgar.iglesias@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.c | 30 +++++++-----------------------
 1 file changed, 7 insertions(+), 23 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 @@ void init_cpreg_list(ARMCPU *cpu)
 }
 
 /*
- * Some registers are not accessible if EL3.NS=0 and EL3 is using AArch32 but
- * they are accessible when EL3 is using AArch64 regardless of EL3.NS.
- *
- * access_el3_aa32ns: Used to check AArch32 register views.
- * access_el3_aa32ns_aa64any: Used to check both AArch32/64 register views.
+ * Some registers are not accessible from AArch32 EL3 if SCR.NS == 0.
  */
 static CPAccessResult access_el3_aa32ns(CPUARMState *env,
                                         const ARMCPRegInfo *ri,
                                         bool isread)
 {
-    bool secure = arm_is_secure_below_el3(env);
-
-    assert(!arm_el_is_aa64(env, 3));
-    if (secure) {
+    if (!is_a64(env) && arm_current_el(env) == 3 &&
+        arm_is_secure_below_el3(env)) {
         return CP_ACCESS_TRAP_UNCATEGORIZED;
     }
     return CP_ACCESS_OK;
 }
 
-static CPAccessResult access_el3_aa32ns_aa64any(CPUARMState *env,
-                                                const ARMCPRegInfo *ri,
-                                                bool isread)
-{
-    if (!arm_el_is_aa64(env, 3)) {
-        return access_el3_aa32ns(env, ri, isread);
-    }
-    return CP_ACCESS_OK;
-}
-
 /* Some secure-only AArch32 registers trap to EL3 if used from
  * Secure EL1 (but are just ordinary UNDEF in other non-EL3 contexts).
  * Note that an access from Secure EL1 can only happen if EL3 is AArch64.
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_no_el2_cp_reginfo[] = {
       .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 },
     { .name = "VTCR_EL2", .state = ARM_CP_STATE_BOTH,
       .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 1, .opc2 = 2,
-      .access = PL2_RW, .accessfn = access_el3_aa32ns_aa64any,
+      .access = PL2_RW, .accessfn = access_el3_aa32ns,
       .type = ARM_CP_CONST, .resetvalue = 0 },
     { .name = "VTTBR", .state = ARM_CP_STATE_AA32,
       .cp = 15, .opc1 = 6, .crm = 2,
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_no_el2_cp_reginfo[] = {
       .type = ARM_CP_CONST, .resetvalue = 0 },
     { .name = "HPFAR_EL2", .state = ARM_CP_STATE_BOTH,
       .opc0 = 3, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 4,
-      .access = PL2_RW, .accessfn = access_el3_aa32ns_aa64any,
+      .access = PL2_RW, .accessfn = access_el3_aa32ns,
       .type = ARM_CP_CONST, .resetvalue = 0 },
     { .name = "HSTR_EL2", .state = ARM_CP_STATE_BOTH,
       .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 3,
@@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu)
             ARMCPRegInfo vpidr_regs[] = {
                 { .name = "VPIDR_EL2", .state = ARM_CP_STATE_BOTH,
                   .opc0 = 3, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 0,
-                  .access = PL2_RW, .accessfn = access_el3_aa32ns_aa64any,
+                  .access = PL2_RW, .accessfn = access_el3_aa32ns,
                   .type = ARM_CP_CONST, .resetvalue = cpu->midr,
                   .fieldoffset = offsetof(CPUARMState, cp15.vpidr_el2) },
                 { .name = "VMPIDR_EL2", .state = ARM_CP_STATE_BOTH,
                   .opc0 = 3, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 5,
-                  .access = PL2_RW, .accessfn = access_el3_aa32ns_aa64any,
+                  .access = PL2_RW, .accessfn = access_el3_aa32ns,
                   .type = ARM_CP_NO_RAW,
                   .writefn = arm_cp_write_ignore, .readfn = mpidr_read },
                 REGINFO_SENTINEL
-- 
2.20.1

From: Joel Stanley <joel@jms.id.au>

There are minimal differences from Qemu's point of view between the A0
and A1 silicon revisions.

As the A1 exercises different code paths in u-boot it is desirable to
emulate that instead.

Signed-off-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Message-id: 20200504093703.261135-1-joel@jms.id.au
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/hw/misc/aspeed_scu.h |  1 +
 hw/arm/aspeed.c              |  8 ++++----
 hw/arm/aspeed_ast2600.c      |  6 +++---
 hw/misc/aspeed_scu.c         | 11 +++++------
 4 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/include/hw/misc/aspeed_scu.h b/include/hw/misc/aspeed_scu.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/misc/aspeed_scu.h
+++ b/include/hw/misc/aspeed_scu.h
@@ -XXX,XX +XXX,XX @@ typedef struct AspeedSCUState {
 #define AST2500_A0_SILICON_REV   0x04000303U
 #define AST2500_A1_SILICON_REV   0x04010303U
 #define AST2600_A0_SILICON_REV   0x05000303U
+#define AST2600_A1_SILICON_REV   0x05010303U
 
 #define ASPEED_IS_AST2500(si_rev)     ((((si_rev) >> 24) & 0xff) == 0x04)
 
diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/aspeed.c
+++ b/hw/arm/aspeed.c
@@ -XXX,XX +XXX,XX @@ struct AspeedBoardState {
 
 /* Tacoma hardware value */
 #define TACOMA_BMC_HW_STRAP1  0x00000000
-#define TACOMA_BMC_HW_STRAP2  0x00000000
+#define TACOMA_BMC_HW_STRAP2  0x00000040
 
 /*
  * The max ram region is for firmwares that scan the address space
@@ -XXX,XX +XXX,XX @@ static void aspeed_machine_ast2600_evb_class_init(ObjectClass *oc, void *data)
     AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc);
 
     mc->desc       = "Aspeed AST2600 EVB (Cortex A7)";
-    amc->soc_name  = "ast2600-a0";
+    amc->soc_name  = "ast2600-a1";
     amc->hw_strap1 = AST2600_EVB_HW_STRAP1;
     amc->hw_strap2 = AST2600_EVB_HW_STRAP2;
     amc->fmc_model = "w25q512jv";
@@ -XXX,XX +XXX,XX @@ static void aspeed_machine_tacoma_class_init(ObjectClass *oc, void *data)
     MachineClass *mc = MACHINE_CLASS(oc);
     AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc);
 
-    mc->desc       = "Aspeed AST2600 EVB (Cortex A7)";
-    amc->soc_name  = "ast2600-a0";
+    mc->desc       = "OpenPOWER Tacoma BMC (Cortex A7)";
+    amc->soc_name  = "ast2600-a1";
     amc->hw_strap1 = TACOMA_BMC_HW_STRAP1;
     amc->hw_strap2 = TACOMA_BMC_HW_STRAP2;
     amc->fmc_model = "mx66l1g45g";
diff --git a/hw/arm/aspeed_ast2600.c b/hw/arm/aspeed_ast2600.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/aspeed_ast2600.c
+++ b/hw/arm/aspeed_ast2600.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_soc_ast2600_class_init(ObjectClass *oc, void *data)
 
     dc->realize      = aspeed_soc_ast2600_realize;
 
-    sc->name         = "ast2600-a0";
+    sc->name         = "ast2600-a1";
     sc->cpu_type     = ARM_CPU_TYPE_NAME("cortex-a7");
-    sc->silicon_rev  = AST2600_A0_SILICON_REV;
+    sc->silicon_rev  = AST2600_A1_SILICON_REV;
     sc->sram_size    = 0x10000;
     sc->spis_num     = 2;
     sc->ehcis_num    = 2;
@@ -XXX,XX +XXX,XX @@ static void aspeed_soc_ast2600_class_init(ObjectClass *oc, void *data)
 }
 
 static const TypeInfo aspeed_soc_ast2600_type_info = {
-    .name           = "ast2600-a0",
+    .name           = "ast2600-a1",
     .parent         = TYPE_ASPEED_SOC,
     .instance_size  = sizeof(AspeedSoCState),
     .instance_init  = aspeed_soc_ast2600_init,
diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_scu.c
+++ b/hw/misc/aspeed_scu.c
@@ -XXX,XX +XXX,XX @@ static uint32_t aspeed_silicon_revs[] = {
     AST2500_A0_SILICON_REV,
     AST2500_A1_SILICON_REV,
     AST2600_A0_SILICON_REV,
+    AST2600_A1_SILICON_REV,
 };
 
 bool is_supported_silicon_rev(uint32_t silicon_rev)
@@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps aspeed_ast2600_scu_ops = {
     .valid.unaligned = false,
 };
 
-static const uint32_t ast2600_a0_resets[ASPEED_AST2600_SCU_NR_REGS] = {
-    [AST2600_SILICON_REV]       = AST2600_SILICON_REV,
-    [AST2600_SILICON_REV2]      = AST2600_SILICON_REV,
-    [AST2600_SYS_RST_CTRL]      = 0xF7CFFEDC | 0x100,
+static const uint32_t ast2600_a1_resets[ASPEED_AST2600_SCU_NR_REGS] = {
+    [AST2600_SYS_RST_CTRL]      = 0xF7C3FED8,
     [AST2600_SYS_RST_CTRL2]     = 0xFFFFFFFC,
-    [AST2600_CLK_STOP_CTRL]     = 0xEFF43E8B,
+    [AST2600_CLK_STOP_CTRL]     = 0xFFFF7F8A,
     [AST2600_CLK_STOP_CTRL2]    = 0xFFF0FFF0,
     [AST2600_SDRAM_HANDSHAKE]   = 0x00000040,  /* SoC completed DRAM init */
     [AST2600_HPLL_PARAM]        = 0x1000405F,
@@ -XXX,XX +XXX,XX @@ static void aspeed_2600_scu_class_init(ObjectClass *klass, void *data)
 
     dc->desc = "ASPEED 2600 System Control Unit";
     dc->reset = aspeed_ast2600_scu_reset;
-    asc->resets = ast2600_a0_resets;
+    asc->resets = ast2600_a1_resets;
     asc->calc_hpll = aspeed_2500_scu_calc_hpll; /* No change since AST2500 */
     asc->apb_divider = 4;
     asc->nr_regs = ASPEED_AST2600_SCU_NR_REGS;
-- 
2.20.1

From: Joel Stanley <joel@jms.id.au>

The AST2600 handles this differently with the extra 'hardlock' state, so
move the testing to the soc specific class' write callback.

Signed-off-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Message-id: 20200505090136.341426-1-joel@jms.id.au
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/misc/aspeed_sdmc.c | 55 +++++++++++++++++++++++++++++++++++--------
 1 file changed, 45 insertions(+), 10 deletions(-)

diff --git a/hw/misc/aspeed_sdmc.c b/hw/misc/aspeed_sdmc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/aspeed_sdmc.c
+++ b/hw/misc/aspeed_sdmc.c
@@ -XXX,XX +XXX,XX @@
 
 /* Protection Key Register */
 #define R_PROT            (0x00 / 4)
+#define   PROT_UNLOCKED      0x01
+#define   PROT_HARDLOCKED    0x10  /* AST2600 */
+#define   PROT_SOFTLOCKED    0x00
+
 #define   PROT_KEY_UNLOCK     0xFC600309
+#define   PROT_KEY_HARDLOCK   0xDEADDEAD /* AST2600 */
 
 /* Configuration Register */
 #define R_CONF            (0x04 / 4)
@@ -XXX,XX +XXX,XX @@ static void aspeed_sdmc_write(void *opaque, hwaddr addr, uint64_t data,
         return;
     }
 
-    if (addr == R_PROT) {
-        s->regs[addr] = (data == PROT_KEY_UNLOCK) ? 1 : 0;
-        return;
-    }
-
-    if (!s->regs[R_PROT]) {
-        qemu_log_mask(LOG_GUEST_ERROR, "%s: SDMC is locked!\n", __func__);
-        return;
-    }
-
     asc->write(s, addr, data);
 }
 
@@ -XXX,XX +XXX,XX @@ static uint32_t aspeed_2400_sdmc_compute_conf(AspeedSDMCState *s, uint32_t data)
 static void aspeed_2400_sdmc_write(AspeedSDMCState *s, uint32_t reg,
                                    uint32_t data)
 {
+    if (reg == R_PROT) {
+        s->regs[reg] = (data == PROT_KEY_UNLOCK) ? PROT_UNLOCKED : PROT_SOFTLOCKED;
+        return;
+    }
+
+    if (!s->regs[R_PROT]) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: SDMC is locked!\n", __func__);
+        return;
+    }
+
     switch (reg) {
     case R_CONF:
         data = aspeed_2400_sdmc_compute_conf(s, data);
@@ -XXX,XX +XXX,XX @@ static uint32_t aspeed_2500_sdmc_compute_conf(AspeedSDMCState *s, uint32_t data)
 static void aspeed_2500_sdmc_write(AspeedSDMCState *s, uint32_t reg,
                                    uint32_t data)
 {
+    if (reg == R_PROT) {
+        s->regs[reg] = (data == PROT_KEY_UNLOCK) ? PROT_UNLOCKED : PROT_SOFTLOCKED;
+        return;
+    }
+
+    if (!s->regs[R_PROT]) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: SDMC is locked!\n", __func__);
+        return;
+    }
+
     switch (reg) {
     case R_CONF:
         data = aspeed_2500_sdmc_compute_conf(s, data);
@@ -XXX,XX +XXX,XX @@ static uint32_t aspeed_2600_sdmc_compute_conf(AspeedSDMCState *s, uint32_t data)
 static void aspeed_2600_sdmc_write(AspeedSDMCState *s, uint32_t reg,
                                    uint32_t data)
 {
+    if (s->regs[R_PROT] == PROT_HARDLOCKED) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: SDMC is locked until system reset!\n",
+                __func__);
+        return;
+    }
+
+    if (reg != R_PROT && s->regs[R_PROT] == PROT_SOFTLOCKED) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: SDMC is locked!\n", __func__);
+        return;
+    }
+
     switch (reg) {
+    case R_PROT:
+        if (data == PROT_KEY_UNLOCK)  {
+            data = PROT_UNLOCKED;
+        } else if (data == PROT_KEY_HARDLOCK) {
+            data = PROT_HARDLOCKED;
+        } else {
+            data = PROT_SOFTLOCKED;
+        }
+        break;
     case R_CONF:
         data = aspeed_2600_sdmc_compute_conf(s, data);
         break;
-- 
2.20.1

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

On the NRF51 series, all peripherals have a fixed I/O size
of 4KiB. Define NRF51_PERIPHERAL_SIZE and use it.

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200504072822.18799-2-f4bug@amsat.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/hw/arm/nrf51.h        | 3 +--
 include/hw/i2c/microbit_i2c.h | 2 +-
 hw/arm/nrf51_soc.c            | 4 ++--
 hw/i2c/microbit_i2c.c         | 2 +-
 hw/timer/nrf51_timer.c        | 2 +-
 5 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/include/hw/arm/nrf51.h b/include/hw/arm/nrf51.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/nrf51.h
+++ b/include/hw/arm/nrf51.h
@@ -XXX,XX +XXX,XX @@
 #define NRF51_IOMEM_BASE      0x40000000
 #define NRF51_IOMEM_SIZE      0x20000000
 
+#define NRF51_PERIPHERAL_SIZE 0x00001000
 #define NRF51_UART_BASE       0x40002000
 #define NRF51_TWI_BASE        0x40003000
-#define NRF51_TWI_SIZE        0x00001000
 #define NRF51_TIMER_BASE      0x40008000
-#define NRF51_TIMER_SIZE      0x00001000
 #define NRF51_RNG_BASE        0x4000D000
 #define NRF51_NVMC_BASE       0x4001E000
 #define NRF51_GPIO_BASE       0x50000000
diff --git a/include/hw/i2c/microbit_i2c.h b/include/hw/i2c/microbit_i2c.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/i2c/microbit_i2c.h
+++ b/include/hw/i2c/microbit_i2c.h
@@ -XXX,XX +XXX,XX @@
 #define MICROBIT_I2C(obj) \
     OBJECT_CHECK(MicrobitI2CState, (obj), TYPE_MICROBIT_I2C)
 
-#define MICROBIT_I2C_NREGS (NRF51_TWI_SIZE / sizeof(uint32_t))
+#define MICROBIT_I2C_NREGS (NRF51_PERIPHERAL_SIZE / sizeof(uint32_t))
 
 typedef struct {
     SysBusDevice parent_obj;
diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/nrf51_soc.c
+++ b/hw/arm/nrf51_soc.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp)
             return;
         }
 
-        base_addr = NRF51_TIMER_BASE + i * NRF51_TIMER_SIZE;
+        base_addr = NRF51_TIMER_BASE + i * NRF51_PERIPHERAL_SIZE;
 
         sysbus_mmio_map(SYS_BUS_DEVICE(&s->timer[i]), 0, base_addr);
         sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer[i]), 0,
@@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp)
 
     /* STUB Peripherals */
     memory_region_init_io(&s->clock, OBJECT(dev_soc), &clock_ops, NULL,
-                          "nrf51_soc.clock", 0x1000);
+                          "nrf51_soc.clock", NRF51_PERIPHERAL_SIZE);
     memory_region_add_subregion_overlap(&s->container,
                                         NRF51_IOMEM_BASE, &s->clock, -1);
 
diff --git a/hw/i2c/microbit_i2c.c b/hw/i2c/microbit_i2c.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/i2c/microbit_i2c.c
+++ b/hw/i2c/microbit_i2c.c
@@ -XXX,XX +XXX,XX @@ static void microbit_i2c_realize(DeviceState *dev, Error **errp)
     MicrobitI2CState *s = MICROBIT_I2C(dev);
 
     memory_region_init_io(&s->iomem, OBJECT(s), &microbit_i2c_ops, s,
-                          "microbit.twi", NRF51_TWI_SIZE);
+                          "microbit.twi", NRF51_PERIPHERAL_SIZE);
     sysbus_init_mmio(sbd, &s->iomem);
 }
 
diff --git a/hw/timer/nrf51_timer.c b/hw/timer/nrf51_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/nrf51_timer.c
+++ b/hw/timer/nrf51_timer.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_timer_init(Object *obj)
     SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
 
     memory_region_init_io(&s->iomem, obj, &rng_ops, s,
-            TYPE_NRF51_TIMER, NRF51_TIMER_SIZE);
+                          TYPE_NRF51_TIMER, NRF51_PERIPHERAL_SIZE);
     sysbus_init_mmio(sbd, &s->iomem);
     sysbus_init_irq(sbd, &s->irq);
 
-- 
2.20.1

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

The NRF51 series SoC have 3 timer peripherals, each having
4 counters. To help differentiate which peripheral is accessed,
display the timer ID in the trace events.

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200504072822.18799-4-f4bug@amsat.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/hw/timer/nrf51_timer.h |  1 +
 hw/arm/nrf51_soc.c             |  5 +++++
 hw/timer/nrf51_timer.c         | 11 +++++++++--
 hw/timer/trace-events          |  4 ++--
 4 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/hw/timer/nrf51_timer.h b/include/hw/timer/nrf51_timer.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/timer/nrf51_timer.h
+++ b/include/hw/timer/nrf51_timer.h
@@ -XXX,XX +XXX,XX @@ typedef struct NRF51TimerState {
     MemoryRegion iomem;
     qemu_irq irq;
 
+    uint8_t id;
     QEMUTimer timer;
     int64_t timer_start_ns;
     int64_t update_counter_ns;
diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/nrf51_soc.c
+++ b/hw/arm/nrf51_soc.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp)
 
     /* TIMER */
     for (i = 0; i < NRF51_NUM_TIMERS; i++) {
+        object_property_set_uint(OBJECT(&s->timer[i]), i, "id", &err);
+        if (err) {
+            error_propagate(errp, err);
+            return;
+        }
         object_property_set_bool(OBJECT(&s->timer[i]), true, "realized", &err);
         if (err) {
             error_propagate(errp, err);
diff --git a/hw/timer/nrf51_timer.c b/hw/timer/nrf51_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/nrf51_timer.c
+++ b/hw/timer/nrf51_timer.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/arm/nrf51.h"
 #include "hw/irq.h"
 #include "hw/timer/nrf51_timer.h"
+#include "hw/qdev-properties.h"
 #include "migration/vmstate.h"
 #include "trace.h"
 
@@ -XXX,XX +XXX,XX @@ static uint64_t nrf51_timer_read(void *opaque, hwaddr offset, unsigned int size)
                       __func__, offset);
     }
 
-    trace_nrf51_timer_read(offset, r, size);
+    trace_nrf51_timer_read(s->id, offset, r, size);
 
     return r;
 }
@@ -XXX,XX +XXX,XX @@ static void nrf51_timer_write(void *opaque, hwaddr offset,
     uint64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     size_t idx;
 
-    trace_nrf51_timer_write(offset, value, size);
+    trace_nrf51_timer_write(s->id, offset, value, size);
 
     switch (offset) {
     case NRF51_TIMER_TASK_START:
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_nrf51_timer = {
     }
 };
 
+static Property nrf51_timer_properties[] = {
+    DEFINE_PROP_UINT8("id", NRF51TimerState, id, 0),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static void nrf51_timer_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->reset = nrf51_timer_reset;
     dc->vmsd = &vmstate_nrf51_timer;
+    device_class_set_props(dc, nrf51_timer_properties);
 }
 
 static const TypeInfo nrf51_timer_info = {
diff --git a/hw/timer/trace-events b/hw/timer/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/trace-events
+++ b/hw/timer/trace-events
@@ -XXX,XX +XXX,XX @@ cmsdk_apb_dualtimer_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK
 cmsdk_apb_dualtimer_reset(void) "CMSDK APB dualtimer: reset"
 
 # nrf51_timer.c
-nrf51_timer_read(uint64_t addr, uint32_t value, unsigned size) "read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
-nrf51_timer_write(uint64_t addr, uint32_t value, unsigned size) "write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
+nrf51_timer_read(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
+nrf51_timer_write(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
 
 # bcm2835_systmr.c
 bcm2835_systmr_irq(bool enable) "timer irq state %u"
-- 
2.20.1

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

Add trace event to display timer's counter value updates.

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200504072822.18799-5-f4bug@amsat.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/timer/nrf51_timer.c | 1 +
 hw/timer/trace-events  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/hw/timer/nrf51_timer.c b/hw/timer/nrf51_timer.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/nrf51_timer.c
+++ b/hw/timer/nrf51_timer.c
@@ -XXX,XX +XXX,XX @@ static void nrf51_timer_write(void *opaque, hwaddr offset,
 
             idx = (offset - NRF51_TIMER_TASK_CAPTURE_0) / 4;
             s->cc[idx] = s->counter;
+            trace_nrf51_timer_set_count(s->id, idx, s->counter);
         }
         break;
     case NRF51_TIMER_EVENT_COMPARE_0 ... NRF51_TIMER_EVENT_COMPARE_3:
diff --git a/hw/timer/trace-events b/hw/timer/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/trace-events
+++ b/hw/timer/trace-events
@@ -XXX,XX +XXX,XX @@ cmsdk_apb_dualtimer_reset(void) "CMSDK APB dualtimer: reset"
 # nrf51_timer.c
 nrf51_timer_read(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
 nrf51_timer_write(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u"
+nrf51_timer_set_count(uint8_t timer_id, uint8_t counter_id, uint32_t value) "timer %u counter %u count 0x%" PRIx32
 
 # bcm2835_systmr.c
 bcm2835_systmr_irq(bool enable) "timer irq state %u"
-- 
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: 20200508154359.7494-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/hw/core/cpu.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -XXX,XX +XXX,XX @@ int cpu_watchpoint_remove(CPUState *cpu, vaddr addr,
                           vaddr len, int flags);
 void cpu_watchpoint_remove_by_ref(CPUState *cpu, CPUWatchpoint *watchpoint);
 void cpu_watchpoint_remove_all(CPUState *cpu, int mask);
+
+/**
+ * cpu_check_watchpoint:
+ * @cpu: cpu context
+ * @addr: guest virtual address
+ * @len: access length
+ * @attrs: memory access attributes
+ * @flags: watchpoint access type
+ * @ra: unwind return address
+ *
+ * Check for a watchpoint hit in [addr, addr+len) of the type
+ * specified by @flags.  Exit via exception with a hit.
+ */
 void cpu_check_watchpoint(CPUState *cpu, vaddr addr, vaddr len,
                           MemTxAttrs attrs, int flags, uintptr_t ra);
+
+/**
+ * cpu_watchpoint_address_matches:
+ * @cpu: cpu context
+ * @addr: guest virtual address
+ * @len: access length
+ *
+ * Return the watchpoint flags that apply to [addr, addr+len).
+ * If no watchpoint is registered for the range, the result is 0.
+ */
 int cpu_watchpoint_address_matches(CPUState *cpu, vaddr addr, vaddr len);
 #endif
 
-- 
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: 20200508154359.7494-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/exec/exec-all.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

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 @@ static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu,
 {
 }
 #endif
+/**
+ * probe_access:
+ * @env: CPUArchState
+ * @addr: guest virtual address to look up
+ * @size: size of the access
+ * @access_type: read, write or execute permission
+ * @mmu_idx: MMU index to use for lookup
+ * @retaddr: return address for unwinding
+ *
+ * Look up the guest virtual address @addr.  Raise an exception if the
+ * page does not satisfy @access_type.  Raise an exception if the
+ * access (@addr, @size) hits a watchpoint.  For writes, mark a clean
+ * page as dirty.
+ *
+ * Finally, return the host address for a page that is backed by RAM,
+ * or NULL if the page requires I/O.
+ */
 void *probe_access(CPUArchState *env, target_ulong addr, int size,
                    MMUAccessType access_type, int mmu_idx, uintptr_t retaddr);
 
-- 
2.20.1

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

We have validated that addr+size does not cross a page boundary.
Therefore we need to validate exactly one page.  We can achieve
that passing any value 1 <= x <= size to page_check_range.

Passing 1 will simplify the next patch.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-5-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/tcg/user-exec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/user-exec.c
+++ b/accel/tcg/user-exec.c
@@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size,
         g_assert_not_reached();
     }
 
-    if (!guest_addr_valid(addr) || page_check_range(addr, size, flags) < 0) {
+    if (!guest_addr_valid(addr) || page_check_range(addr, 1, flags) < 0) {
         CPUState *cpu = env_cpu(env);
         CPUClass *cc = CPU_GET_CLASS(cpu);
         cc->tlb_fill(cpu, addr, size, access_type, MMU_USER_IDX, false,
-- 
2.20.1

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

This new interface will allow targets to probe for a page
and then handle watchpoints themselves.  This will be most
useful for vector predicated memory operations, where one
page lookup can be used for many operations, and one test
can avoid many watchpoint checks.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-6-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/exec/cpu-all.h  |  13 ++-
 include/exec/exec-all.h |  22 +++++
 accel/tcg/cputlb.c      | 177 ++++++++++++++++++++--------------------
 accel/tcg/user-exec.c   |  43 ++++++++--
 4 files changed, 158 insertions(+), 97 deletions(-)

diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/cpu-all.h
+++ b/include/exec/cpu-all.h
@@ -XXX,XX +XXX,XX @@ CPUArchState *cpu_copy(CPUArchState *env);
      | CPU_INTERRUPT_TGT_EXT_3   \
      | CPU_INTERRUPT_TGT_EXT_4)
 
-#if !defined(CONFIG_USER_ONLY)
+#ifdef CONFIG_USER_ONLY
+
+/*
+ * Allow some level of source compatibility with softmmu.  We do not
+ * support any of the more exotic features, so only invalid pages may
+ * be signaled by probe_access_flags().
+ */
+#define TLB_INVALID_MASK    (1 << (TARGET_PAGE_BITS_MIN - 1))
+#define TLB_MMIO            0
+#define TLB_WATCHPOINT      0
+
+#else
 
 /*
  * Flags stored in the low bits of the TLB virtual address.
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 @@ static inline void *probe_read(CPUArchState *env, target_ulong addr, int size,
     return probe_access(env, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr);
 }
 
+/**
+ * probe_access_flags:
+ * @env: CPUArchState
+ * @addr: guest virtual address to look up
+ * @access_type: read, write or execute permission
+ * @mmu_idx: MMU index to use for lookup
+ * @nonfault: suppress the fault
+ * @phost: return value for host address
+ * @retaddr: return address for unwinding
+ *
+ * Similar to probe_access, loosely returning the TLB_FLAGS_MASK for
+ * the page, and storing the host address for RAM in @phost.
+ *
+ * If @nonfault is set, do not raise an exception but return TLB_INVALID_MASK.
+ * Do not handle watchpoints, but include TLB_WATCHPOINT in the returned flags.
+ * Do handle clean pages, so exclude TLB_NOTDIRY from the returned flags.
+ * For simplicity, all "mmio-like" flags are folded to TLB_MMIO.
+ */
+int probe_access_flags(CPUArchState *env, target_ulong addr,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool nonfault, void **phost, uintptr_t retaddr);
+
 #define CODE_GEN_ALIGN           16 /* must be >= of the size of a icache line */
 
 /* Estimated block size for TB allocation.  */
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 notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size,
     }
 }
 
-/*
- * Probe for whether the specified guest access is permitted. If it is not
- * permitted then an exception will be taken in the same way as if this
- * were a real access (and we will not return).
- * If the size is 0 or the page requires I/O access, returns NULL; otherwise,
- * returns the address of the host page similar to tlb_vaddr_to_host().
- */
-void *probe_access(CPUArchState *env, target_ulong addr, int size,
-                   MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
+static int probe_access_internal(CPUArchState *env, target_ulong addr,
+                                 int fault_size, MMUAccessType access_type,
+                                 int mmu_idx, bool nonfault,
+                                 void **phost, uintptr_t retaddr)
 {
     uintptr_t index = tlb_index(env, mmu_idx, addr);
     CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
-    target_ulong tlb_addr;
-    size_t elt_ofs;
-    int wp_access;
-
-    g_assert(-(addr | TARGET_PAGE_MASK) >= size);
-
-    switch (access_type) {
-    case MMU_DATA_LOAD:
-        elt_ofs = offsetof(CPUTLBEntry, addr_read);
-        wp_access = BP_MEM_READ;
-        break;
-    case MMU_DATA_STORE:
-        elt_ofs = offsetof(CPUTLBEntry, addr_write);
-        wp_access = BP_MEM_WRITE;
-        break;
-    case MMU_INST_FETCH:
-        elt_ofs = offsetof(CPUTLBEntry, addr_code);
-        wp_access = BP_MEM_READ;
-        break;
-    default:
-        g_assert_not_reached();
-    }
-    tlb_addr = tlb_read_ofs(entry, elt_ofs);
-
-    if (unlikely(!tlb_hit(tlb_addr, addr))) {
-        if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs,
-                            addr & TARGET_PAGE_MASK)) {
-            tlb_fill(env_cpu(env), addr, size, access_type, mmu_idx, retaddr);
-            /* TLB resize via tlb_fill may have moved the entry. */
-            index = tlb_index(env, mmu_idx, addr);
-            entry = tlb_entry(env, mmu_idx, addr);
-        }
-        tlb_addr = tlb_read_ofs(entry, elt_ofs);
-    }
-
-    if (!size) {
-        return NULL;
-    }
-
-    if (unlikely(tlb_addr & TLB_FLAGS_MASK)) {
-        CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
-
-        /* Reject I/O access, or other required slow-path.  */
-        if (tlb_addr & (TLB_MMIO | TLB_BSWAP | TLB_DISCARD_WRITE)) {
-            return NULL;
-        }
-
-        /* Handle watchpoints.  */
-        if (tlb_addr & TLB_WATCHPOINT) {
-            cpu_check_watchpoint(env_cpu(env), addr, size,
-                                 iotlbentry->attrs, wp_access, retaddr);
-        }
-
-        /* Handle clean RAM pages.  */
-        if (tlb_addr & TLB_NOTDIRTY) {
-            notdirty_write(env_cpu(env), addr, size, iotlbentry, retaddr);
-        }
-    }
-
-    return (void *)((uintptr_t)addr + entry->addend);
-}
-
-void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
-                        MMUAccessType access_type, int mmu_idx)
-{
-    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
-    target_ulong tlb_addr, page;
+    target_ulong tlb_addr, page_addr;
     size_t elt_ofs;
+    int flags;
 
     switch (access_type) {
     case MMU_DATA_LOAD:
@@ -XXX,XX +XXX,XX @@ void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
     default:
         g_assert_not_reached();
     }
-
-    page = addr & TARGET_PAGE_MASK;
     tlb_addr = tlb_read_ofs(entry, elt_ofs);
 
-    if (!tlb_hit_page(tlb_addr, page)) {
-        uintptr_t index = tlb_index(env, mmu_idx, addr);
-
-        if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page)) {
+    page_addr = addr & TARGET_PAGE_MASK;
+    if (!tlb_hit_page(tlb_addr, page_addr)) {
+        if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page_addr)) {
             CPUState *cs = env_cpu(env);
             CPUClass *cc = CPU_GET_CLASS(cs);
 
-            if (!cc->tlb_fill(cs, addr, 0, access_type, mmu_idx, true, 0)) {
+            if (!cc->tlb_fill(cs, addr, fault_size, access_type,
+                              mmu_idx, nonfault, retaddr)) {
                 /* Non-faulting page table read failed.  */
-                return NULL;
+                *phost = NULL;
+                return TLB_INVALID_MASK;
             }
 
             /* TLB resize via tlb_fill may have moved the entry.  */
@@ -XXX,XX +XXX,XX @@ void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
         }
         tlb_addr = tlb_read_ofs(entry, elt_ofs);
     }
+    flags = tlb_addr & TLB_FLAGS_MASK;
 
-    if (tlb_addr & ~TARGET_PAGE_MASK) {
-        /* IO access */
+    /* Fold all "mmio-like" bits into TLB_MMIO.  This is not RAM.  */
+    if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) {
+        *phost = NULL;
+        return TLB_MMIO;
+    }
+
+    /* Everything else is RAM. */
+    *phost = (void *)((uintptr_t)addr + entry->addend);
+    return flags;
+}
+
+int probe_access_flags(CPUArchState *env, target_ulong addr,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool nonfault, void **phost, uintptr_t retaddr)
+{
+    int flags;
+
+    flags = probe_access_internal(env, addr, 0, access_type, mmu_idx,
+                                  nonfault, phost, retaddr);
+
+    /* Handle clean RAM pages.  */
+    if (unlikely(flags & TLB_NOTDIRTY)) {
+        uintptr_t index = tlb_index(env, mmu_idx, addr);
+        CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
+
+        notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr);
+        flags &= ~TLB_NOTDIRTY;
+    }
+
+    return flags;
+}
+
+void *probe_access(CPUArchState *env, target_ulong addr, int size,
+                   MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
+{
+    void *host;
+    int flags;
+
+    g_assert(-(addr | TARGET_PAGE_MASK) >= size);
+
+    flags = probe_access_internal(env, addr, size, access_type, mmu_idx,
+                                  false, &host, retaddr);
+
+    /* Per the interface, size == 0 merely faults the access. */
+    if (size == 0) {
         return NULL;
     }
 
-    return (void *)((uintptr_t)addr + entry->addend);
+    if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) {
+        uintptr_t index = tlb_index(env, mmu_idx, addr);
+        CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
+
+        /* Handle watchpoints.  */
+        if (flags & TLB_WATCHPOINT) {
+            int wp_access = (access_type == MMU_DATA_STORE
+                             ? BP_MEM_WRITE : BP_MEM_READ);
+            cpu_check_watchpoint(env_cpu(env), addr, size,
+                                 iotlbentry->attrs, wp_access, retaddr);
+        }
+
+        /* Handle clean RAM pages.  */
+        if (flags & TLB_NOTDIRTY) {
+            notdirty_write(env_cpu(env), addr, 1, iotlbentry, retaddr);
+        }
+    }
+
+    return host;
 }
 
+void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
+                        MMUAccessType access_type, int mmu_idx)
+{
+    void *host;
+    int flags;
+
+    flags = probe_access_internal(env, addr, 0, access_type,
+                                  mmu_idx, true, &host, 0);
+
+    /* No combination of flags are expected by the caller. */
+    return flags ? NULL : host;
+}
 
 #ifdef CONFIG_PLUGIN
 /*
diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/user-exec.c
+++ b/accel/tcg/user-exec.c
@@ -XXX,XX +XXX,XX @@ static inline int handle_cpu_signal(uintptr_t pc, siginfo_t *info,
     g_assert_not_reached();
 }
 
-void *probe_access(CPUArchState *env, target_ulong addr, int size,
-                   MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
+static int probe_access_internal(CPUArchState *env, target_ulong addr,
+                                 int fault_size, MMUAccessType access_type,
+                                 bool nonfault, uintptr_t ra)
 {
     int flags;
 
-    g_assert(-(addr | TARGET_PAGE_MASK) >= size);
-
     switch (access_type) {
     case MMU_DATA_STORE:
         flags = PAGE_WRITE;
@@ -XXX,XX +XXX,XX @@ void *probe_access(CPUArchState *env, target_ulong addr, int size,
     }
 
     if (!guest_addr_valid(addr) || page_check_range(addr, 1, flags) < 0) {
-        CPUState *cpu = env_cpu(env);
-        CPUClass *cc = CPU_GET_CLASS(cpu);
-        cc->tlb_fill(cpu, addr, size, access_type, MMU_USER_IDX, false,
-                     retaddr);
-        g_assert_not_reached();
+        if (nonfault) {
+            return TLB_INVALID_MASK;
+        } else {
+            CPUState *cpu = env_cpu(env);
+            CPUClass *cc = CPU_GET_CLASS(cpu);
+            cc->tlb_fill(cpu, addr, fault_size, access_type,
+                         MMU_USER_IDX, false, ra);
+            g_assert_not_reached();
+        }
     }
+    return 0;
+}
+
+int probe_access_flags(CPUArchState *env, target_ulong addr,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool nonfault, void **phost, uintptr_t ra)
+{
+    int flags;
+
+    flags = probe_access_internal(env, addr, 0, access_type, nonfault, ra);
+    *phost = flags ? NULL : g2h(addr);
+    return flags;
+}
+
+void *probe_access(CPUArchState *env, target_ulong addr, int size,
+                   MMUAccessType access_type, int mmu_idx, uintptr_t ra)
+{
+    int flags;
+
+    g_assert(-(addr | TARGET_PAGE_MASK) >= size);
+    flags = probe_access_internal(env, addr, size, access_type, false, ra);
+    g_assert(flags == 0);
 
     return size ? g2h(addr) : NULL;
 }
-- 
2.20.1

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

We currently have target-endian versions of these operations,
but no easy way to force a specific endianness.  This can be
helpful if the target has endian-specific operations, or a mode
that swaps endianness.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/devel/loads-stores.rst |  39 +++--
 include/exec/cpu_ldst.h     | 283 +++++++++++++++++++++++++++---------
 accel/tcg/cputlb.c          | 236 ++++++++++++++++++++++--------
 accel/tcg/user-exec.c       | 211 ++++++++++++++++++++++-----
 4 files changed, 587 insertions(+), 182 deletions(-)

diff --git a/docs/devel/loads-stores.rst b/docs/devel/loads-stores.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/devel/loads-stores.rst
+++ b/docs/devel/loads-stores.rst
@@ -XXX,XX +XXX,XX @@ function, which is a return address into the generated code.
 
 Function names follow the pattern:
 
-load: ``cpu_ld{sign}{size}_mmuidx_ra(env, ptr, mmuidx, retaddr)``
+load: ``cpu_ld{sign}{size}{end}_mmuidx_ra(env, ptr, mmuidx, retaddr)``
 
-store: ``cpu_st{size}_mmuidx_ra(env, ptr, val, mmuidx, retaddr)``
+store: ``cpu_st{size}{end}_mmuidx_ra(env, ptr, val, mmuidx, retaddr)``
 
 ``sign``
  - (empty) : for 32 or 64 bit sizes
@@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}_mmuidx_ra(env, ptr, val, mmuidx, retaddr)``
  - ``l`` : 32 bits
  - ``q`` : 64 bits
 
+``end``
+ - (empty) : for target endian, or 8 bit sizes
+ - ``_be`` : big endian
+ - ``_le`` : little endian
+
 Regexes for git grep:
- - ``\<cpu_ld[us]\?[bwlq]_mmuidx_ra\>``
- - ``\<cpu_st[bwlq]_mmuidx_ra\>``
+ - ``\<cpu_ld[us]\?[bwlq](_[bl]e)\?_mmuidx_ra\>``
+ - ``\<cpu_st[bwlq](_[bl]e)\?_mmuidx_ra\>``
 
 ``cpu_{ld,st}*_data_ra``
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -XXX,XX +XXX,XX @@ be performed with a context other than the default.
 
 Function names follow the pattern:
 
-load: ``cpu_ld{sign}{size}_data_ra(env, ptr, ra)``
+load: ``cpu_ld{sign}{size}{end}_data_ra(env, ptr, ra)``
 
-store: ``cpu_st{size}_data_ra(env, ptr, val, ra)``
+store: ``cpu_st{size}{end}_data_ra(env, ptr, val, ra)``
 
 ``sign``
  - (empty) : for 32 or 64 bit sizes
@@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}_data_ra(env, ptr, val, ra)``
  - ``l`` : 32 bits
  - ``q`` : 64 bits
 
+``end``
+ - (empty) : for target endian, or 8 bit sizes
+ - ``_be`` : big endian
+ - ``_le`` : little endian
+
 Regexes for git grep:
- - ``\<cpu_ld[us]\?[bwlq]_data_ra\>``
- - ``\<cpu_st[bwlq]_data_ra\>``
+ - ``\<cpu_ld[us]\?[bwlq](_[bl]e)\?_data_ra\>``
+ - ``\<cpu_st[bwlq](_[bl]e)\?_data_ra\>``
 
 ``cpu_{ld,st}*_data``
 ~~~~~~~~~~~~~~~~~~~~~
@@ -XXX,XX +XXX,XX @@ the CPU state anyway.
 
 Function names follow the pattern:
 
-load: ``cpu_ld{sign}{size}_data(env, ptr)``
+load: ``cpu_ld{sign}{size}{end}_data(env, ptr)``
 
-store: ``cpu_st{size}_data(env, ptr, val)``
+store: ``cpu_st{size}{end}_data(env, ptr, val)``
 
 ``sign``
  - (empty) : for 32 or 64 bit sizes
@@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}_data(env, ptr, val)``
  - ``l`` : 32 bits
  - ``q`` : 64 bits
 
+``end``
+ - (empty) : for target endian, or 8 bit sizes
+ - ``_be`` : big endian
+ - ``_le`` : little endian
+
 Regexes for git grep
- - ``\<cpu_ld[us]\?[bwlq]_data\>``
- - ``\<cpu_st[bwlq]_data\+\>``
+ - ``\<cpu_ld[us]\?[bwlq](_[bl]e)\?_data\>``
+ - ``\<cpu_st[bwlq](_[bl]e)\?_data\+\>``
 
 ``cpu_ld*_code``
 ~~~~~~~~~~~~~~~~
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index XXXXXXX..XXXXXXX 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -XXX,XX +XXX,XX @@
  *
  * The syntax for the accessors is:
  *
- * load:  cpu_ld{sign}{size}_{mmusuffix}(env, ptr)
- *        cpu_ld{sign}{size}_{mmusuffix}_ra(env, ptr, retaddr)
- *        cpu_ld{sign}{size}_mmuidx_ra(env, ptr, mmu_idx, retaddr)
+ * load:  cpu_ld{sign}{size}{end}_{mmusuffix}(env, ptr)
+ *        cpu_ld{sign}{size}{end}_{mmusuffix}_ra(env, ptr, retaddr)
+ *        cpu_ld{sign}{size}{end}_mmuidx_ra(env, ptr, mmu_idx, retaddr)
  *
- * store: cpu_st{size}_{mmusuffix}(env, ptr, val)
- *        cpu_st{size}_{mmusuffix}_ra(env, ptr, val, retaddr)
- *        cpu_st{size}_mmuidx_ra(env, ptr, val, mmu_idx, retaddr)
+ * store: cpu_st{size}{end}_{mmusuffix}(env, ptr, val)
+ *        cpu_st{size}{end}_{mmusuffix}_ra(env, ptr, val, retaddr)
+ *        cpu_st{size}{end}_mmuidx_ra(env, ptr, val, mmu_idx, retaddr)
  *
  * sign is:
  * (empty): for 32 and 64 bit sizes
@@ -XXX,XX +XXX,XX @@
  *   l: 32 bits
  *   q: 64 bits
  *
+ * end is:
+ * (empty): for target native endian, or for 8 bit access
+ *     _be: for forced big endian
+ *     _le: for forced little endian
+ *
  * mmusuffix is one of the generic suffixes "data" or "code", or "mmuidx".
  * The "mmuidx" suffix carries an extra mmu_idx argument that specifies
  * the index to use; the "data" and "code" suffixes take the index from
@@ -XXX,XX +XXX,XX @@ typedef target_ulong abi_ptr;
 #endif
 
 uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr);
-uint32_t cpu_lduw_data(CPUArchState *env, abi_ptr ptr);
-uint32_t cpu_ldl_data(CPUArchState *env, abi_ptr ptr);
-uint64_t cpu_ldq_data(CPUArchState *env, abi_ptr ptr);
 int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr);
-int cpu_ldsw_data(CPUArchState *env, abi_ptr ptr);
 
-uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr);
-uint32_t cpu_lduw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr);
-uint32_t cpu_ldl_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr);
-uint64_t cpu_ldq_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr);
-int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr);
-int cpu_ldsw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr);
+uint32_t cpu_lduw_be_data(CPUArchState *env, abi_ptr ptr);
+int cpu_ldsw_be_data(CPUArchState *env, abi_ptr ptr);
+uint32_t cpu_ldl_be_data(CPUArchState *env, abi_ptr ptr);
+uint64_t cpu_ldq_be_data(CPUArchState *env, abi_ptr ptr);
+
+uint32_t cpu_lduw_le_data(CPUArchState *env, abi_ptr ptr);
+int cpu_ldsw_le_data(CPUArchState *env, abi_ptr ptr);
+uint32_t cpu_ldl_le_data(CPUArchState *env, abi_ptr ptr);
+uint64_t cpu_ldq_le_data(CPUArchState *env, abi_ptr ptr);
+
+uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+
+uint32_t cpu_lduw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+int cpu_ldsw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+uint32_t cpu_ldl_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+uint64_t cpu_ldq_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+
+uint32_t cpu_lduw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+int cpu_ldsw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+uint32_t cpu_ldl_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
+uint64_t cpu_ldq_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra);
 
 void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
-void cpu_stw_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
-void cpu_stl_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
-void cpu_stq_data(CPUArchState *env, abi_ptr ptr, uint64_t val);
+
+void cpu_stw_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
+void cpu_stl_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
+void cpu_stq_be_data(CPUArchState *env, abi_ptr ptr, uint64_t val);
+
+void cpu_stw_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
+void cpu_stl_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val);
+void cpu_stq_le_data(CPUArchState *env, abi_ptr ptr, uint64_t val);
 
 void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr);
-void cpu_stw_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr);
-void cpu_stl_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr);
-void cpu_stq_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint64_t val, uintptr_t retaddr);
+                     uint32_t val, uintptr_t ra);
+
+void cpu_stw_be_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t ra);
+void cpu_stl_be_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t ra);
+void cpu_stq_be_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint64_t val, uintptr_t ra);
+
+void cpu_stw_le_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t ra);
+void cpu_stl_le_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t ra);
+void cpu_stq_le_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint64_t val, uintptr_t ra);
 
 #if defined(CONFIG_USER_ONLY)
 
@@ -XXX,XX +XXX,XX @@ static inline uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr,
     return cpu_ldub_data_ra(env, addr, ra);
 }
 
-static inline uint32_t cpu_lduw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                          int mmu_idx, uintptr_t ra)
-{
-    return cpu_lduw_data_ra(env, addr, ra);
-}
-
-static inline uint32_t cpu_ldl_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                         int mmu_idx, uintptr_t ra)
-{
-    return cpu_ldl_data_ra(env, addr, ra);
-}
-
-static inline uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                         int mmu_idx, uintptr_t ra)
-{
-    return cpu_ldq_data_ra(env, addr, ra);
-}
-
 static inline int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                                      int mmu_idx, uintptr_t ra)
 {
     return cpu_ldsb_data_ra(env, addr, ra);
 }
 
-static inline int cpu_ldsw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                     int mmu_idx, uintptr_t ra)
+static inline uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                             int mmu_idx, uintptr_t ra)
 {
-    return cpu_ldsw_data_ra(env, addr, ra);
+    return cpu_lduw_be_data_ra(env, addr, ra);
+}
+
+static inline int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        int mmu_idx, uintptr_t ra)
+{
+    return cpu_ldsw_be_data_ra(env, addr, ra);
+}
+
+static inline uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                            int mmu_idx, uintptr_t ra)
+{
+    return cpu_ldl_be_data_ra(env, addr, ra);
+}
+
+static inline uint64_t cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                            int mmu_idx, uintptr_t ra)
+{
+    return cpu_ldq_be_data_ra(env, addr, ra);
+}
+
+static inline uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                             int mmu_idx, uintptr_t ra)
+{
+    return cpu_lduw_le_data_ra(env, addr, ra);
+}
+
+static inline int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        int mmu_idx, uintptr_t ra)
+{
+    return cpu_ldsw_le_data_ra(env, addr, ra);
+}
+
+static inline uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                            int mmu_idx, uintptr_t ra)
+{
+    return cpu_ldl_le_data_ra(env, addr, ra);
+}
+
+static inline uint64_t cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                            int mmu_idx, uintptr_t ra)
+{
+    return cpu_ldq_le_data_ra(env, addr, ra);
 }
 
 static inline void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr,
@@ -XXX,XX +XXX,XX @@ static inline void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr,
     cpu_stb_data_ra(env, addr, val, ra);
 }
 
-static inline void cpu_stw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                     uint32_t val, int mmu_idx, uintptr_t ra)
+static inline void cpu_stw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        uint32_t val, int mmu_idx,
+                                        uintptr_t ra)
 {
-    cpu_stw_data_ra(env, addr, val, ra);
+    cpu_stw_be_data_ra(env, addr, val, ra);
 }
 
-static inline void cpu_stl_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                     uint32_t val, int mmu_idx, uintptr_t ra)
+static inline void cpu_stl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        uint32_t val, int mmu_idx,
+                                        uintptr_t ra)
 {
-    cpu_stl_data_ra(env, addr, val, ra);
+    cpu_stl_be_data_ra(env, addr, val, ra);
 }
 
-static inline void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                                     uint64_t val, int mmu_idx, uintptr_t ra)
+static inline void cpu_stq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        uint64_t val, int mmu_idx,
+                                        uintptr_t ra)
 {
-    cpu_stq_data_ra(env, addr, val, ra);
+    cpu_stq_be_data_ra(env, addr, val, ra);
+}
+
+static inline void cpu_stw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        uint32_t val, int mmu_idx,
+                                        uintptr_t ra)
+{
+    cpu_stw_le_data_ra(env, addr, val, ra);
+}
+
+static inline void cpu_stl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        uint32_t val, int mmu_idx,
+                                        uintptr_t ra)
+{
+    cpu_stl_le_data_ra(env, addr, val, ra);
+}
+
+static inline void cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                                        uint64_t val, int mmu_idx,
+                                        uintptr_t ra)
+{
+    cpu_stq_le_data_ra(env, addr, val, ra);
 }
 
 #else
@@ -XXX,XX +XXX,XX @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx,
 
 uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                             int mmu_idx, uintptr_t ra);
-uint32_t cpu_lduw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                            int mmu_idx, uintptr_t ra);
-uint32_t cpu_ldl_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                           int mmu_idx, uintptr_t ra);
-uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                           int mmu_idx, uintptr_t ra);
-
 int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                        int mmu_idx, uintptr_t ra);
-int cpu_ldsw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                       int mmu_idx, uintptr_t ra);
+
+uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                               int mmu_idx, uintptr_t ra);
+int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                          int mmu_idx, uintptr_t ra);
+uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra);
+uint64_t cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra);
+
+uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                               int mmu_idx, uintptr_t ra);
+int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                          int mmu_idx, uintptr_t ra);
+uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra);
+uint64_t cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra);
 
 void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
                        int mmu_idx, uintptr_t retaddr);
-void cpu_stw_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
-                       int mmu_idx, uintptr_t retaddr);
-void cpu_stl_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
-                       int mmu_idx, uintptr_t retaddr);
-void cpu_stq_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val,
-                       int mmu_idx, uintptr_t retaddr);
+
+void cpu_stw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr);
+void cpu_stl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr);
+void cpu_stq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val,
+                          int mmu_idx, uintptr_t retaddr);
+
+void cpu_stw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr);
+void cpu_stl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr);
+void cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val,
+                          int mmu_idx, uintptr_t retaddr);
 
 #endif /* defined(CONFIG_USER_ONLY) */
 
+#ifdef TARGET_WORDS_BIGENDIAN
+# define cpu_lduw_data        cpu_lduw_be_data
+# define cpu_ldsw_data        cpu_ldsw_be_data
+# define cpu_ldl_data         cpu_ldl_be_data
+# define cpu_ldq_data         cpu_ldq_be_data
+# define cpu_lduw_data_ra     cpu_lduw_be_data_ra
+# define cpu_ldsw_data_ra     cpu_ldsw_be_data_ra
+# define cpu_ldl_data_ra      cpu_ldl_be_data_ra
+# define cpu_ldq_data_ra      cpu_ldq_be_data_ra
+# define cpu_lduw_mmuidx_ra   cpu_lduw_be_mmuidx_ra
+# define cpu_ldsw_mmuidx_ra   cpu_ldsw_be_mmuidx_ra
+# define cpu_ldl_mmuidx_ra    cpu_ldl_be_mmuidx_ra
+# define cpu_ldq_mmuidx_ra    cpu_ldq_be_mmuidx_ra
+# define cpu_stw_data         cpu_stw_be_data
+# define cpu_stl_data         cpu_stl_be_data
+# define cpu_stq_data         cpu_stq_be_data
+# define cpu_stw_data_ra      cpu_stw_be_data_ra
+# define cpu_stl_data_ra      cpu_stl_be_data_ra
+# define cpu_stq_data_ra      cpu_stq_be_data_ra
+# define cpu_stw_mmuidx_ra    cpu_stw_be_mmuidx_ra
+# define cpu_stl_mmuidx_ra    cpu_stl_be_mmuidx_ra
+# define cpu_stq_mmuidx_ra    cpu_stq_be_mmuidx_ra
+#else
+# define cpu_lduw_data        cpu_lduw_le_data
+# define cpu_ldsw_data        cpu_ldsw_le_data
+# define cpu_ldl_data         cpu_ldl_le_data
+# define cpu_ldq_data         cpu_ldq_le_data
+# define cpu_lduw_data_ra     cpu_lduw_le_data_ra
+# define cpu_ldsw_data_ra     cpu_ldsw_le_data_ra
+# define cpu_ldl_data_ra      cpu_ldl_le_data_ra
+# define cpu_ldq_data_ra      cpu_ldq_le_data_ra
+# define cpu_lduw_mmuidx_ra   cpu_lduw_le_mmuidx_ra
+# define cpu_ldsw_mmuidx_ra   cpu_ldsw_le_mmuidx_ra
+# define cpu_ldl_mmuidx_ra    cpu_ldl_le_mmuidx_ra
+# define cpu_ldq_mmuidx_ra    cpu_ldq_le_mmuidx_ra
+# define cpu_stw_data         cpu_stw_le_data
+# define cpu_stl_data         cpu_stl_le_data
+# define cpu_stq_data         cpu_stq_le_data
+# define cpu_stw_data_ra      cpu_stw_le_data_ra
+# define cpu_stl_data_ra      cpu_stl_le_data_ra
+# define cpu_stq_data_ra      cpu_stq_le_data_ra
+# define cpu_stw_mmuidx_ra    cpu_stw_le_mmuidx_ra
+# define cpu_stl_mmuidx_ra    cpu_stl_le_mmuidx_ra
+# define cpu_stq_mmuidx_ra    cpu_stq_le_mmuidx_ra
+#endif
+
 uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr);
 uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr);
 uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr);
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 @@ int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr,
                                    full_ldub_mmu);
 }
 
-uint32_t cpu_lduw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                            int mmu_idx, uintptr_t ra)
+uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                               int mmu_idx, uintptr_t ra)
 {
-    return cpu_load_helper(env, addr, mmu_idx, ra, MO_TEUW,
-                           MO_TE == MO_LE
-                           ? full_le_lduw_mmu : full_be_lduw_mmu);
+    return cpu_load_helper(env, addr, mmu_idx, ra, MO_BEUW, full_be_lduw_mmu);
 }
 
-int cpu_ldsw_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                       int mmu_idx, uintptr_t ra)
+int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                          int mmu_idx, uintptr_t ra)
 {
-    return (int16_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_TESW,
-                                    MO_TE == MO_LE
-                                    ? full_le_lduw_mmu : full_be_lduw_mmu);
+    return (int16_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_BESW,
+                                    full_be_lduw_mmu);
 }
 
-uint32_t cpu_ldl_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                           int mmu_idx, uintptr_t ra)
+uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra)
 {
-    return cpu_load_helper(env, addr, mmu_idx, ra, MO_TEUL,
-                           MO_TE == MO_LE
-                           ? full_le_ldul_mmu : full_be_ldul_mmu);
+    return cpu_load_helper(env, addr, mmu_idx, ra, MO_BEUL, full_be_ldul_mmu);
 }
 
-uint64_t cpu_ldq_mmuidx_ra(CPUArchState *env, abi_ptr addr,
-                           int mmu_idx, uintptr_t ra)
+uint64_t cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra)
 {
-    return cpu_load_helper(env, addr, mmu_idx, ra, MO_TEQ,
-                           MO_TE == MO_LE
-                           ? helper_le_ldq_mmu : helper_be_ldq_mmu);
+    return cpu_load_helper(env, addr, mmu_idx, ra, MO_BEQ, helper_be_ldq_mmu);
+}
+
+uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                               int mmu_idx, uintptr_t ra)
+{
+    return cpu_load_helper(env, addr, mmu_idx, ra, MO_LEUW, full_le_lduw_mmu);
+}
+
+int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                          int mmu_idx, uintptr_t ra)
+{
+    return (int16_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_LESW,
+                                    full_le_lduw_mmu);
+}
+
+uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra)
+{
+    return cpu_load_helper(env, addr, mmu_idx, ra, MO_LEUL, full_le_ldul_mmu);
+}
+
+uint64_t cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr,
+                              int mmu_idx, uintptr_t ra)
+{
+    return cpu_load_helper(env, addr, mmu_idx, ra, MO_LEQ, helper_le_ldq_mmu);
 }
 
 uint32_t cpu_ldub_data_ra(CPUArchState *env, target_ulong ptr,
@@ -XXX,XX +XXX,XX @@ int cpu_ldsb_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr)
     return cpu_ldsb_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
 }
 
-uint32_t cpu_lduw_data_ra(CPUArchState *env, target_ulong ptr,
-                          uintptr_t retaddr)
+uint32_t cpu_lduw_be_data_ra(CPUArchState *env, target_ulong ptr,
+                             uintptr_t retaddr)
 {
-    return cpu_lduw_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+    return cpu_lduw_be_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
 }
 
-int cpu_ldsw_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr)
+int cpu_ldsw_be_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr)
 {
-    return cpu_ldsw_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+    return cpu_ldsw_be_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
 }
 
-uint32_t cpu_ldl_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr)
+uint32_t cpu_ldl_be_data_ra(CPUArchState *env, target_ulong ptr,
+                            uintptr_t retaddr)
 {
-    return cpu_ldl_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+    return cpu_ldl_be_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
 }
 
-uint64_t cpu_ldq_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr)
+uint64_t cpu_ldq_be_data_ra(CPUArchState *env, target_ulong ptr,
+                            uintptr_t retaddr)
 {
-    return cpu_ldq_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+    return cpu_ldq_be_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+}
+
+uint32_t cpu_lduw_le_data_ra(CPUArchState *env, target_ulong ptr,
+                             uintptr_t retaddr)
+{
+    return cpu_lduw_le_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+}
+
+int cpu_ldsw_le_data_ra(CPUArchState *env, target_ulong ptr, uintptr_t retaddr)
+{
+    return cpu_ldsw_le_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+}
+
+uint32_t cpu_ldl_le_data_ra(CPUArchState *env, target_ulong ptr,
+                            uintptr_t retaddr)
+{
+    return cpu_ldl_le_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
+}
+
+uint64_t cpu_ldq_le_data_ra(CPUArchState *env, target_ulong ptr,
+                            uintptr_t retaddr)
+{
+    return cpu_ldq_le_mmuidx_ra(env, ptr, cpu_mmu_index(env, false), retaddr);
 }
 
 uint32_t cpu_ldub_data(CPUArchState *env, target_ulong ptr)
@@ -XXX,XX +XXX,XX @@ int cpu_ldsb_data(CPUArchState *env, target_ulong ptr)
     return cpu_ldsb_data_ra(env, ptr, 0);
 }
 
-uint32_t cpu_lduw_data(CPUArchState *env, target_ulong ptr)
+uint32_t cpu_lduw_be_data(CPUArchState *env, target_ulong ptr)
 {
-    return cpu_lduw_data_ra(env, ptr, 0);
+    return cpu_lduw_be_data_ra(env, ptr, 0);
 }
 
-int cpu_ldsw_data(CPUArchState *env, target_ulong ptr)
+int cpu_ldsw_be_data(CPUArchState *env, target_ulong ptr)
 {
-    return cpu_ldsw_data_ra(env, ptr, 0);
+    return cpu_ldsw_be_data_ra(env, ptr, 0);
 }
 
-uint32_t cpu_ldl_data(CPUArchState *env, target_ulong ptr)
+uint32_t cpu_ldl_be_data(CPUArchState *env, target_ulong ptr)
 {
-    return cpu_ldl_data_ra(env, ptr, 0);
+    return cpu_ldl_be_data_ra(env, ptr, 0);
 }
 
-uint64_t cpu_ldq_data(CPUArchState *env, target_ulong ptr)
+uint64_t cpu_ldq_be_data(CPUArchState *env, target_ulong ptr)
 {
-    return cpu_ldq_data_ra(env, ptr, 0);
+    return cpu_ldq_be_data_ra(env, ptr, 0);
+}
+
+uint32_t cpu_lduw_le_data(CPUArchState *env, target_ulong ptr)
+{
+    return cpu_lduw_le_data_ra(env, ptr, 0);
+}
+
+int cpu_ldsw_le_data(CPUArchState *env, target_ulong ptr)
+{
+    return cpu_ldsw_le_data_ra(env, ptr, 0);
+}
+
+uint32_t cpu_ldl_le_data(CPUArchState *env, target_ulong ptr)
+{
+    return cpu_ldl_le_data_ra(env, ptr, 0);
+}
+
+uint64_t cpu_ldq_le_data(CPUArchState *env, target_ulong ptr)
+{
+    return cpu_ldq_le_data_ra(env, ptr, 0);
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ void cpu_stb_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
     cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_UB);
 }
 
-void cpu_stw_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
-                       int mmu_idx, uintptr_t retaddr)
+void cpu_stw_be_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr)
 {
-    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEUW);
+    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_BEUW);
 }
 
-void cpu_stl_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
-                       int mmu_idx, uintptr_t retaddr)
+void cpu_stl_be_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr)
 {
-    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEUL);
+    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_BEUL);
 }
 
-void cpu_stq_mmuidx_ra(CPUArchState *env, target_ulong addr, uint64_t val,
-                       int mmu_idx, uintptr_t retaddr)
+void cpu_stq_be_mmuidx_ra(CPUArchState *env, target_ulong addr, uint64_t val,
+                          int mmu_idx, uintptr_t retaddr)
 {
-    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_TEQ);
+    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_BEQ);
+}
+
+void cpu_stw_le_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr)
+{
+    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_LEUW);
+}
+
+void cpu_stl_le_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val,
+                          int mmu_idx, uintptr_t retaddr)
+{
+    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_LEUL);
+}
+
+void cpu_stq_le_mmuidx_ra(CPUArchState *env, target_ulong addr, uint64_t val,
+                          int mmu_idx, uintptr_t retaddr)
+{
+    cpu_store_helper(env, addr, val, mmu_idx, retaddr, MO_LEQ);
 }
 
 void cpu_stb_data_ra(CPUArchState *env, target_ulong ptr,
@@ -XXX,XX +XXX,XX @@ void cpu_stb_data_ra(CPUArchState *env, target_ulong ptr,
     cpu_stb_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
 }
 
-void cpu_stw_data_ra(CPUArchState *env, target_ulong ptr,
-                     uint32_t val, uintptr_t retaddr)
+void cpu_stw_be_data_ra(CPUArchState *env, target_ulong ptr,
+                        uint32_t val, uintptr_t retaddr)
 {
-    cpu_stw_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
+    cpu_stw_be_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
 }
 
-void cpu_stl_data_ra(CPUArchState *env, target_ulong ptr,
-                     uint32_t val, uintptr_t retaddr)
+void cpu_stl_be_data_ra(CPUArchState *env, target_ulong ptr,
+                        uint32_t val, uintptr_t retaddr)
 {
-    cpu_stl_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
+    cpu_stl_be_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
 }
 
-void cpu_stq_data_ra(CPUArchState *env, target_ulong ptr,
-                     uint64_t val, uintptr_t retaddr)
+void cpu_stq_be_data_ra(CPUArchState *env, target_ulong ptr,
+                        uint64_t val, uintptr_t retaddr)
 {
-    cpu_stq_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
+    cpu_stq_be_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
+}
+
+void cpu_stw_le_data_ra(CPUArchState *env, target_ulong ptr,
+                        uint32_t val, uintptr_t retaddr)
+{
+    cpu_stw_le_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
+}
+
+void cpu_stl_le_data_ra(CPUArchState *env, target_ulong ptr,
+                        uint32_t val, uintptr_t retaddr)
+{
+    cpu_stl_le_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
+}
+
+void cpu_stq_le_data_ra(CPUArchState *env, target_ulong ptr,
+                        uint64_t val, uintptr_t retaddr)
+{
+    cpu_stq_le_mmuidx_ra(env, ptr, val, cpu_mmu_index(env, false), retaddr);
 }
 
 void cpu_stb_data(CPUArchState *env, target_ulong ptr, uint32_t val)
@@ -XXX,XX +XXX,XX @@ void cpu_stb_data(CPUArchState *env, target_ulong ptr, uint32_t val)
     cpu_stb_data_ra(env, ptr, val, 0);
 }
 
-void cpu_stw_data(CPUArchState *env, target_ulong ptr, uint32_t val)
+void cpu_stw_be_data(CPUArchState *env, target_ulong ptr, uint32_t val)
 {
-    cpu_stw_data_ra(env, ptr, val, 0);
+    cpu_stw_be_data_ra(env, ptr, val, 0);
 }
 
-void cpu_stl_data(CPUArchState *env, target_ulong ptr, uint32_t val)
+void cpu_stl_be_data(CPUArchState *env, target_ulong ptr, uint32_t val)
 {
-    cpu_stl_data_ra(env, ptr, val, 0);
+    cpu_stl_be_data_ra(env, ptr, val, 0);
 }
 
-void cpu_stq_data(CPUArchState *env, target_ulong ptr, uint64_t val)
+void cpu_stq_be_data(CPUArchState *env, target_ulong ptr, uint64_t val)
 {
-    cpu_stq_data_ra(env, ptr, val, 0);
+    cpu_stq_be_data_ra(env, ptr, val, 0);
+}
+
+void cpu_stw_le_data(CPUArchState *env, target_ulong ptr, uint32_t val)
+{
+    cpu_stw_le_data_ra(env, ptr, val, 0);
+}
+
+void cpu_stl_le_data(CPUArchState *env, target_ulong ptr, uint32_t val)
+{
+    cpu_stl_le_data_ra(env, ptr, val, 0);
+}
+
+void cpu_stq_le_data(CPUArchState *env, target_ulong ptr, uint64_t val)
+{
+    cpu_stq_le_data_ra(env, ptr, val, 0);
 }
 
 /* First set of helpers allows passing in of OI and RETADDR.  This makes
diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/tcg/user-exec.c
+++ b/accel/tcg/user-exec.c
@@ -XXX,XX +XXX,XX @@ int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr)
     return ret;
 }
 
-uint32_t cpu_lduw_data(CPUArchState *env, abi_ptr ptr)
+uint32_t cpu_lduw_be_data(CPUArchState *env, abi_ptr ptr)
 {
     uint32_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TEUW, MMU_USER_IDX, false);
+    uint16_t meminfo = trace_mem_get_info(MO_BEUW, MMU_USER_IDX, false);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = lduw_p(g2h(ptr));
+    ret = lduw_be_p(g2h(ptr));
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
     return ret;
 }
 
-int cpu_ldsw_data(CPUArchState *env, abi_ptr ptr)
+int cpu_ldsw_be_data(CPUArchState *env, abi_ptr ptr)
 {
     int ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TESW, MMU_USER_IDX, false);
+    uint16_t meminfo = trace_mem_get_info(MO_BESW, MMU_USER_IDX, false);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldsw_p(g2h(ptr));
+    ret = ldsw_be_p(g2h(ptr));
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
     return ret;
 }
 
-uint32_t cpu_ldl_data(CPUArchState *env, abi_ptr ptr)
+uint32_t cpu_ldl_be_data(CPUArchState *env, abi_ptr ptr)
 {
     uint32_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TEUL, MMU_USER_IDX, false);
+    uint16_t meminfo = trace_mem_get_info(MO_BEUL, MMU_USER_IDX, false);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldl_p(g2h(ptr));
+    ret = ldl_be_p(g2h(ptr));
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
     return ret;
 }
 
-uint64_t cpu_ldq_data(CPUArchState *env, abi_ptr ptr)
+uint64_t cpu_ldq_be_data(CPUArchState *env, abi_ptr ptr)
 {
     uint64_t ret;
-    uint16_t meminfo = trace_mem_get_info(MO_TEQ, MMU_USER_IDX, false);
+    uint16_t meminfo = trace_mem_get_info(MO_BEQ, MMU_USER_IDX, false);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    ret = ldq_p(g2h(ptr));
+    ret = ldq_be_p(g2h(ptr));
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+    return ret;
+}
+
+uint32_t cpu_lduw_le_data(CPUArchState *env, abi_ptr ptr)
+{
+    uint32_t ret;
+    uint16_t meminfo = trace_mem_get_info(MO_LEUW, MMU_USER_IDX, false);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    ret = lduw_le_p(g2h(ptr));
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+    return ret;
+}
+
+int cpu_ldsw_le_data(CPUArchState *env, abi_ptr ptr)
+{
+    int ret;
+    uint16_t meminfo = trace_mem_get_info(MO_LESW, MMU_USER_IDX, false);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    ret = ldsw_le_p(g2h(ptr));
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+    return ret;
+}
+
+uint32_t cpu_ldl_le_data(CPUArchState *env, abi_ptr ptr)
+{
+    uint32_t ret;
+    uint16_t meminfo = trace_mem_get_info(MO_LEUL, MMU_USER_IDX, false);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    ret = ldl_le_p(g2h(ptr));
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+    return ret;
+}
+
+uint64_t cpu_ldq_le_data(CPUArchState *env, abi_ptr ptr)
+{
+    uint64_t ret;
+    uint16_t meminfo = trace_mem_get_info(MO_LEQ, MMU_USER_IDX, false);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    ret = ldq_le_p(g2h(ptr));
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
     return ret;
 }
@@ -XXX,XX +XXX,XX @@ int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
     return ret;
 }
 
-uint32_t cpu_lduw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+uint32_t cpu_lduw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
 {
     uint32_t ret;
 
     set_helper_retaddr(retaddr);
-    ret = cpu_lduw_data(env, ptr);
+    ret = cpu_lduw_be_data(env, ptr);
     clear_helper_retaddr();
     return ret;
 }
 
-int cpu_ldsw_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+int cpu_ldsw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
 {
     int ret;
 
     set_helper_retaddr(retaddr);
-    ret = cpu_ldsw_data(env, ptr);
+    ret = cpu_ldsw_be_data(env, ptr);
     clear_helper_retaddr();
     return ret;
 }
 
-uint32_t cpu_ldl_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+uint32_t cpu_ldl_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
 {
     uint32_t ret;
 
     set_helper_retaddr(retaddr);
-    ret = cpu_ldl_data(env, ptr);
+    ret = cpu_ldl_be_data(env, ptr);
     clear_helper_retaddr();
     return ret;
 }
 
-uint64_t cpu_ldq_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+uint64_t cpu_ldq_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
 {
     uint64_t ret;
 
     set_helper_retaddr(retaddr);
-    ret = cpu_ldq_data(env, ptr);
+    ret = cpu_ldq_be_data(env, ptr);
+    clear_helper_retaddr();
+    return ret;
+}
+
+uint32_t cpu_lduw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+{
+    uint32_t ret;
+
+    set_helper_retaddr(retaddr);
+    ret = cpu_lduw_le_data(env, ptr);
+    clear_helper_retaddr();
+    return ret;
+}
+
+int cpu_ldsw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+{
+    int ret;
+
+    set_helper_retaddr(retaddr);
+    ret = cpu_ldsw_le_data(env, ptr);
+    clear_helper_retaddr();
+    return ret;
+}
+
+uint32_t cpu_ldl_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+{
+    uint32_t ret;
+
+    set_helper_retaddr(retaddr);
+    ret = cpu_ldl_le_data(env, ptr);
+    clear_helper_retaddr();
+    return ret;
+}
+
+uint64_t cpu_ldq_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr)
+{
+    uint64_t ret;
+
+    set_helper_retaddr(retaddr);
+    ret = cpu_ldq_le_data(env, ptr);
     clear_helper_retaddr();
     return ret;
 }
@@ -XXX,XX +XXX,XX @@ void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
 }
 
-void cpu_stw_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
+void cpu_stw_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
 {
-    uint16_t meminfo = trace_mem_get_info(MO_TEUW, MMU_USER_IDX, true);
+    uint16_t meminfo = trace_mem_get_info(MO_BEUW, MMU_USER_IDX, true);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stw_p(g2h(ptr), val);
+    stw_be_p(g2h(ptr), val);
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
 }
 
-void cpu_stl_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
+void cpu_stl_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
 {
-    uint16_t meminfo = trace_mem_get_info(MO_TEUL, MMU_USER_IDX, true);
+    uint16_t meminfo = trace_mem_get_info(MO_BEUL, MMU_USER_IDX, true);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stl_p(g2h(ptr), val);
+    stl_be_p(g2h(ptr), val);
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
 }
 
-void cpu_stq_data(CPUArchState *env, abi_ptr ptr, uint64_t val)
+void cpu_stq_be_data(CPUArchState *env, abi_ptr ptr, uint64_t val)
 {
-    uint16_t meminfo = trace_mem_get_info(MO_TEQ, MMU_USER_IDX, true);
+    uint16_t meminfo = trace_mem_get_info(MO_BEQ, MMU_USER_IDX, true);
 
     trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
-    stq_p(g2h(ptr), val);
+    stq_be_p(g2h(ptr), val);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+}
+
+void cpu_stw_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
+{
+    uint16_t meminfo = trace_mem_get_info(MO_LEUW, MMU_USER_IDX, true);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    stw_le_p(g2h(ptr), val);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+}
+
+void cpu_stl_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val)
+{
+    uint16_t meminfo = trace_mem_get_info(MO_LEUL, MMU_USER_IDX, true);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    stl_le_p(g2h(ptr), val);
+    qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
+}
+
+void cpu_stq_le_data(CPUArchState *env, abi_ptr ptr, uint64_t val)
+{
+    uint16_t meminfo = trace_mem_get_info(MO_LEQ, MMU_USER_IDX, true);
+
+    trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo);
+    stq_le_p(g2h(ptr), val);
     qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo);
 }
 
@@ -XXX,XX +XXX,XX @@ void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr,
     clear_helper_retaddr();
 }
 
-void cpu_stw_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr)
+void cpu_stw_be_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t retaddr)
 {
     set_helper_retaddr(retaddr);
-    cpu_stw_data(env, ptr, val);
+    cpu_stw_be_data(env, ptr, val);
     clear_helper_retaddr();
 }
 
-void cpu_stl_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint32_t val, uintptr_t retaddr)
+void cpu_stl_be_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t retaddr)
 {
     set_helper_retaddr(retaddr);
-    cpu_stl_data(env, ptr, val);
+    cpu_stl_be_data(env, ptr, val);
     clear_helper_retaddr();
 }
 
-void cpu_stq_data_ra(CPUArchState *env, abi_ptr ptr,
-                     uint64_t val, uintptr_t retaddr)
+void cpu_stq_be_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint64_t val, uintptr_t retaddr)
 {
     set_helper_retaddr(retaddr);
-    cpu_stq_data(env, ptr, val);
+    cpu_stq_be_data(env, ptr, val);
+    clear_helper_retaddr();
+}
+
+void cpu_stw_le_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t retaddr)
+{
+    set_helper_retaddr(retaddr);
+    cpu_stw_le_data(env, ptr, val);
+    clear_helper_retaddr();
+}
+
+void cpu_stl_le_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint32_t val, uintptr_t retaddr)
+{
+    set_helper_retaddr(retaddr);
+    cpu_stl_le_data(env, ptr, val);
+    clear_helper_retaddr();
+}
+
+void cpu_stq_le_data_ra(CPUArchState *env, abi_ptr ptr,
+                        uint64_t val, uintptr_t retaddr)
+{
+    set_helper_retaddr(retaddr);
+    cpu_stq_le_data(env, ptr, val);
     clear_helper_retaddr();
 }
 
-- 
2.20.1

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

Use the "normal" memory access functions, rather than the
softmmu internal helper functions directly.

Since fb901c905dc3, cpu_mem_index is now a simple extract
from env->hflags and not a large computation.  Which means
that it's now more work to pass around this value than it
is to recompute it.

This only adjusts the primitives, and does not clean up
all of the uses within sve_helper.c.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 221 ++++++++++++++++------------------------
 1 file changed, 86 insertions(+), 135 deletions(-)

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 @@ typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host,
  * Load one element into @vd + @reg_off from (@env, @vaddr, @ra).
  * The controlling predicate is known to be true.
  */
-typedef void sve_ld1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off,
-                            target_ulong vaddr, TCGMemOpIdx oi, uintptr_t ra);
-typedef sve_ld1_tlb_fn sve_st1_tlb_fn;
+typedef void sve_ldst1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off,
+                              target_ulong vaddr, uintptr_t retaddr);
 
 /*
  * Generate the above primitives.
@@ -XXX,XX +XXX,XX @@ static intptr_t sve_##NAME##_host(void *vd, void *vg, void *host,           \
     return mem_off;                                                         \
 }
 
-#ifdef CONFIG_SOFTMMU
-#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \
+#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, TLB) \
 static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off,  \
-                             target_ulong addr, TCGMemOpIdx oi, uintptr_t ra)  \
+                             target_ulong addr, uintptr_t ra)               \
 {                                                                           \
-    TYPEM val = TLB(env, addr, oi, ra);                                     \
-    *(TYPEE *)(vd + H(reg_off)) = val;                                      \
+    *(TYPEE *)(vd + H(reg_off)) = (TYPEM)TLB(env, addr, ra);                \
 }
-#else
-#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB)                  \
+
+#define DO_ST_TLB(NAME, H, TYPEE, TYPEM, TLB) \
 static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off,  \
-                             target_ulong addr, TCGMemOpIdx oi, uintptr_t ra)  \
+                             target_ulong addr, uintptr_t ra)               \
 {                                                                           \
-    TYPEM val = HOST(g2h(addr));                                            \
-    *(TYPEE *)(vd + H(reg_off)) = val;                                      \
+    TLB(env, addr, (TYPEM)*(TYPEE *)(vd + H(reg_off)), ra);                 \
 }
-#endif
 
 #define DO_LD_PRIM_1(NAME, H, TE, TM)                   \
     DO_LD_HOST(NAME, H, TE, TM, ldub_p)                 \
-    DO_LD_TLB(NAME, H, TE, TM, ldub_p, 0, helper_ret_ldub_mmu)
+    DO_LD_TLB(NAME, H, TE, TM, cpu_ldub_data_ra)
 
 DO_LD_PRIM_1(ld1bb,  H1,   uint8_t,  uint8_t)
 DO_LD_PRIM_1(ld1bhu, H1_2, uint16_t, uint8_t)
@@ -XXX,XX +XXX,XX @@ DO_LD_PRIM_1(ld1bss, H1_4, uint32_t,  int8_t)
 DO_LD_PRIM_1(ld1bdu,     , uint64_t, uint8_t)
 DO_LD_PRIM_1(ld1bds,     , uint64_t,  int8_t)
 
-#define DO_LD_PRIM_2(NAME, end, MOEND, H, TE, TM, PH, PT)  \
-    DO_LD_HOST(NAME##_##end, H, TE, TM, PH##_##end##_p)    \
-    DO_LD_TLB(NAME##_##end, H, TE, TM, PH##_##end##_p,     \
-              MOEND, helper_##end##_##PT##_mmu)
+#define DO_ST_PRIM_1(NAME, H, TE, TM)                   \
+    DO_ST_TLB(st1##NAME, H, TE, TM, cpu_stb_data_ra)
 
-DO_LD_PRIM_2(ld1hh,  le, MO_LE, H1_2, uint16_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hsu, le, MO_LE, H1_4, uint32_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hss, le, MO_LE, H1_4, uint32_t,  int16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hdu, le, MO_LE,     , uint64_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hds, le, MO_LE,     , uint64_t,  int16_t, lduw, lduw)
+DO_ST_PRIM_1(bb,   H1,  uint8_t, uint8_t)
+DO_ST_PRIM_1(bh, H1_2, uint16_t, uint8_t)
+DO_ST_PRIM_1(bs, H1_4, uint32_t, uint8_t)
+DO_ST_PRIM_1(bd,     , uint64_t, uint8_t)
 
-DO_LD_PRIM_2(ld1ss,  le, MO_LE, H1_4, uint32_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sdu, le, MO_LE,     , uint64_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sds, le, MO_LE,     , uint64_t,  int32_t, ldl, ldul)
+#define DO_LD_PRIM_2(NAME, H, TE, TM, LD) \
+    DO_LD_HOST(ld1##NAME##_be, H, TE, TM, LD##_be_p)    \
+    DO_LD_HOST(ld1##NAME##_le, H, TE, TM, LD##_le_p)    \
+    DO_LD_TLB(ld1##NAME##_be, H, TE, TM, cpu_##LD##_be_data_ra) \
+    DO_LD_TLB(ld1##NAME##_le, H, TE, TM, cpu_##LD##_le_data_ra)
 
-DO_LD_PRIM_2(ld1dd,  le, MO_LE,     , uint64_t, uint64_t, ldq, ldq)
+#define DO_ST_PRIM_2(NAME, H, TE, TM, ST) \
+    DO_ST_TLB(st1##NAME##_be, H, TE, TM, cpu_##ST##_be_data_ra) \
+    DO_ST_TLB(st1##NAME##_le, H, TE, TM, cpu_##ST##_le_data_ra)
 
-DO_LD_PRIM_2(ld1hh,  be, MO_BE, H1_2, uint16_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hsu, be, MO_BE, H1_4, uint32_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hss, be, MO_BE, H1_4, uint32_t,  int16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hdu, be, MO_BE,     , uint64_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hds, be, MO_BE,     , uint64_t,  int16_t, lduw, lduw)
+DO_LD_PRIM_2(hh,  H1_2, uint16_t, uint16_t, lduw)
+DO_LD_PRIM_2(hsu, H1_4, uint32_t, uint16_t, lduw)
+DO_LD_PRIM_2(hss, H1_4, uint32_t,  int16_t, lduw)
+DO_LD_PRIM_2(hdu,     , uint64_t, uint16_t, lduw)
+DO_LD_PRIM_2(hds,     , uint64_t,  int16_t, lduw)
 
-DO_LD_PRIM_2(ld1ss,  be, MO_BE, H1_4, uint32_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sdu, be, MO_BE,     , uint64_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sds, be, MO_BE,     , uint64_t,  int32_t, ldl, ldul)
+DO_ST_PRIM_2(hh, H1_2, uint16_t, uint16_t, stw)
+DO_ST_PRIM_2(hs, H1_4, uint32_t, uint16_t, stw)
+DO_ST_PRIM_2(hd,     , uint64_t, uint16_t, stw)
 
-DO_LD_PRIM_2(ld1dd,  be, MO_BE,     , uint64_t, uint64_t, ldq, ldq)
+DO_LD_PRIM_2(ss,  H1_4, uint32_t, uint32_t, ldl)
+DO_LD_PRIM_2(sdu,     , uint64_t, uint32_t, ldl)
+DO_LD_PRIM_2(sds,     , uint64_t,  int32_t, ldl)
+
+DO_ST_PRIM_2(ss, H1_4, uint32_t, uint32_t, stl)
+DO_ST_PRIM_2(sd,     , uint64_t, uint32_t, stl)
+
+DO_LD_PRIM_2(dd,     , uint64_t, uint64_t, ldq)
+DO_ST_PRIM_2(dd,     , uint64_t, uint64_t, stq)
 
 #undef DO_LD_TLB
+#undef DO_ST_TLB
 #undef DO_LD_HOST
 #undef DO_LD_PRIM_1
+#undef DO_ST_PRIM_1
 #undef DO_LD_PRIM_2
+#undef DO_ST_PRIM_2
 
 /*
  * Skip through a sequence of inactive elements in the guarding predicate @vg,
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
                       uint32_t desc, const uintptr_t retaddr,
                       const int esz, const int msz,
                       sve_ld1_host_fn *host_fn,
-                      sve_ld1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
     const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const int mmu_idx = get_mmuidx(oi);
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
          * on I/O memory, it may succeed but not bring in the TLB entry.
          * But even then we have still made forward progress.
          */
-        tlb_fn(env, &scratch, reg_off, addr + mem_off, oi, retaddr);
+        tlb_fn(env, &scratch, reg_off, addr + mem_off, retaddr);
         reg_off += 1 << esz;
     }
 #endif
@@ -XXX,XX +XXX,XX @@ DO_LD1_2(ld1dd,  3, 3)
  */
 static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, int size, uintptr_t ra,
-                      sve_ld1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch[2] = { };
@@ -XXX,XX +XXX,XX @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, &scratch[0], i, addr, oi, ra);
-                tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
+                tlb_fn(env, &scratch[0], i, addr, ra);
+                tlb_fn(env, &scratch[1], i, addr + size, ra);
             }
             i += size, pg >>= size;
             addr += 2 * size;
@@ -XXX,XX +XXX,XX @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
 
 static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, int size, uintptr_t ra,
-                      sve_ld1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch[3] = { };
@@ -XXX,XX +XXX,XX @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, &scratch[0], i, addr, oi, ra);
-                tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
-                tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra);
+                tlb_fn(env, &scratch[0], i, addr, ra);
+                tlb_fn(env, &scratch[1], i, addr + size, ra);
+                tlb_fn(env, &scratch[2], i, addr + 2 * size, ra);
             }
             i += size, pg >>= size;
             addr += 3 * size;
@@ -XXX,XX +XXX,XX @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
 
 static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, int size, uintptr_t ra,
-                      sve_ld1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch[4] = { };
@@ -XXX,XX +XXX,XX @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, &scratch[0], i, addr, oi, ra);
-                tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
-                tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra);
-                tlb_fn(env, &scratch[3], i, addr + 3 * size, oi, ra);
+                tlb_fn(env, &scratch[0], i, addr, ra);
+                tlb_fn(env, &scratch[1], i, addr + size, ra);
+                tlb_fn(env, &scratch[2], i, addr + 2 * size, ra);
+                tlb_fn(env, &scratch[3], i, addr + 3 * size, ra);
             }
             i += size, pg >>= size;
             addr += 4 * size;
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
                         uint32_t desc, const uintptr_t retaddr,
                         const int esz, const int msz,
                         sve_ld1_host_fn *host_fn,
-                        sve_ld1_tlb_fn *tlb_fn)
+                        sve_ldst1_tlb_fn *tlb_fn)
 {
     const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const int mmu_idx = get_mmuidx(oi);
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
      * Perform one normal read, which will fault or not.
      * But it is likely to bring the page into the tlb.
      */
-    tlb_fn(env, vd, reg_off, addr + mem_off, oi, retaddr);
+    tlb_fn(env, vd, reg_off, addr + mem_off, retaddr);
 
     /* After any fault, zero any leading predicated false elts.  */
     swap_memzero(vd, reg_off);
@@ -XXX,XX +XXX,XX @@ DO_LDFF1_LDNF1_2(dd,  3, 3)
 #undef DO_LDFF1_LDNF1_1
 #undef DO_LDFF1_LDNF1_2
 
-/*
- * Store contiguous data, protected by a governing predicate.
- */
-
-#ifdef CONFIG_SOFTMMU
-#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \
-static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off,  \
-                             target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \
-{                                                                           \
-    TLB(env, addr, *(TYPEM *)(vd + H(reg_off)), oi, ra);                    \
-}
-#else
-#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \
-static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off,  \
-                             target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \
-{                                                                           \
-    HOST(g2h(addr), *(TYPEM *)(vd + H(reg_off)));                           \
-}
-#endif
-
-DO_ST_TLB(st1bb,   H1,  uint8_t, stb_p, 0, helper_ret_stb_mmu)
-DO_ST_TLB(st1bh, H1_2, uint16_t, stb_p, 0, helper_ret_stb_mmu)
-DO_ST_TLB(st1bs, H1_4, uint32_t, stb_p, 0, helper_ret_stb_mmu)
-DO_ST_TLB(st1bd,     , uint64_t, stb_p, 0, helper_ret_stb_mmu)
-
-DO_ST_TLB(st1hh_le, H1_2, uint16_t, stw_le_p, MO_LE, helper_le_stw_mmu)
-DO_ST_TLB(st1hs_le, H1_4, uint32_t, stw_le_p, MO_LE, helper_le_stw_mmu)
-DO_ST_TLB(st1hd_le,     , uint64_t, stw_le_p, MO_LE, helper_le_stw_mmu)
-
-DO_ST_TLB(st1ss_le, H1_4, uint32_t, stl_le_p, MO_LE, helper_le_stl_mmu)
-DO_ST_TLB(st1sd_le,     , uint64_t, stl_le_p, MO_LE, helper_le_stl_mmu)
-
-DO_ST_TLB(st1dd_le,     , uint64_t, stq_le_p, MO_LE, helper_le_stq_mmu)
-
-DO_ST_TLB(st1hh_be, H1_2, uint16_t, stw_be_p, MO_BE, helper_be_stw_mmu)
-DO_ST_TLB(st1hs_be, H1_4, uint32_t, stw_be_p, MO_BE, helper_be_stw_mmu)
-DO_ST_TLB(st1hd_be,     , uint64_t, stw_be_p, MO_BE, helper_be_stw_mmu)
-
-DO_ST_TLB(st1ss_be, H1_4, uint32_t, stl_be_p, MO_BE, helper_be_stl_mmu)
-DO_ST_TLB(st1sd_be,     , uint64_t, stl_be_p, MO_BE, helper_be_stl_mmu)
-
-DO_ST_TLB(st1dd_be,     , uint64_t, stq_be_p, MO_BE, helper_be_stq_mmu)
-
-#undef DO_ST_TLB
-
 /*
  * Common helpers for all contiguous 1,2,3,4-register predicated stores.
  */
 static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, const uintptr_t ra,
                       const int esize, const int msize,
-                      sve_st1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     void *vd = &env->vfp.zregs[rd];
@@ -XXX,XX +XXX,XX @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, vd, i, addr, oi, ra);
+                tlb_fn(env, vd, i, addr, ra);
             }
             i += esize, pg >>= esize;
             addr += msize;
@@ -XXX,XX +XXX,XX @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
 static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, const uintptr_t ra,
                       const int esize, const int msize,
-                      sve_st1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     void *d1 = &env->vfp.zregs[rd];
@@ -XXX,XX +XXX,XX @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, d1, i, addr, oi, ra);
-                tlb_fn(env, d2, i, addr + msize, oi, ra);
+                tlb_fn(env, d1, i, addr, ra);
+                tlb_fn(env, d2, i, addr + msize, ra);
             }
             i += esize, pg >>= esize;
             addr += 2 * msize;
@@ -XXX,XX +XXX,XX @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
 static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, const uintptr_t ra,
                       const int esize, const int msize,
-                      sve_st1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     void *d1 = &env->vfp.zregs[rd];
@@ -XXX,XX +XXX,XX @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, d1, i, addr, oi, ra);
-                tlb_fn(env, d2, i, addr + msize, oi, ra);
-                tlb_fn(env, d3, i, addr + 2 * msize, oi, ra);
+                tlb_fn(env, d1, i, addr, ra);
+                tlb_fn(env, d2, i, addr + msize, ra);
+                tlb_fn(env, d3, i, addr + 2 * msize, ra);
             }
             i += esize, pg >>= esize;
             addr += 3 * msize;
@@ -XXX,XX +XXX,XX @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
 static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
                       uint32_t desc, const uintptr_t ra,
                       const int esize, const int msize,
-                      sve_st1_tlb_fn *tlb_fn)
+                      sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     intptr_t i, oprsz = simd_oprsz(desc);
     void *d1 = &env->vfp.zregs[rd];
@@ -XXX,XX +XXX,XX @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
             if (pg & 1) {
-                tlb_fn(env, d1, i, addr, oi, ra);
-                tlb_fn(env, d2, i, addr + msize, oi, ra);
-                tlb_fn(env, d3, i, addr + 2 * msize, oi, ra);
-                tlb_fn(env, d4, i, addr + 3 * msize, oi, ra);
+                tlb_fn(env, d1, i, addr, ra);
+                tlb_fn(env, d2, i, addr + msize, ra);
+                tlb_fn(env, d3, i, addr + 2 * msize, ra);
+                tlb_fn(env, d4, i, addr + 3 * msize, ra);
             }
             i += esize, pg >>= esize;
             addr += 4 * msize;
@@ -XXX,XX +XXX,XX @@ static target_ulong off_zd_d(void *reg, intptr_t reg_ofs)
 
 static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
                        target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
+                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch = { };
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
         do {
             if (likely(pg & 1)) {
                 target_ulong off = off_fn(vm, i);
-                tlb_fn(env, &scratch, i, base + (off << scale), oi, ra);
+                tlb_fn(env, &scratch, i, base + (off << scale), ra);
             }
             i += 4, pg >>= 4;
         } while (i & 15);
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
 
 static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
                        target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
+                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     intptr_t i, oprsz = simd_oprsz(desc) / 8;
     ARMVectorReg scratch = { };
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
         uint8_t pg = *(uint8_t *)(vg + H1(i));
         if (likely(pg & 1)) {
             target_ulong off = off_fn(vm, i * 8);
-            tlb_fn(env, &scratch, i * 8, base + (off << scale), oi, ra);
+            tlb_fn(env, &scratch, i * 8, base + (off << scale), ra);
         }
     }
     clear_helper_retaddr();
@@ -XXX,XX +XXX,XX @@ DO_LD_NF(dd_be,      , uint64_t, uint64_t, ldq_be_p)
  */
 static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
                                 target_ulong base, uint32_t desc, uintptr_t ra,
-                                zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn,
+                                zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn,
                                 sve_ld1_nf_fn *nonfault_fn)
 {
     const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
@@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
         set_helper_retaddr(ra);
         addr = off_fn(vm, reg_off);
         addr = base + (addr << scale);
-        tlb_fn(env, vd, reg_off, addr, oi, ra);
+        tlb_fn(env, vd, reg_off, addr, ra);
 
         /* The rest of the reads will be non-faulting.  */
         clear_helper_retaddr();
@@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
 
 static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
                                 target_ulong base, uint32_t desc, uintptr_t ra,
-                                zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn,
+                                zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn,
                                 sve_ld1_nf_fn *nonfault_fn)
 {
     const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
@@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
         set_helper_retaddr(ra);
         addr = off_fn(vm, reg_off);
         addr = base + (addr << scale);
-        tlb_fn(env, vd, reg_off, addr, oi, ra);
+        tlb_fn(env, vd, reg_off, addr, ra);
 
         /* The rest of the reads will be non-faulting.  */
         clear_helper_retaddr();
@@ -XXX,XX +XXX,XX @@ DO_LDFF1_ZPZ_D(dd_be, zd)
 
 static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
                        target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
+                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     intptr_t i, oprsz = simd_oprsz(desc);
 
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
         do {
             if (likely(pg & 1)) {
                 target_ulong off = off_fn(vm, i);
-                tlb_fn(env, vd, i, base + (off << scale), oi, ra);
+                tlb_fn(env, vd, i, base + (off << scale), ra);
             }
             i += 4, pg >>= 4;
         } while (i & 15);
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
 
 static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
                        target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
+                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     intptr_t i, oprsz = simd_oprsz(desc) / 8;
 
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
         uint8_t pg = *(uint8_t *)(vg + H1(i));
         if (likely(pg & 1)) {
             target_ulong off = off_fn(vm, i * 8);
-            tlb_fn(env, vd, i * 8, base + (off << scale), oi, ra);
+            tlb_fn(env, vd, i * 8, base + (off << scale), ra);
         }
     }
     clear_helper_retaddr();
-- 
2.20.1

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

Since we converted back to cpu_*_data_ra, we do not need to
do this ourselves.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 38 --------------------------------------
 1 file changed, 38 deletions(-)

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 @@ static intptr_t max_for_page(target_ulong base, intptr_t mem_off,
     return MIN(split, mem_max - mem_off) + mem_off;
 }
 
-#ifndef CONFIG_USER_ONLY
-/* These are normally defined only for CONFIG_USER_ONLY in <exec/cpu_ldst.h> */
-static inline void set_helper_retaddr(uintptr_t ra) { }
-static inline void clear_helper_retaddr(void) { }
-#endif
-
 /*
  * The result of tlb_vaddr_to_host for user-only is just g2h(x),
  * which is always non-null.  Elide the useless test.
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
         return;
     }
     mem_off = reg_off >> diffsz;
-    set_helper_retaddr(retaddr);
 
     /*
      * If the (remaining) load is entirely within a single page, then:
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
         if (test_host_page(host)) {
             mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max);
             tcg_debug_assert(mem_off == mem_max);
-            clear_helper_retaddr();
             /* After having taken any fault, zero leading inactive elements. */
             swap_memzero(vd, reg_off);
             return;
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
     }
 #endif
 
-    clear_helper_retaddr();
     memcpy(vd, &scratch, reg_max);
 }
 
@@ -XXX,XX +XXX,XX @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch[2] = { };
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += 2 * size;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 
     /* Wait until all exceptions have been raised to write back.  */
     memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz);
@@ -XXX,XX +XXX,XX @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch[3] = { };
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += 3 * size;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 
     /* Wait until all exceptions have been raised to write back.  */
     memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz);
@@ -XXX,XX +XXX,XX @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch[4] = { };
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += 4 * size;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 
     /* Wait until all exceptions have been raised to write back.  */
     memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz);
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
         return;
     }
     mem_off = reg_off >> diffsz;
-    set_helper_retaddr(retaddr);
 
     /*
      * If the (remaining) load is entirely within a single page, then:
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
         if (test_host_page(host)) {
             mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max);
             tcg_debug_assert(mem_off == mem_max);
-            clear_helper_retaddr();
             /* After any fault, zero any leading inactive elements.  */
             swap_memzero(vd, reg_off);
             return;
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
     }
 #endif
 
-    clear_helper_retaddr();
     record_fault(env, reg_off, reg_max);
 }
 
@@ -XXX,XX +XXX,XX @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
     intptr_t i, oprsz = simd_oprsz(desc);
     void *vd = &env->vfp.zregs[rd];
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += msize;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 }
 
 static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
@@ -XXX,XX +XXX,XX @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
     void *d1 = &env->vfp.zregs[rd];
     void *d2 = &env->vfp.zregs[(rd + 1) & 31];
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += 2 * msize;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 }
 
 static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
@@ -XXX,XX +XXX,XX @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
     void *d2 = &env->vfp.zregs[(rd + 1) & 31];
     void *d3 = &env->vfp.zregs[(rd + 2) & 31];
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += 3 * msize;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 }
 
 static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
@@ -XXX,XX +XXX,XX @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
     void *d3 = &env->vfp.zregs[(rd + 2) & 31];
     void *d4 = &env->vfp.zregs[(rd + 3) & 31];
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
             addr += 4 * msize;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 }
 
 #define DO_STN_1(N, NAME, ESIZE) \
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
     intptr_t i, oprsz = simd_oprsz(desc);
     ARMVectorReg scratch = { };
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
             i += 4, pg >>= 4;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 
     /* Wait until all exceptions have been raised to write back.  */
     memcpy(vd, &scratch, oprsz);
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
     intptr_t i, oprsz = simd_oprsz(desc) / 8;
     ARMVectorReg scratch = { };
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; i++) {
         uint8_t pg = *(uint8_t *)(vg + H1(i));
         if (likely(pg & 1)) {
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
             tlb_fn(env, &scratch, i * 8, base + (off << scale), ra);
         }
     }
-    clear_helper_retaddr();
 
     /* Wait until all exceptions have been raised to write back.  */
     memcpy(vd, &scratch, oprsz * 8);
@@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
     reg_off = find_next_active(vg, 0, reg_max, MO_32);
     if (likely(reg_off < reg_max)) {
         /* Perform one normal read, which will fault or not.  */
-        set_helper_retaddr(ra);
         addr = off_fn(vm, reg_off);
         addr = base + (addr << scale);
         tlb_fn(env, vd, reg_off, addr, ra);
 
         /* The rest of the reads will be non-faulting.  */
-        clear_helper_retaddr();
     }
 
     /* After any fault, zero the leading predicated false elements.  */
@@ -XXX,XX +XXX,XX @@ static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
     reg_off = find_next_active(vg, 0, reg_max, MO_64);
     if (likely(reg_off < reg_max)) {
         /* Perform one normal read, which will fault or not.  */
-        set_helper_retaddr(ra);
         addr = off_fn(vm, reg_off);
         addr = base + (addr << scale);
         tlb_fn(env, vd, reg_off, addr, ra);
 
         /* The rest of the reads will be non-faulting.  */
-        clear_helper_retaddr();
     }
 
     /* After any fault, zero the leading predicated false elements.  */
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     intptr_t i, oprsz = simd_oprsz(desc);
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; ) {
         uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
         do {
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
             i += 4, pg >>= 4;
         } while (i & 15);
     }
-    clear_helper_retaddr();
 }
 
 static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     intptr_t i, oprsz = simd_oprsz(desc) / 8;
 
-    set_helper_retaddr(ra);
     for (i = 0; i < oprsz; i++) {
         uint8_t pg = *(uint8_t *)(vg + H1(i));
         if (likely(pg & 1)) {
@@ -XXX,XX +XXX,XX @@ static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
             tlb_fn(env, vd, i * 8, base + (off << scale), ra);
         }
     }
-    clear_helper_retaddr();
 }
 
 #define DO_ST1_ZPZ_S(MEM, OFS) \
-- 
2.20.1

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

For contiguous predicated memory operations, we want to
minimize the number of tlb lookups performed.  We have
open-coded this for sve_ld1_r, but for correctness with
MTE we will need this for all of the memory operations.

Create a structure that holds the bounds of active elements,
and metadata for two pages.  Add routines to find those
active elements, lookup the pages, and run watchpoints
for those pages.

Temporarily mark the functions unused to avoid Werror.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 263 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 261 insertions(+), 2 deletions(-)

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(sve_cpy_z_d)(void *vd, void *vg, uint64_t val, uint32_t desc)
     }
 }
 
-/* Big-endian hosts need to frob the byte indicies.  If the copy
+/* Big-endian hosts need to frob the byte indices.  If the copy
  * happens to be 8-byte aligned, then no frobbing necessary.
  */
 static void swap_memmove(void *vd, void *vs, size_t n)
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
 /*
  * Load elements into @vd, controlled by @vg, from @host + @mem_ofs.
  * Memory is valid through @host + @mem_max.  The register element
- * indicies are inferred from @mem_ofs, as modified by the types for
+ * indices are inferred from @mem_ofs, as modified by the types for
  * which the helper is built.  Return the @mem_ofs of the first element
  * not loaded (which is @mem_max if they are all loaded).
  *
@@ -XXX,XX +XXX,XX @@ static intptr_t max_for_page(target_ulong base, intptr_t mem_off,
     return MIN(split, mem_max - mem_off) + mem_off;
 }
 
+/*
+ * Resolve the guest virtual address to info->host and info->flags.
+ * If @nofault, return false if the page is invalid, otherwise
+ * exit via page fault exception.
+ */
+
+typedef struct {
+    void *host;
+    int flags;
+    MemTxAttrs attrs;
+} SVEHostPage;
+
+static bool sve_probe_page(SVEHostPage *info, bool nofault,
+                           CPUARMState *env, target_ulong addr,
+                           int mem_off, MMUAccessType access_type,
+                           int mmu_idx, uintptr_t retaddr)
+{
+    int flags;
+
+    addr += mem_off;
+    flags = probe_access_flags(env, addr, access_type, mmu_idx, nofault,
+                               &info->host, retaddr);
+    info->flags = flags;
+
+    if (flags & TLB_INVALID_MASK) {
+        g_assert(nofault);
+        return false;
+    }
+
+    /* Ensure that info->host[] is relative to addr, not addr + mem_off. */
+    info->host -= mem_off;
+
+#ifdef CONFIG_USER_ONLY
+    memset(&info->attrs, 0, sizeof(info->attrs));
+#else
+    /*
+     * Find the iotlbentry for addr and return the transaction attributes.
+     * This *must* be present in the TLB because we just found the mapping.
+     */
+    {
+        uintptr_t index = tlb_index(env, mmu_idx, addr);
+
+# ifdef CONFIG_DEBUG_TCG
+        CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
+        target_ulong comparator = (access_type == MMU_DATA_LOAD
+                                   ? entry->addr_read
+                                   : tlb_addr_write(entry));
+        g_assert(tlb_hit(comparator, addr));
+# endif
+
+        CPUIOTLBEntry *iotlbentry = &env_tlb(env)->d[mmu_idx].iotlb[index];
+        info->attrs = iotlbentry->attrs;
+    }
+#endif
+
+    return true;
+}
+
+
+/*
+ * Analyse contiguous data, protected by a governing predicate.
+ */
+
+typedef enum {
+    FAULT_NO,
+    FAULT_FIRST,
+    FAULT_ALL,
+} SVEContFault;
+
+typedef struct {
+    /*
+     * First and last element wholly contained within the two pages.
+     * mem_off_first[0] and reg_off_first[0] are always set >= 0.
+     * reg_off_last[0] may be < 0 if the first element crosses pages.
+     * All of mem_off_first[1], reg_off_first[1] and reg_off_last[1]
+     * are set >= 0 only if there are complete elements on a second page.
+     *
+     * The reg_off_* offsets are relative to the internal vector register.
+     * The mem_off_first offset is relative to the memory address; the
+     * two offsets are different when a load operation extends, a store
+     * operation truncates, or for multi-register operations.
+     */
+    int16_t mem_off_first[2];
+    int16_t reg_off_first[2];
+    int16_t reg_off_last[2];
+
+    /*
+     * One element that is misaligned and spans both pages,
+     * or -1 if there is no such active element.
+     */
+    int16_t mem_off_split;
+    int16_t reg_off_split;
+
+    /*
+     * The byte offset at which the entire operation crosses a page boundary.
+     * Set >= 0 if and only if the entire operation spans two pages.
+     */
+    int16_t page_split;
+
+    /* TLB data for the two pages. */
+    SVEHostPage page[2];
+} SVEContLdSt;
+
+/*
+ * Find first active element on each page, and a loose bound for the
+ * final element on each page.  Identify any single element that spans
+ * the page boundary.  Return true if there are any active elements.
+ */
+static bool __attribute__((unused))
+sve_cont_ldst_elements(SVEContLdSt *info, target_ulong addr, uint64_t *vg,
+                       intptr_t reg_max, int esz, int msize)
+{
+    const int esize = 1 << esz;
+    const uint64_t pg_mask = pred_esz_masks[esz];
+    intptr_t reg_off_first = -1, reg_off_last = -1, reg_off_split;
+    intptr_t mem_off_last, mem_off_split;
+    intptr_t page_split, elt_split;
+    intptr_t i;
+
+    /* Set all of the element indices to -1, and the TLB data to 0. */
+    memset(info, -1, offsetof(SVEContLdSt, page));
+    memset(info->page, 0, sizeof(info->page));
+
+    /* Gross scan over the entire predicate to find bounds. */
+    i = 0;
+    do {
+        uint64_t pg = vg[i] & pg_mask;
+        if (pg) {
+            reg_off_last = i * 64 + 63 - clz64(pg);
+            if (reg_off_first < 0) {
+                reg_off_first = i * 64 + ctz64(pg);
+            }
+        }
+    } while (++i * 64 < reg_max);
+
+    if (unlikely(reg_off_first < 0)) {
+        /* No active elements, no pages touched. */
+        return false;
+    }
+    tcg_debug_assert(reg_off_last >= 0 && reg_off_last < reg_max);
+
+    info->reg_off_first[0] = reg_off_first;
+    info->mem_off_first[0] = (reg_off_first >> esz) * msize;
+    mem_off_last = (reg_off_last >> esz) * msize;
+
+    page_split = -(addr | TARGET_PAGE_MASK);
+    if (likely(mem_off_last + msize <= page_split)) {
+        /* The entire operation fits within a single page. */
+        info->reg_off_last[0] = reg_off_last;
+        return true;
+    }
+
+    info->page_split = page_split;
+    elt_split = page_split / msize;
+    reg_off_split = elt_split << esz;
+    mem_off_split = elt_split * msize;
+
+    /*
+     * This is the last full element on the first page, but it is not
+     * necessarily active.  If there is no full element, i.e. the first
+     * active element is the one that's split, this value remains -1.
+     * It is useful as iteration bounds.
+     */
+    if (elt_split != 0) {
+        info->reg_off_last[0] = reg_off_split - esize;
+    }
+
+    /* Determine if an unaligned element spans the pages.  */
+    if (page_split % msize != 0) {
+        /* It is helpful to know if the split element is active. */
+        if ((vg[reg_off_split >> 6] >> (reg_off_split & 63)) & 1) {
+            info->reg_off_split = reg_off_split;
+            info->mem_off_split = mem_off_split;
+
+            if (reg_off_split == reg_off_last) {
+                /* The page crossing element is last. */
+                return true;
+            }
+        }
+        reg_off_split += esize;
+        mem_off_split += msize;
+    }
+
+    /*
+     * We do want the first active element on the second page, because
+     * this may affect the address reported in an exception.
+     */
+    reg_off_split = find_next_active(vg, reg_off_split, reg_max, esz);
+    tcg_debug_assert(reg_off_split <= reg_off_last);
+    info->reg_off_first[1] = reg_off_split;
+    info->mem_off_first[1] = (reg_off_split >> esz) * msize;
+    info->reg_off_last[1] = reg_off_last;
+    return true;
+}
+
+/*
+ * Resolve the guest virtual addresses to info->page[].
+ * Control the generation of page faults with @fault.  Return false if
+ * there is no work to do, which can only happen with @fault == FAULT_NO.
+ */
+static bool __attribute__((unused))
+sve_cont_ldst_pages(SVEContLdSt *info, SVEContFault fault, CPUARMState *env,
+                    target_ulong addr, MMUAccessType access_type,
+                    uintptr_t retaddr)
+{
+    int mmu_idx = cpu_mmu_index(env, false);
+    int mem_off = info->mem_off_first[0];
+    bool nofault = fault == FAULT_NO;
+    bool have_work = true;
+
+    if (!sve_probe_page(&info->page[0], nofault, env, addr, mem_off,
+                        access_type, mmu_idx, retaddr)) {
+        /* No work to be done. */
+        return false;
+    }
+
+    if (likely(info->page_split < 0)) {
+        /* The entire operation was on the one page. */
+        return true;
+    }
+
+    /*
+     * If the second page is invalid, then we want the fault address to be
+     * the first byte on that page which is accessed.
+     */
+    if (info->mem_off_split >= 0) {
+        /*
+         * There is an element split across the pages.  The fault address
+         * should be the first byte of the second page.
+         */
+        mem_off = info->page_split;
+        /*
+         * If the split element is also the first active element
+         * of the vector, then:  For first-fault we should continue
+         * to generate faults for the second page.  For no-fault,
+         * we have work only if the second page is valid.
+         */
+        if (info->mem_off_first[0] < info->mem_off_split) {
+            nofault = FAULT_FIRST;
+            have_work = false;
+        }
+    } else {
+        /*
+         * There is no element split across the pages.  The fault address
+         * should be the first active element on the second page.
+         */
+        mem_off = info->mem_off_first[1];
+        /*
+         * There must have been one active element on the first page,
+         * so we're out of first-fault territory.
+         */
+        nofault = fault != FAULT_ALL;
+    }
+
+    have_work |= sve_probe_page(&info->page[1], nofault, env, addr, mem_off,
+                                access_type, mmu_idx, retaddr);
+    return have_work;
+}
+
 /*
  * The result of tlb_vaddr_to_host for user-only is just g2h(x),
  * which is always non-null.  Elide the useless test.
-- 
2.20.1

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

The current interface includes a loop; change it to load a
single element.  We will then be able to use the function
for ld{2,3,4} where individual vector elements are not adjacent.

Replace each call with the simplest possible loop over active
elements.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 124 ++++++++++++++++++++--------------------
 1 file changed, 63 insertions(+), 61 deletions(-)

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(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
  */
 
 /*
- * Load elements into @vd, controlled by @vg, from @host + @mem_ofs.
- * Memory is valid through @host + @mem_max.  The register element
- * indices are inferred from @mem_ofs, as modified by the types for
- * which the helper is built.  Return the @mem_ofs of the first element
- * not loaded (which is @mem_max if they are all loaded).
- *
- * For softmmu, we have fully validated the guest page.  For user-only,
- * we cannot fully validate without taking the mmap lock, but since we
- * know the access is within one host page, if any access is valid they
- * all must be valid.  However, when @vg is all false, it may be that
- * no access is valid.
+ * Load one element into @vd + @reg_off from @host.
+ * The controlling predicate is known to be true.
  */
-typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host,
-                                 intptr_t mem_ofs, intptr_t mem_max);
+typedef void sve_ldst1_host_fn(void *vd, intptr_t reg_off, void *host);
 
 /*
  * Load one element into @vd + @reg_off from (@env, @vaddr, @ra).
@@ -XXX,XX +XXX,XX @@ typedef void sve_ldst1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off,
  */
 
 #define DO_LD_HOST(NAME, H, TYPEE, TYPEM, HOST) \
-static intptr_t sve_##NAME##_host(void *vd, void *vg, void *host,           \
-                                  intptr_t mem_off, const intptr_t mem_max) \
-{                                                                           \
-    intptr_t reg_off = mem_off * (sizeof(TYPEE) / sizeof(TYPEM));           \
-    uint64_t *pg = vg;                                                      \
-    while (mem_off + sizeof(TYPEM) <= mem_max) {                            \
-        TYPEM val = 0;                                                      \
-        if (likely((pg[reg_off >> 6] >> (reg_off & 63)) & 1)) {             \
-            val = HOST(host + mem_off);                                     \
-        }                                                                   \
-        *(TYPEE *)(vd + H(reg_off)) = val;                                  \
-        mem_off += sizeof(TYPEM), reg_off += sizeof(TYPEE);                 \
-    }                                                                       \
-    return mem_off;                                                         \
+static void sve_##NAME##_host(void *vd, intptr_t reg_off, void *host)  \
+{                                                                      \
+    TYPEM val = HOST(host);                                            \
+    *(TYPEE *)(vd + H(reg_off)) = val;                                 \
 }
 
 #define DO_LD_TLB(NAME, H, TYPEE, TYPEM, TLB) \
@@ -XXX,XX +XXX,XX @@ static inline bool test_host_page(void *host)
 static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
                       uint32_t desc, const uintptr_t retaddr,
                       const int esz, const int msz,
-                      sve_ld1_host_fn *host_fn,
+                      sve_ldst1_host_fn *host_fn,
                       sve_ldst1_tlb_fn *tlb_fn)
 {
     const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
     if (likely(split == mem_max)) {
         host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
         if (test_host_page(host)) {
-            mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max);
-            tcg_debug_assert(mem_off == mem_max);
+            intptr_t i = reg_off;
+            host -= mem_off;
+            do {
+                host_fn(vd, i, host + (i >> diffsz));
+                i = find_next_active(vg, i + (1 << esz), reg_max, esz);
+            } while (i < reg_max);
             /* After having taken any fault, zero leading inactive elements. */
             swap_memzero(vd, reg_off);
             return;
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
      */
 #ifdef CONFIG_USER_ONLY
     swap_memzero(&scratch, reg_off);
-    host_fn(&scratch, vg, g2h(addr), mem_off, mem_max);
+    host = g2h(addr);
+    do {
+        host_fn(&scratch, reg_off, host + (reg_off >> diffsz));
+        reg_off += 1 << esz;
+        reg_off = find_next_active(vg, reg_off, reg_max, esz);
+    } while (reg_off < reg_max);
 #else
     memset(&scratch, 0, reg_max);
     goto start;
@@ -XXX,XX +XXX,XX @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
             host = tlb_vaddr_to_host(env, addr + mem_off,
                                      MMU_DATA_LOAD, mmu_idx);
             if (host) {
-                mem_off = host_fn(&scratch, vg, host - mem_off,
-                                  mem_off, split);
-                reg_off = mem_off << diffsz;
+                host -= mem_off;
+                do {
+                    host_fn(&scratch, reg_off, host + mem_off);
+                    reg_off += 1 << esz;
+                    reg_off = find_next_active(vg, reg_off, reg_max, esz);
+                    mem_off = reg_off >> diffsz;
+                } while (split - mem_off >= (1 << msz));
                 continue;
             }
         }
@@ -XXX,XX +XXX,XX @@ static void record_fault(CPUARMState *env, uintptr_t i, uintptr_t oprsz)
 static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
                         uint32_t desc, const uintptr_t retaddr,
                         const int esz, const int msz,
-                        sve_ld1_host_fn *host_fn,
+                        sve_ldst1_host_fn *host_fn,
                         sve_ldst1_tlb_fn *tlb_fn)
 {
     const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
     const int diffsz = esz - msz;
     const intptr_t reg_max = simd_oprsz(desc);
     const intptr_t mem_max = reg_max >> diffsz;
-    intptr_t split, reg_off, mem_off;
+    intptr_t split, reg_off, mem_off, i;
     void *host;
 
     /* Skip to the first active element.  */
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
     if (likely(split == mem_max)) {
         host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
         if (test_host_page(host)) {
-            mem_off = host_fn(vd, vg, host - mem_off, mem_off, mem_max);
-            tcg_debug_assert(mem_off == mem_max);
+            i = reg_off;
+            host -= mem_off;
+            do {
+                host_fn(vd, i, host + (i >> diffsz));
+                i = find_next_active(vg, i + (1 << esz), reg_max, esz);
+            } while (i < reg_max);
             /* After any fault, zero any leading inactive elements.  */
             swap_memzero(vd, reg_off);
             return;
         }
     }
 
-#ifdef CONFIG_USER_ONLY
-    /*
-     * The page(s) containing this first element at ADDR+MEM_OFF must
-     * be valid.  Considering that this first element may be misaligned
-     * and cross a page boundary itself, take the rest of the page from
-     * the last byte of the element.
-     */
-    split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max);
-    mem_off = host_fn(vd, vg, g2h(addr), mem_off, split);
-
-    /* After any fault, zero any leading inactive elements.  */
-    swap_memzero(vd, reg_off);
-    reg_off = mem_off << diffsz;
-#else
     /*
      * Perform one normal read, which will fault or not.
      * But it is likely to bring the page into the tlb.
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
     if (split >= (1 << msz)) {
         host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
         if (host) {
-            mem_off = host_fn(vd, vg, host - mem_off, mem_off, split);
-            reg_off = mem_off << diffsz;
+            host -= mem_off;
+            do {
+                host_fn(vd, reg_off, host + mem_off);
+                reg_off += 1 << esz;
+                reg_off = find_next_active(vg, reg_off, reg_max, esz);
+                mem_off = reg_off >> diffsz;
+            } while (split - mem_off >= (1 << msz));
         }
     }
-#endif
 
     record_fault(env, reg_off, reg_max);
 }
@@ -XXX,XX +XXX,XX @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
  */
 static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
                         uint32_t desc, const int esz, const int msz,
-                        sve_ld1_host_fn *host_fn)
+                        sve_ldst1_host_fn *host_fn)
 {
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     void *vd = &env->vfp.zregs[rd];
@@ -XXX,XX +XXX,XX @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
     host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx);
     if (likely(page_check_range(addr, mem_max, PAGE_READ) == 0)) {
         /* The entire operation is valid and will not fault.  */
-        host_fn(vd, vg, host, 0, mem_max);
+        reg_off = 0;
+        do {
+            mem_off = reg_off >> diffsz;
+            host_fn(vd, reg_off, host + mem_off);
+            reg_off += 1 << esz;
+            reg_off = find_next_active(vg, reg_off, reg_max, esz);
+        } while (reg_off < reg_max);
         return;
     }
 #endif
@@ -XXX,XX +XXX,XX @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
     if (page_check_range(addr + mem_off, 1 << msz, PAGE_READ) == 0) {
         /* At least one load is valid; take the rest of the page.  */
         split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max);
-        mem_off = host_fn(vd, vg, host, mem_off, split);
-        reg_off = mem_off << diffsz;
+        do {
+            host_fn(vd, reg_off, host + mem_off);
+            reg_off += 1 << esz;
+            reg_off = find_next_active(vg, reg_off, reg_max, esz);
+            mem_off = reg_off >> diffsz;
+        } while (split - mem_off >= (1 << msz));
     }
 #else
     /*
@@ -XXX,XX +XXX,XX @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
     host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
     split = max_for_page(addr, mem_off, mem_max);
     if (host && split >= (1 << msz)) {
-        mem_off = host_fn(vd, vg, host - mem_off, mem_off, split);
-        reg_off = mem_off << diffsz;
+        host -= mem_off;
+        do {
+            host_fn(vd, reg_off, host + mem_off);
+            reg_off += 1 << esz;
+            reg_off = find_next_active(vg, reg_off, reg_max, esz);
+            mem_off = reg_off >> diffsz;
+        } while (split - mem_off >= (1 << msz));
     }
 #endif
 
-- 
2.20.1

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

First use of the new helper functions, so we can remove the
unused markup.  No longer need a scratch for user-only, as
we completely probe the page set before reading; system mode
still requires a scratch for MMIO.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 188 +++++++++++++++++++++-------------------
 1 file changed, 97 insertions(+), 91 deletions(-)

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 @@ typedef struct {
  * final element on each page.  Identify any single element that spans
  * the page boundary.  Return true if there are any active elements.
  */
-static bool __attribute__((unused))
-sve_cont_ldst_elements(SVEContLdSt *info, target_ulong addr, uint64_t *vg,
-                       intptr_t reg_max, int esz, int msize)
+static bool sve_cont_ldst_elements(SVEContLdSt *info, target_ulong addr,
+                                   uint64_t *vg, intptr_t reg_max,
+                                   int esz, int msize)
 {
     const int esize = 1 << esz;
     const uint64_t pg_mask = pred_esz_masks[esz];
@@ -XXX,XX +XXX,XX @@ sve_cont_ldst_elements(SVEContLdSt *info, target_ulong addr, uint64_t *vg,
  * Control the generation of page faults with @fault.  Return false if
  * there is no work to do, which can only happen with @fault == FAULT_NO.
  */
-static bool __attribute__((unused))
-sve_cont_ldst_pages(SVEContLdSt *info, SVEContFault fault, CPUARMState *env,
-                    target_ulong addr, MMUAccessType access_type,
-                    uintptr_t retaddr)
+static bool sve_cont_ldst_pages(SVEContLdSt *info, SVEContFault fault,
+                                CPUARMState *env, target_ulong addr,
+                                MMUAccessType access_type, uintptr_t retaddr)
 {
     int mmu_idx = cpu_mmu_index(env, false);
     int mem_off = info->mem_off_first[0];
@@ -XXX,XX +XXX,XX @@ static inline bool test_host_page(void *host)
 /*
  * Common helper for all contiguous one-register predicated loads.
  */
-static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
-                      uint32_t desc, const uintptr_t retaddr,
-                      const int esz, const int msz,
-                      sve_ldst1_host_fn *host_fn,
-                      sve_ldst1_tlb_fn *tlb_fn)
+static inline QEMU_ALWAYS_INLINE
+void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
+               uint32_t desc, const uintptr_t retaddr,
+               const int esz, const int msz,
+               sve_ldst1_host_fn *host_fn,
+               sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
-    const int mmu_idx = get_mmuidx(oi);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     void *vd = &env->vfp.zregs[rd];
-    const int diffsz = esz - msz;
     const intptr_t reg_max = simd_oprsz(desc);
-    const intptr_t mem_max = reg_max >> diffsz;
-    ARMVectorReg scratch;
+    intptr_t reg_off, reg_last, mem_off;
+    SVEContLdSt info;
     void *host;
-    intptr_t split, reg_off, mem_off;
+    int flags;
 
-    /* Find the first active element.  */
-    reg_off = find_next_active(vg, 0, reg_max, esz);
-    if (unlikely(reg_off == reg_max)) {
+    /* Find the active elements.  */
+    if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, 1 << msz)) {
         /* The entire predicate was false; no load occurs.  */
         memset(vd, 0, reg_max);
         return;
     }
-    mem_off = reg_off >> diffsz;
 
-    /*
-     * If the (remaining) load is entirely within a single page, then:
-     * For softmmu, and the tlb hits, then no faults will occur;
-     * For user-only, either the first load will fault or none will.
-     * We can thus perform the load directly to the destination and
-     * Vd will be unmodified on any exception path.
-     */
-    split = max_for_page(addr, mem_off, mem_max);
-    if (likely(split == mem_max)) {
-        host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
-        if (test_host_page(host)) {
-            intptr_t i = reg_off;
-            host -= mem_off;
-            do {
-                host_fn(vd, i, host + (i >> diffsz));
-                i = find_next_active(vg, i + (1 << esz), reg_max, esz);
-            } while (i < reg_max);
-            /* After having taken any fault, zero leading inactive elements. */
-            swap_memzero(vd, reg_off);
-            return;
-        }
-    }
+    /* Probe the page(s).  Exit with exception for any invalid page. */
+    sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, retaddr);
 
-    /*
-     * Perform the predicated read into a temporary, thus ensuring
-     * if the load of the last element faults, Vd is not modified.
-     */
+    flags = info.page[0].flags | info.page[1].flags;
+    if (unlikely(flags != 0)) {
 #ifdef CONFIG_USER_ONLY
-    swap_memzero(&scratch, reg_off);
-    host = g2h(addr);
-    do {
-        host_fn(&scratch, reg_off, host + (reg_off >> diffsz));
-        reg_off += 1 << esz;
-        reg_off = find_next_active(vg, reg_off, reg_max, esz);
-    } while (reg_off < reg_max);
+        g_assert_not_reached();
 #else
-    memset(&scratch, 0, reg_max);
-    goto start;
-    while (1) {
-        reg_off = find_next_active(vg, reg_off, reg_max, esz);
-        if (reg_off >= reg_max) {
-            break;
-        }
-        mem_off = reg_off >> diffsz;
-        split = max_for_page(addr, mem_off, mem_max);
+        /*
+         * At least one page includes MMIO (or watchpoints).
+         * Any bus operation can fail with cpu_transaction_failed,
+         * which for ARM will raise SyncExternal.  Perform the load
+         * into scratch memory to preserve register state until the end.
+         */
+        ARMVectorReg scratch;
 
-    start:
-        if (split - mem_off >= (1 << msz)) {
-            /* At least one whole element on this page.  */
-            host = tlb_vaddr_to_host(env, addr + mem_off,
-                                     MMU_DATA_LOAD, mmu_idx);
-            if (host) {
-                host -= mem_off;
-                do {
-                    host_fn(&scratch, reg_off, host + mem_off);
-                    reg_off += 1 << esz;
-                    reg_off = find_next_active(vg, reg_off, reg_max, esz);
-                    mem_off = reg_off >> diffsz;
-                } while (split - mem_off >= (1 << msz));
-                continue;
+        memset(&scratch, 0, reg_max);
+        mem_off = info.mem_off_first[0];
+        reg_off = info.reg_off_first[0];
+        reg_last = info.reg_off_last[1];
+        if (reg_last < 0) {
+            reg_last = info.reg_off_split;
+            if (reg_last < 0) {
+                reg_last = info.reg_off_last[0];
             }
         }
 
-        /*
-         * Perform one normal read.  This may fault, longjmping out to the
-         * main loop in order to raise an exception.  It may succeed, and
-         * as a side-effect load the TLB entry for the next round.  Finally,
-         * in the extremely unlikely case we're performing this operation
-         * on I/O memory, it may succeed but not bring in the TLB entry.
-         * But even then we have still made forward progress.
-         */
-        tlb_fn(env, &scratch, reg_off, addr + mem_off, retaddr);
-        reg_off += 1 << esz;
-    }
-#endif
+        do {
+            uint64_t pg = vg[reg_off >> 6];
+            do {
+                if ((pg >> (reg_off & 63)) & 1) {
+                    tlb_fn(env, &scratch, reg_off, addr + mem_off, retaddr);
+                }
+                reg_off += 1 << esz;
+                mem_off += 1 << msz;
+            } while (reg_off & 63);
+        } while (reg_off <= reg_last);
 
-    memcpy(vd, &scratch, reg_max);
+        memcpy(vd, &scratch, reg_max);
+        return;
+#endif
+    }
+
+    /* The entire operation is in RAM, on valid pages. */
+
+    memset(vd, 0, reg_max);
+    mem_off = info.mem_off_first[0];
+    reg_off = info.reg_off_first[0];
+    reg_last = info.reg_off_last[0];
+    host = info.page[0].host;
+
+    while (reg_off <= reg_last) {
+        uint64_t pg = vg[reg_off >> 6];
+        do {
+            if ((pg >> (reg_off & 63)) & 1) {
+                host_fn(vd, reg_off, host + mem_off);
+            }
+            reg_off += 1 << esz;
+            mem_off += 1 << msz;
+        } while (reg_off <= reg_last && (reg_off & 63));
+    }
+
+    /*
+     * Use the slow path to manage the cross-page misalignment.
+     * But we know this is RAM and cannot trap.
+     */
+    mem_off = info.mem_off_split;
+    if (unlikely(mem_off >= 0)) {
+        tlb_fn(env, vd, info.reg_off_split, addr + mem_off, retaddr);
+    }
+
+    mem_off = info.mem_off_first[1];
+    if (unlikely(mem_off >= 0)) {
+        reg_off = info.reg_off_first[1];
+        reg_last = info.reg_off_last[1];
+        host = info.page[1].host;
+
+        do {
+            uint64_t pg = vg[reg_off >> 6];
+            do {
+                if ((pg >> (reg_off & 63)) & 1) {
+                    host_fn(vd, reg_off, host + mem_off);
+                }
+                reg_off += 1 << esz;
+                mem_off += 1 << msz;
+            } while (reg_off & 63);
+        } while (reg_off <= reg_last);
+    }
 }
 
 #define DO_LD1_1(NAME, ESZ) \
-- 
2.20.1

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

Handle all of the watchpoints for active elements all at once,
before we've modified the vector register.  This removes the
TLB_WATCHPOINT bit from page[].flags, which means that we can
use the normal fast path via RAM.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 72 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 71 insertions(+), 1 deletion(-)

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 @@ static bool sve_cont_ldst_pages(SVEContLdSt *info, SVEContFault fault,
     return have_work;
 }
 
+static void sve_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env,
+                                      uint64_t *vg, target_ulong addr,
+                                      int esize, int msize, int wp_access,
+                                      uintptr_t retaddr)
+{
+#ifndef CONFIG_USER_ONLY
+    intptr_t mem_off, reg_off, reg_last;
+    int flags0 = info->page[0].flags;
+    int flags1 = info->page[1].flags;
+
+    if (likely(!((flags0 | flags1) & TLB_WATCHPOINT))) {
+        return;
+    }
+
+    /* Indicate that watchpoints are handled. */
+    info->page[0].flags = flags0 & ~TLB_WATCHPOINT;
+    info->page[1].flags = flags1 & ~TLB_WATCHPOINT;
+
+    if (flags0 & TLB_WATCHPOINT) {
+        mem_off = info->mem_off_first[0];
+        reg_off = info->reg_off_first[0];
+        reg_last = info->reg_off_last[0];
+
+        while (reg_off <= reg_last) {
+            uint64_t pg = vg[reg_off >> 6];
+            do {
+                if ((pg >> (reg_off & 63)) & 1) {
+                    cpu_check_watchpoint(env_cpu(env), addr + mem_off,
+                                         msize, info->page[0].attrs,
+                                         wp_access, retaddr);
+                }
+                reg_off += esize;
+                mem_off += msize;
+            } while (reg_off <= reg_last && (reg_off & 63));
+        }
+    }
+
+    mem_off = info->mem_off_split;
+    if (mem_off >= 0) {
+        cpu_check_watchpoint(env_cpu(env), addr + mem_off, msize,
+                             info->page[0].attrs, wp_access, retaddr);
+    }
+
+    mem_off = info->mem_off_first[1];
+    if ((flags1 & TLB_WATCHPOINT) && mem_off >= 0) {
+        reg_off = info->reg_off_first[1];
+        reg_last = info->reg_off_last[1];
+
+        do {
+            uint64_t pg = vg[reg_off >> 6];
+            do {
+                if ((pg >> (reg_off & 63)) & 1) {
+                    cpu_check_watchpoint(env_cpu(env), addr + mem_off,
+                                         msize, info->page[1].attrs,
+                                         wp_access, retaddr);
+                }
+                reg_off += esize;
+                mem_off += msize;
+            } while (reg_off & 63);
+        } while (reg_off <= reg_last);
+    }
+#endif
+}
+
 /*
  * The result of tlb_vaddr_to_host for user-only is just g2h(x),
  * which is always non-null.  Elide the useless test.
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
     /* Probe the page(s).  Exit with exception for any invalid page. */
     sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, retaddr);
 
+    /* Handle watchpoints for all active elements. */
+    sve_cont_ldst_watchpoints(&info, env, vg, addr, 1 << esz, 1 << msz,
+                              BP_MEM_READ, retaddr);
+
+    /* TODO: MTE check. */
+
     flags = info.page[0].flags | info.page[1].flags;
     if (unlikely(flags != 0)) {
 #ifdef CONFIG_USER_ONLY
         g_assert_not_reached();
 #else
         /*
-         * At least one page includes MMIO (or watchpoints).
+         * At least one page includes MMIO.
          * Any bus operation can fail with cpu_transaction_failed,
          * which for ARM will raise SyncExternal.  Perform the load
          * into scratch memory to preserve register state until the end.
-- 
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: 20200508154359.7494-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 223 ++++++++++++++--------------------------
 1 file changed, 79 insertions(+), 144 deletions(-)

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 @@ static inline bool test_host_page(void *host)
 }
 
 /*
- * Common helper for all contiguous one-register predicated loads.
+ * Common helper for all contiguous 1,2,3,4-register predicated stores.
  */
 static inline QEMU_ALWAYS_INLINE
-void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
+void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
                uint32_t desc, const uintptr_t retaddr,
-               const int esz, const int msz,
+               const int esz, const int msz, const int N,
                sve_ldst1_host_fn *host_fn,
                sve_ldst1_tlb_fn *tlb_fn)
 {
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    void *vd = &env->vfp.zregs[rd];
     const intptr_t reg_max = simd_oprsz(desc);
     intptr_t reg_off, reg_last, mem_off;
     SVEContLdSt info;
     void *host;
-    int flags;
+    int flags, i;
 
     /* Find the active elements.  */
-    if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, 1 << msz)) {
+    if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, N << msz)) {
         /* The entire predicate was false; no load occurs.  */
-        memset(vd, 0, reg_max);
+        for (i = 0; i < N; ++i) {
+            memset(&env->vfp.zregs[(rd + i) & 31], 0, reg_max);
+        }
         return;
     }
 
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
     sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, retaddr);
 
     /* Handle watchpoints for all active elements. */
-    sve_cont_ldst_watchpoints(&info, env, vg, addr, 1 << esz, 1 << msz,
+    sve_cont_ldst_watchpoints(&info, env, vg, addr, 1 << esz, N << msz,
                               BP_MEM_READ, retaddr);
 
     /* TODO: MTE check. */
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
          * which for ARM will raise SyncExternal.  Perform the load
          * into scratch memory to preserve register state until the end.
          */
-        ARMVectorReg scratch;
+        ARMVectorReg scratch[4] = { };
 
-        memset(&scratch, 0, reg_max);
         mem_off = info.mem_off_first[0];
         reg_off = info.reg_off_first[0];
         reg_last = info.reg_off_last[1];
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
             uint64_t pg = vg[reg_off >> 6];
             do {
                 if ((pg >> (reg_off & 63)) & 1) {
-                    tlb_fn(env, &scratch, reg_off, addr + mem_off, retaddr);
+                    for (i = 0; i < N; ++i) {
+                        tlb_fn(env, &scratch[i], reg_off,
+                               addr + mem_off + (i << msz), retaddr);
+                    }
                 }
                 reg_off += 1 << esz;
-                mem_off += 1 << msz;
+                mem_off += N << msz;
             } while (reg_off & 63);
         } while (reg_off <= reg_last);
 
-        memcpy(vd, &scratch, reg_max);
+        for (i = 0; i < N; ++i) {
+            memcpy(&env->vfp.zregs[(rd + i) & 31], &scratch[i], reg_max);
+        }
         return;
 #endif
     }
 
     /* The entire operation is in RAM, on valid pages. */
 
-    memset(vd, 0, reg_max);
+    for (i = 0; i < N; ++i) {
+        memset(&env->vfp.zregs[(rd + i) & 31], 0, reg_max);
+    }
+
     mem_off = info.mem_off_first[0];
     reg_off = info.reg_off_first[0];
     reg_last = info.reg_off_last[0];
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
         uint64_t pg = vg[reg_off >> 6];
         do {
             if ((pg >> (reg_off & 63)) & 1) {
-                host_fn(vd, reg_off, host + mem_off);
+                for (i = 0; i < N; ++i) {
+                    host_fn(&env->vfp.zregs[(rd + i) & 31], reg_off,
+                            host + mem_off + (i << msz));
+                }
             }
             reg_off += 1 << esz;
-            mem_off += 1 << msz;
+            mem_off += N << msz;
         } while (reg_off <= reg_last && (reg_off & 63));
     }
 
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
      */
     mem_off = info.mem_off_split;
     if (unlikely(mem_off >= 0)) {
-        tlb_fn(env, vd, info.reg_off_split, addr + mem_off, retaddr);
+        reg_off = info.reg_off_split;
+        for (i = 0; i < N; ++i) {
+            tlb_fn(env, &env->vfp.zregs[(rd + i) & 31], reg_off,
+                   addr + mem_off + (i << msz), retaddr);
+        }
     }
 
     mem_off = info.mem_off_first[1];
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
             uint64_t pg = vg[reg_off >> 6];
             do {
                 if ((pg >> (reg_off & 63)) & 1) {
-                    host_fn(vd, reg_off, host + mem_off);
+                    for (i = 0; i < N; ++i) {
+                        host_fn(&env->vfp.zregs[(rd + i) & 31], reg_off,
+                                host + mem_off + (i << msz));
+                    }
                 }
                 reg_off += 1 << esz;
-                mem_off += 1 << msz;
+                mem_off += N << msz;
             } while (reg_off & 63);
         } while (reg_off <= reg_last);
     }
@@ -XXX,XX +XXX,XX @@ void sve_ld1_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
 void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg,        \
                             target_ulong addr, uint32_t desc)  \
 {                                                              \
-    sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, 0,            \
+    sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, 1,      \
               sve_##NAME##_host, sve_##NAME##_tlb);            \
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg,        \
 void HELPER(sve_##NAME##_le_r)(CPUARMState *env, void *vg,        \
                                target_ulong addr, uint32_t desc)  \
 {                                                                 \
-    sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ,             \
+    sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1,          \
               sve_##NAME##_le_host, sve_##NAME##_le_tlb);         \
 }                                                                 \
 void HELPER(sve_##NAME##_be_r)(CPUARMState *env, void *vg,        \
                                target_ulong addr, uint32_t desc)  \
 {                                                                 \
-    sve_ld1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ,             \
+    sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1,          \
               sve_##NAME##_be_host, sve_##NAME##_be_tlb);         \
 }
 
-DO_LD1_1(ld1bb,  0)
-DO_LD1_1(ld1bhu, 1)
-DO_LD1_1(ld1bhs, 1)
-DO_LD1_1(ld1bsu, 2)
-DO_LD1_1(ld1bss, 2)
-DO_LD1_1(ld1bdu, 3)
-DO_LD1_1(ld1bds, 3)
+DO_LD1_1(ld1bb,  MO_8)
+DO_LD1_1(ld1bhu, MO_16)
+DO_LD1_1(ld1bhs, MO_16)
+DO_LD1_1(ld1bsu, MO_32)
+DO_LD1_1(ld1bss, MO_32)
+DO_LD1_1(ld1bdu, MO_64)
+DO_LD1_1(ld1bds, MO_64)
 
-DO_LD1_2(ld1hh,  1, 1)
-DO_LD1_2(ld1hsu, 2, 1)
-DO_LD1_2(ld1hss, 2, 1)
-DO_LD1_2(ld1hdu, 3, 1)
-DO_LD1_2(ld1hds, 3, 1)
+DO_LD1_2(ld1hh,  MO_16, MO_16)
+DO_LD1_2(ld1hsu, MO_32, MO_16)
+DO_LD1_2(ld1hss, MO_32, MO_16)
+DO_LD1_2(ld1hdu, MO_64, MO_16)
+DO_LD1_2(ld1hds, MO_64, MO_16)
 
-DO_LD1_2(ld1ss,  2, 2)
-DO_LD1_2(ld1sdu, 3, 2)
-DO_LD1_2(ld1sds, 3, 2)
+DO_LD1_2(ld1ss,  MO_32, MO_32)
+DO_LD1_2(ld1sdu, MO_64, MO_32)
+DO_LD1_2(ld1sds, MO_64, MO_32)
 
-DO_LD1_2(ld1dd,  3, 3)
+DO_LD1_2(ld1dd,  MO_64, MO_64)
 
 #undef DO_LD1_1
 #undef DO_LD1_2
 
-/*
- * Common helpers for all contiguous 2,3,4-register predicated loads.
- */
-static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, int size, uintptr_t ra,
-                      sve_ldst1_tlb_fn *tlb_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    ARMVectorReg scratch[2] = { };
-
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, &scratch[0], i, addr, ra);
-                tlb_fn(env, &scratch[1], i, addr + size, ra);
-            }
-            i += size, pg >>= size;
-            addr += 2 * size;
-        } while (i & 15);
-    }
-
-    /* Wait until all exceptions have been raised to write back.  */
-    memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz);
-    memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz);
-}
-
-static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, int size, uintptr_t ra,
-                      sve_ldst1_tlb_fn *tlb_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    ARMVectorReg scratch[3] = { };
-
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, &scratch[0], i, addr, ra);
-                tlb_fn(env, &scratch[1], i, addr + size, ra);
-                tlb_fn(env, &scratch[2], i, addr + 2 * size, ra);
-            }
-            i += size, pg >>= size;
-            addr += 3 * size;
-        } while (i & 15);
-    }
-
-    /* Wait until all exceptions have been raised to write back.  */
-    memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz);
-    memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz);
-    memcpy(&env->vfp.zregs[(rd + 2) & 31], &scratch[2], oprsz);
-}
-
-static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, int size, uintptr_t ra,
-                      sve_ldst1_tlb_fn *tlb_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    ARMVectorReg scratch[4] = { };
-
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, &scratch[0], i, addr, ra);
-                tlb_fn(env, &scratch[1], i, addr + size, ra);
-                tlb_fn(env, &scratch[2], i, addr + 2 * size, ra);
-                tlb_fn(env, &scratch[3], i, addr + 3 * size, ra);
-            }
-            i += size, pg >>= size;
-            addr += 4 * size;
-        } while (i & 15);
-    }
-
-    /* Wait until all exceptions have been raised to write back.  */
-    memcpy(&env->vfp.zregs[rd], &scratch[0], oprsz);
-    memcpy(&env->vfp.zregs[(rd + 1) & 31], &scratch[1], oprsz);
-    memcpy(&env->vfp.zregs[(rd + 2) & 31], &scratch[2], oprsz);
-    memcpy(&env->vfp.zregs[(rd + 3) & 31], &scratch[3], oprsz);
-}
-
 #define DO_LDN_1(N) \
-void QEMU_FLATTEN HELPER(sve_ld##N##bb_r) \
-    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)  \
-{                                                                   \
-    sve_ld##N##_r(env, vg, addr, desc, 1, GETPC(), sve_ld1bb_tlb);  \
+void HELPER(sve_ld##N##bb_r)(CPUARMState *env, void *vg,        \
+                             target_ulong addr, uint32_t desc)  \
+{                                                               \
+    sve_ldN_r(env, vg, addr, desc, GETPC(), MO_8, MO_8, N,      \
+              sve_ld1bb_host, sve_ld1bb_tlb);                   \
 }
 
-#define DO_LDN_2(N, SUFF, SIZE)                                       \
-void QEMU_FLATTEN HELPER(sve_ld##N##SUFF##_le_r)                      \
-    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)    \
+#define DO_LDN_2(N, SUFF, ESZ) \
+void HELPER(sve_ld##N##SUFF##_le_r)(CPUARMState *env, void *vg,       \
+                                    target_ulong addr, uint32_t desc) \
 {                                                                     \
-    sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(),                 \
-                  sve_ld1##SUFF##_le_tlb);                            \
+    sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, ESZ, N,              \
+              sve_ld1##SUFF##_le_host, sve_ld1##SUFF##_le_tlb);       \
 }                                                                     \
-void QEMU_FLATTEN HELPER(sve_ld##N##SUFF##_be_r)                      \
-    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)    \
+void HELPER(sve_ld##N##SUFF##_be_r)(CPUARMState *env, void *vg,       \
+                                    target_ulong addr, uint32_t desc) \
 {                                                                     \
-    sve_ld##N##_r(env, vg, addr, desc, SIZE, GETPC(),                 \
-                  sve_ld1##SUFF##_be_tlb);                            \
+    sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, ESZ, N,              \
+              sve_ld1##SUFF##_be_host, sve_ld1##SUFF##_be_tlb);       \
 }
 
 DO_LDN_1(2)
 DO_LDN_1(3)
 DO_LDN_1(4)
 
-DO_LDN_2(2, hh, 2)
-DO_LDN_2(3, hh, 2)
-DO_LDN_2(4, hh, 2)
+DO_LDN_2(2, hh, MO_16)
+DO_LDN_2(3, hh, MO_16)
+DO_LDN_2(4, hh, MO_16)
 
-DO_LDN_2(2, ss, 4)
-DO_LDN_2(3, ss, 4)
-DO_LDN_2(4, ss, 4)
+DO_LDN_2(2, ss, MO_32)
+DO_LDN_2(3, ss, MO_32)
+DO_LDN_2(4, ss, MO_32)
 
-DO_LDN_2(2, dd, 8)
-DO_LDN_2(3, dd, 8)
-DO_LDN_2(4, dd, 8)
+DO_LDN_2(2, dd, MO_64)
+DO_LDN_2(3, dd, MO_64)
+DO_LDN_2(4, dd, MO_64)
 
 #undef DO_LDN_1
 #undef DO_LDN_2
-- 
2.20.1

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

With sve_cont_ldst_pages, the differences between first-fault and no-fault
are minimal, so unify the routines.  With cpu_probe_watchpoint, we are able
to make progress through pages with TLB_WATCHPOINT set when the watchpoint
does not actually fire.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-15-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 346 +++++++++++++++++++---------------------
 1 file changed, 162 insertions(+), 184 deletions(-)

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 @@ static intptr_t find_next_active(uint64_t *vg, intptr_t reg_off,
     return reg_off;
 }
 
-/*
- * Return the maximum offset <= @mem_max which is still within the page
- * referenced by @base + @mem_off.
- */
-static intptr_t max_for_page(target_ulong base, intptr_t mem_off,
-                             intptr_t mem_max)
-{
-    target_ulong addr = base + mem_off;
-    intptr_t split = -(intptr_t)(addr | TARGET_PAGE_MASK);
-    return MIN(split, mem_max - mem_off) + mem_off;
-}
-
 /*
  * Resolve the guest virtual address to info->host and info->flags.
  * If @nofault, return false if the page is invalid, otherwise
@@ -XXX,XX +XXX,XX @@ static void sve_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env,
 #endif
 }
 
-/*
- * The result of tlb_vaddr_to_host for user-only is just g2h(x),
- * which is always non-null.  Elide the useless test.
- */
-static inline bool test_host_page(void *host)
-{
-#ifdef CONFIG_USER_ONLY
-    return true;
-#else
-    return likely(host != NULL);
-#endif
-}
-
 /*
  * Common helper for all contiguous 1,2,3,4-register predicated stores.
  */
@@ -XXX,XX +XXX,XX @@ static void record_fault(CPUARMState *env, uintptr_t i, uintptr_t oprsz)
 }
 
 /*
- * Common helper for all contiguous first-fault loads.
+ * Common helper for all contiguous no-fault and first-fault loads.
  */
-static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
-                        uint32_t desc, const uintptr_t retaddr,
-                        const int esz, const int msz,
-                        sve_ldst1_host_fn *host_fn,
-                        sve_ldst1_tlb_fn *tlb_fn)
+static inline QEMU_ALWAYS_INLINE
+void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr,
+                   uint32_t desc, const uintptr_t retaddr,
+                   const int esz, const int msz, const SVEContFault fault,
+                   sve_ldst1_host_fn *host_fn,
+                   sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
-    const int mmu_idx = get_mmuidx(oi);
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
     void *vd = &env->vfp.zregs[rd];
-    const int diffsz = esz - msz;
     const intptr_t reg_max = simd_oprsz(desc);
-    const intptr_t mem_max = reg_max >> diffsz;
-    intptr_t split, reg_off, mem_off, i;
+    intptr_t reg_off, mem_off, reg_last;
+    SVEContLdSt info;
+    int flags;
     void *host;
 
-    /* Skip to the first active element.  */
-    reg_off = find_next_active(vg, 0, reg_max, esz);
-    if (unlikely(reg_off == reg_max)) {
+    /* Find the active elements.  */
+    if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, 1 << msz)) {
         /* The entire predicate was false; no load occurs.  */
         memset(vd, 0, reg_max);
         return;
     }
-    mem_off = reg_off >> diffsz;
+    reg_off = info.reg_off_first[0];
 
-    /*
-     * If the (remaining) load is entirely within a single page, then:
-     * For softmmu, and the tlb hits, then no faults will occur;
-     * For user-only, either the first load will fault or none will.
-     * We can thus perform the load directly to the destination and
-     * Vd will be unmodified on any exception path.
-     */
-    split = max_for_page(addr, mem_off, mem_max);
-    if (likely(split == mem_max)) {
-        host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
-        if (test_host_page(host)) {
-            i = reg_off;
-            host -= mem_off;
-            do {
-                host_fn(vd, i, host + (i >> diffsz));
-                i = find_next_active(vg, i + (1 << esz), reg_max, esz);
-            } while (i < reg_max);
-            /* After any fault, zero any leading inactive elements.  */
+    /* Probe the page(s). */
+    if (!sve_cont_ldst_pages(&info, fault, env, addr, MMU_DATA_LOAD, retaddr)) {
+        /* Fault on first element. */
+        tcg_debug_assert(fault == FAULT_NO);
+        memset(vd, 0, reg_max);
+        goto do_fault;
+    }
+
+    mem_off = info.mem_off_first[0];
+    flags = info.page[0].flags;
+
+    if (fault == FAULT_FIRST) {
+        /*
+         * Special handling of the first active element,
+         * if it crosses a page boundary or is MMIO.
+         */
+        bool is_split = mem_off == info.mem_off_split;
+        /* TODO: MTE check. */
+        if (unlikely(flags != 0) || unlikely(is_split)) {
+            /*
+             * Use the slow path for cross-page handling.
+             * Might trap for MMIO or watchpoints.
+             */
+            tlb_fn(env, vd, reg_off, addr + mem_off, retaddr);
+
+            /* After any fault, zero the other elements. */
             swap_memzero(vd, reg_off);
-            return;
+            reg_off += 1 << esz;
+            mem_off += 1 << msz;
+            swap_memzero(vd + reg_off, reg_max - reg_off);
+
+            if (is_split) {
+                goto second_page;
+            }
+        } else {
+            memset(vd, 0, reg_max);
+        }
+    } else {
+        memset(vd, 0, reg_max);
+        if (unlikely(mem_off == info.mem_off_split)) {
+            /* The first active element crosses a page boundary. */
+            flags |= info.page[1].flags;
+            if (unlikely(flags & TLB_MMIO)) {
+                /* Some page is MMIO, see below. */
+                goto do_fault;
+            }
+            if (unlikely(flags & TLB_WATCHPOINT) &&
+                (cpu_watchpoint_address_matches
+                 (env_cpu(env), addr + mem_off, 1 << msz)
+                 & BP_MEM_READ)) {
+                /* Watchpoint hit, see below. */
+                goto do_fault;
+            }
+            /* TODO: MTE check. */
+            /*
+             * Use the slow path for cross-page handling.
+             * This is RAM, without a watchpoint, and will not trap.
+             */
+            tlb_fn(env, vd, reg_off, addr + mem_off, retaddr);
+            goto second_page;
         }
     }
 
     /*
-     * Perform one normal read, which will fault or not.
-     * But it is likely to bring the page into the tlb.
+     * From this point on, all memory operations are MemSingleNF.
+     *
+     * Per the MemSingleNF pseudocode, a no-fault load from Device memory
+     * must not actually hit the bus -- it returns (UNKNOWN, FAULT) instead.
+     *
+     * Unfortuately we do not have access to the memory attributes from the
+     * PTE to tell Device memory from Normal memory.  So we make a mostly
+     * correct check, and indicate (UNKNOWN, FAULT) for any MMIO.
+     * This gives the right answer for the common cases of "Normal memory,
+     * backed by host RAM" and "Device memory, backed by MMIO".
+     * The architecture allows us to suppress an NF load and return
+     * (UNKNOWN, FAULT) for any reason, so our behaviour for the corner
+     * case of "Normal memory, backed by MMIO" is permitted.  The case we
+     * get wrong is "Device memory, backed by host RAM", for which we
+     * should return (UNKNOWN, FAULT) for but do not.
+     *
+     * Similarly, CPU_BP breakpoints would raise exceptions, and so
+     * return (UNKNOWN, FAULT).  For simplicity, we consider gdb and
+     * architectural breakpoints the same.
      */
-    tlb_fn(env, vd, reg_off, addr + mem_off, retaddr);
+    if (unlikely(flags & TLB_MMIO)) {
+        goto do_fault;
+    }
 
-    /* After any fault, zero any leading predicated false elts.  */
-    swap_memzero(vd, reg_off);
-    mem_off += 1 << msz;
-    reg_off += 1 << esz;
+    reg_last = info.reg_off_last[0];
+    host = info.page[0].host;
 
-    /* Try again to read the balance of the page.  */
-    split = max_for_page(addr, mem_off - 1, mem_max);
-    if (split >= (1 << msz)) {
-        host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
-        if (host) {
-            host -= mem_off;
-            do {
+    do {
+        uint64_t pg = *(uint64_t *)(vg + (reg_off >> 3));
+        do {
+            if ((pg >> (reg_off & 63)) & 1) {
+                if (unlikely(flags & TLB_WATCHPOINT) &&
+                    (cpu_watchpoint_address_matches
+                     (env_cpu(env), addr + mem_off, 1 << msz)
+                     & BP_MEM_READ)) {
+                    goto do_fault;
+                }
+                /* TODO: MTE check. */
                 host_fn(vd, reg_off, host + mem_off);
-                reg_off += 1 << esz;
-                reg_off = find_next_active(vg, reg_off, reg_max, esz);
-                mem_off = reg_off >> diffsz;
-            } while (split - mem_off >= (1 << msz));
-        }
-    }
-
-    record_fault(env, reg_off, reg_max);
-}
-
-/*
- * Common helper for all contiguous no-fault loads.
- */
-static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
-                        uint32_t desc, const int esz, const int msz,
-                        sve_ldst1_host_fn *host_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    void *vd = &env->vfp.zregs[rd];
-    const int diffsz = esz - msz;
-    const intptr_t reg_max = simd_oprsz(desc);
-    const intptr_t mem_max = reg_max >> diffsz;
-    const int mmu_idx = cpu_mmu_index(env, false);
-    intptr_t split, reg_off, mem_off;
-    void *host;
-
-#ifdef CONFIG_USER_ONLY
-    host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx);
-    if (likely(page_check_range(addr, mem_max, PAGE_READ) == 0)) {
-        /* The entire operation is valid and will not fault.  */
-        reg_off = 0;
-        do {
-            mem_off = reg_off >> diffsz;
-            host_fn(vd, reg_off, host + mem_off);
+            }
             reg_off += 1 << esz;
-            reg_off = find_next_active(vg, reg_off, reg_max, esz);
-        } while (reg_off < reg_max);
-        return;
-    }
-#endif
+            mem_off += 1 << msz;
+        } while (reg_off <= reg_last && (reg_off & 63));
+    } while (reg_off <= reg_last);
 
-    /* There will be no fault, so we may modify in advance.  */
-    memset(vd, 0, reg_max);
-
-    /* Skip to the first active element.  */
-    reg_off = find_next_active(vg, 0, reg_max, esz);
-    if (unlikely(reg_off == reg_max)) {
-        /* The entire predicate was false; no load occurs.  */
-        return;
-    }
-    mem_off = reg_off >> diffsz;
-
-#ifdef CONFIG_USER_ONLY
-    if (page_check_range(addr + mem_off, 1 << msz, PAGE_READ) == 0) {
-        /* At least one load is valid; take the rest of the page.  */
-        split = max_for_page(addr, mem_off + (1 << msz) - 1, mem_max);
-        do {
-            host_fn(vd, reg_off, host + mem_off);
-            reg_off += 1 << esz;
-            reg_off = find_next_active(vg, reg_off, reg_max, esz);
-            mem_off = reg_off >> diffsz;
-        } while (split - mem_off >= (1 << msz));
-    }
-#else
     /*
-     * If the address is not in the TLB, we have no way to bring the
-     * entry into the TLB without also risking a fault.  Note that
-     * the corollary is that we never load from an address not in RAM.
-     *
-     * This last is out of spec, in a weird corner case.
-     * Per the MemNF/MemSingleNF pseudocode, a NF load from Device memory
-     * must not actually hit the bus -- it returns UNKNOWN data instead.
-     * But if you map non-RAM with Normal memory attributes and do a NF
-     * load then it should access the bus.  (Nobody ought actually do this
-     * in the real world, obviously.)
-     *
-     * Then there are the annoying special cases with watchpoints...
-     * TODO: Add a form of non-faulting loads using cc->tlb_fill(probe=true).
+     * MemSingleNF is allowed to fail for any reason.  We have special
+     * code above to handle the first element crossing a page boundary.
+     * As an implementation choice, decline to handle a cross-page element
+     * in any other position.
      */
-    host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
-    split = max_for_page(addr, mem_off, mem_max);
-    if (host && split >= (1 << msz)) {
-        host -= mem_off;
-        do {
-            host_fn(vd, reg_off, host + mem_off);
-            reg_off += 1 << esz;
-            reg_off = find_next_active(vg, reg_off, reg_max, esz);
-            mem_off = reg_off >> diffsz;
-        } while (split - mem_off >= (1 << msz));
+    reg_off = info.reg_off_split;
+    if (reg_off >= 0) {
+        goto do_fault;
     }
-#endif
 
+ second_page:
+    reg_off = info.reg_off_first[1];
+    if (likely(reg_off < 0)) {
+        /* No active elements on the second page.  All done. */
+        return;
+    }
+
+    /*
+     * MemSingleNF is allowed to fail for any reason.  As an implementation
+     * choice, decline to handle elements on the second page.  This should
+     * be low frequency as the guest walks through memory -- the next
+     * iteration of the guest's loop should be aligned on the page boundary,
+     * and then all following iterations will stay aligned.
+     */
+
+ do_fault:
     record_fault(env, reg_off, reg_max);
 }
 
@@ -XXX,XX +XXX,XX @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
 void HELPER(sve_ldff1##PART##_r)(CPUARMState *env, void *vg,            \
                                  target_ulong addr, uint32_t desc)      \
 {                                                                       \
-    sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, 0,                   \
-                sve_ld1##PART##_host, sve_ld1##PART##_tlb);             \
+    sve_ldnfff1_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, FAULT_FIRST, \
+                  sve_ld1##PART##_host, sve_ld1##PART##_tlb);           \
 }                                                                       \
 void HELPER(sve_ldnf1##PART##_r)(CPUARMState *env, void *vg,            \
                                  target_ulong addr, uint32_t desc)      \
 {                                                                       \
-    sve_ldnf1_r(env, vg, addr, desc, ESZ, 0, sve_ld1##PART##_host);     \
+    sve_ldnfff1_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, FAULT_NO,    \
+                  sve_ld1##PART##_host, sve_ld1##PART##_tlb);           \
 }
 
 #define DO_LDFF1_LDNF1_2(PART, ESZ, MSZ) \
 void HELPER(sve_ldff1##PART##_le_r)(CPUARMState *env, void *vg,         \
                                     target_ulong addr, uint32_t desc)   \
 {                                                                       \
-    sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ,                 \
-                sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb);       \
+    sve_ldnfff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_FIRST,  \
+                  sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb);     \
 }                                                                       \
 void HELPER(sve_ldnf1##PART##_le_r)(CPUARMState *env, void *vg,         \
                                     target_ulong addr, uint32_t desc)   \
 {                                                                       \
-    sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_le_host); \
+    sve_ldnfff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_NO,     \
+                  sve_ld1##PART##_le_host, sve_ld1##PART##_le_tlb);     \
 }                                                                       \
 void HELPER(sve_ldff1##PART##_be_r)(CPUARMState *env, void *vg,         \
                                     target_ulong addr, uint32_t desc)   \
 {                                                                       \
-    sve_ldff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ,                 \
-                sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb);       \
+    sve_ldnfff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_FIRST,  \
+                  sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb);     \
 }                                                                       \
 void HELPER(sve_ldnf1##PART##_be_r)(CPUARMState *env, void *vg,         \
                                     target_ulong addr, uint32_t desc)   \
 {                                                                       \
-    sve_ldnf1_r(env, vg, addr, desc, ESZ, MSZ, sve_ld1##PART##_be_host); \
+    sve_ldnfff1_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, FAULT_NO,     \
+                  sve_ld1##PART##_be_host, sve_ld1##PART##_be_tlb);     \
 }
 
-DO_LDFF1_LDNF1_1(bb,  0)
-DO_LDFF1_LDNF1_1(bhu, 1)
-DO_LDFF1_LDNF1_1(bhs, 1)
-DO_LDFF1_LDNF1_1(bsu, 2)
-DO_LDFF1_LDNF1_1(bss, 2)
-DO_LDFF1_LDNF1_1(bdu, 3)
-DO_LDFF1_LDNF1_1(bds, 3)
+DO_LDFF1_LDNF1_1(bb,  MO_8)
+DO_LDFF1_LDNF1_1(bhu, MO_16)
+DO_LDFF1_LDNF1_1(bhs, MO_16)
+DO_LDFF1_LDNF1_1(bsu, MO_32)
+DO_LDFF1_LDNF1_1(bss, MO_32)
+DO_LDFF1_LDNF1_1(bdu, MO_64)
+DO_LDFF1_LDNF1_1(bds, MO_64)
 
-DO_LDFF1_LDNF1_2(hh,  1, 1)
-DO_LDFF1_LDNF1_2(hsu, 2, 1)
-DO_LDFF1_LDNF1_2(hss, 2, 1)
-DO_LDFF1_LDNF1_2(hdu, 3, 1)
-DO_LDFF1_LDNF1_2(hds, 3, 1)
+DO_LDFF1_LDNF1_2(hh,  MO_16, MO_16)
+DO_LDFF1_LDNF1_2(hsu, MO_32, MO_16)
+DO_LDFF1_LDNF1_2(hss, MO_32, MO_16)
+DO_LDFF1_LDNF1_2(hdu, MO_64, MO_16)
+DO_LDFF1_LDNF1_2(hds, MO_64, MO_16)
 
-DO_LDFF1_LDNF1_2(ss,  2, 2)
-DO_LDFF1_LDNF1_2(sdu, 3, 2)
-DO_LDFF1_LDNF1_2(sds, 3, 2)
+DO_LDFF1_LDNF1_2(ss,  MO_32, MO_32)
+DO_LDFF1_LDNF1_2(sdu, MO_64, MO_32)
+DO_LDFF1_LDNF1_2(sds, MO_64, MO_32)
 
-DO_LDFF1_LDNF1_2(dd,  3, 3)
+DO_LDFF1_LDNF1_2(dd,  MO_64, MO_64)
 
 #undef DO_LDFF1_LDNF1_1
 #undef DO_LDFF1_LDNF1_2
-- 
2.20.1

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

Follow the model set up for contiguous loads.  This handles
watchpoints correctly for contiguous stores, recognizing the
exception before any changes to memory.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-16-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 285 ++++++++++++++++++++++------------------
 1 file changed, 159 insertions(+), 126 deletions(-)

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 @@ static void sve_##NAME##_host(void *vd, intptr_t reg_off, void *host)  \
     *(TYPEE *)(vd + H(reg_off)) = val;                                 \
 }
 
+#define DO_ST_HOST(NAME, H, TYPEE, TYPEM, HOST) \
+static void sve_##NAME##_host(void *vd, intptr_t reg_off, void *host)  \
+{ HOST(host, (TYPEM)*(TYPEE *)(vd + H(reg_off))); }
+
 #define DO_LD_TLB(NAME, H, TYPEE, TYPEM, TLB) \
 static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off,  \
                              target_ulong addr, uintptr_t ra)               \
@@ -XXX,XX +XXX,XX @@ DO_LD_PRIM_1(ld1bdu,     , uint64_t, uint8_t)
 DO_LD_PRIM_1(ld1bds,     , uint64_t,  int8_t)
 
 #define DO_ST_PRIM_1(NAME, H, TE, TM)                   \
+    DO_ST_HOST(st1##NAME, H, TE, TM, stb_p)             \
     DO_ST_TLB(st1##NAME, H, TE, TM, cpu_stb_data_ra)
 
 DO_ST_PRIM_1(bb,   H1,  uint8_t, uint8_t)
@@ -XXX,XX +XXX,XX @@ DO_ST_PRIM_1(bd,     , uint64_t, uint8_t)
     DO_LD_TLB(ld1##NAME##_le, H, TE, TM, cpu_##LD##_le_data_ra)
 
 #define DO_ST_PRIM_2(NAME, H, TE, TM, ST) \
+    DO_ST_HOST(st1##NAME##_be, H, TE, TM, ST##_be_p)    \
+    DO_ST_HOST(st1##NAME##_le, H, TE, TM, ST##_le_p)    \
     DO_ST_TLB(st1##NAME##_be, H, TE, TM, cpu_##ST##_be_data_ra) \
     DO_ST_TLB(st1##NAME##_le, H, TE, TM, cpu_##ST##_le_data_ra)
 
@@ -XXX,XX +XXX,XX @@ DO_LDFF1_LDNF1_2(dd,  MO_64, MO_64)
 #undef DO_LDFF1_LDNF1_2
 
 /*
- * Common helpers for all contiguous 1,2,3,4-register predicated stores.
+ * Common helper for all contiguous 1,2,3,4-register predicated stores.
  */
-static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, const uintptr_t ra,
-                      const int esize, const int msize,
-                      sve_ldst1_tlb_fn *tlb_fn)
+
+static inline QEMU_ALWAYS_INLINE
+void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, uint32_t desc,
+               const uintptr_t retaddr, const int esz,
+               const int msz, const int N,
+               sve_ldst1_host_fn *host_fn,
+               sve_ldst1_tlb_fn *tlb_fn)
 {
     const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    void *vd = &env->vfp.zregs[rd];
+    const intptr_t reg_max = simd_oprsz(desc);
+    intptr_t reg_off, reg_last, mem_off;
+    SVEContLdSt info;
+    void *host;
+    int i, flags;
 
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, vd, i, addr, ra);
+    /* Find the active elements.  */
+    if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, N << msz)) {
+        /* The entire predicate was false; no store occurs.  */
+        return;
+    }
+
+    /* Probe the page(s).  Exit with exception for any invalid page. */
+    sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, retaddr);
+
+    /* Handle watchpoints for all active elements. */
+    sve_cont_ldst_watchpoints(&info, env, vg, addr, 1 << esz, N << msz,
+                              BP_MEM_WRITE, retaddr);
+
+    /* TODO: MTE check. */
+
+    flags = info.page[0].flags | info.page[1].flags;
+    if (unlikely(flags != 0)) {
+#ifdef CONFIG_USER_ONLY
+        g_assert_not_reached();
+#else
+        /*
+         * At least one page includes MMIO.
+         * Any bus operation can fail with cpu_transaction_failed,
+         * which for ARM will raise SyncExternal.  We cannot avoid
+         * this fault and will leave with the store incomplete.
+         */
+        mem_off = info.mem_off_first[0];
+        reg_off = info.reg_off_first[0];
+        reg_last = info.reg_off_last[1];
+        if (reg_last < 0) {
+            reg_last = info.reg_off_split;
+            if (reg_last < 0) {
+                reg_last = info.reg_off_last[0];
             }
-            i += esize, pg >>= esize;
-            addr += msize;
-        } while (i & 15);
+        }
+
+        do {
+            uint64_t pg = vg[reg_off >> 6];
+            do {
+                if ((pg >> (reg_off & 63)) & 1) {
+                    for (i = 0; i < N; ++i) {
+                        tlb_fn(env, &env->vfp.zregs[(rd + i) & 31], reg_off,
+                               addr + mem_off + (i << msz), retaddr);
+                    }
+                }
+                reg_off += 1 << esz;
+                mem_off += N << msz;
+            } while (reg_off & 63);
+        } while (reg_off <= reg_last);
+        return;
+#endif
+    }
+
+    mem_off = info.mem_off_first[0];
+    reg_off = info.reg_off_first[0];
+    reg_last = info.reg_off_last[0];
+    host = info.page[0].host;
+
+    while (reg_off <= reg_last) {
+        uint64_t pg = vg[reg_off >> 6];
+        do {
+            if ((pg >> (reg_off & 63)) & 1) {
+                for (i = 0; i < N; ++i) {
+                    host_fn(&env->vfp.zregs[(rd + i) & 31], reg_off,
+                            host + mem_off + (i << msz));
+                }
+            }
+            reg_off += 1 << esz;
+            mem_off += N << msz;
+        } while (reg_off <= reg_last && (reg_off & 63));
+    }
+
+    /*
+     * Use the slow path to manage the cross-page misalignment.
+     * But we know this is RAM and cannot trap.
+     */
+    mem_off = info.mem_off_split;
+    if (unlikely(mem_off >= 0)) {
+        reg_off = info.reg_off_split;
+        for (i = 0; i < N; ++i) {
+            tlb_fn(env, &env->vfp.zregs[(rd + i) & 31], reg_off,
+                   addr + mem_off + (i << msz), retaddr);
+        }
+    }
+
+    mem_off = info.mem_off_first[1];
+    if (unlikely(mem_off >= 0)) {
+        reg_off = info.reg_off_first[1];
+        reg_last = info.reg_off_last[1];
+        host = info.page[1].host;
+
+        do {
+            uint64_t pg = vg[reg_off >> 6];
+            do {
+                if ((pg >> (reg_off & 63)) & 1) {
+                    for (i = 0; i < N; ++i) {
+                        host_fn(&env->vfp.zregs[(rd + i) & 31], reg_off,
+                                host + mem_off + (i << msz));
+                    }
+                }
+                reg_off += 1 << esz;
+                mem_off += N << msz;
+            } while (reg_off & 63);
+        } while (reg_off <= reg_last);
     }
 }
 
-static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, const uintptr_t ra,
-                      const int esize, const int msize,
-                      sve_ldst1_tlb_fn *tlb_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    void *d1 = &env->vfp.zregs[rd];
-    void *d2 = &env->vfp.zregs[(rd + 1) & 31];
-
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, d1, i, addr, ra);
-                tlb_fn(env, d2, i, addr + msize, ra);
-            }
-            i += esize, pg >>= esize;
-            addr += 2 * msize;
-        } while (i & 15);
-    }
-}
-
-static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, const uintptr_t ra,
-                      const int esize, const int msize,
-                      sve_ldst1_tlb_fn *tlb_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    void *d1 = &env->vfp.zregs[rd];
-    void *d2 = &env->vfp.zregs[(rd + 1) & 31];
-    void *d3 = &env->vfp.zregs[(rd + 2) & 31];
-
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, d1, i, addr, ra);
-                tlb_fn(env, d2, i, addr + msize, ra);
-                tlb_fn(env, d3, i, addr + 2 * msize, ra);
-            }
-            i += esize, pg >>= esize;
-            addr += 3 * msize;
-        } while (i & 15);
-    }
-}
-
-static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
-                      uint32_t desc, const uintptr_t ra,
-                      const int esize, const int msize,
-                      sve_ldst1_tlb_fn *tlb_fn)
-{
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    void *d1 = &env->vfp.zregs[rd];
-    void *d2 = &env->vfp.zregs[(rd + 1) & 31];
-    void *d3 = &env->vfp.zregs[(rd + 2) & 31];
-    void *d4 = &env->vfp.zregs[(rd + 3) & 31];
-
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
-        do {
-            if (pg & 1) {
-                tlb_fn(env, d1, i, addr, ra);
-                tlb_fn(env, d2, i, addr + msize, ra);
-                tlb_fn(env, d3, i, addr + 2 * msize, ra);
-                tlb_fn(env, d4, i, addr + 3 * msize, ra);
-            }
-            i += esize, pg >>= esize;
-            addr += 4 * msize;
-        } while (i & 15);
-    }
-}
-
-#define DO_STN_1(N, NAME, ESIZE) \
-void QEMU_FLATTEN HELPER(sve_st##N##NAME##_r) \
-    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)  \
+#define DO_STN_1(N, NAME, ESZ) \
+void HELPER(sve_st##N##NAME##_r)(CPUARMState *env, void *vg,        \
+                                 target_ulong addr, uint32_t desc)  \
 {                                                                   \
-    sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, 1,           \
-                  sve_st1##NAME##_tlb);                             \
+    sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, N,           \
+              sve_st1##NAME##_host, sve_st1##NAME##_tlb);           \
 }
 
-#define DO_STN_2(N, NAME, ESIZE, MSIZE) \
-void QEMU_FLATTEN HELPER(sve_st##N##NAME##_le_r) \
-    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)    \
+#define DO_STN_2(N, NAME, ESZ, MSZ) \
+void HELPER(sve_st##N##NAME##_le_r)(CPUARMState *env, void *vg,       \
+                                    target_ulong addr, uint32_t desc) \
 {                                                                     \
-    sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE,         \
-                  sve_st1##NAME##_le_tlb);                            \
+    sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, N,              \
+              sve_st1##NAME##_le_host, sve_st1##NAME##_le_tlb);       \
 }                                                                     \
-void QEMU_FLATTEN HELPER(sve_st##N##NAME##_be_r)                      \
-    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)    \
+void HELPER(sve_st##N##NAME##_be_r)(CPUARMState *env, void *vg,       \
+                                    target_ulong addr, uint32_t desc) \
 {                                                                     \
-    sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE,         \
-                  sve_st1##NAME##_be_tlb);                            \
+    sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, N,              \
+              sve_st1##NAME##_be_host, sve_st1##NAME##_be_tlb);       \
 }
 
-DO_STN_1(1, bb, 1)
-DO_STN_1(1, bh, 2)
-DO_STN_1(1, bs, 4)
-DO_STN_1(1, bd, 8)
-DO_STN_1(2, bb, 1)
-DO_STN_1(3, bb, 1)
-DO_STN_1(4, bb, 1)
+DO_STN_1(1, bb, MO_8)
+DO_STN_1(1, bh, MO_16)
+DO_STN_1(1, bs, MO_32)
+DO_STN_1(1, bd, MO_64)
+DO_STN_1(2, bb, MO_8)
+DO_STN_1(3, bb, MO_8)
+DO_STN_1(4, bb, MO_8)
 
-DO_STN_2(1, hh, 2, 2)
-DO_STN_2(1, hs, 4, 2)
-DO_STN_2(1, hd, 8, 2)
-DO_STN_2(2, hh, 2, 2)
-DO_STN_2(3, hh, 2, 2)
-DO_STN_2(4, hh, 2, 2)
+DO_STN_2(1, hh, MO_16, MO_16)
+DO_STN_2(1, hs, MO_32, MO_16)
+DO_STN_2(1, hd, MO_64, MO_16)
+DO_STN_2(2, hh, MO_16, MO_16)
+DO_STN_2(3, hh, MO_16, MO_16)
+DO_STN_2(4, hh, MO_16, MO_16)
 
-DO_STN_2(1, ss, 4, 4)
-DO_STN_2(1, sd, 8, 4)
-DO_STN_2(2, ss, 4, 4)
-DO_STN_2(3, ss, 4, 4)
-DO_STN_2(4, ss, 4, 4)
+DO_STN_2(1, ss, MO_32, MO_32)
+DO_STN_2(1, sd, MO_64, MO_32)
+DO_STN_2(2, ss, MO_32, MO_32)
+DO_STN_2(3, ss, MO_32, MO_32)
+DO_STN_2(4, ss, MO_32, MO_32)
 
-DO_STN_2(1, dd, 8, 8)
-DO_STN_2(2, dd, 8, 8)
-DO_STN_2(3, dd, 8, 8)
-DO_STN_2(4, dd, 8, 8)
+DO_STN_2(1, dd, MO_64, MO_64)
+DO_STN_2(2, dd, MO_64, MO_64)
+DO_STN_2(3, dd, MO_64, MO_64)
+DO_STN_2(4, dd, MO_64, MO_64)
 
 #undef DO_STN_1
 #undef DO_STN_2
-- 
2.20.1

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

This avoids the need for a separate set of helpers to implement
no-fault semantics, and will enable MTE in the future.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-17-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 323 ++++++++++++++++------------------------
 1 file changed, 127 insertions(+), 196 deletions(-)

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_LD1_ZPZ_D(dd_be, zd)
 
 /* First fault loads with a vector index.  */
 
-/* Load one element into VD+REG_OFF from (ENV,VADDR) without faulting.
- * The controlling predicate is known to be true.  Return true if the
- * load was successful.
- */
-typedef bool sve_ld1_nf_fn(CPUARMState *env, void *vd, intptr_t reg_off,
-                           target_ulong vaddr, int mmu_idx);
-
-#ifdef CONFIG_SOFTMMU
-#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \
-static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \
-                              target_ulong addr, int mmu_idx)               \
-{                                                                           \
-    target_ulong next_page = -(addr | TARGET_PAGE_MASK);                    \
-    if (likely(next_page - addr >= sizeof(TYPEM))) {                        \
-        void *host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD, mmu_idx);  \
-        if (likely(host)) {                                                 \
-            TYPEM val = HOST(host);                                         \
-            *(TYPEE *)(vd + H(reg_off)) = val;                              \
-            return true;                                                    \
-        }                                                                   \
-    }                                                                       \
-    return false;                                                           \
-}
-#else
-#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \
-static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \
-                            target_ulong addr, int mmu_idx)                 \
-{                                                                           \
-    if (likely(page_check_range(addr, sizeof(TYPEM), PAGE_READ))) {         \
-        TYPEM val = HOST(g2h(addr));                                        \
-        *(TYPEE *)(vd + H(reg_off)) = val;                                  \
-        return true;                                                        \
-    }                                                                       \
-    return false;                                                           \
-}
-#endif
-
-DO_LD_NF(bsu, H1_4, uint32_t, uint8_t, ldub_p)
-DO_LD_NF(bss, H1_4, uint32_t,  int8_t, ldsb_p)
-DO_LD_NF(bdu,     , uint64_t, uint8_t, ldub_p)
-DO_LD_NF(bds,     , uint64_t,  int8_t, ldsb_p)
-
-DO_LD_NF(hsu_le, H1_4, uint32_t, uint16_t, lduw_le_p)
-DO_LD_NF(hss_le, H1_4, uint32_t,  int16_t, ldsw_le_p)
-DO_LD_NF(hsu_be, H1_4, uint32_t, uint16_t, lduw_be_p)
-DO_LD_NF(hss_be, H1_4, uint32_t,  int16_t, ldsw_be_p)
-DO_LD_NF(hdu_le,     , uint64_t, uint16_t, lduw_le_p)
-DO_LD_NF(hds_le,     , uint64_t,  int16_t, ldsw_le_p)
-DO_LD_NF(hdu_be,     , uint64_t, uint16_t, lduw_be_p)
-DO_LD_NF(hds_be,     , uint64_t,  int16_t, ldsw_be_p)
-
-DO_LD_NF(ss_le,  H1_4, uint32_t, uint32_t, ldl_le_p)
-DO_LD_NF(ss_be,  H1_4, uint32_t, uint32_t, ldl_be_p)
-DO_LD_NF(sdu_le,     , uint64_t, uint32_t, ldl_le_p)
-DO_LD_NF(sds_le,     , uint64_t,  int32_t, ldl_le_p)
-DO_LD_NF(sdu_be,     , uint64_t, uint32_t, ldl_be_p)
-DO_LD_NF(sds_be,     , uint64_t,  int32_t, ldl_be_p)
-
-DO_LD_NF(dd_le,      , uint64_t, uint64_t, ldq_le_p)
-DO_LD_NF(dd_be,      , uint64_t, uint64_t, ldq_be_p)
-
 /*
- * Common helper for all gather first-faulting loads.
+ * Common helpers for all gather first-faulting loads.
  */
-static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
-                                target_ulong base, uint32_t desc, uintptr_t ra,
-                                zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn,
-                                sve_ld1_nf_fn *nonfault_fn)
+
+static inline QEMU_ALWAYS_INLINE
+void sve_ldff1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
+                 target_ulong base, uint32_t desc, uintptr_t retaddr,
+                 const int esz, const int msz, zreg_off_fn *off_fn,
+                 sve_ldst1_host_fn *host_fn,
+                 sve_ldst1_tlb_fn *tlb_fn)
 {
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
-    const int mmu_idx = get_mmuidx(oi);
+    const int mmu_idx = cpu_mmu_index(env, false);
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t reg_off, reg_max = simd_oprsz(desc);
-    target_ulong addr;
+    const int esize = 1 << esz;
+    const int msize = 1 << msz;
+    const intptr_t reg_max = simd_oprsz(desc);
+    intptr_t reg_off;
+    SVEHostPage info;
+    target_ulong addr, in_page;
 
     /* Skip to the first true predicate.  */
-    reg_off = find_next_active(vg, 0, reg_max, MO_32);
-    if (likely(reg_off < reg_max)) {
-        /* Perform one normal read, which will fault or not.  */
-        addr = off_fn(vm, reg_off);
-        addr = base + (addr << scale);
-        tlb_fn(env, vd, reg_off, addr, ra);
-
-        /* The rest of the reads will be non-faulting.  */
+    reg_off = find_next_active(vg, 0, reg_max, esz);
+    if (unlikely(reg_off >= reg_max)) {
+        /* The entire predicate was false; no load occurs.  */
+        memset(vd, 0, reg_max);
+        return;
     }
 
-    /* After any fault, zero the leading predicated false elements.  */
+    /*
+     * Probe the first element, allowing faults.
+     */
+    addr = base + (off_fn(vm, reg_off) << scale);
+    tlb_fn(env, vd, reg_off, addr, retaddr);
+
+    /* After any fault, zero the other elements. */
     swap_memzero(vd, reg_off);
+    reg_off += esize;
+    swap_memzero(vd + reg_off, reg_max - reg_off);
 
-    while (likely((reg_off += 4) < reg_max)) {
-        uint64_t pg = *(uint64_t *)(vg + (reg_off >> 6) * 8);
-        if (likely((pg >> (reg_off & 63)) & 1)) {
-            addr = off_fn(vm, reg_off);
-            addr = base + (addr << scale);
-            if (!nonfault_fn(env, vd, reg_off, addr, mmu_idx)) {
-                record_fault(env, reg_off, reg_max);
-                break;
+    /*
+     * Probe the remaining elements, not allowing faults.
+     */
+    while (reg_off < reg_max) {
+        uint64_t pg = vg[reg_off >> 6];
+        do {
+            if (likely((pg >> (reg_off & 63)) & 1)) {
+                addr = base + (off_fn(vm, reg_off) << scale);
+                in_page = -(addr | TARGET_PAGE_MASK);
+
+                if (unlikely(in_page < msize)) {
+                    /* Stop if the element crosses a page boundary. */
+                    goto fault;
+                }
+
+                sve_probe_page(&info, true, env, addr, 0, MMU_DATA_LOAD,
+                               mmu_idx, retaddr);
+                if (unlikely(info.flags & (TLB_INVALID_MASK | TLB_MMIO))) {
+                    goto fault;
+                }
+                if (unlikely(info.flags & TLB_WATCHPOINT) &&
+                    (cpu_watchpoint_address_matches
+                     (env_cpu(env), addr, msize) & BP_MEM_READ)) {
+                    goto fault;
+                }
+                /* TODO: MTE check. */
+
+                host_fn(vd, reg_off, info.host);
             }
-        } else {
-            *(uint32_t *)(vd + H1_4(reg_off)) = 0;
-        }
+            reg_off += esize;
+        } while (reg_off & 63);
     }
+    return;
+
+ fault:
+    record_fault(env, reg_off, reg_max);
 }
 
-static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
-                                target_ulong base, uint32_t desc, uintptr_t ra,
-                                zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn,
-                                sve_ld1_nf_fn *nonfault_fn)
-{
-    const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
-    const int mmu_idx = get_mmuidx(oi);
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t reg_off, reg_max = simd_oprsz(desc);
-    target_ulong addr;
-
-    /* Skip to the first true predicate.  */
-    reg_off = find_next_active(vg, 0, reg_max, MO_64);
-    if (likely(reg_off < reg_max)) {
-        /* Perform one normal read, which will fault or not.  */
-        addr = off_fn(vm, reg_off);
-        addr = base + (addr << scale);
-        tlb_fn(env, vd, reg_off, addr, ra);
-
-        /* The rest of the reads will be non-faulting.  */
-    }
-
-    /* After any fault, zero the leading predicated false elements.  */
-    swap_memzero(vd, reg_off);
-
-    while (likely((reg_off += 8) < reg_max)) {
-        uint8_t pg = *(uint8_t *)(vg + H1(reg_off >> 3));
-        if (likely(pg & 1)) {
-            addr = off_fn(vm, reg_off);
-            addr = base + (addr << scale);
-            if (!nonfault_fn(env, vd, reg_off, addr, mmu_idx)) {
-                record_fault(env, reg_off, reg_max);
-                break;
-            }
-        } else {
-            *(uint64_t *)(vd + reg_off) = 0;
-        }
-    }
+#define DO_LDFF1_ZPZ_S(MEM, OFS, MSZ) \
+void HELPER(sve_ldff##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                   void *vm, target_ulong base, uint32_t desc) \
+{                                                                              \
+    sve_ldff1_z(env, vd, vg, vm, base, desc, GETPC(), MO_32, MSZ,              \
+                off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb);       \
 }
 
-#define DO_LDFF1_ZPZ_S(MEM, OFS) \
-void HELPER(sve_ldff##MEM##_##OFS)                                      \
-    (CPUARMState *env, void *vd, void *vg, void *vm,                    \
-     target_ulong base, uint32_t desc)                                  \
-{                                                                       \
-    sve_ldff1_zs(env, vd, vg, vm, base, desc, GETPC(),                  \
-                 off_##OFS##_s, sve_ld1##MEM##_tlb, sve_ld##MEM##_nf);  \
+#define DO_LDFF1_ZPZ_D(MEM, OFS, MSZ) \
+void HELPER(sve_ldff##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                   void *vm, target_ulong base, uint32_t desc) \
+{                                                                              \
+    sve_ldff1_z(env, vd, vg, vm, base, desc, GETPC(), MO_64, MSZ,              \
+                off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb);       \
 }
 
-#define DO_LDFF1_ZPZ_D(MEM, OFS) \
-void HELPER(sve_ldff##MEM##_##OFS)                                      \
-    (CPUARMState *env, void *vd, void *vg, void *vm,                    \
-     target_ulong base, uint32_t desc)                                  \
-{                                                                       \
-    sve_ldff1_zd(env, vd, vg, vm, base, desc, GETPC(),                  \
-                 off_##OFS##_d, sve_ld1##MEM##_tlb, sve_ld##MEM##_nf);  \
-}
+DO_LDFF1_ZPZ_S(bsu, zsu, MO_8)
+DO_LDFF1_ZPZ_S(bsu, zss, MO_8)
+DO_LDFF1_ZPZ_D(bdu, zsu, MO_8)
+DO_LDFF1_ZPZ_D(bdu, zss, MO_8)
+DO_LDFF1_ZPZ_D(bdu, zd, MO_8)
 
-DO_LDFF1_ZPZ_S(bsu, zsu)
-DO_LDFF1_ZPZ_S(bsu, zss)
-DO_LDFF1_ZPZ_D(bdu, zsu)
-DO_LDFF1_ZPZ_D(bdu, zss)
-DO_LDFF1_ZPZ_D(bdu, zd)
+DO_LDFF1_ZPZ_S(bss, zsu, MO_8)
+DO_LDFF1_ZPZ_S(bss, zss, MO_8)
+DO_LDFF1_ZPZ_D(bds, zsu, MO_8)
+DO_LDFF1_ZPZ_D(bds, zss, MO_8)
+DO_LDFF1_ZPZ_D(bds, zd, MO_8)
 
-DO_LDFF1_ZPZ_S(bss, zsu)
-DO_LDFF1_ZPZ_S(bss, zss)
-DO_LDFF1_ZPZ_D(bds, zsu)
-DO_LDFF1_ZPZ_D(bds, zss)
-DO_LDFF1_ZPZ_D(bds, zd)
+DO_LDFF1_ZPZ_S(hsu_le, zsu, MO_16)
+DO_LDFF1_ZPZ_S(hsu_le, zss, MO_16)
+DO_LDFF1_ZPZ_D(hdu_le, zsu, MO_16)
+DO_LDFF1_ZPZ_D(hdu_le, zss, MO_16)
+DO_LDFF1_ZPZ_D(hdu_le, zd, MO_16)
 
-DO_LDFF1_ZPZ_S(hsu_le, zsu)
-DO_LDFF1_ZPZ_S(hsu_le, zss)
-DO_LDFF1_ZPZ_D(hdu_le, zsu)
-DO_LDFF1_ZPZ_D(hdu_le, zss)
-DO_LDFF1_ZPZ_D(hdu_le, zd)
+DO_LDFF1_ZPZ_S(hsu_be, zsu, MO_16)
+DO_LDFF1_ZPZ_S(hsu_be, zss, MO_16)
+DO_LDFF1_ZPZ_D(hdu_be, zsu, MO_16)
+DO_LDFF1_ZPZ_D(hdu_be, zss, MO_16)
+DO_LDFF1_ZPZ_D(hdu_be, zd, MO_16)
 
-DO_LDFF1_ZPZ_S(hsu_be, zsu)
-DO_LDFF1_ZPZ_S(hsu_be, zss)
-DO_LDFF1_ZPZ_D(hdu_be, zsu)
-DO_LDFF1_ZPZ_D(hdu_be, zss)
-DO_LDFF1_ZPZ_D(hdu_be, zd)
+DO_LDFF1_ZPZ_S(hss_le, zsu, MO_16)
+DO_LDFF1_ZPZ_S(hss_le, zss, MO_16)
+DO_LDFF1_ZPZ_D(hds_le, zsu, MO_16)
+DO_LDFF1_ZPZ_D(hds_le, zss, MO_16)
+DO_LDFF1_ZPZ_D(hds_le, zd, MO_16)
 
-DO_LDFF1_ZPZ_S(hss_le, zsu)
-DO_LDFF1_ZPZ_S(hss_le, zss)
-DO_LDFF1_ZPZ_D(hds_le, zsu)
-DO_LDFF1_ZPZ_D(hds_le, zss)
-DO_LDFF1_ZPZ_D(hds_le, zd)
+DO_LDFF1_ZPZ_S(hss_be, zsu, MO_16)
+DO_LDFF1_ZPZ_S(hss_be, zss, MO_16)
+DO_LDFF1_ZPZ_D(hds_be, zsu, MO_16)
+DO_LDFF1_ZPZ_D(hds_be, zss, MO_16)
+DO_LDFF1_ZPZ_D(hds_be, zd, MO_16)
 
-DO_LDFF1_ZPZ_S(hss_be, zsu)
-DO_LDFF1_ZPZ_S(hss_be, zss)
-DO_LDFF1_ZPZ_D(hds_be, zsu)
-DO_LDFF1_ZPZ_D(hds_be, zss)
-DO_LDFF1_ZPZ_D(hds_be, zd)
+DO_LDFF1_ZPZ_S(ss_le,  zsu, MO_32)
+DO_LDFF1_ZPZ_S(ss_le,  zss, MO_32)
+DO_LDFF1_ZPZ_D(sdu_le, zsu, MO_32)
+DO_LDFF1_ZPZ_D(sdu_le, zss, MO_32)
+DO_LDFF1_ZPZ_D(sdu_le, zd, MO_32)
 
-DO_LDFF1_ZPZ_S(ss_le,  zsu)
-DO_LDFF1_ZPZ_S(ss_le,  zss)
-DO_LDFF1_ZPZ_D(sdu_le, zsu)
-DO_LDFF1_ZPZ_D(sdu_le, zss)
-DO_LDFF1_ZPZ_D(sdu_le, zd)
+DO_LDFF1_ZPZ_S(ss_be,  zsu, MO_32)
+DO_LDFF1_ZPZ_S(ss_be,  zss, MO_32)
+DO_LDFF1_ZPZ_D(sdu_be, zsu, MO_32)
+DO_LDFF1_ZPZ_D(sdu_be, zss, MO_32)
+DO_LDFF1_ZPZ_D(sdu_be, zd, MO_32)
 
-DO_LDFF1_ZPZ_S(ss_be,  zsu)
-DO_LDFF1_ZPZ_S(ss_be,  zss)
-DO_LDFF1_ZPZ_D(sdu_be, zsu)
-DO_LDFF1_ZPZ_D(sdu_be, zss)
-DO_LDFF1_ZPZ_D(sdu_be, zd)
+DO_LDFF1_ZPZ_D(sds_le, zsu, MO_32)
+DO_LDFF1_ZPZ_D(sds_le, zss, MO_32)
+DO_LDFF1_ZPZ_D(sds_le, zd, MO_32)
 
-DO_LDFF1_ZPZ_D(sds_le, zsu)
-DO_LDFF1_ZPZ_D(sds_le, zss)
-DO_LDFF1_ZPZ_D(sds_le, zd)
+DO_LDFF1_ZPZ_D(sds_be, zsu, MO_32)
+DO_LDFF1_ZPZ_D(sds_be, zss, MO_32)
+DO_LDFF1_ZPZ_D(sds_be, zd, MO_32)
 
-DO_LDFF1_ZPZ_D(sds_be, zsu)
-DO_LDFF1_ZPZ_D(sds_be, zss)
-DO_LDFF1_ZPZ_D(sds_be, zd)
+DO_LDFF1_ZPZ_D(dd_le, zsu, MO_64)
+DO_LDFF1_ZPZ_D(dd_le, zss, MO_64)
+DO_LDFF1_ZPZ_D(dd_le, zd, MO_64)
 
-DO_LDFF1_ZPZ_D(dd_le, zsu)
-DO_LDFF1_ZPZ_D(dd_le, zss)
-DO_LDFF1_ZPZ_D(dd_le, zd)
-
-DO_LDFF1_ZPZ_D(dd_be, zsu)
-DO_LDFF1_ZPZ_D(dd_be, zss)
-DO_LDFF1_ZPZ_D(dd_be, zd)
+DO_LDFF1_ZPZ_D(dd_be, zsu, MO_64)
+DO_LDFF1_ZPZ_D(dd_be, zss, MO_64)
+DO_LDFF1_ZPZ_D(dd_be, zd, MO_64)
 
 /* Stores with a vector index.  */
 
-- 
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: 20200508154359.7494-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 182 ++++++++++++++++++++++++----------------
 1 file changed, 111 insertions(+), 71 deletions(-)

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_LDFF1_ZPZ_D(dd_be, zd, MO_64)
 
 /* Stores with a vector index.  */
 
-static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
-                       target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
+static inline QEMU_ALWAYS_INLINE
+void sve_st1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
+               target_ulong base, uint32_t desc, uintptr_t retaddr,
+               int esize, int msize, zreg_off_fn *off_fn,
+               sve_ldst1_host_fn *host_fn,
+               sve_ldst1_tlb_fn *tlb_fn)
 {
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t i, oprsz = simd_oprsz(desc);
+    const int mmu_idx = cpu_mmu_index(env, false);
+    const intptr_t reg_max = simd_oprsz(desc);
+    void *host[ARM_MAX_VQ * 4];
+    intptr_t reg_off, i;
+    SVEHostPage info, info2;
 
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
+    /*
+     * Probe all of the elements for host addresses and flags.
+     */
+    i = reg_off = 0;
+    do {
+        uint64_t pg = vg[reg_off >> 6];
         do {
-            if (likely(pg & 1)) {
-                target_ulong off = off_fn(vm, i);
-                tlb_fn(env, vd, i, base + (off << scale), ra);
+            target_ulong addr = base + (off_fn(vm, reg_off) << scale);
+            target_ulong in_page = -(addr | TARGET_PAGE_MASK);
+
+            host[i] = NULL;
+            if (likely((pg >> (reg_off & 63)) & 1)) {
+                if (likely(in_page >= msize)) {
+                    sve_probe_page(&info, false, env, addr, 0, MMU_DATA_STORE,
+                                   mmu_idx, retaddr);
+                    host[i] = info.host;
+                } else {
+                    /*
+                     * Element crosses the page boundary.
+                     * Probe both pages, but do not record the host address,
+                     * so that we use the slow path.
+                     */
+                    sve_probe_page(&info, false, env, addr, 0,
+                                   MMU_DATA_STORE, mmu_idx, retaddr);
+                    sve_probe_page(&info2, false, env, addr + in_page, 0,
+                                   MMU_DATA_STORE, mmu_idx, retaddr);
+                    info.flags |= info2.flags;
+                }
+
+                if (unlikely(info.flags & TLB_WATCHPOINT)) {
+                    cpu_check_watchpoint(env_cpu(env), addr, msize,
+                                         info.attrs, BP_MEM_WRITE, retaddr);
+                }
+                /* TODO: MTE check. */
             }
-            i += 4, pg >>= 4;
-        } while (i & 15);
-    }
-}
+            i += 1;
+            reg_off += esize;
+        } while (reg_off & 63);
+    } while (reg_off < reg_max);
 
-static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
-                       target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
-{
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t i, oprsz = simd_oprsz(desc) / 8;
-
-    for (i = 0; i < oprsz; i++) {
-        uint8_t pg = *(uint8_t *)(vg + H1(i));
-        if (likely(pg & 1)) {
-            target_ulong off = off_fn(vm, i * 8);
-            tlb_fn(env, vd, i * 8, base + (off << scale), ra);
+    /*
+     * Now that we have recognized all exceptions except SyncExternal
+     * (from TLB_MMIO), which we cannot avoid, perform all of the stores.
+     *
+     * Note for the common case of an element in RAM, not crossing a page
+     * boundary, we have stored the host address in host[].  This doubles
+     * as a first-level check against the predicate, since only enabled
+     * elements have non-null host addresses.
+     */
+    i = reg_off = 0;
+    do {
+        void *h = host[i];
+        if (likely(h != NULL)) {
+            host_fn(vd, reg_off, h);
+        } else if ((vg[reg_off >> 6] >> (reg_off & 63)) & 1) {
+            target_ulong addr = base + (off_fn(vm, reg_off) << scale);
+            tlb_fn(env, vd, reg_off, addr, retaddr);
         }
-    }
+        i += 1;
+        reg_off += esize;
+    } while (reg_off < reg_max);
 }
 
-#define DO_ST1_ZPZ_S(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_st##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_st1_zs(env, vd, vg, vm, base, desc, GETPC(),         \
-              off_##OFS##_s, sve_st1##MEM##_tlb);            \
+#define DO_ST1_ZPZ_S(MEM, OFS, MSZ) \
+void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 4, 1 << MSZ,             \
+              off_##OFS##_s, sve_st1##MEM##_host, sve_st1##MEM##_tlb);       \
 }
 
-#define DO_ST1_ZPZ_D(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_st##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_st1_zd(env, vd, vg, vm, base, desc, GETPC(),         \
-               off_##OFS##_d, sve_st1##MEM##_tlb);           \
+#define DO_ST1_ZPZ_D(MEM, OFS, MSZ) \
+void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 8, 1 << MSZ,             \
+              off_##OFS##_d, sve_st1##MEM##_host, sve_st1##MEM##_tlb);       \
 }
 
-DO_ST1_ZPZ_S(bs, zsu)
-DO_ST1_ZPZ_S(hs_le, zsu)
-DO_ST1_ZPZ_S(hs_be, zsu)
-DO_ST1_ZPZ_S(ss_le, zsu)
-DO_ST1_ZPZ_S(ss_be, zsu)
+DO_ST1_ZPZ_S(bs, zsu, MO_8)
+DO_ST1_ZPZ_S(hs_le, zsu, MO_16)
+DO_ST1_ZPZ_S(hs_be, zsu, MO_16)
+DO_ST1_ZPZ_S(ss_le, zsu, MO_32)
+DO_ST1_ZPZ_S(ss_be, zsu, MO_32)
 
-DO_ST1_ZPZ_S(bs, zss)
-DO_ST1_ZPZ_S(hs_le, zss)
-DO_ST1_ZPZ_S(hs_be, zss)
-DO_ST1_ZPZ_S(ss_le, zss)
-DO_ST1_ZPZ_S(ss_be, zss)
+DO_ST1_ZPZ_S(bs, zss, MO_8)
+DO_ST1_ZPZ_S(hs_le, zss, MO_16)
+DO_ST1_ZPZ_S(hs_be, zss, MO_16)
+DO_ST1_ZPZ_S(ss_le, zss, MO_32)
+DO_ST1_ZPZ_S(ss_be, zss, MO_32)
 
-DO_ST1_ZPZ_D(bd, zsu)
-DO_ST1_ZPZ_D(hd_le, zsu)
-DO_ST1_ZPZ_D(hd_be, zsu)
-DO_ST1_ZPZ_D(sd_le, zsu)
-DO_ST1_ZPZ_D(sd_be, zsu)
-DO_ST1_ZPZ_D(dd_le, zsu)
-DO_ST1_ZPZ_D(dd_be, zsu)
+DO_ST1_ZPZ_D(bd, zsu, MO_8)
+DO_ST1_ZPZ_D(hd_le, zsu, MO_16)
+DO_ST1_ZPZ_D(hd_be, zsu, MO_16)
+DO_ST1_ZPZ_D(sd_le, zsu, MO_32)
+DO_ST1_ZPZ_D(sd_be, zsu, MO_32)
+DO_ST1_ZPZ_D(dd_le, zsu, MO_64)
+DO_ST1_ZPZ_D(dd_be, zsu, MO_64)
 
-DO_ST1_ZPZ_D(bd, zss)
-DO_ST1_ZPZ_D(hd_le, zss)
-DO_ST1_ZPZ_D(hd_be, zss)
-DO_ST1_ZPZ_D(sd_le, zss)
-DO_ST1_ZPZ_D(sd_be, zss)
-DO_ST1_ZPZ_D(dd_le, zss)
-DO_ST1_ZPZ_D(dd_be, zss)
+DO_ST1_ZPZ_D(bd, zss, MO_8)
+DO_ST1_ZPZ_D(hd_le, zss, MO_16)
+DO_ST1_ZPZ_D(hd_be, zss, MO_16)
+DO_ST1_ZPZ_D(sd_le, zss, MO_32)
+DO_ST1_ZPZ_D(sd_be, zss, MO_32)
+DO_ST1_ZPZ_D(dd_le, zss, MO_64)
+DO_ST1_ZPZ_D(dd_be, zss, MO_64)
 
-DO_ST1_ZPZ_D(bd, zd)
-DO_ST1_ZPZ_D(hd_le, zd)
-DO_ST1_ZPZ_D(hd_be, zd)
-DO_ST1_ZPZ_D(sd_le, zd)
-DO_ST1_ZPZ_D(sd_be, zd)
-DO_ST1_ZPZ_D(dd_le, zd)
-DO_ST1_ZPZ_D(dd_be, zd)
+DO_ST1_ZPZ_D(bd, zd, MO_8)
+DO_ST1_ZPZ_D(hd_le, zd, MO_16)
+DO_ST1_ZPZ_D(hd_be, zd, MO_16)
+DO_ST1_ZPZ_D(sd_le, zd, MO_32)
+DO_ST1_ZPZ_D(sd_be, zd, MO_32)
+DO_ST1_ZPZ_D(dd_le, zd, MO_64)
+DO_ST1_ZPZ_D(dd_be, zd, MO_64)
 
 #undef DO_ST1_ZPZ_S
 #undef DO_ST1_ZPZ_D
-- 
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: 20200508154359.7494-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/sve_helper.c | 208 +++++++++++++++++++++-------------------
 1 file changed, 109 insertions(+), 99 deletions(-)

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 @@ static target_ulong off_zd_d(void *reg, intptr_t reg_ofs)
     return *(uint64_t *)(reg + reg_ofs);
 }
 
-static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
-                       target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
+static inline QEMU_ALWAYS_INLINE
+void sve_ld1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
+               target_ulong base, uint32_t desc, uintptr_t retaddr,
+               int esize, int msize, zreg_off_fn *off_fn,
+               sve_ldst1_host_fn *host_fn,
+               sve_ldst1_tlb_fn *tlb_fn)
 {
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t i, oprsz = simd_oprsz(desc);
-    ARMVectorReg scratch = { };
+    const int mmu_idx = cpu_mmu_index(env, false);
+    const intptr_t reg_max = simd_oprsz(desc);
+    ARMVectorReg scratch;
+    intptr_t reg_off;
+    SVEHostPage info, info2;
 
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
+    memset(&scratch, 0, reg_max);
+    reg_off = 0;
+    do {
+        uint64_t pg = vg[reg_off >> 6];
         do {
             if (likely(pg & 1)) {
-                target_ulong off = off_fn(vm, i);
-                tlb_fn(env, &scratch, i, base + (off << scale), ra);
+                target_ulong addr = base + (off_fn(vm, reg_off) << scale);
+                target_ulong in_page = -(addr | TARGET_PAGE_MASK);
+
+                sve_probe_page(&info, false, env, addr, 0, MMU_DATA_LOAD,
+                               mmu_idx, retaddr);
+
+                if (likely(in_page >= msize)) {
+                    if (unlikely(info.flags & TLB_WATCHPOINT)) {
+                        cpu_check_watchpoint(env_cpu(env), addr, msize,
+                                             info.attrs, BP_MEM_READ, retaddr);
+                    }
+                    /* TODO: MTE check */
+                    host_fn(&scratch, reg_off, info.host);
+                } else {
+                    /* Element crosses the page boundary. */
+                    sve_probe_page(&info2, false, env, addr + in_page, 0,
+                                   MMU_DATA_LOAD, mmu_idx, retaddr);
+                    if (unlikely((info.flags | info2.flags) & TLB_WATCHPOINT)) {
+                        cpu_check_watchpoint(env_cpu(env), addr,
+                                             msize, info.attrs,
+                                             BP_MEM_READ, retaddr);
+                    }
+                    /* TODO: MTE check */
+                    tlb_fn(env, &scratch, reg_off, addr, retaddr);
+                }
             }
-            i += 4, pg >>= 4;
-        } while (i & 15);
-    }
+            reg_off += esize;
+            pg >>= esize;
+        } while (reg_off & 63);
+    } while (reg_off < reg_max);
 
     /* Wait until all exceptions have been raised to write back.  */
-    memcpy(vd, &scratch, oprsz);
+    memcpy(vd, &scratch, reg_max);
 }
 
-static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
-                       target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
-{
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t i, oprsz = simd_oprsz(desc) / 8;
-    ARMVectorReg scratch = { };
-
-    for (i = 0; i < oprsz; i++) {
-        uint8_t pg = *(uint8_t *)(vg + H1(i));
-        if (likely(pg & 1)) {
-            target_ulong off = off_fn(vm, i * 8);
-            tlb_fn(env, &scratch, i * 8, base + (off << scale), ra);
-        }
-    }
-
-    /* Wait until all exceptions have been raised to write back.  */
-    memcpy(vd, &scratch, oprsz * 8);
+#define DO_LD1_ZPZ_S(MEM, OFS, MSZ) \
+void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 4, 1 << MSZ,             \
+              off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb);       \
 }
 
-#define DO_LD1_ZPZ_S(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_ld##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_ld1_zs(env, vd, vg, vm, base, desc, GETPC(),         \
-              off_##OFS##_s, sve_ld1##MEM##_tlb);            \
+#define DO_LD1_ZPZ_D(MEM, OFS, MSZ) \
+void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 8, 1 << MSZ,             \
+              off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb);       \
 }
 
-#define DO_LD1_ZPZ_D(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_ld##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_ld1_zd(env, vd, vg, vm, base, desc, GETPC(),         \
-               off_##OFS##_d, sve_ld1##MEM##_tlb);           \
-}
+DO_LD1_ZPZ_S(bsu, zsu, MO_8)
+DO_LD1_ZPZ_S(bsu, zss, MO_8)
+DO_LD1_ZPZ_D(bdu, zsu, MO_8)
+DO_LD1_ZPZ_D(bdu, zss, MO_8)
+DO_LD1_ZPZ_D(bdu, zd, MO_8)
 
-DO_LD1_ZPZ_S(bsu, zsu)
-DO_LD1_ZPZ_S(bsu, zss)
-DO_LD1_ZPZ_D(bdu, zsu)
-DO_LD1_ZPZ_D(bdu, zss)
-DO_LD1_ZPZ_D(bdu, zd)
+DO_LD1_ZPZ_S(bss, zsu, MO_8)
+DO_LD1_ZPZ_S(bss, zss, MO_8)
+DO_LD1_ZPZ_D(bds, zsu, MO_8)
+DO_LD1_ZPZ_D(bds, zss, MO_8)
+DO_LD1_ZPZ_D(bds, zd, MO_8)
 
-DO_LD1_ZPZ_S(bss, zsu)
-DO_LD1_ZPZ_S(bss, zss)
-DO_LD1_ZPZ_D(bds, zsu)
-DO_LD1_ZPZ_D(bds, zss)
-DO_LD1_ZPZ_D(bds, zd)
+DO_LD1_ZPZ_S(hsu_le, zsu, MO_16)
+DO_LD1_ZPZ_S(hsu_le, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_le, zsu, MO_16)
+DO_LD1_ZPZ_D(hdu_le, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_le, zd, MO_16)
 
-DO_LD1_ZPZ_S(hsu_le, zsu)
-DO_LD1_ZPZ_S(hsu_le, zss)
-DO_LD1_ZPZ_D(hdu_le, zsu)
-DO_LD1_ZPZ_D(hdu_le, zss)
-DO_LD1_ZPZ_D(hdu_le, zd)
+DO_LD1_ZPZ_S(hsu_be, zsu, MO_16)
+DO_LD1_ZPZ_S(hsu_be, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_be, zsu, MO_16)
+DO_LD1_ZPZ_D(hdu_be, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_be, zd, MO_16)
 
-DO_LD1_ZPZ_S(hsu_be, zsu)
-DO_LD1_ZPZ_S(hsu_be, zss)
-DO_LD1_ZPZ_D(hdu_be, zsu)
-DO_LD1_ZPZ_D(hdu_be, zss)
-DO_LD1_ZPZ_D(hdu_be, zd)
+DO_LD1_ZPZ_S(hss_le, zsu, MO_16)
+DO_LD1_ZPZ_S(hss_le, zss, MO_16)
+DO_LD1_ZPZ_D(hds_le, zsu, MO_16)
+DO_LD1_ZPZ_D(hds_le, zss, MO_16)
+DO_LD1_ZPZ_D(hds_le, zd, MO_16)
 
-DO_LD1_ZPZ_S(hss_le, zsu)
-DO_LD1_ZPZ_S(hss_le, zss)
-DO_LD1_ZPZ_D(hds_le, zsu)
-DO_LD1_ZPZ_D(hds_le, zss)
-DO_LD1_ZPZ_D(hds_le, zd)
+DO_LD1_ZPZ_S(hss_be, zsu, MO_16)
+DO_LD1_ZPZ_S(hss_be, zss, MO_16)
+DO_LD1_ZPZ_D(hds_be, zsu, MO_16)
+DO_LD1_ZPZ_D(hds_be, zss, MO_16)
+DO_LD1_ZPZ_D(hds_be, zd, MO_16)
 
-DO_LD1_ZPZ_S(hss_be, zsu)
-DO_LD1_ZPZ_S(hss_be, zss)
-DO_LD1_ZPZ_D(hds_be, zsu)
-DO_LD1_ZPZ_D(hds_be, zss)
-DO_LD1_ZPZ_D(hds_be, zd)
+DO_LD1_ZPZ_S(ss_le, zsu, MO_32)
+DO_LD1_ZPZ_S(ss_le, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_le, zsu, MO_32)
+DO_LD1_ZPZ_D(sdu_le, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_le, zd, MO_32)
 
-DO_LD1_ZPZ_S(ss_le, zsu)
-DO_LD1_ZPZ_S(ss_le, zss)
-DO_LD1_ZPZ_D(sdu_le, zsu)
-DO_LD1_ZPZ_D(sdu_le, zss)
-DO_LD1_ZPZ_D(sdu_le, zd)
+DO_LD1_ZPZ_S(ss_be, zsu, MO_32)
+DO_LD1_ZPZ_S(ss_be, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_be, zsu, MO_32)
+DO_LD1_ZPZ_D(sdu_be, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_be, zd, MO_32)
 
-DO_LD1_ZPZ_S(ss_be, zsu)
-DO_LD1_ZPZ_S(ss_be, zss)
-DO_LD1_ZPZ_D(sdu_be, zsu)
-DO_LD1_ZPZ_D(sdu_be, zss)
-DO_LD1_ZPZ_D(sdu_be, zd)
+DO_LD1_ZPZ_D(sds_le, zsu, MO_32)
+DO_LD1_ZPZ_D(sds_le, zss, MO_32)
+DO_LD1_ZPZ_D(sds_le, zd, MO_32)
 
-DO_LD1_ZPZ_D(sds_le, zsu)
-DO_LD1_ZPZ_D(sds_le, zss)
-DO_LD1_ZPZ_D(sds_le, zd)
+DO_LD1_ZPZ_D(sds_be, zsu, MO_32)
+DO_LD1_ZPZ_D(sds_be, zss, MO_32)
+DO_LD1_ZPZ_D(sds_be, zd, MO_32)
 
-DO_LD1_ZPZ_D(sds_be, zsu)
-DO_LD1_ZPZ_D(sds_be, zss)
-DO_LD1_ZPZ_D(sds_be, zd)
+DO_LD1_ZPZ_D(dd_le, zsu, MO_64)
+DO_LD1_ZPZ_D(dd_le, zss, MO_64)
+DO_LD1_ZPZ_D(dd_le, zd, MO_64)
 
-DO_LD1_ZPZ_D(dd_le, zsu)
-DO_LD1_ZPZ_D(dd_le, zss)
-DO_LD1_ZPZ_D(dd_le, zd)
-
-DO_LD1_ZPZ_D(dd_be, zsu)
-DO_LD1_ZPZ_D(dd_be, zss)
-DO_LD1_ZPZ_D(dd_be, zd)
+DO_LD1_ZPZ_D(dd_be, zsu, MO_64)
+DO_LD1_ZPZ_D(dd_be, zss, MO_64)
+DO_LD1_ZPZ_D(dd_be, zd, MO_64)
 
 #undef DO_LD1_ZPZ_S
 #undef DO_LD1_ZPZ_D
-- 
2.20.1

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

None of the sve helpers use TCGMemOpIdx any longer, so we can
stop passing it.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200508154359.7494-20-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/internals.h     |  5 -----
 target/arm/sve_helper.c    | 14 +++++++-------
 target/arm/translate-sve.c | 17 +++--------------
 3 files changed, 10 insertions(+), 26 deletions(-)

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 @@ static inline int arm_num_ctx_cmps(ARMCPU *cpu)
     }
 }
 
-/* Note make_memop_idx reserves 4 bits for mmu_idx, and MO_BSWAP is bit 3.
- * Thus a TCGMemOpIdx, without any MO_ALIGN bits, fits in 8 bits.
- */
-#define MEMOPIDX_SHIFT  8
-
 /**
  * v7m_using_psp: Return true if using process stack pointer
  * Return true if the CPU is currently using the process stack
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 sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
                sve_ldst1_host_fn *host_fn,
                sve_ldst1_tlb_fn *tlb_fn)
 {
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
+    const unsigned rd = simd_data(desc);
     const intptr_t reg_max = simd_oprsz(desc);
     intptr_t reg_off, reg_last, mem_off;
     SVEContLdSt info;
@@ -XXX,XX +XXX,XX @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr,
                    sve_ldst1_host_fn *host_fn,
                    sve_ldst1_tlb_fn *tlb_fn)
 {
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
+    const unsigned rd = simd_data(desc);
     void *vd = &env->vfp.zregs[rd];
     const intptr_t reg_max = simd_oprsz(desc);
     intptr_t reg_off, mem_off, reg_last;
@@ -XXX,XX +XXX,XX @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, uint32_t desc,
                sve_ldst1_host_fn *host_fn,
                sve_ldst1_tlb_fn *tlb_fn)
 {
-    const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
+    const unsigned rd = simd_data(desc);
     const intptr_t reg_max = simd_oprsz(desc);
     intptr_t reg_off, reg_last, mem_off;
     SVEContLdSt info;
@@ -XXX,XX +XXX,XX @@ void sve_ld1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
                sve_ldst1_host_fn *host_fn,
                sve_ldst1_tlb_fn *tlb_fn)
 {
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     const int mmu_idx = cpu_mmu_index(env, false);
     const intptr_t reg_max = simd_oprsz(desc);
+    const int scale = simd_data(desc);
     ARMVectorReg scratch;
     intptr_t reg_off;
     SVEHostPage info, info2;
@@ -XXX,XX +XXX,XX @@ void sve_ldff1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
                  sve_ldst1_tlb_fn *tlb_fn)
 {
     const int mmu_idx = cpu_mmu_index(env, false);
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
+    const intptr_t reg_max = simd_oprsz(desc);
+    const int scale = simd_data(desc);
     const int esize = 1 << esz;
     const int msize = 1 << msz;
-    const intptr_t reg_max = simd_oprsz(desc);
     intptr_t reg_off;
     SVEHostPage info;
     target_ulong addr, in_page;
@@ -XXX,XX +XXX,XX @@ void sve_st1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
                sve_ldst1_host_fn *host_fn,
                sve_ldst1_tlb_fn *tlb_fn)
 {
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
     const int mmu_idx = cpu_mmu_index(env, false);
     const intptr_t reg_max = simd_oprsz(desc);
+    const int scale = simd_data(desc);
     void *host[ARM_MAX_VQ * 4];
     intptr_t reg_off, i;
     SVEHostPage info, info2;
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 const uint8_t dtype_esz[16] = {
     3, 2, 1, 3
 };
 
-static TCGMemOpIdx sve_memopidx(DisasContext *s, int dtype)
-{
-    return make_memop_idx(s->be_data | dtype_mop[dtype], get_mem_index(s));
-}
-
 static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
                        int dtype, gen_helper_gvec_mem *fn)
 {
@@ -XXX,XX +XXX,XX @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
      * registers as pointers, so encode the regno into the data field.
      * For consistency, do this even for LD1.
      */
-    desc = sve_memopidx(s, dtype);
-    desc |= zt << MEMOPIDX_SHIFT;
-    desc = simd_desc(vsz, vsz, desc);
+    desc = simd_desc(vsz, vsz, zt);
     t_desc = tcg_const_i32(desc);
     t_pg = tcg_temp_new_ptr();
 
@@ -XXX,XX +XXX,XX @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz)
     int desc, poff;
 
     /* Load the first quadword using the normal predicated load helpers.  */
-    desc = sve_memopidx(s, msz_dtype(s, msz));
-    desc |= zt << MEMOPIDX_SHIFT;
-    desc = simd_desc(16, 16, desc);
+    desc = simd_desc(16, 16, zt);
     t_desc = tcg_const_i32(desc);
 
     poff = pred_full_reg_offset(s, pg);
@@ -XXX,XX +XXX,XX @@ static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm,
     TCGv_i32 t_desc;
     int desc;
 
-    desc = sve_memopidx(s, msz_dtype(s, msz));
-    desc |= scale << MEMOPIDX_SHIFT;
-    desc = simd_desc(vsz, vsz, desc);
+    desc = simd_desc(vsz, vsz, scale);
     t_desc = tcg_const_i32(desc);
 
     tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg));
-- 
2.20.1

From: Philippe Mathieu-Daudé <philmd@redhat.com>

We want to move the inlined declarations of set_feature()
from cpu*.c to cpu.h. To avoid clashing with the KVM
declarations, inline the few KVM calls.

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200504172448.9402-2-philmd@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/kvm32.c | 13 ++++---------
 target/arm/kvm64.c | 22 ++++++----------------
 2 files changed, 10 insertions(+), 25 deletions(-)

diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/kvm32.c
+++ b/target/arm/kvm32.c
@@ -XXX,XX +XXX,XX @@
 #include "internals.h"
 #include "qemu/log.h"
 
-static inline void set_feature(uint64_t *features, int feature)
-{
-    *features |= 1ULL << feature;
-}
-
 static int read_sys_reg32(int fd, uint32_t *pret, uint64_t id)
 {
     struct kvm_one_reg idreg = { .id = id, .addr = (uintptr_t)pret };
@@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
      * timers; this in turn implies most of the other feature
      * bits, but a few must be tested.
      */
-    set_feature(&features, ARM_FEATURE_V7VE);
-    set_feature(&features, ARM_FEATURE_GENERIC_TIMER);
+    features |= 1ULL << ARM_FEATURE_V7VE;
+    features |= 1ULL << ARM_FEATURE_GENERIC_TIMER;
 
     if (extract32(id_pfr0, 12, 4) == 1) {
-        set_feature(&features, ARM_FEATURE_THUMB2EE);
+        features |= 1ULL << ARM_FEATURE_THUMB2EE;
     }
     if (extract32(ahcf->isar.mvfr1, 12, 4) == 1) {
-        set_feature(&features, ARM_FEATURE_NEON);
+        features |= 1ULL << ARM_FEATURE_NEON;
     }
 
     ahcf->features = features;
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 @@ void kvm_arm_pmu_set_irq(CPUState *cs, int irq)
     }
 }
 
-static inline void set_feature(uint64_t *features, int feature)
-{
-    *features |= 1ULL << feature;
-}
-
-static inline void unset_feature(uint64_t *features, int feature)
-{
-    *features &= ~(1ULL << feature);
-}
-
 static int read_sys_reg32(int fd, uint32_t *pret, uint64_t id)
 {
     uint64_t ret;
@@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
      * with VFPv4+Neon; this in turn implies most of the other
      * feature bits.
      */
-    set_feature(&features, ARM_FEATURE_V8);
-    set_feature(&features, ARM_FEATURE_NEON);
-    set_feature(&features, ARM_FEATURE_AARCH64);
-    set_feature(&features, ARM_FEATURE_PMU);
-    set_feature(&features, ARM_FEATURE_GENERIC_TIMER);
+    features |= 1ULL << ARM_FEATURE_V8;
+    features |= 1ULL << ARM_FEATURE_NEON;
+    features |= 1ULL << ARM_FEATURE_AARCH64;
+    features |= 1ULL << ARM_FEATURE_PMU;
+    features |= 1ULL << ARM_FEATURE_GENERIC_TIMER;
 
     ahcf->features = features;
 
@@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs)
     if (cpu->has_pmu) {
         cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PMU_V3;
     } else {
-        unset_feature(&env->features, ARM_FEATURE_PMU);
+        env->features &= ~(1ULL << ARM_FEATURE_PMU);
     }
     if (cpu_isar_feature(aa64_sve, cpu)) {
         assert(kvm_arm_sve_supported(cs));
-- 
2.20.1

From: Thomas Huth <thuth@redhat.com>

Move the common set_feature() and unset_feature() functions
from cpu.c and cpu64.c to cpu.h.

Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200504172448.9402-3-philmd@redhat.com
Message-ID: <20190921150420.30743-2-thuth@redhat.com>
[PMD: Split Thomas's patch in two: set_feature, cpu_register]
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h   | 10 ++++++++++
 target/arm/cpu.c   | 10 ----------
 target/arm/cpu64.c | 10 ----------
 3 files changed, 10 insertions(+), 20 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 @@ typedef struct CPUARMState {
     void *gicv3state;
 } CPUARMState;
 
+static inline void set_feature(CPUARMState *env, int feature)
+{
+    env->features |= 1ULL << feature;
+}
+
+static inline void unset_feature(CPUARMState *env, int feature)
+{
+    env->features &= ~(1ULL << feature);
+}
+
 /**
  * ARMELChangeHookFn:
  * type of a function which can be registered via arm_register_el_change_hook()
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 bool arm_cpu_virtio_is_big_endian(CPUState *cs)
 
 #endif
 
-static inline void set_feature(CPUARMState *env, int feature)
-{
-    env->features |= 1ULL << feature;
-}
-
-static inline void unset_feature(CPUARMState *env, int feature)
-{
-    env->features &= ~(1ULL << feature);
-}
-
 static int
 print_insn_thumb1(bfd_vma pc, disassemble_info *info)
 {
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 @@
 #include "kvm_arm.h"
 #include "qapi/visitor.h"
 
-static inline void set_feature(CPUARMState *env, int feature)
-{
-    env->features |= 1ULL << feature;
-}
-
-static inline void unset_feature(CPUARMState *env, int feature)
-{
-    env->features &= ~(1ULL << feature);
-}
-
 #ifndef CONFIG_USER_ONLY
 static uint64_t a57_a53_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
-- 
2.20.1

From: Philippe Mathieu-Daudé <philmd@redhat.com>

Use ARRAY_SIZE() to iterate over ARMCPUInfo[].

Since on the aarch64-linux-user build, arm_cpus[] is empty, add
the cpu_count variable and only iterate when it is non-zero.

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200504172448.9402-4-philmd@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.c   | 16 +++++++++-------
 target/arm/cpu64.c |  8 +++-----
 2 files changed, 12 insertions(+), 12 deletions(-)

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 const ARMCPUInfo arm_cpus[] = {
     { .name = "any",         .initfn = arm_max_initfn },
 #endif
 #endif
-    { .name = NULL }
 };
 
 static Property arm_cpu_properties[] = {
@@ -XXX,XX +XXX,XX @@ static const TypeInfo idau_interface_type_info = {
 
 static void arm_cpu_register_types(void)
 {
-    const ARMCPUInfo *info = arm_cpus;
+    const size_t cpu_count = ARRAY_SIZE(arm_cpus);
 
     type_register_static(&arm_cpu_type_info);
     type_register_static(&idau_interface_type_info);
 
-    while (info->name) {
-        arm_cpu_register(info);
-        info++;
-    }
-
 #ifdef CONFIG_KVM
     type_register_static(&host_arm_cpu_type_info);
 #endif
+
+    if (cpu_count) {
+        size_t i;
+
+        for (i = 0; i < cpu_count; ++i) {
+            arm_cpu_register(&arm_cpus[i]);
+        }
+    }
 }
 
 type_init(arm_cpu_register_types)
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 const ARMCPUInfo aarch64_cpus[] = {
     { .name = "cortex-a53",         .initfn = aarch64_a53_initfn },
     { .name = "cortex-a72",         .initfn = aarch64_a72_initfn },
     { .name = "max",                .initfn = aarch64_max_initfn },
-    { .name = NULL }
 };
 
 static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp)
@@ -XXX,XX +XXX,XX @@ static const TypeInfo aarch64_cpu_type_info = {
 
 static void aarch64_cpu_register_types(void)
 {
-    const ARMCPUInfo *info = aarch64_cpus;
+    size_t i;
 
     type_register_static(&aarch64_cpu_type_info);
 
-    while (info->name) {
-        aarch64_cpu_register(info);
-        info++;
+    for (i = 0; i < ARRAY_SIZE(aarch64_cpus); ++i) {
+        aarch64_cpu_register(&aarch64_cpus[i]);
     }
 }
 
-- 
2.20.1

From: Philippe Mathieu-Daudé <philmd@redhat.com>

As IDAU is a v8M feature, restrict it to the Aarch32 CPUs.

Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200504172448.9402-5-philmd@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 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 @@ static void arm_cpu_register_types(void)
     const size_t cpu_count = ARRAY_SIZE(arm_cpus);
 
     type_register_static(&arm_cpu_type_info);
-    type_register_static(&idau_interface_type_info);
 
 #ifdef CONFIG_KVM
     type_register_static(&host_arm_cpu_type_info);
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_register_types(void)
     if (cpu_count) {
         size_t i;
 
+        type_register_static(&idau_interface_type_info);
         for (i = 0; i < cpu_count; ++i) {
             arm_cpu_register(&arm_cpus[i]);
         }
-- 
2.20.1

From: Philippe Mathieu-Daudé <philmd@redhat.com>

A KVM-only build won't be able to run TCG cpus.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200504172448.9402-6-philmd@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.c         | 634 -------------------------------------
 target/arm/cpu_tcg.c     | 664 +++++++++++++++++++++++++++++++++++++++
 target/arm/Makefile.objs |   1 +
 3 files changed, 665 insertions(+), 634 deletions(-)
 create mode 100644 target/arm/cpu_tcg.c

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 @@ bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
     return true;
 }
 
-#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
-static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
-{
-    CPUClass *cc = CPU_GET_CLASS(cs);
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
-    bool ret = false;
-
-    /*
-     * ARMv7-M interrupt masking works differently than -A or -R.
-     * There is no FIQ/IRQ distinction. Instead of I and F bits
-     * masking FIQ and IRQ interrupts, an exception is taken only
-     * if it is higher priority than the current execution priority
-     * (which depends on state like BASEPRI, FAULTMASK and the
-     * currently active exception).
-     */
-    if (interrupt_request & CPU_INTERRUPT_HARD
-        && (armv7m_nvic_can_take_pending_exception(env->nvic))) {
-        cs->exception_index = EXCP_IRQ;
-        cc->do_interrupt(cs);
-        ret = true;
-    }
-    return ret;
-}
-#endif
-
 void arm_cpu_update_virq(ARMCPU *cpu)
 {
     /*
@@ -XXX,XX +XXX,XX @@ static ObjectClass *arm_cpu_class_by_name(const char *cpu_model)
 /* CPU models. These are not needed for the AArch64 linux-user build. */
 #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
 
-static void arm926_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "arm,arm926";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN);
-    cpu->midr = 0x41069265;
-    cpu->reset_fpsid = 0x41011090;
-    cpu->ctr = 0x1dd20d2;
-    cpu->reset_sctlr = 0x00090078;
-
-    /*
-     * ARMv5 does not have the ID_ISAR registers, but we can still
-     * set the field to indicate Jazelle support within QEMU.
-     */
-    cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1);
-    /*
-     * Similarly, we need to set MVFR0 fields to enable vfp and short vector
-     * support even though ARMv5 doesn't have this register.
-     */
-    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1);
-    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSP, 1);
-    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1);
-}
-
-static void arm946_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "arm,arm946";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_PMSA);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    cpu->midr = 0x41059461;
-    cpu->ctr = 0x0f004006;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void arm1026_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "arm,arm1026";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_AUXCR);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN);
-    cpu->midr = 0x4106a262;
-    cpu->reset_fpsid = 0x410110a0;
-    cpu->ctr = 0x1dd20d2;
-    cpu->reset_sctlr = 0x00090078;
-    cpu->reset_auxcr = 1;
-
-    /*
-     * ARMv5 does not have the ID_ISAR registers, but we can still
-     * set the field to indicate Jazelle support within QEMU.
-     */
-    cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1);
-    /*
-     * Similarly, we need to set MVFR0 fields to enable vfp and short vector
-     * support even though ARMv5 doesn't have this register.
-     */
-    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1);
-    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSP, 1);
-    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1);
-
-    {
-        /* The 1026 had an IFAR at c6,c0,0,1 rather than the ARMv6 c6,c0,0,2 */
-        ARMCPRegInfo ifar = {
-            .name = "IFAR", .cp = 15, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 1,
-            .access = PL1_RW,
-            .fieldoffset = offsetof(CPUARMState, cp15.ifar_ns),
-            .resetvalue = 0
-        };
-        define_one_arm_cp_reg(cpu, &ifar);
-    }
-}
-
-static void arm1136_r2_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-    /*
-     * What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an
-     * older core than plain "arm1136". In particular this does not
-     * have the v6K features.
-     * These ID register values are correct for 1136 but may be wrong
-     * for 1136_r2 (in particular r0p2 does not actually implement most
-     * of the ID registers).
-     */
-
-    cpu->dtb_compatible = "arm,arm1136";
-    set_feature(&cpu->env, ARM_FEATURE_V6);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS);
-    cpu->midr = 0x4107b362;
-    cpu->reset_fpsid = 0x410120b4;
-    cpu->isar.mvfr0 = 0x11111111;
-    cpu->isar.mvfr1 = 0x00000000;
-    cpu->ctr = 0x1dd20d2;
-    cpu->reset_sctlr = 0x00050078;
-    cpu->id_pfr0 = 0x111;
-    cpu->id_pfr1 = 0x1;
-    cpu->isar.id_dfr0 = 0x2;
-    cpu->id_afr0 = 0x3;
-    cpu->isar.id_mmfr0 = 0x01130003;
-    cpu->isar.id_mmfr1 = 0x10030302;
-    cpu->isar.id_mmfr2 = 0x01222110;
-    cpu->isar.id_isar0 = 0x00140011;
-    cpu->isar.id_isar1 = 0x12002111;
-    cpu->isar.id_isar2 = 0x11231111;
-    cpu->isar.id_isar3 = 0x01102131;
-    cpu->isar.id_isar4 = 0x141;
-    cpu->reset_auxcr = 7;
-}
-
-static void arm1136_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "arm,arm1136";
-    set_feature(&cpu->env, ARM_FEATURE_V6K);
-    set_feature(&cpu->env, ARM_FEATURE_V6);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS);
-    cpu->midr = 0x4117b363;
-    cpu->reset_fpsid = 0x410120b4;
-    cpu->isar.mvfr0 = 0x11111111;
-    cpu->isar.mvfr1 = 0x00000000;
-    cpu->ctr = 0x1dd20d2;
-    cpu->reset_sctlr = 0x00050078;
-    cpu->id_pfr0 = 0x111;
-    cpu->id_pfr1 = 0x1;
-    cpu->isar.id_dfr0 = 0x2;
-    cpu->id_afr0 = 0x3;
-    cpu->isar.id_mmfr0 = 0x01130003;
-    cpu->isar.id_mmfr1 = 0x10030302;
-    cpu->isar.id_mmfr2 = 0x01222110;
-    cpu->isar.id_isar0 = 0x00140011;
-    cpu->isar.id_isar1 = 0x12002111;
-    cpu->isar.id_isar2 = 0x11231111;
-    cpu->isar.id_isar3 = 0x01102131;
-    cpu->isar.id_isar4 = 0x141;
-    cpu->reset_auxcr = 7;
-}
-
-static void arm1176_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "arm,arm1176";
-    set_feature(&cpu->env, ARM_FEATURE_V6K);
-    set_feature(&cpu->env, ARM_FEATURE_VAPA);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG);
-    set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS);
-    set_feature(&cpu->env, ARM_FEATURE_EL3);
-    cpu->midr = 0x410fb767;
-    cpu->reset_fpsid = 0x410120b5;
-    cpu->isar.mvfr0 = 0x11111111;
-    cpu->isar.mvfr1 = 0x00000000;
-    cpu->ctr = 0x1dd20d2;
-    cpu->reset_sctlr = 0x00050078;
-    cpu->id_pfr0 = 0x111;
-    cpu->id_pfr1 = 0x11;
-    cpu->isar.id_dfr0 = 0x33;
-    cpu->id_afr0 = 0;
-    cpu->isar.id_mmfr0 = 0x01130003;
-    cpu->isar.id_mmfr1 = 0x10030302;
-    cpu->isar.id_mmfr2 = 0x01222100;
-    cpu->isar.id_isar0 = 0x0140011;
-    cpu->isar.id_isar1 = 0x12002111;
-    cpu->isar.id_isar2 = 0x11231121;
-    cpu->isar.id_isar3 = 0x01102131;
-    cpu->isar.id_isar4 = 0x01141;
-    cpu->reset_auxcr = 7;
-}
-
-static void arm11mpcore_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "arm,arm11mpcore";
-    set_feature(&cpu->env, ARM_FEATURE_V6K);
-    set_feature(&cpu->env, ARM_FEATURE_VAPA);
-    set_feature(&cpu->env, ARM_FEATURE_MPIDR);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    cpu->midr = 0x410fb022;
-    cpu->reset_fpsid = 0x410120b4;
-    cpu->isar.mvfr0 = 0x11111111;
-    cpu->isar.mvfr1 = 0x00000000;
-    cpu->ctr = 0x1d192992; /* 32K icache 32K dcache */
-    cpu->id_pfr0 = 0x111;
-    cpu->id_pfr1 = 0x1;
-    cpu->isar.id_dfr0 = 0;
-    cpu->id_afr0 = 0x2;
-    cpu->isar.id_mmfr0 = 0x01100103;
-    cpu->isar.id_mmfr1 = 0x10020302;
-    cpu->isar.id_mmfr2 = 0x01222000;
-    cpu->isar.id_isar0 = 0x00100011;
-    cpu->isar.id_isar1 = 0x12002111;
-    cpu->isar.id_isar2 = 0x11221011;
-    cpu->isar.id_isar3 = 0x01102131;
-    cpu->isar.id_isar4 = 0x141;
-    cpu->reset_auxcr = 1;
-}
-
-static void cortex_m0_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-    set_feature(&cpu->env, ARM_FEATURE_V6);
-    set_feature(&cpu->env, ARM_FEATURE_M);
-
-    cpu->midr = 0x410cc200;
-}
-
-static void cortex_m3_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-    set_feature(&cpu->env, ARM_FEATURE_V7);
-    set_feature(&cpu->env, ARM_FEATURE_M);
-    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
-    cpu->midr = 0x410fc231;
-    cpu->pmsav7_dregion = 8;
-    cpu->id_pfr0 = 0x00000030;
-    cpu->id_pfr1 = 0x00000200;
-    cpu->isar.id_dfr0 = 0x00100000;
-    cpu->id_afr0 = 0x00000000;
-    cpu->isar.id_mmfr0 = 0x00000030;
-    cpu->isar.id_mmfr1 = 0x00000000;
-    cpu->isar.id_mmfr2 = 0x00000000;
-    cpu->isar.id_mmfr3 = 0x00000000;
-    cpu->isar.id_isar0 = 0x01141110;
-    cpu->isar.id_isar1 = 0x02111000;
-    cpu->isar.id_isar2 = 0x21112231;
-    cpu->isar.id_isar3 = 0x01111110;
-    cpu->isar.id_isar4 = 0x01310102;
-    cpu->isar.id_isar5 = 0x00000000;
-    cpu->isar.id_isar6 = 0x00000000;
-}
-
-static void cortex_m4_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    set_feature(&cpu->env, ARM_FEATURE_V7);
-    set_feature(&cpu->env, ARM_FEATURE_M);
-    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
-    set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP);
-    cpu->midr = 0x410fc240; /* r0p0 */
-    cpu->pmsav7_dregion = 8;
-    cpu->isar.mvfr0 = 0x10110021;
-    cpu->isar.mvfr1 = 0x11000011;
-    cpu->isar.mvfr2 = 0x00000000;
-    cpu->id_pfr0 = 0x00000030;
-    cpu->id_pfr1 = 0x00000200;
-    cpu->isar.id_dfr0 = 0x00100000;
-    cpu->id_afr0 = 0x00000000;
-    cpu->isar.id_mmfr0 = 0x00000030;
-    cpu->isar.id_mmfr1 = 0x00000000;
-    cpu->isar.id_mmfr2 = 0x00000000;
-    cpu->isar.id_mmfr3 = 0x00000000;
-    cpu->isar.id_isar0 = 0x01141110;
-    cpu->isar.id_isar1 = 0x02111000;
-    cpu->isar.id_isar2 = 0x21112231;
-    cpu->isar.id_isar3 = 0x01111110;
-    cpu->isar.id_isar4 = 0x01310102;
-    cpu->isar.id_isar5 = 0x00000000;
-    cpu->isar.id_isar6 = 0x00000000;
-}
-
-static void cortex_m7_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    set_feature(&cpu->env, ARM_FEATURE_V7);
-    set_feature(&cpu->env, ARM_FEATURE_M);
-    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
-    set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP);
-    cpu->midr = 0x411fc272; /* r1p2 */
-    cpu->pmsav7_dregion = 8;
-    cpu->isar.mvfr0 = 0x10110221;
-    cpu->isar.mvfr1 = 0x12000011;
-    cpu->isar.mvfr2 = 0x00000040;
-    cpu->id_pfr0 = 0x00000030;
-    cpu->id_pfr1 = 0x00000200;
-    cpu->isar.id_dfr0 = 0x00100000;
-    cpu->id_afr0 = 0x00000000;
-    cpu->isar.id_mmfr0 = 0x00100030;
-    cpu->isar.id_mmfr1 = 0x00000000;
-    cpu->isar.id_mmfr2 = 0x01000000;
-    cpu->isar.id_mmfr3 = 0x00000000;
-    cpu->isar.id_isar0 = 0x01101110;
-    cpu->isar.id_isar1 = 0x02112000;
-    cpu->isar.id_isar2 = 0x20232231;
-    cpu->isar.id_isar3 = 0x01111131;
-    cpu->isar.id_isar4 = 0x01310132;
-    cpu->isar.id_isar5 = 0x00000000;
-    cpu->isar.id_isar6 = 0x00000000;
-}
-
-static void cortex_m33_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    set_feature(&cpu->env, ARM_FEATURE_V8);
-    set_feature(&cpu->env, ARM_FEATURE_M);
-    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
-    set_feature(&cpu->env, ARM_FEATURE_M_SECURITY);
-    set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP);
-    cpu->midr = 0x410fd213; /* r0p3 */
-    cpu->pmsav7_dregion = 16;
-    cpu->sau_sregion = 8;
-    cpu->isar.mvfr0 = 0x10110021;
-    cpu->isar.mvfr1 = 0x11000011;
-    cpu->isar.mvfr2 = 0x00000040;
-    cpu->id_pfr0 = 0x00000030;
-    cpu->id_pfr1 = 0x00000210;
-    cpu->isar.id_dfr0 = 0x00200000;
-    cpu->id_afr0 = 0x00000000;
-    cpu->isar.id_mmfr0 = 0x00101F40;
-    cpu->isar.id_mmfr1 = 0x00000000;
-    cpu->isar.id_mmfr2 = 0x01000000;
-    cpu->isar.id_mmfr3 = 0x00000000;
-    cpu->isar.id_isar0 = 0x01101110;
-    cpu->isar.id_isar1 = 0x02212000;
-    cpu->isar.id_isar2 = 0x20232232;
-    cpu->isar.id_isar3 = 0x01111131;
-    cpu->isar.id_isar4 = 0x01310132;
-    cpu->isar.id_isar5 = 0x00000000;
-    cpu->isar.id_isar6 = 0x00000000;
-    cpu->clidr = 0x00000000;
-    cpu->ctr = 0x8000c000;
-}
-
-static void arm_v7m_class_init(ObjectClass *oc, void *data)
-{
-    ARMCPUClass *acc = ARM_CPU_CLASS(oc);
-    CPUClass *cc = CPU_CLASS(oc);
-
-    acc->info = data;
-#ifndef CONFIG_USER_ONLY
-    cc->do_interrupt = arm_v7m_cpu_do_interrupt;
-#endif
-
-    cc->cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt;
-}
-
-static const ARMCPRegInfo cortexr5_cp_reginfo[] = {
-    /* Dummy the TCM region regs for the moment */
-    { .name = "ATCM", .cp = 15, .opc1 = 0, .crn = 9, .crm = 1, .opc2 = 0,
-      .access = PL1_RW, .type = ARM_CP_CONST },
-    { .name = "BTCM", .cp = 15, .opc1 = 0, .crn = 9, .crm = 1, .opc2 = 1,
-      .access = PL1_RW, .type = ARM_CP_CONST },
-    { .name = "DCACHE_INVAL", .cp = 15, .opc1 = 0, .crn = 15, .crm = 5,
-      .opc2 = 0, .access = PL1_W, .type = ARM_CP_NOP },
-    REGINFO_SENTINEL
-};
-
-static void cortex_r5_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    set_feature(&cpu->env, ARM_FEATURE_V7);
-    set_feature(&cpu->env, ARM_FEATURE_V7MP);
-    set_feature(&cpu->env, ARM_FEATURE_PMSA);
-    set_feature(&cpu->env, ARM_FEATURE_PMU);
-    cpu->midr = 0x411fc153; /* r1p3 */
-    cpu->id_pfr0 = 0x0131;
-    cpu->id_pfr1 = 0x001;
-    cpu->isar.id_dfr0 = 0x010400;
-    cpu->id_afr0 = 0x0;
-    cpu->isar.id_mmfr0 = 0x0210030;
-    cpu->isar.id_mmfr1 = 0x00000000;
-    cpu->isar.id_mmfr2 = 0x01200000;
-    cpu->isar.id_mmfr3 = 0x0211;
-    cpu->isar.id_isar0 = 0x02101111;
-    cpu->isar.id_isar1 = 0x13112111;
-    cpu->isar.id_isar2 = 0x21232141;
-    cpu->isar.id_isar3 = 0x01112131;
-    cpu->isar.id_isar4 = 0x0010142;
-    cpu->isar.id_isar5 = 0x0;
-    cpu->isar.id_isar6 = 0x0;
-    cpu->mp_is_up = true;
-    cpu->pmsav7_dregion = 16;
-    define_arm_cp_regs(cpu, cortexr5_cp_reginfo);
-}
-
-static void cortex_r5f_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cortex_r5_initfn(obj);
-    cpu->isar.mvfr0 = 0x10110221;
-    cpu->isar.mvfr1 = 0x00000011;
-}
-
 static const ARMCPRegInfo cortexa8_cp_reginfo[] = {
     { .name = "L2LOCKDOWN", .cp = 15, .crn = 9, .crm = 0, .opc1 = 1, .opc2 = 0,
       .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 },
@@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj)
     define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
 }
 
-static void ti925t_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-    set_feature(&cpu->env, ARM_FEATURE_V4T);
-    set_feature(&cpu->env, ARM_FEATURE_OMAPCP);
-    cpu->midr = ARM_CPUID_TI925T;
-    cpu->ctr = 0x5109149;
-    cpu->reset_sctlr = 0x00000070;
-}
-
-static void sa1100_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "intel,sa1100";
-    set_feature(&cpu->env, ARM_FEATURE_STRONGARM);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    cpu->midr = 0x4401A11B;
-    cpu->reset_sctlr = 0x00000070;
-}
-
-static void sa1110_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-    set_feature(&cpu->env, ARM_FEATURE_STRONGARM);
-    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
-    cpu->midr = 0x6901B119;
-    cpu->reset_sctlr = 0x00000070;
-}
-
-static void pxa250_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    cpu->midr = 0x69052100;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa255_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    cpu->midr = 0x69052d00;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa260_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    cpu->midr = 0x69052903;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa261_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    cpu->midr = 0x69052d05;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa262_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    cpu->midr = 0x69052d06;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa270a0_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
-    cpu->midr = 0x69054110;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa270a1_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
-    cpu->midr = 0x69054111;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa270b0_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
-    cpu->midr = 0x69054112;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa270b1_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
-    cpu->midr = 0x69054113;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa270c0_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
-    cpu->midr = 0x69054114;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
-static void pxa270c5_initfn(Object *obj)
-{
-    ARMCPU *cpu = ARM_CPU(obj);
-
-    cpu->dtb_compatible = "marvell,xscale";
-    set_feature(&cpu->env, ARM_FEATURE_V5);
-    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
-    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
-    cpu->midr = 0x69054117;
-    cpu->ctr = 0xd172172;
-    cpu->reset_sctlr = 0x00000078;
-}
-
 #ifndef TARGET_AARCH64
 /* -cpu max: if KVM is enabled, like -cpu host (best possible with this host);
  * otherwise, a CPU with as many features enabled as our emulation supports.
@@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj)
 
 static const ARMCPUInfo arm_cpus[] = {
 #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
-    { .name = "arm926",      .initfn = arm926_initfn },
-    { .name = "arm946",      .initfn = arm946_initfn },
-    { .name = "arm1026",     .initfn = arm1026_initfn },
-    /*
-     * What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an
-     * older core than plain "arm1136". In particular this does not
-     * have the v6K features.
-     */
-    { .name = "arm1136-r2",  .initfn = arm1136_r2_initfn },
-    { .name = "arm1136",     .initfn = arm1136_initfn },
-    { .name = "arm1176",     .initfn = arm1176_initfn },
-    { .name = "arm11mpcore", .initfn = arm11mpcore_initfn },
-    { .name = "cortex-m0",   .initfn = cortex_m0_initfn,
-                             .class_init = arm_v7m_class_init },
-    { .name = "cortex-m3",   .initfn = cortex_m3_initfn,
-                             .class_init = arm_v7m_class_init },
-    { .name = "cortex-m4",   .initfn = cortex_m4_initfn,
-                             .class_init = arm_v7m_class_init },
-    { .name = "cortex-m7",   .initfn = cortex_m7_initfn,
-                             .class_init = arm_v7m_class_init },
-    { .name = "cortex-m33",  .initfn = cortex_m33_initfn,
-                             .class_init = arm_v7m_class_init },
-    { .name = "cortex-r5",   .initfn = cortex_r5_initfn },
-    { .name = "cortex-r5f",  .initfn = cortex_r5f_initfn },
     { .name = "cortex-a7",   .initfn = cortex_a7_initfn },
     { .name = "cortex-a8",   .initfn = cortex_a8_initfn },
     { .name = "cortex-a9",   .initfn = cortex_a9_initfn },
     { .name = "cortex-a15",  .initfn = cortex_a15_initfn },
-    { .name = "ti925t",      .initfn = ti925t_initfn },
-    { .name = "sa1100",      .initfn = sa1100_initfn },
-    { .name = "sa1110",      .initfn = sa1110_initfn },
-    { .name = "pxa250",      .initfn = pxa250_initfn },
-    { .name = "pxa255",      .initfn = pxa255_initfn },
-    { .name = "pxa260",      .initfn = pxa260_initfn },
-    { .name = "pxa261",      .initfn = pxa261_initfn },
-    { .name = "pxa262",      .initfn = pxa262_initfn },
-    /* "pxa270" is an alias for "pxa270-a0" */
-    { .name = "pxa270",      .initfn = pxa270a0_initfn },
-    { .name = "pxa270-a0",   .initfn = pxa270a0_initfn },
-    { .name = "pxa270-a1",   .initfn = pxa270a1_initfn },
-    { .name = "pxa270-b0",   .initfn = pxa270b0_initfn },
-    { .name = "pxa270-b1",   .initfn = pxa270b1_initfn },
-    { .name = "pxa270-c0",   .initfn = pxa270c0_initfn },
-    { .name = "pxa270-c5",   .initfn = pxa270c5_initfn },
 #ifndef TARGET_AARCH64
     { .name = "max",         .initfn = arm_max_initfn },
 #endif
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/target/arm/cpu_tcg.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * QEMU ARM TCG CPUs.
+ *
+ * Copyright (c) 2012 SUSE LINUX Products GmbH
+ *
+ * This code is licensed under the GNU GPL v2 or later.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "internals.h"
+
+/* CPU models. These are not needed for the AArch64 linux-user build. */
+#if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64)
+
+static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
+{
+    CPUClass *cc = CPU_GET_CLASS(cs);
+    ARMCPU *cpu = ARM_CPU(cs);
+    CPUARMState *env = &cpu->env;
+    bool ret = false;
+
+    /*
+     * ARMv7-M interrupt masking works differently than -A or -R.
+     * There is no FIQ/IRQ distinction. Instead of I and F bits
+     * masking FIQ and IRQ interrupts, an exception is taken only
+     * if it is higher priority than the current execution priority
+     * (which depends on state like BASEPRI, FAULTMASK and the
+     * currently active exception).
+     */
+    if (interrupt_request & CPU_INTERRUPT_HARD
+        && (armv7m_nvic_can_take_pending_exception(env->nvic))) {
+        cs->exception_index = EXCP_IRQ;
+        cc->do_interrupt(cs);
+        ret = true;
+    }
+    return ret;
+}
+
+static void arm926_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,arm926";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN);
+    cpu->midr = 0x41069265;
+    cpu->reset_fpsid = 0x41011090;
+    cpu->ctr = 0x1dd20d2;
+    cpu->reset_sctlr = 0x00090078;
+
+    /*
+     * ARMv5 does not have the ID_ISAR registers, but we can still
+     * set the field to indicate Jazelle support within QEMU.
+     */
+    cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1);
+    /*
+     * Similarly, we need to set MVFR0 fields to enable vfp and short vector
+     * support even though ARMv5 doesn't have this register.
+     */
+    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1);
+    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSP, 1);
+    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1);
+}
+
+static void arm946_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,arm946";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_PMSA);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    cpu->midr = 0x41059461;
+    cpu->ctr = 0x0f004006;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void arm1026_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,arm1026";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_AUXCR);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN);
+    cpu->midr = 0x4106a262;
+    cpu->reset_fpsid = 0x410110a0;
+    cpu->ctr = 0x1dd20d2;
+    cpu->reset_sctlr = 0x00090078;
+    cpu->reset_auxcr = 1;
+
+    /*
+     * ARMv5 does not have the ID_ISAR registers, but we can still
+     * set the field to indicate Jazelle support within QEMU.
+     */
+    cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1);
+    /*
+     * Similarly, we need to set MVFR0 fields to enable vfp and short vector
+     * support even though ARMv5 doesn't have this register.
+     */
+    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1);
+    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSP, 1);
+    cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1);
+
+    {
+        /* The 1026 had an IFAR at c6,c0,0,1 rather than the ARMv6 c6,c0,0,2 */
+        ARMCPRegInfo ifar = {
+            .name = "IFAR", .cp = 15, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 1,
+            .access = PL1_RW,
+            .fieldoffset = offsetof(CPUARMState, cp15.ifar_ns),
+            .resetvalue = 0
+        };
+        define_one_arm_cp_reg(cpu, &ifar);
+    }
+}
+
+static void arm1136_r2_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    /*
+     * What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an
+     * older core than plain "arm1136". In particular this does not
+     * have the v6K features.
+     * These ID register values are correct for 1136 but may be wrong
+     * for 1136_r2 (in particular r0p2 does not actually implement most
+     * of the ID registers).
+     */
+
+    cpu->dtb_compatible = "arm,arm1136";
+    set_feature(&cpu->env, ARM_FEATURE_V6);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS);
+    cpu->midr = 0x4107b362;
+    cpu->reset_fpsid = 0x410120b4;
+    cpu->isar.mvfr0 = 0x11111111;
+    cpu->isar.mvfr1 = 0x00000000;
+    cpu->ctr = 0x1dd20d2;
+    cpu->reset_sctlr = 0x00050078;
+    cpu->id_pfr0 = 0x111;
+    cpu->id_pfr1 = 0x1;
+    cpu->isar.id_dfr0 = 0x2;
+    cpu->id_afr0 = 0x3;
+    cpu->isar.id_mmfr0 = 0x01130003;
+    cpu->isar.id_mmfr1 = 0x10030302;
+    cpu->isar.id_mmfr2 = 0x01222110;
+    cpu->isar.id_isar0 = 0x00140011;
+    cpu->isar.id_isar1 = 0x12002111;
+    cpu->isar.id_isar2 = 0x11231111;
+    cpu->isar.id_isar3 = 0x01102131;
+    cpu->isar.id_isar4 = 0x141;
+    cpu->reset_auxcr = 7;
+}
+
+static void arm1136_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,arm1136";
+    set_feature(&cpu->env, ARM_FEATURE_V6K);
+    set_feature(&cpu->env, ARM_FEATURE_V6);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS);
+    cpu->midr = 0x4117b363;
+    cpu->reset_fpsid = 0x410120b4;
+    cpu->isar.mvfr0 = 0x11111111;
+    cpu->isar.mvfr1 = 0x00000000;
+    cpu->ctr = 0x1dd20d2;
+    cpu->reset_sctlr = 0x00050078;
+    cpu->id_pfr0 = 0x111;
+    cpu->id_pfr1 = 0x1;
+    cpu->isar.id_dfr0 = 0x2;
+    cpu->id_afr0 = 0x3;
+    cpu->isar.id_mmfr0 = 0x01130003;
+    cpu->isar.id_mmfr1 = 0x10030302;
+    cpu->isar.id_mmfr2 = 0x01222110;
+    cpu->isar.id_isar0 = 0x00140011;
+    cpu->isar.id_isar1 = 0x12002111;
+    cpu->isar.id_isar2 = 0x11231111;
+    cpu->isar.id_isar3 = 0x01102131;
+    cpu->isar.id_isar4 = 0x141;
+    cpu->reset_auxcr = 7;
+}
+
+static void arm1176_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,arm1176";
+    set_feature(&cpu->env, ARM_FEATURE_V6K);
+    set_feature(&cpu->env, ARM_FEATURE_VAPA);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG);
+    set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS);
+    set_feature(&cpu->env, ARM_FEATURE_EL3);
+    cpu->midr = 0x410fb767;
+    cpu->reset_fpsid = 0x410120b5;
+    cpu->isar.mvfr0 = 0x11111111;
+    cpu->isar.mvfr1 = 0x00000000;
+    cpu->ctr = 0x1dd20d2;
+    cpu->reset_sctlr = 0x00050078;
+    cpu->id_pfr0 = 0x111;
+    cpu->id_pfr1 = 0x11;
+    cpu->isar.id_dfr0 = 0x33;
+    cpu->id_afr0 = 0;
+    cpu->isar.id_mmfr0 = 0x01130003;
+    cpu->isar.id_mmfr1 = 0x10030302;
+    cpu->isar.id_mmfr2 = 0x01222100;
+    cpu->isar.id_isar0 = 0x0140011;
+    cpu->isar.id_isar1 = 0x12002111;
+    cpu->isar.id_isar2 = 0x11231121;
+    cpu->isar.id_isar3 = 0x01102131;
+    cpu->isar.id_isar4 = 0x01141;
+    cpu->reset_auxcr = 7;
+}
+
+static void arm11mpcore_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,arm11mpcore";
+    set_feature(&cpu->env, ARM_FEATURE_V6K);
+    set_feature(&cpu->env, ARM_FEATURE_VAPA);
+    set_feature(&cpu->env, ARM_FEATURE_MPIDR);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    cpu->midr = 0x410fb022;
+    cpu->reset_fpsid = 0x410120b4;
+    cpu->isar.mvfr0 = 0x11111111;
+    cpu->isar.mvfr1 = 0x00000000;
+    cpu->ctr = 0x1d192992; /* 32K icache 32K dcache */
+    cpu->id_pfr0 = 0x111;
+    cpu->id_pfr1 = 0x1;
+    cpu->isar.id_dfr0 = 0;
+    cpu->id_afr0 = 0x2;
+    cpu->isar.id_mmfr0 = 0x01100103;
+    cpu->isar.id_mmfr1 = 0x10020302;
+    cpu->isar.id_mmfr2 = 0x01222000;
+    cpu->isar.id_isar0 = 0x00100011;
+    cpu->isar.id_isar1 = 0x12002111;
+    cpu->isar.id_isar2 = 0x11221011;
+    cpu->isar.id_isar3 = 0x01102131;
+    cpu->isar.id_isar4 = 0x141;
+    cpu->reset_auxcr = 1;
+}
+
+static void cortex_m0_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    set_feature(&cpu->env, ARM_FEATURE_V6);
+    set_feature(&cpu->env, ARM_FEATURE_M);
+
+    cpu->midr = 0x410cc200;
+}
+
+static void cortex_m3_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    set_feature(&cpu->env, ARM_FEATURE_V7);
+    set_feature(&cpu->env, ARM_FEATURE_M);
+    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
+    cpu->midr = 0x410fc231;
+    cpu->pmsav7_dregion = 8;
+    cpu->id_pfr0 = 0x00000030;
+    cpu->id_pfr1 = 0x00000200;
+    cpu->isar.id_dfr0 = 0x00100000;
+    cpu->id_afr0 = 0x00000000;
+    cpu->isar.id_mmfr0 = 0x00000030;
+    cpu->isar.id_mmfr1 = 0x00000000;
+    cpu->isar.id_mmfr2 = 0x00000000;
+    cpu->isar.id_mmfr3 = 0x00000000;
+    cpu->isar.id_isar0 = 0x01141110;
+    cpu->isar.id_isar1 = 0x02111000;
+    cpu->isar.id_isar2 = 0x21112231;
+    cpu->isar.id_isar3 = 0x01111110;
+    cpu->isar.id_isar4 = 0x01310102;
+    cpu->isar.id_isar5 = 0x00000000;
+    cpu->isar.id_isar6 = 0x00000000;
+}
+
+static void cortex_m4_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    set_feature(&cpu->env, ARM_FEATURE_V7);
+    set_feature(&cpu->env, ARM_FEATURE_M);
+    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
+    set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP);
+    cpu->midr = 0x410fc240; /* r0p0 */
+    cpu->pmsav7_dregion = 8;
+    cpu->isar.mvfr0 = 0x10110021;
+    cpu->isar.mvfr1 = 0x11000011;
+    cpu->isar.mvfr2 = 0x00000000;
+    cpu->id_pfr0 = 0x00000030;
+    cpu->id_pfr1 = 0x00000200;
+    cpu->isar.id_dfr0 = 0x00100000;
+    cpu->id_afr0 = 0x00000000;
+    cpu->isar.id_mmfr0 = 0x00000030;
+    cpu->isar.id_mmfr1 = 0x00000000;
+    cpu->isar.id_mmfr2 = 0x00000000;
+    cpu->isar.id_mmfr3 = 0x00000000;
+    cpu->isar.id_isar0 = 0x01141110;
+    cpu->isar.id_isar1 = 0x02111000;
+    cpu->isar.id_isar2 = 0x21112231;
+    cpu->isar.id_isar3 = 0x01111110;
+    cpu->isar.id_isar4 = 0x01310102;
+    cpu->isar.id_isar5 = 0x00000000;
+    cpu->isar.id_isar6 = 0x00000000;
+}
+
+static void cortex_m7_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    set_feature(&cpu->env, ARM_FEATURE_V7);
+    set_feature(&cpu->env, ARM_FEATURE_M);
+    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
+    set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP);
+    cpu->midr = 0x411fc272; /* r1p2 */
+    cpu->pmsav7_dregion = 8;
+    cpu->isar.mvfr0 = 0x10110221;
+    cpu->isar.mvfr1 = 0x12000011;
+    cpu->isar.mvfr2 = 0x00000040;
+    cpu->id_pfr0 = 0x00000030;
+    cpu->id_pfr1 = 0x00000200;
+    cpu->isar.id_dfr0 = 0x00100000;
+    cpu->id_afr0 = 0x00000000;
+    cpu->isar.id_mmfr0 = 0x00100030;
+    cpu->isar.id_mmfr1 = 0x00000000;
+    cpu->isar.id_mmfr2 = 0x01000000;
+    cpu->isar.id_mmfr3 = 0x00000000;
+    cpu->isar.id_isar0 = 0x01101110;
+    cpu->isar.id_isar1 = 0x02112000;
+    cpu->isar.id_isar2 = 0x20232231;
+    cpu->isar.id_isar3 = 0x01111131;
+    cpu->isar.id_isar4 = 0x01310132;
+    cpu->isar.id_isar5 = 0x00000000;
+    cpu->isar.id_isar6 = 0x00000000;
+}
+
+static void cortex_m33_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    set_feature(&cpu->env, ARM_FEATURE_V8);
+    set_feature(&cpu->env, ARM_FEATURE_M);
+    set_feature(&cpu->env, ARM_FEATURE_M_MAIN);
+    set_feature(&cpu->env, ARM_FEATURE_M_SECURITY);
+    set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP);
+    cpu->midr = 0x410fd213; /* r0p3 */
+    cpu->pmsav7_dregion = 16;
+    cpu->sau_sregion = 8;
+    cpu->isar.mvfr0 = 0x10110021;
+    cpu->isar.mvfr1 = 0x11000011;
+    cpu->isar.mvfr2 = 0x00000040;
+    cpu->id_pfr0 = 0x00000030;
+    cpu->id_pfr1 = 0x00000210;
+    cpu->isar.id_dfr0 = 0x00200000;
+    cpu->id_afr0 = 0x00000000;
+    cpu->isar.id_mmfr0 = 0x00101F40;
+    cpu->isar.id_mmfr1 = 0x00000000;
+    cpu->isar.id_mmfr2 = 0x01000000;
+    cpu->isar.id_mmfr3 = 0x00000000;
+    cpu->isar.id_isar0 = 0x01101110;
+    cpu->isar.id_isar1 = 0x02212000;
+    cpu->isar.id_isar2 = 0x20232232;
+    cpu->isar.id_isar3 = 0x01111131;
+    cpu->isar.id_isar4 = 0x01310132;
+    cpu->isar.id_isar5 = 0x00000000;
+    cpu->isar.id_isar6 = 0x00000000;
+    cpu->clidr = 0x00000000;
+    cpu->ctr = 0x8000c000;
+}
+
+static const ARMCPRegInfo cortexr5_cp_reginfo[] = {
+    /* Dummy the TCM region regs for the moment */
+    { .name = "ATCM", .cp = 15, .opc1 = 0, .crn = 9, .crm = 1, .opc2 = 0,
+      .access = PL1_RW, .type = ARM_CP_CONST },
+    { .name = "BTCM", .cp = 15, .opc1 = 0, .crn = 9, .crm = 1, .opc2 = 1,
+      .access = PL1_RW, .type = ARM_CP_CONST },
+    { .name = "DCACHE_INVAL", .cp = 15, .opc1 = 0, .crn = 15, .crm = 5,
+      .opc2 = 0, .access = PL1_W, .type = ARM_CP_NOP },
+    REGINFO_SENTINEL
+};
+
+static void cortex_r5_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    set_feature(&cpu->env, ARM_FEATURE_V7);
+    set_feature(&cpu->env, ARM_FEATURE_V7MP);
+    set_feature(&cpu->env, ARM_FEATURE_PMSA);
+    set_feature(&cpu->env, ARM_FEATURE_PMU);
+    cpu->midr = 0x411fc153; /* r1p3 */
+    cpu->id_pfr0 = 0x0131;
+    cpu->id_pfr1 = 0x001;
+    cpu->isar.id_dfr0 = 0x010400;
+    cpu->id_afr0 = 0x0;
+    cpu->isar.id_mmfr0 = 0x0210030;
+    cpu->isar.id_mmfr1 = 0x00000000;
+    cpu->isar.id_mmfr2 = 0x01200000;
+    cpu->isar.id_mmfr3 = 0x0211;
+    cpu->isar.id_isar0 = 0x02101111;
+    cpu->isar.id_isar1 = 0x13112111;
+    cpu->isar.id_isar2 = 0x21232141;
+    cpu->isar.id_isar3 = 0x01112131;
+    cpu->isar.id_isar4 = 0x0010142;
+    cpu->isar.id_isar5 = 0x0;
+    cpu->isar.id_isar6 = 0x0;
+    cpu->mp_is_up = true;
+    cpu->pmsav7_dregion = 16;
+    define_arm_cp_regs(cpu, cortexr5_cp_reginfo);
+}
+
+static void cortex_r5f_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cortex_r5_initfn(obj);
+    cpu->isar.mvfr0 = 0x10110221;
+    cpu->isar.mvfr1 = 0x00000011;
+}
+
+static void ti925t_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    set_feature(&cpu->env, ARM_FEATURE_V4T);
+    set_feature(&cpu->env, ARM_FEATURE_OMAPCP);
+    cpu->midr = ARM_CPUID_TI925T;
+    cpu->ctr = 0x5109149;
+    cpu->reset_sctlr = 0x00000070;
+}
+
+static void sa1100_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "intel,sa1100";
+    set_feature(&cpu->env, ARM_FEATURE_STRONGARM);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    cpu->midr = 0x4401A11B;
+    cpu->reset_sctlr = 0x00000070;
+}
+
+static void sa1110_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+    set_feature(&cpu->env, ARM_FEATURE_STRONGARM);
+    set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS);
+    cpu->midr = 0x6901B119;
+    cpu->reset_sctlr = 0x00000070;
+}
+
+static void pxa250_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    cpu->midr = 0x69052100;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa255_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    cpu->midr = 0x69052d00;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa260_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    cpu->midr = 0x69052903;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa261_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    cpu->midr = 0x69052d05;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa262_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    cpu->midr = 0x69052d06;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa270a0_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
+    cpu->midr = 0x69054110;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa270a1_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
+    cpu->midr = 0x69054111;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa270b0_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
+    cpu->midr = 0x69054112;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa270b1_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
+    cpu->midr = 0x69054113;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa270c0_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
+    cpu->midr = 0x69054114;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void pxa270c5_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "marvell,xscale";
+    set_feature(&cpu->env, ARM_FEATURE_V5);
+    set_feature(&cpu->env, ARM_FEATURE_XSCALE);
+    set_feature(&cpu->env, ARM_FEATURE_IWMMXT);
+    cpu->midr = 0x69054117;
+    cpu->ctr = 0xd172172;
+    cpu->reset_sctlr = 0x00000078;
+}
+
+static void arm_v7m_class_init(ObjectClass *oc, void *data)
+{
+    ARMCPUClass *acc = ARM_CPU_CLASS(oc);
+    CPUClass *cc = CPU_CLASS(oc);
+
+    acc->info = data;
+#ifndef CONFIG_USER_ONLY
+    cc->do_interrupt = arm_v7m_cpu_do_interrupt;
+#endif
+
+    cc->cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt;
+}
+
+static const ARMCPUInfo arm_tcg_cpus[] = {
+    { .name = "arm926",      .initfn = arm926_initfn },
+    { .name = "arm946",      .initfn = arm946_initfn },
+    { .name = "arm1026",     .initfn = arm1026_initfn },
+    /*
+     * What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an
+     * older core than plain "arm1136". In particular this does not
+     * have the v6K features.
+     */
+    { .name = "arm1136-r2",  .initfn = arm1136_r2_initfn },
+    { .name = "arm1136",     .initfn = arm1136_initfn },
+    { .name = "arm1176",     .initfn = arm1176_initfn },
+    { .name = "arm11mpcore", .initfn = arm11mpcore_initfn },
+    { .name = "cortex-m0",   .initfn = cortex_m0_initfn,
+                             .class_init = arm_v7m_class_init },
+    { .name = "cortex-m3",   .initfn = cortex_m3_initfn,
+                             .class_init = arm_v7m_class_init },
+    { .name = "cortex-m4",   .initfn = cortex_m4_initfn,
+                             .class_init = arm_v7m_class_init },
+    { .name = "cortex-m7",   .initfn = cortex_m7_initfn,
+                             .class_init = arm_v7m_class_init },
+    { .name = "cortex-m33",  .initfn = cortex_m33_initfn,
+                             .class_init = arm_v7m_class_init },
+    { .name = "cortex-r5",   .initfn = cortex_r5_initfn },
+    { .name = "cortex-r5f",  .initfn = cortex_r5f_initfn },
+    { .name = "ti925t",      .initfn = ti925t_initfn },
+    { .name = "sa1100",      .initfn = sa1100_initfn },
+    { .name = "sa1110",      .initfn = sa1110_initfn },
+    { .name = "pxa250",      .initfn = pxa250_initfn },
+    { .name = "pxa255",      .initfn = pxa255_initfn },
+    { .name = "pxa260",      .initfn = pxa260_initfn },
+    { .name = "pxa261",      .initfn = pxa261_initfn },
+    { .name = "pxa262",      .initfn = pxa262_initfn },
+    /* "pxa270" is an alias for "pxa270-a0" */
+    { .name = "pxa270",      .initfn = pxa270a0_initfn },
+    { .name = "pxa270-a0",   .initfn = pxa270a0_initfn },
+    { .name = "pxa270-a1",   .initfn = pxa270a1_initfn },
+    { .name = "pxa270-b0",   .initfn = pxa270b0_initfn },
+    { .name = "pxa270-b1",   .initfn = pxa270b1_initfn },
+    { .name = "pxa270-c0",   .initfn = pxa270c0_initfn },
+    { .name = "pxa270-c5",   .initfn = pxa270c5_initfn },
+};
+
+static void arm_tcg_cpu_register_types(void)
+{
+    size_t i;
+
+    for (i = 0; i < ARRAY_SIZE(arm_tcg_cpus); ++i) {
+        arm_cpu_register(&arm_tcg_cpus[i]);
+    }
+}
+
+type_init(arm_tcg_cpu_register_types)
+
+#endif /* !CONFIG_USER_ONLY || !TARGET_AARCH64 */
diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/Makefile.objs
+++ b/target/arm/Makefile.objs
@@ -XXX,XX +XXX,XX @@ obj-y += translate.o op_helper.o
 obj-y += crypto_helper.o
 obj-y += iwmmxt_helper.o vec_helper.o neon_helper.o
 obj-y += m_helper.o
+obj-y += cpu_tcg.o
 
 obj-$(CONFIG_SOFTMMU) += psci.o
 
-- 
2.20.1

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

I can't find proper documentation or datasheet, but it is likely
a MMIO mapped serial device mapped in the 0x80000000..0x8000ffff
range belongs to the SoC address space, thus is always mapped in
the memory bus.
Map the devices on the bus regardless a chardev is attached to it.

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Jan Kiszka <jan.kiszka@web.de>
Message-id: 20200505095945.23146-1-f4bug@amsat.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/musicpal.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/musicpal.c
+++ b/hw/arm/musicpal.c
@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)
                           pic[MP_TIMER2_IRQ], pic[MP_TIMER3_IRQ],
                           pic[MP_TIMER4_IRQ], NULL);
 
-    if (serial_hd(0)) {
-        serial_mm_init(address_space_mem, MP_UART1_BASE, 2, pic[MP_UART1_IRQ],
-                       1825000, serial_hd(0), DEVICE_NATIVE_ENDIAN);
-    }
-    if (serial_hd(1)) {
-        serial_mm_init(address_space_mem, MP_UART2_BASE, 2, pic[MP_UART2_IRQ],
-                       1825000, serial_hd(1), DEVICE_NATIVE_ENDIAN);
-    }
+    serial_mm_init(address_space_mem, MP_UART1_BASE, 2, pic[MP_UART1_IRQ],
+                   1825000, serial_hd(0), DEVICE_NATIVE_ENDIAN);
+    serial_mm_init(address_space_mem, MP_UART2_BASE, 2, pic[MP_UART2_IRQ],
+                   1825000, serial_hd(1), DEVICE_NATIVE_ENDIAN);
 
     /* Register flash */
     dinfo = drive_get(IF_PFLASH, 0, 0);
-- 
2.20.1

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

Now that we can pass 7 parameters, do not encode register
operands within simd_data.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Taylor Simpson <tsimpson@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200507172352.15418-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  45 +++++++----
 target/arm/sve_helper.c    | 157 ++++++++++++++-----------------------
 target/arm/translate-sve.c |  70 ++++++-----------
 3 files changed, 114 insertions(+), 158 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_6(sve_fcadd_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fcadd_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
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_ZPZ_FP(sve_ucvt_dd, uint64_t,     , uint64_to_float64)
 
 #undef DO_ZPZ_FP
 
-/* 4-operand predicated multiply-add.  This requires 7 operands to pass
- * "properly", so we need to encode some of the registers into DESC.
- */
-QEMU_BUILD_BUG_ON(SIMD_DATA_SHIFT + 20 > 32);
-
-static void do_fmla_zpzzz_h(CPUARMState *env, void *vg, uint32_t desc,
+static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg,
+                            float_status *status, uint32_t desc,
                             uint16_t neg1, uint16_t neg3)
 {
     intptr_t i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     do {
@@ -XXX,XX +XXX,XX @@ static void do_fmla_zpzzz_h(CPUARMState *env, void *vg, uint32_t desc,
                 e1 = *(uint16_t *)(vn + H1_2(i)) ^ neg1;
                 e2 = *(uint16_t *)(vm + H1_2(i));
                 e3 = *(uint16_t *)(va + H1_2(i)) ^ neg3;
-                r = float16_muladd(e1, e2, e3, 0, &env->vfp.fp_status_f16);
+                r = float16_muladd(e1, e2, e3, 0, status);
                 *(uint16_t *)(vd + H1_2(i)) = r;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0, 0);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0, 0);
 }
 
-void HELPER(sve_fmls_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmls_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0x8000, 0);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0x8000, 0);
 }
 
-void HELPER(sve_fnmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0x8000, 0x8000);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0x8000, 0x8000);
 }
 
-void HELPER(sve_fnmls_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmls_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0, 0x8000);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0, 0x8000);
 }
 
-static void do_fmla_zpzzz_s(CPUARMState *env, void *vg, uint32_t desc,
+static void do_fmla_zpzzz_s(void *vd, void *vn, void *vm, void *va, void *vg,
+                            float_status *status, uint32_t desc,
                             uint32_t neg1, uint32_t neg3)
 {
     intptr_t i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     do {
@@ -XXX,XX +XXX,XX @@ static void do_fmla_zpzzz_s(CPUARMState *env, void *vg, uint32_t desc,
                 e1 = *(uint32_t *)(vn + H1_4(i)) ^ neg1;
                 e2 = *(uint32_t *)(vm + H1_4(i));
                 e3 = *(uint32_t *)(va + H1_4(i)) ^ neg3;
-                r = float32_muladd(e1, e2, e3, 0, &env->vfp.fp_status);
+                r = float32_muladd(e1, e2, e3, 0, status);
                 *(uint32_t *)(vd + H1_4(i)) = r;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0, 0);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0, 0);
 }
 
-void HELPER(sve_fmls_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmls_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0x80000000, 0);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0x80000000, 0);
 }
 
-void HELPER(sve_fnmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0x80000000, 0x80000000);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0x80000000, 0x80000000);
 }
 
-void HELPER(sve_fnmls_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmls_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0, 0x80000000);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0, 0x80000000);
 }
 
-static void do_fmla_zpzzz_d(CPUARMState *env, void *vg, uint32_t desc,
+static void do_fmla_zpzzz_d(void *vd, void *vn, void *vm, void *va, void *vg,
+                            float_status *status, uint32_t desc,
                             uint64_t neg1, uint64_t neg3)
 {
     intptr_t i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     do {
@@ -XXX,XX +XXX,XX @@ static void do_fmla_zpzzz_d(CPUARMState *env, void *vg, uint32_t desc,
                 e1 = *(uint64_t *)(vn + i) ^ neg1;
                 e2 = *(uint64_t *)(vm + i);
                 e3 = *(uint64_t *)(va + i) ^ neg3;
-                r = float64_muladd(e1, e2, e3, 0, &env->vfp.fp_status);
+                r = float64_muladd(e1, e2, e3, 0, status);
                 *(uint64_t *)(vd + i) = r;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, 0, 0);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, 0, 0);
 }
 
-void HELPER(sve_fmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, INT64_MIN, 0);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, INT64_MIN, 0);
 }
 
-void HELPER(sve_fnmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, INT64_MIN, INT64_MIN);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, INT64_MIN, INT64_MIN);
 }
 
-void HELPER(sve_fnmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, 0, INT64_MIN);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, 0, INT64_MIN);
 }
 
 /* Two operand floating-point comparison controlled by a predicate.
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg,
  * FP Complex Multiply
  */
 
-QEMU_BUILD_BUG_ON(SIMD_DATA_SHIFT + 22 > 32);
-
-void HELPER(sve_fcmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fcmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
     intptr_t j, i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2);
+    unsigned rot = simd_data(desc);
     bool flip = rot & 1;
     float16 neg_imag, neg_real;
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     neg_imag = float16_set_sign(0, (rot & 2) != 0);
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
 
             if (likely((pg >> (i & 63)) & 1)) {
                 d = *(float16 *)(va + H1_2(i));
-                d = float16_muladd(e2, e1, d, 0, &env->vfp.fp_status_f16);
+                d = float16_muladd(e2, e1, d, 0, status);
                 *(float16 *)(vd + H1_2(i)) = d;
             }
             if (likely((pg >> (j & 63)) & 1)) {
                 d = *(float16 *)(va + H1_2(j));
-                d = float16_muladd(e4, e3, d, 0, &env->vfp.fp_status_f16);
+                d = float16_muladd(e4, e3, d, 0, status);
                 *(float16 *)(vd + H1_2(j)) = d;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fcmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fcmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
     intptr_t j, i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2);
+    unsigned rot = simd_data(desc);
     bool flip = rot & 1;
     float32 neg_imag, neg_real;
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     neg_imag = float32_set_sign(0, (rot & 2) != 0);
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
 
             if (likely((pg >> (i & 63)) & 1)) {
                 d = *(float32 *)(va + H1_2(i));
-                d = float32_muladd(e2, e1, d, 0, &env->vfp.fp_status);
+                d = float32_muladd(e2, e1, d, 0, status);
                 *(float32 *)(vd + H1_2(i)) = d;
             }
             if (likely((pg >> (j & 63)) & 1)) {
                 d = *(float32 *)(va + H1_2(j));
-                d = float32_muladd(e4, e3, d, 0, &env->vfp.fp_status);
+                d = float32_muladd(e4, e3, d, 0, status);
                 *(float32 *)(vd + H1_2(j)) = d;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fcmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
     intptr_t j, i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2);
+    unsigned rot = simd_data(desc);
     bool flip = rot & 1;
     float64 neg_imag, neg_real;
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     neg_imag = float64_set_sign(0, (rot & 2) != 0);
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
 
             if (likely((pg >> (i & 63)) & 1)) {
                 d = *(float64 *)(va + H1_2(i));
-                d = float64_muladd(e2, e1, d, 0, &env->vfp.fp_status);
+                d = float64_muladd(e2, e1, d, 0, status);
                 *(float64 *)(vd + H1_2(i)) = d;
             }
             if (likely((pg >> (j & 63)) & 1)) {
                 d = *(float64 *)(va + H1_2(j));
-                d = float64_muladd(e4, e3, d, 0, &env->vfp.fp_status);
+                d = float64_muladd(e4, e3, d, 0, status);
                 *(float64 *)(vd + H1_2(j)) = d;
             }
         } while (i & 63);
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_FCADD(DisasContext *s, arg_FCADD *a)
     return true;
 }
 
-typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32);
-
-static bool do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla *fn)
+static bool do_fmla(DisasContext *s, arg_rprrr_esz *a,
+                    gen_helper_gvec_5_ptr *fn)
 {
-    if (fn == NULL) {
+    if (a->esz == 0) {
         return false;
     }
-    if (!sve_access_check(s)) {
-        return true;
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16);
+        tcg_gen_gvec_5_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),
+                           pred_full_reg_offset(s, a->pg),
+                           status, vsz, vsz, 0, fn);
+        tcg_temp_free_ptr(status);
     }
-
-    unsigned vsz = vec_full_reg_size(s);
-    unsigned desc;
-    TCGv_i32 t_desc;
-    TCGv_ptr pg = tcg_temp_new_ptr();
-
-    /* We would need 7 operands to pass these arguments "properly".
-     * So we encode all the register numbers into the descriptor.
-     */
-    desc = deposit32(a->rd, 5, 5, a->rn);
-    desc = deposit32(desc, 10, 5, a->rm);
-    desc = deposit32(desc, 15, 5, a->ra);
-    desc = simd_desc(vsz, vsz, desc);
-
-    t_desc = tcg_const_i32(desc);
-    tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg));
-    fn(cpu_env, pg, t_desc);
-    tcg_temp_free_i32(t_desc);
-    tcg_temp_free_ptr(pg);
     return true;
 }
 
 #define DO_FMLA(NAME, name) \
 static bool trans_##NAME(DisasContext *s, arg_rprrr_esz *a)          \
 {                                                                    \
-    static gen_helper_sve_fmla * const fns[4] = {                    \
+    static gen_helper_gvec_5_ptr * const fns[4] = {                  \
         NULL, gen_helper_sve_##name##_h,                             \
         gen_helper_sve_##name##_s, gen_helper_sve_##name##_d         \
     };                                                               \
@@ -XXX,XX +XXX,XX @@ DO_FMLA(FNMLS_zpzzz, fnmls_zpzzz)
 
 static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a)
 {
-    static gen_helper_sve_fmla * const fns[3] = {
+    static gen_helper_gvec_5_ptr * const fns[4] = {
+        NULL,
         gen_helper_sve_fcmla_zpzzz_h,
         gen_helper_sve_fcmla_zpzzz_s,
         gen_helper_sve_fcmla_zpzzz_d,
@@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a)
     }
     if (sve_access_check(s)) {
         unsigned vsz = vec_full_reg_size(s);
-        unsigned desc;
-        TCGv_i32 t_desc;
-        TCGv_ptr pg = tcg_temp_new_ptr();
-
-        /* We would need 7 operands to pass these arguments "properly".
-         * So we encode all the register numbers into the descriptor.
-         */
-        desc = deposit32(a->rd, 5, 5, a->rn);
-        desc = deposit32(desc, 10, 5, a->rm);
-        desc = deposit32(desc, 15, 5, a->ra);
-        desc = deposit32(desc, 20, 2, a->rot);
-        desc = sextract32(desc, 0, 22);
-        desc = simd_desc(vsz, vsz, desc);
-
-        t_desc = tcg_const_i32(desc);
-        tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg));
-        fns[a->esz - 1](cpu_env, pg, t_desc);
-        tcg_temp_free_i32(t_desc);
-        tcg_temp_free_ptr(pg);
+        TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16);
+        tcg_gen_gvec_5_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),
+                           pred_full_reg_offset(s, a->pg),
+                           status, vsz, vsz, a->rot, fns[a->esz]);
+        tcg_temp_free_ptr(status);
     }
     return true;
 }
-- 
2.20.1

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

DUP (indexed) can duplicate 128-bit elements, so using esz
unconditionally can assert in tcg_gen_gvec_dup_imm.

Fixes: 8711e71f9cbb
Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Message-id: 20200507172352.15418-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/translate-sve.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

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_DUP_x(DisasContext *s, arg_DUP_x *a)
             unsigned nofs = vec_reg_offset(s, a->rn, index, esz);
             tcg_gen_gvec_dup_mem(esz, dofs, nofs, vsz, vsz);
         } else {
-            tcg_gen_gvec_dup_imm(esz, dofs, vsz, vsz, 0);
+            /*
+             * While dup_mem handles 128-bit elements, dup_imm does not.
+             * Thankfully element size doesn't matter for splatting zero.
+             */
+            tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0);
         }
     }
     return true;
-- 
2.20.1

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