Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20220302' into staging

target-arm queue:
 * mps3-an547: Add missing user ahb interfaces
 * hw/arm/mps2-tz.c: Update AN547 documentation URL
 * hw/input/tsc210x: Don't abort on bad SPI word widths
 * hw/i2c: flatten pca954x mux device
 * target/arm: Support PSCI 1.1 and SMCCC 1.0
 * target/arm: Fix early free of TCG temp in handle_simd_shift_fpint_conv()
 * tests/qtest: add qtests for npcm7xx sdhci
 * Implement FEAT_LVA
 * Implement FEAT_LPA
 * Implement FEAT_LPA2 (but do not enable it yet)
 * Report KVM's actual PSCI version to guest in dtb
 * ui/cocoa.m: Fix updateUIInfo threading issues
 * ui/cocoa.m: Remove unnecessary NSAutoreleasePools

# gpg: Signature made Wed 02 Mar 2022 20:52:06 GMT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20220302: (26 commits)
  ui/cocoa.m: Remove unnecessary NSAutoreleasePools
  ui/cocoa.m: Fix updateUIInfo threading issues
  target/arm: Report KVM's actual PSCI version to guest in dtb
  target/arm: Implement FEAT_LPA2
  target/arm: Advertise all page sizes for -cpu max
  target/arm: Validate tlbi TG matches translation granule in use
  target/arm: Fix TLBIRange.base for 16k and 64k pages
  target/arm: Introduce tlbi_aa64_get_range
  target/arm: Extend arm_fi_to_lfsc to level -1
  target/arm: Implement FEAT_LPA
  target/arm: Implement FEAT_LVA
  target/arm: Prepare DBGBVR and DBGWVR for FEAT_LVA
  target/arm: Honor TCR_ELx.{I}PS
  target/arm: Use MAKE_64BIT_MASK to compute indexmask
  target/arm: Pass outputsize down to check_s2_mmu_setup
  target/arm: Move arm_pamax out of line
  target/arm: Fault on invalid TCR_ELx.TxSZ
  target/arm: Set TCR_EL1.TSZ for user-only
  hw/registerfields: Add FIELD_SEX<N> and FIELD_SDP<N>
  tests/qtest: add qtests for npcm7xx sdhci
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

20 files changed, 737 insertions, 193 deletions

diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index 144dc49..520fd39 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -24,9 +24,12 @@ the following architecture extensions:
 - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions)
 - FEAT_JSCVT (JavaScript conversion instructions)
 - FEAT_LOR (Limited ordering regions)
+- FEAT_LPA (Large Physical Address space)
+- FEAT_LPA2 (Large Physical and virtual Address space v2)
 - FEAT_LRCPC (Load-acquire RCpc instructions)
 - FEAT_LRCPC2 (Load-acquire RCpc instructions v2)
 - FEAT_LSE (Large System Extensions)
+- FEAT_LVA (Large Virtual Address space)
 - FEAT_MTE (Memory Tagging Extension)
 - FEAT_MTE2 (Memory Tagging Extension)
 - FEAT_MTE3 (MTE Asymmetric Fault Handling)
diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index b1e9597..a47f38d 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -488,9 +488,14 @@ static void fdt_add_psci_node(void *fdt)
     }
 
     qemu_fdt_add_subnode(fdt, "/psci");
-    if (armcpu->psci_version == 2) {
-        const char comp[] = "arm,psci-0.2\0arm,psci";
-        qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp));
+    if (armcpu->psci_version >= QEMU_PSCI_VERSION_0_2) {
+        if (armcpu->psci_version < QEMU_PSCI_VERSION_1_0) {
+            const char comp[] = "arm,psci-0.2\0arm,psci";
+            qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp));
+        } else {
+            const char comp[] = "arm,psci-1.0\0arm,psci-0.2\0arm,psci";
+            qemu_fdt_setprop(fdt, "/psci", "compatible", comp, sizeof(comp));
+        }
 
         cpu_off_fn = QEMU_PSCI_0_2_FN_CPU_OFF;
         if (arm_feature(&armcpu->env, ARM_FEATURE_AARCH64)) {
diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index f40e854..4017392 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -32,7 +32,7 @@
  * Application Note AN524:
  * https://developer.arm.com/documentation/dai0524/latest/
  * Application Note AN547:
- * https://developer.arm.com/-/media/Arm%20Developer%20Community/PDF/DAI0547B_SSE300_PLUS_U55_FPGA_for_mps3.pdf
+ * https://developer.arm.com/documentation/dai0547/latest/
  *
  * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide
  * (ARM ECM0601256) for the details of some of the device layout:
@@ -1078,6 +1078,10 @@ static void mps2tz_common_init(MachineState *machine)
                 { "gpio1", make_unimp_dev, &mms->gpio[1], 0x41101000, 0x1000 },
                 { "gpio2", make_unimp_dev, &mms->gpio[2], 0x41102000, 0x1000 },
                 { "gpio3", make_unimp_dev, &mms->gpio[3], 0x41103000, 0x1000 },
+                { /* port 4 USER AHB interface 0 */ },
+                { /* port 5 USER AHB interface 1 */ },
+                { /* port 6 USER AHB interface 2 */ },
+                { /* port 7 USER AHB interface 3 */ },
                 { "eth-usb", make_eth_usb, NULL, 0x41400000, 0x200000, { 49 } },
             },
         },
diff --git a/hw/i2c/i2c_mux_pca954x.c b/hw/i2c/i2c_mux_pca954x.c
index 847c599..a9517b6 100644
--- a/hw/i2c/i2c_mux_pca954x.c
+++ b/hw/i2c/i2c_mux_pca954x.c
@@ -31,24 +31,6 @@
 #define PCA9546_CHANNEL_COUNT 4
 
 /*
- * struct Pca954xChannel - The i2c mux device will have N of these states
- * that own the i2c channel bus.
- * @bus: The owned channel bus.
- * @enabled: Is this channel active?
- */
-typedef struct Pca954xChannel {
-    SysBusDevice parent;
-
-    I2CBus       *bus;
-
-    bool         enabled;
-} Pca954xChannel;
-
-#define TYPE_PCA954X_CHANNEL "pca954x-channel"
-#define PCA954X_CHANNEL(obj) \
-    OBJECT_CHECK(Pca954xChannel, (obj), TYPE_PCA954X_CHANNEL)
-
-/*
  * struct Pca954xState - The pca954x state object.
  * @control: The value written to the mux control.
  * @channel: The set of i2c channel buses that act as channels which own the
@@ -59,8 +41,8 @@ typedef struct Pca954xState {
 
     uint8_t control;
 
-    /* The channel i2c buses. */
-    Pca954xChannel channel[PCA9548_CHANNEL_COUNT];
+    bool enabled[PCA9548_CHANNEL_COUNT];
+    I2CBus *bus[PCA9548_CHANNEL_COUNT];
 } Pca954xState;
 
 /*
@@ -98,11 +80,11 @@ static bool pca954x_match(I2CSlave *candidate, uint8_t address,
     }
 
     for (i = 0; i < mc->nchans; i++) {
-        if (!mux->channel[i].enabled) {
+        if (!mux->enabled[i]) {
             continue;
         }
 
-        if (i2c_scan_bus(mux->channel[i].bus, address, broadcast,
+        if (i2c_scan_bus(mux->bus[i], address, broadcast,
                          current_devs)) {
             if (!broadcast) {
                 return true;
@@ -125,9 +107,9 @@ static void pca954x_enable_channel(Pca954xState *s, uint8_t enable_mask)
      */
     for (i = 0; i < mc->nchans; i++) {
         if (enable_mask & (1 << i)) {
-            s->channel[i].enabled = true;
+            s->enabled[i] = true;
         } else {
-            s->channel[i].enabled = false;
+            s->enabled[i] = false;
         }
     }
 }
@@ -184,23 +166,7 @@ I2CBus *pca954x_i2c_get_bus(I2CSlave *mux, uint8_t channel)
     Pca954xState *pca954x = PCA954X(mux);
 
     g_assert(channel < pc->nchans);
-    return I2C_BUS(qdev_get_child_bus(DEVICE(&pca954x->channel[channel]),
-                                      "i2c-bus"));
-}
-
-static void pca954x_channel_init(Object *obj)
-{
-    Pca954xChannel *s = PCA954X_CHANNEL(obj);
-    s->bus = i2c_init_bus(DEVICE(s), "i2c-bus");
-
-    /* Start all channels as disabled. */
-    s->enabled = false;
-}
-
-static void pca954x_channel_class_init(ObjectClass *klass, void *data)
-{
-    DeviceClass *dc = DEVICE_CLASS(klass);
-    dc->desc = "Pca954x Channel";
+    return pca954x->bus[channel];
 }
 
 static void pca9546_class_init(ObjectClass *klass, void *data)
@@ -215,28 +181,19 @@ static void pca9548_class_init(ObjectClass *klass, void *data)
     s->nchans = PCA9548_CHANNEL_COUNT;
 }
 
-static void pca954x_realize(DeviceState *dev, Error **errp)
-{
-    Pca954xState *s = PCA954X(dev);
-    Pca954xClass *c = PCA954X_GET_CLASS(s);
-    int i;
-
-    /* SMBus modules. Cannot fail. */
-    for (i = 0; i < c->nchans; i++) {
-        sysbus_realize(SYS_BUS_DEVICE(&s->channel[i]), &error_abort);
-    }
-}
-
 static void pca954x_init(Object *obj)
 {
     Pca954xState *s = PCA954X(obj);
     Pca954xClass *c = PCA954X_GET_CLASS(obj);
     int i;
 
-    /* Only initialize the children we expect. */
+    /* SMBus modules. Cannot fail. */
     for (i = 0; i < c->nchans; i++) {
-        object_initialize_child(obj, "channel[*]", &s->channel[i],
-                                TYPE_PCA954X_CHANNEL);
+        g_autofree gchar *bus_name = g_strdup_printf("i2c.%d", i);
+
+        /* start all channels as disabled. */
+        s->enabled[i] = false;
+        s->bus[i] = i2c_init_bus(DEVICE(s), bus_name);
     }
 }
 
@@ -252,7 +209,6 @@ static void pca954x_class_init(ObjectClass *klass, void *data)
     rc->phases.enter = pca954x_enter_reset;
 
     dc->desc = "Pca954x i2c-mux";
-    dc->realize = pca954x_realize;
 
     k->write_data = pca954x_write_data;
     k->receive_byte = pca954x_read_byte;
@@ -278,13 +234,6 @@ static const TypeInfo pca954x_info[] = {
         .parent        = TYPE_PCA954X,
         .class_init    = pca9548_class_init,
     },
-    {
-        .name = TYPE_PCA954X_CHANNEL,
-        .parent = TYPE_SYS_BUS_DEVICE,
-        .class_init = pca954x_channel_class_init,
-        .instance_size = sizeof(Pca954xChannel),
-        .instance_init = pca954x_channel_init,
-    }
 };
 
 DEFINE_TYPES(pca954x_info)
diff --git a/hw/input/tsc210x.c b/hw/input/tsc210x.c
index b0d5c2d..df7313d 100644
--- a/hw/input/tsc210x.c
+++ b/hw/input/tsc210x.c
@@ -24,6 +24,7 @@
 #include "hw/hw.h"
 #include "audio/audio.h"
 #include "qemu/timer.h"
+#include "qemu/log.h"
 #include "sysemu/reset.h"
 #include "ui/console.h"
 #include "hw/arm/omap.h"            /* For I2SCodec */
@@ -910,8 +911,11 @@ uint32_t tsc210x_txrx(void *opaque, uint32_t value, int len)
     TSC210xState *s = opaque;
     uint32_t ret = 0;
 
-    if (len != 16)
-        hw_error("%s: FIXME: bad SPI word width %i\n", __func__, len);
+    if (len != 16) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: bad SPI word width %i\n", __func__, len);
+        return 0;
+    }
 
     /* TODO: sequential reads etc - how do we make sure the host doesn't
      * unintentionally read out a conversion result from a register while
diff --git a/include/hw/registerfields.h b/include/hw/registerfields.h
index f2a3c9c..3a88e13 100644
--- a/include/hw/registerfields.h
+++ b/include/hw/registerfields.h
@@ -59,6 +59,19 @@
     extract64((storage), R_ ## reg ## _ ## field ## _SHIFT,               \
               R_ ## reg ## _ ## field ## _LENGTH)
 
+#define FIELD_SEX8(storage, reg, field)                                   \
+    sextract8((storage), R_ ## reg ## _ ## field ## _SHIFT,               \
+              R_ ## reg ## _ ## field ## _LENGTH)
+#define FIELD_SEX16(storage, reg, field)                                  \
+    sextract16((storage), R_ ## reg ## _ ## field ## _SHIFT,              \
+               R_ ## reg ## _ ## field ## _LENGTH)
+#define FIELD_SEX32(storage, reg, field)                                  \
+    sextract32((storage), R_ ## reg ## _ ## field ## _SHIFT,              \
+               R_ ## reg ## _ ## field ## _LENGTH)
+#define FIELD_SEX64(storage, reg, field)                                  \
+    sextract64((storage), R_ ## reg ## _ ## field ## _SHIFT,              \
+               R_ ## reg ## _ ## field ## _LENGTH)
+
 /* Extract a field from an array of registers */
 #define ARRAY_FIELD_EX32(regs, reg, field)                                \
     FIELD_EX32((regs)[R_ ## reg], reg, field)
@@ -95,7 +108,40 @@
     _d; })
 #define FIELD_DP64(storage, reg, field, val) ({                           \
     struct {                                                              \
-        uint64_t v:R_ ## reg ## _ ## field ## _LENGTH;                \
+        uint64_t v:R_ ## reg ## _ ## field ## _LENGTH;                    \
+    } _v = { .v = val };                                                  \
+    uint64_t _d;                                                          \
+    _d = deposit64((storage), R_ ## reg ## _ ## field ## _SHIFT,          \
+                  R_ ## reg ## _ ## field ## _LENGTH, _v.v);              \
+    _d; })
+
+#define FIELD_SDP8(storage, reg, field, val) ({                           \
+    struct {                                                              \
+        signed int v:R_ ## reg ## _ ## field ## _LENGTH;                  \
+    } _v = { .v = val };                                                  \
+    uint8_t _d;                                                           \
+    _d = deposit32((storage), R_ ## reg ## _ ## field ## _SHIFT,          \
+                  R_ ## reg ## _ ## field ## _LENGTH, _v.v);              \
+    _d; })
+#define FIELD_SDP16(storage, reg, field, val) ({                          \
+    struct {                                                              \
+        signed int v:R_ ## reg ## _ ## field ## _LENGTH;                  \
+    } _v = { .v = val };                                                  \
+    uint16_t _d;                                                          \
+    _d = deposit32((storage), R_ ## reg ## _ ## field ## _SHIFT,          \
+                  R_ ## reg ## _ ## field ## _LENGTH, _v.v);              \
+    _d; })
+#define FIELD_SDP32(storage, reg, field, val) ({                          \
+    struct {                                                              \
+        signed int v:R_ ## reg ## _ ## field ## _LENGTH;                  \
+    } _v = { .v = val };                                                  \
+    uint32_t _d;                                                          \
+    _d = deposit32((storage), R_ ## reg ## _ ## field ## _SHIFT,          \
+                  R_ ## reg ## _ ## field ## _LENGTH, _v.v);              \
+    _d; })
+#define FIELD_SDP64(storage, reg, field, val) ({                          \
+    struct {                                                              \
+        int64_t v:R_ ## reg ## _ ## field ## _LENGTH;                     \
     } _v = { .v = val };                                                  \
     uint64_t _d;                                                          \
     _d = deposit64((storage), R_ ## reg ## _ ## field ## _SHIFT,          \
diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h
index 7f38d33..b59d505 100644
--- a/target/arm/cpu-param.h
+++ b/target/arm/cpu-param.h
@@ -10,8 +10,8 @@
 
 #ifdef TARGET_AARCH64
 # define TARGET_LONG_BITS             64
-# define TARGET_PHYS_ADDR_SPACE_BITS  48
-# define TARGET_VIRT_ADDR_SPACE_BITS  48
+# define TARGET_PHYS_ADDR_SPACE_BITS  52
+# define TARGET_VIRT_ADDR_SPACE_BITS  52
 #else
 # define TARGET_LONG_BITS             32
 # define TARGET_PHYS_ADDR_SPACE_BITS  40
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index c085dc1..7091684 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -206,10 +206,11 @@ static void arm_cpu_reset(DeviceState *dev)
                 aarch64_sve_zcr_get_valid_len(cpu, cpu->sve_default_vq - 1);
         }
         /*
+         * Enable 48-bit address space (TODO: take reserved_va into account).
          * Enable TBI0 but not TBI1.
          * Note that this must match useronly_clean_ptr.
          */
-        env->cp15.tcr_el[1].raw_tcr = (1ULL << 37);
+        env->cp15.tcr_el[1].raw_tcr = 5 | (1ULL << 37);
 
         /* Enable MTE */
         if (cpu_isar_feature(aa64_mte, cpu)) {
@@ -1110,11 +1111,12 @@ static void arm_cpu_initfn(Object *obj)
      * picky DTB consumer will also provide a helpful error message.
      */
     cpu->dtb_compatible = "qemu,unknown";
-    cpu->psci_version = 1; /* By default assume PSCI v0.1 */
+    cpu->psci_version = QEMU_PSCI_VERSION_0_1; /* By default assume PSCI v0.1 */
     cpu->kvm_target = QEMU_KVM_ARM_TARGET_NONE;
 
     if (tcg_enabled() || hvf_enabled()) {
-        cpu->psci_version = 2; /* TCG and HVF implement PSCI 0.2 */
+        /* TCG and HVF implement PSCI 1.1 */
+        cpu->psci_version = QEMU_PSCI_VERSION_1_1;
     }
 }
 
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index c6a4d50..24d9fff 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -4284,11 +4284,38 @@ static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0;
 }
 
+static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id)
+{
+    return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1;
+}
+
+static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id)
+{
+    unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2);
+    return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id));
+}
+
+static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2;
+}
+
+static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id)
+{
+    unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2);
+    return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id));
+}
+
 static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0;
 }
 
+static inline bool isar_feature_aa64_lva(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0;
+}
+
 static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0;
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 1171ab1..2fdc16b 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -795,7 +795,11 @@ static void aarch64_max_initfn(Object *obj)
     cpu->isar.id_aa64pfr1 = t;
 
     t = cpu->isar.id_aa64mmfr0;
-    t = FIELD_DP64(t, ID_AA64MMFR0, PARANGE, 5); /* PARange: 48 bits */
+    t = FIELD_DP64(t, ID_AA64MMFR0, PARANGE, 6); /* FEAT_LPA: 52 bits */
+    t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16, 1);   /* 16k pages supported */
+    t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16_2, 2); /* 16k stage2 supported */
+    t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN64_2, 2); /* 64k stage2 supported */
+    t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN4_2, 2);  /*  4k stage2 supported */
     cpu->isar.id_aa64mmfr0 = t;
 
     t = cpu->isar.id_aa64mmfr1;
@@ -811,6 +815,7 @@ static void aarch64_max_initfn(Object *obj)
     t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1);
     t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* TTCNP */
     t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* TTST */
+    t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */
     cpu->isar.id_aa64mmfr2 = t;
 
     t = cpu->isar.id_aa64zfr0;
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 7bf50fd..088956e 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -4511,70 +4511,73 @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
 }
 
 #ifdef TARGET_AARCH64
-static uint64_t tlbi_aa64_range_get_length(CPUARMState *env,
-                                           uint64_t value)
-{
-    unsigned int page_shift;
-    unsigned int page_size_granule;
-    uint64_t num;
-    uint64_t scale;
-    uint64_t exponent;
+typedef struct {
+    uint64_t base;
     uint64_t length;
+} TLBIRange;
+
+static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx,
+                                     uint64_t value)
+{
+    unsigned int page_size_granule, page_shift, num, scale, exponent;
+    /* Extract one bit to represent the va selector in use. */
+    uint64_t select = sextract64(value, 36, 1);
+    ARMVAParameters param = aa64_va_parameters(env, select, mmuidx, true);
+    TLBIRange ret = { };
 
-    num = extract64(value, 39, 5);
-    scale = extract64(value, 44, 2);
     page_size_granule = extract64(value, 46, 2);
 
-    if (page_size_granule == 0) {
-        qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n",
+    /* The granule encoded in value must match the granule in use. */
+    if (page_size_granule != (param.using64k ? 3 : param.using16k ? 2 : 1)) {
+        qemu_log_mask(LOG_GUEST_ERROR, "Invalid tlbi page size granule %d\n",
                       page_size_granule);
-        return 0;
+        return ret;
     }
 
     page_shift = (page_size_granule - 1) * 2 + 12;
-
+    num = extract64(value, 39, 5);
+    scale = extract64(value, 44, 2);
     exponent = (5 * scale) + 1;
-    length = (num + 1) << (exponent + page_shift);
 
-    return length;
-}
+    ret.length = (num + 1) << (exponent + page_shift);
 
-static uint64_t tlbi_aa64_range_get_base(CPUARMState *env, uint64_t value,
-                                        bool two_ranges)
-{
-    /* TODO: ARMv8.7 FEAT_LPA2 */
-    uint64_t pageaddr;
-
-    if (two_ranges) {
-        pageaddr = sextract64(value, 0, 37) << TARGET_PAGE_BITS;
+    if (param.select) {
+        ret.base = sextract64(value, 0, 37);
     } else {
-        pageaddr = extract64(value, 0, 37) << TARGET_PAGE_BITS;
+        ret.base = extract64(value, 0, 37);
+    }
+    if (param.ds) {
+        /*
+         * With DS=1, BaseADDR is always shifted 16 so that it is able
+         * to address all 52 va bits.  The input address is perforce
+         * aligned on a 64k boundary regardless of translation granule.
+         */
+        page_shift = 16;
     }
+    ret.base <<= page_shift;
 
-    return pageaddr;
+    return ret;
 }
 
 static void do_rvae_write(CPUARMState *env, uint64_t value,
                           int idxmap, bool synced)
 {
     ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap);
-    bool two_ranges = regime_has_2_ranges(one_idx);
-    uint64_t baseaddr, length;
+    TLBIRange range;
     int bits;
 
-    baseaddr = tlbi_aa64_range_get_base(env, value, two_ranges);
-    length = tlbi_aa64_range_get_length(env, value);
-    bits = tlbbits_for_regime(env, one_idx, baseaddr);
+    range = tlbi_aa64_get_range(env, one_idx, value);
+    bits = tlbbits_for_regime(env, one_idx, range.base);
 
     if (synced) {
         tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env),
-                                                  baseaddr,
-                                                  length,
+                                                  range.base,
+                                                  range.length,
                                                   idxmap,
                                                   bits);
     } else {
-        tlb_flush_range_by_mmuidx(env_cpu(env), baseaddr,
-                                  length, idxmap, bits);
+        tlb_flush_range_by_mmuidx(env_cpu(env), range.base,
+                                  range.length, idxmap, bits);
     }
 }
 
@@ -6423,11 +6426,18 @@ static void dbgwvr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     ARMCPU *cpu = env_archcpu(env);
     int i = ri->crm;
 
-    /* Bits [63:49] are hardwired to the value of bit [48]; that is, the
-     * register reads and behaves as if values written are sign extended.
+    /*
      * Bits [1:0] are RES0.
+     *
+     * It is IMPLEMENTATION DEFINED whether [63:49] ([63:53] with FEAT_LVA)
+     * are hardwired to the value of bit [48] ([52] with FEAT_LVA), or if
+     * they contain the value written.  It is CONSTRAINED UNPREDICTABLE
+     * whether the RESS bits are ignored when comparing an address.
+     *
+     * Therefore we are allowed to compare the entire register, which lets
+     * us avoid considering whether or not FEAT_LVA is actually enabled.
      */
-    value = sextract64(value, 0, 49) & ~3ULL;
+    value &= ~3ULL;
 
     raw_write(env, ri, value);
     hw_watchpoint_update(cpu, i);
@@ -6473,10 +6483,19 @@ void hw_breakpoint_update(ARMCPU *cpu, int n)
     case 0: /* unlinked address match */
     case 1: /* linked address match */
     {
-        /* Bits [63:49] are hardwired to the value of bit [48]; that is,
-         * we behave as if the register was sign extended. Bits [1:0] are
-         * RES0. The BAS field is used to allow setting breakpoints on 16
-         * bit wide instructions; it is CONSTRAINED UNPREDICTABLE whether
+        /*
+         * Bits [1:0] are RES0.
+         *
+         * It is IMPLEMENTATION DEFINED whether bits [63:49]
+         * ([63:53] for FEAT_LVA) are hardwired to a copy of the sign bit
+         * of the VA field ([48] or [52] for FEAT_LVA), or whether the
+         * value is read as written.  It is CONSTRAINED UNPREDICTABLE
+         * whether the RESS bits are ignored when comparing an address.
+         * Therefore we are allowed to compare the entire register, which
+         * lets us avoid considering whether FEAT_LVA is actually enabled.
+         *
+         * The BAS field is used to allow setting breakpoints on 16-bit
+         * wide instructions; it is CONSTRAINED UNPREDICTABLE whether
          * a bp will fire if the addresses covered by the bp and the addresses
          * covered by the insn overlap but the insn doesn't start at the
          * start of the bp address range. We choose to require the insn and
@@ -6489,7 +6508,7 @@ void hw_breakpoint_update(ARMCPU *cpu, int n)
          * See also figure D2-3 in the v8 ARM ARM (DDI0487A.c).
          */
         int bas = extract64(bcr, 5, 4);
-        addr = sextract64(bvr, 0, 49) & ~3ULL;
+        addr = bvr & ~3ULL;
         if (bas == 0) {
             return;
         }
@@ -11065,13 +11084,18 @@ do_fault:
  * false otherwise.
  */
 static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level,
-                               int inputsize, int stride)
+                               int inputsize, int stride, int outputsize)
 {
     const int grainsize = stride + 3;
     int startsizecheck;
 
-    /* Negative levels are never allowed.  */
-    if (level < 0) {
+    /*
+     * Negative levels are usually not allowed...
+     * Except for FEAT_LPA2, 4k page table, 52-bit address space, which
+     * begins with level -1.  Note that previous feature tests will have
+     * eliminated this combination if it is not enabled.
+     */
+    if (level < (inputsize == 52 && stride == 9 ? -1 : 0)) {
         return false;
     }
 
@@ -11081,22 +11105,19 @@ static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level,
     }
 
     if (is_aa64) {
-        CPUARMState *env = &cpu->env;
-        unsigned int pamax = arm_pamax(cpu);
-
         switch (stride) {
         case 13: /* 64KB Pages.  */
-            if (level == 0 || (level == 1 && pamax <= 42)) {
+            if (level == 0 || (level == 1 && outputsize <= 42)) {
                 return false;
             }
             break;
         case 11: /* 16KB Pages.  */
-            if (level == 0 || (level == 1 && pamax <= 40)) {
+            if (level == 0 || (level == 1 && outputsize <= 40)) {
                 return false;
             }
             break;
         case 9: /* 4KB Pages.  */
-            if (level == 0 && pamax <= 42) {
+            if (level == 0 && outputsize <= 42) {
                 return false;
             }
             break;
@@ -11105,8 +11126,8 @@ static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level,
         }
 
         /* Inputsize checks.  */
-        if (inputsize > pamax &&
-            (arm_el_is_aa64(env, 1) || inputsize > 40)) {
+        if (inputsize > outputsize &&
+            (arm_el_is_aa64(&cpu->env, 1) || inputsize > 40)) {
             /* This is CONSTRAINED UNPREDICTABLE and we choose to fault.  */
             return false;
         }
@@ -11152,6 +11173,31 @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs)
 }
 #endif /* !CONFIG_USER_ONLY */
 
+/* This mapping is common between ID_AA64MMFR0.PARANGE and TCR_ELx.{I}PS. */
+static const uint8_t pamax_map[] = {
+    [0] = 32,
+    [1] = 36,
+    [2] = 40,
+    [3] = 42,
+    [4] = 44,
+    [5] = 48,
+    [6] = 52,
+};
+
+/* The cpu-specific constant value of PAMax; also used by hw/arm/virt. */
+unsigned int arm_pamax(ARMCPU *cpu)
+{
+    unsigned int parange =
+        FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE);
+
+    /*
+     * id_aa64mmfr0 is a read-only register so values outside of the
+     * supported mappings can be considered an implementation error.
+     */
+    assert(parange < ARRAY_SIZE(pamax_map));
+    return pamax_map[parange];
+}
+
 static int aa64_va_parameter_tbi(uint64_t tcr, ARMMMUIdx mmu_idx)
 {
     if (regime_has_2_ranges(mmu_idx)) {
@@ -11190,8 +11236,9 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
                                    ARMMMUIdx mmu_idx, bool data)
 {
     uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr;
-    bool epd, hpd, using16k, using64k;
-    int select, tsz, tbi, max_tsz;
+    bool epd, hpd, using16k, using64k, tsz_oob, ds;
+    int select, tsz, tbi, max_tsz, min_tsz, ps, sh;
+    ARMCPU *cpu = env_archcpu(env);
 
     if (!regime_has_2_ranges(mmu_idx)) {
         select = 0;
@@ -11205,6 +11252,9 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
             hpd = extract32(tcr, 24, 1);
         }
         epd = false;
+        sh = extract32(tcr, 12, 2);
+        ps = extract32(tcr, 16, 3);
+        ds = extract64(tcr, 32, 1);
     } else {
         /*
          * Bit 55 is always between the two regions, and is canonical for
@@ -11214,6 +11264,7 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
         if (!select) {
             tsz = extract32(tcr, 0, 6);
             epd = extract32(tcr, 7, 1);
+            sh = extract32(tcr, 12, 2);
             using64k = extract32(tcr, 14, 1);
             using16k = extract32(tcr, 15, 1);
             hpd = extract64(tcr, 41, 1);
@@ -11223,18 +11274,61 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
             using64k = tg == 3;
             tsz = extract32(tcr, 16, 6);
             epd = extract32(tcr, 23, 1);
+            sh = extract32(tcr, 28, 2);
             hpd = extract64(tcr, 42, 1);
         }
+        ps = extract64(tcr, 32, 3);
+        ds = extract64(tcr, 59, 1);
     }
 
-    if (cpu_isar_feature(aa64_st, env_archcpu(env))) {
+    if (cpu_isar_feature(aa64_st, cpu)) {
         max_tsz = 48 - using64k;
     } else {
         max_tsz = 39;
     }
 
-    tsz = MIN(tsz, max_tsz);
-    tsz = MAX(tsz, 16);  /* TODO: ARMv8.2-LVA  */
+    /*
+     * DS is RES0 unless FEAT_LPA2 is supported for the given page size;
+     * adjust the effective value of DS, as documented.
+     */
+    min_tsz = 16;
+    if (using64k) {
+        if (cpu_isar_feature(aa64_lva, cpu)) {
+            min_tsz = 12;
+        }
+        ds = false;
+    } else if (ds) {
+        switch (mmu_idx) {
+        case ARMMMUIdx_Stage2:
+        case ARMMMUIdx_Stage2_S:
+            if (using16k) {
+                ds = cpu_isar_feature(aa64_tgran16_2_lpa2, cpu);
+            } else {
+                ds = cpu_isar_feature(aa64_tgran4_2_lpa2, cpu);
+            }
+            break;
+        default:
+            if (using16k) {
+                ds = cpu_isar_feature(aa64_tgran16_lpa2, cpu);
+            } else {
+                ds = cpu_isar_feature(aa64_tgran4_lpa2, cpu);
+            }
+            break;
+        }
+        if (ds) {
+            min_tsz = 12;
+        }
+    }
+
+    if (tsz > max_tsz) {
+        tsz = max_tsz;
+        tsz_oob = true;
+    } else if (tsz < min_tsz) {
+        tsz = min_tsz;
+        tsz_oob = true;
+    } else {
+        tsz_oob = false;
+    }
 
     /* Present TBI as a composite with TBID.  */
     tbi = aa64_va_parameter_tbi(tcr, mmu_idx);
@@ -11245,12 +11339,16 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
 
     return (ARMVAParameters) {
         .tsz = tsz,
+        .ps = ps,
+        .sh = sh,
         .select = select,
         .tbi = tbi,
         .epd = epd,
         .hpd = hpd,
         .using16k = using16k,
         .using64k = using64k,
+        .tsz_oob = tsz_oob,
+        .ds = ds,
     };
 }
 
@@ -11361,7 +11459,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
     target_ulong page_size;
     uint32_t attrs;
     int32_t stride;
-    int addrsize, inputsize;
+    int addrsize, inputsize, outputsize;
     TCR *tcr = regime_tcr(env, mmu_idx);
     int ap, ns, xn, pxn;
     uint32_t el = regime_el(env, mmu_idx);
@@ -11371,16 +11469,44 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
 
     /* TODO: This code does not support shareability levels. */
     if (aarch64) {
+        int ps;
+
         param = aa64_va_parameters(env, address, mmu_idx,
                                    access_type != MMU_INST_FETCH);
         level = 0;
+
+        /*
+         * If TxSZ is programmed to a value larger than the maximum,
+         * or smaller than the effective minimum, it is IMPLEMENTATION
+         * DEFINED whether we behave as if the field were programmed
+         * within bounds, or if a level 0 Translation fault is generated.
+         *
+         * With FEAT_LVA, fault on less than minimum becomes required,
+         * so our choice is to always raise the fault.
+         */
+        if (param.tsz_oob) {
+            fault_type = ARMFault_Translation;
+            goto do_fault;
+        }
+
         addrsize = 64 - 8 * param.tbi;
         inputsize = 64 - param.tsz;
+
+        /*
+         * Bound PS by PARANGE to find the effective output address size.
+         * ID_AA64MMFR0 is a read-only register so values outside of the
+         * supported mappings can be considered an implementation error.
+         */
+        ps = FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE);
+        ps = MIN(ps, param.ps);
+        assert(ps < ARRAY_SIZE(pamax_map));
+        outputsize = pamax_map[ps];
     } else {
         param = aa32_va_parameters(env, address, mmu_idx);
         level = 1;
         addrsize = (mmu_idx == ARMMMUIdx_Stage2 ? 40 : 32);
         inputsize = addrsize - param.tsz;
+        outputsize = 40;
     }
 
     /*
@@ -11448,10 +11574,19 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
          * VTCR_EL2.SL0 field (whose interpretation depends on the page size)
          */
         uint32_t sl0 = extract32(tcr->raw_tcr, 6, 2);
+        uint32_t sl2 = extract64(tcr->raw_tcr, 33, 1);
         uint32_t startlevel;
         bool ok;
 
-        if (!aarch64 || stride == 9) {
+        /* SL2 is RES0 unless DS=1 & 4kb granule. */
+        if (param.ds && stride == 9 && sl2) {
+            if (sl0 != 0) {
+                level = 0;
+                fault_type = ARMFault_Translation;
+                goto do_fault;
+            }
+            startlevel = -1;
+        } else if (!aarch64 || stride == 9) {
             /* AArch32 or 4KB pages */
             startlevel = 2 - sl0;
 
@@ -11465,7 +11600,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
 
         /* Check that the starting level is valid. */
         ok = check_s2_mmu_setup(cpu, aarch64, startlevel,
-                                inputsize, stride);
+                                inputsize, stride, outputsize);
         if (!ok) {
             fault_type = ARMFault_Translation;
             goto do_fault;
@@ -11473,24 +11608,49 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
         level = startlevel;
     }
 
-    indexmask_grainsize = (1ULL << (stride + 3)) - 1;
-    indexmask = (1ULL << (inputsize - (stride * (4 - level)))) - 1;
+    indexmask_grainsize = MAKE_64BIT_MASK(0, stride + 3);
+    indexmask = MAKE_64BIT_MASK(0, inputsize - (stride * (4 - level)));
 
     /* Now we can extract the actual base address from the TTBR */
     descaddr = extract64(ttbr, 0, 48);
+
+    /*
+     * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [5:2] of TTBR.
+     *
+     * Otherwise, if the base address is out of range, raise AddressSizeFault.
+     * In the pseudocode, this is !IsZero(baseregister<47:outputsize>),
+     * but we've just cleared the bits above 47, so simplify the test.
+     */
+    if (outputsize > 48) {
+        descaddr |= extract64(ttbr, 2, 4) << 48;
+    } else if (descaddr >> outputsize) {
+        level = 0;
+        fault_type = ARMFault_AddressSize;
+        goto do_fault;
+    }
+
     /*
      * We rely on this masking to clear the RES0 bits at the bottom of the TTBR
      * and also to mask out CnP (bit 0) which could validly be non-zero.
      */
     descaddr &= ~indexmask;
 
-    /* The address field in the descriptor goes up to bit 39 for ARMv7
-     * but up to bit 47 for ARMv8, but we use the descaddrmask
-     * up to bit 39 for AArch32, because we don't need other bits in that case
-     * to construct next descriptor address (anyway they should be all zeroes).
-     */
-    descaddrmask = ((1ull << (aarch64 ? 48 : 40)) - 1) &
-                   ~indexmask_grainsize;
+    /*
+     * For AArch32, the address field in the descriptor goes up to bit 39
+     * for both v7 and v8.  However, for v8 the SBZ bits [47:40] must be 0
+     * or an AddressSize fault is raised.  So for v8 we extract those SBZ
+     * bits as part of the address, which will be checked via outputsize.
+     * For AArch64, the address field goes up to bit 47, or 49 with FEAT_LPA2;
+     * the highest bits of a 52-bit output are placed elsewhere.
+     */
+    if (param.ds) {
+        descaddrmask = MAKE_64BIT_MASK(0, 50);
+    } else if (arm_feature(env, ARM_FEATURE_V8)) {
+        descaddrmask = MAKE_64BIT_MASK(0, 48);
+    } else {
+        descaddrmask = MAKE_64BIT_MASK(0, 40);
+    }
+    descaddrmask &= ~indexmask_grainsize;
 
     /* Secure accesses start with the page table in secure memory and
      * can be downgraded to non-secure at any step. Non-secure accesses
@@ -11515,8 +11675,26 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
             /* Invalid, or the Reserved level 3 encoding */
             goto do_fault;
         }
+
         descaddr = descriptor & descaddrmask;
 
+        /*
+         * For FEAT_LPA and PS=6, bits [51:48] of descaddr are in [15:12]
+         * of descriptor.  For FEAT_LPA2 and effective DS, bits [51:50] of
+         * descaddr are in [9:8].  Otherwise, if descaddr is out of range,
+         * raise AddressSizeFault.
+         */
+        if (outputsize > 48) {
+            if (param.ds) {
+                descaddr |= extract64(descriptor, 8, 2) << 50;
+            } else {
+                descaddr |= extract64(descriptor, 12, 4) << 48;
+            }
+        } else if (descaddr >> outputsize) {
+            fault_type = ARMFault_AddressSize;
+            goto do_fault;
+        }
+
         if ((descriptor & 2) && (level < 3)) {
             /* Table entry. The top five bits are attributes which may
              * propagate down through lower levels of the table (and
@@ -11605,7 +11783,17 @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address,
         assert(attrindx <= 7);
         cacheattrs->attrs = extract64(mair, attrindx * 8, 8);
     }
-    cacheattrs->shareability = extract32(attrs, 6, 2);
+
+    /*
+     * For FEAT_LPA2 and effective DS, the SH field in the attributes
+     * was re-purposed for output address bits.  The SH attribute in
+     * that case comes from TCR_ELx, which we extracted earlier.
+     */
+    if (param.ds) {
+        cacheattrs->shareability = param.sh;
+    } else {
+        cacheattrs->shareability = extract32(attrs, 6, 2);
+    }
 
     *phys_ptr = descaddr;
     *page_size_ptr = page_size;
diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c
index 4d4ddab..8c34f86 100644
--- a/target/arm/hvf/hvf.c
+++ b/target/arm/hvf/hvf.c
@@ -678,7 +678,7 @@ static bool hvf_handle_psci_call(CPUState *cpu)
 
     switch (param[0]) {
     case QEMU_PSCI_0_2_FN_PSCI_VERSION:
-        ret = QEMU_PSCI_0_2_RET_VERSION_0_2;
+        ret = QEMU_PSCI_VERSION_1_1;
         break;
     case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE:
         ret = QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED; /* No trusted OS */
@@ -746,6 +746,31 @@ static bool hvf_handle_psci_call(CPUState *cpu)
     case QEMU_PSCI_0_2_FN_MIGRATE:
         ret = QEMU_PSCI_RET_NOT_SUPPORTED;
         break;
+    case QEMU_PSCI_1_0_FN_PSCI_FEATURES:
+        switch (param[1]) {
+        case QEMU_PSCI_0_2_FN_PSCI_VERSION:
+        case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+        case QEMU_PSCI_0_2_FN_AFFINITY_INFO:
+        case QEMU_PSCI_0_2_FN64_AFFINITY_INFO:
+        case QEMU_PSCI_0_2_FN_SYSTEM_RESET:
+        case QEMU_PSCI_0_2_FN_SYSTEM_OFF:
+        case QEMU_PSCI_0_1_FN_CPU_ON:
+        case QEMU_PSCI_0_2_FN_CPU_ON:
+        case QEMU_PSCI_0_2_FN64_CPU_ON:
+        case QEMU_PSCI_0_1_FN_CPU_OFF:
+        case QEMU_PSCI_0_2_FN_CPU_OFF:
+        case QEMU_PSCI_0_1_FN_CPU_SUSPEND:
+        case QEMU_PSCI_0_2_FN_CPU_SUSPEND:
+        case QEMU_PSCI_0_2_FN64_CPU_SUSPEND:
+        case QEMU_PSCI_1_0_FN_PSCI_FEATURES:
+            ret = 0;
+            break;
+        case QEMU_PSCI_0_1_FN_MIGRATE:
+        case QEMU_PSCI_0_2_FN_MIGRATE:
+        default:
+            ret = QEMU_PSCI_RET_NOT_SUPPORTED;
+        }
+        break;
     default:
         return false;
     }
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 3f05748..a34be2e 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -243,24 +243,7 @@ static inline void update_spsel(CPUARMState *env, uint32_t imm)
  * Returns the implementation defined bit-width of physical addresses.
  * The ARMv8 reference manuals refer to this as PAMax().
  */
-static inline unsigned int arm_pamax(ARMCPU *cpu)
-{
-    static const unsigned int pamax_map[] = {
-        [0] = 32,
-        [1] = 36,
-        [2] = 40,
-        [3] = 42,
-        [4] = 44,
-        [5] = 48,
-    };
-    unsigned int parange =
-        FIELD_EX64(cpu->isar.id_aa64mmfr0, ID_AA64MMFR0, PARANGE);
-
-    /* id_aa64mmfr0 is a read-only register so values outside of the
-     * supported mappings can be considered an implementation error.  */
-    assert(parange < ARRAY_SIZE(pamax_map));
-    return pamax_map[parange];
-}
+unsigned int arm_pamax(ARMCPU *cpu);
 
 /* Return true if extended addresses are enabled.
  * This is always the case if our translation regime is 64 bit,
@@ -479,28 +462,51 @@ static inline uint32_t arm_fi_to_lfsc(ARMMMUFaultInfo *fi)
     case ARMFault_None:
         return 0;
     case ARMFault_AddressSize:
-        fsc = fi->level & 3;
+        assert(fi->level >= -1 && fi->level <= 3);
+        if (fi->level < 0) {
+            fsc = 0b101001;
+        } else {
+            fsc = fi->level;
+        }
         break;
     case ARMFault_AccessFlag:
-        fsc = (fi->level & 3) | (0x2 << 2);
+        assert(fi->level >= 0 && fi->level <= 3);
+        fsc = 0b001000 | fi->level;
         break;
     case ARMFault_Permission:
-        fsc = (fi->level & 3) | (0x3 << 2);
+        assert(fi->level >= 0 && fi->level <= 3);
+        fsc = 0b001100 | fi->level;
         break;
     case ARMFault_Translation:
-        fsc = (fi->level & 3) | (0x1 << 2);
+        assert(fi->level >= -1 && fi->level <= 3);
+        if (fi->level < 0) {
+            fsc = 0b101011;
+        } else {
+            fsc = 0b000100 | fi->level;
+        }
         break;
     case ARMFault_SyncExternal:
         fsc = 0x10 | (fi->ea << 12);
         break;
     case ARMFault_SyncExternalOnWalk:
-        fsc = (fi->level & 3) | (0x5 << 2) | (fi->ea << 12);
+        assert(fi->level >= -1 && fi->level <= 3);
+        if (fi->level < 0) {
+            fsc = 0b010011;
+        } else {
+            fsc = 0b010100 | fi->level;
+        }
+        fsc |= fi->ea << 12;
         break;
     case ARMFault_SyncParity:
         fsc = 0x18;
         break;
     case ARMFault_SyncParityOnWalk:
-        fsc = (fi->level & 3) | (0x7 << 2);
+        assert(fi->level >= -1 && fi->level <= 3);
+        if (fi->level < 0) {
+            fsc = 0b011011;
+        } else {
+            fsc = 0b011100 | fi->level;
+        }
         break;
     case ARMFault_AsyncParity:
         fsc = 0x19;
@@ -1049,12 +1055,16 @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id)
  */
 typedef struct ARMVAParameters {
     unsigned tsz    : 8;
+    unsigned ps     : 3;
+    unsigned sh     : 2;
     unsigned select : 1;
     bool tbi        : 1;
     bool epd        : 1;
     bool hpd        : 1;
     bool using16k   : 1;
     bool using64k   : 1;
+    bool tsz_oob    : 1;  /* tsz has been clamped to legal range */
+    bool ds         : 1;
 } ARMVAParameters;
 
 ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va,
diff --git a/target/arm/kvm-consts.h b/target/arm/kvm-consts.h
index 580f1c1..faacf96 100644
--- a/target/arm/kvm-consts.h
+++ b/target/arm/kvm-consts.h
@@ -77,6 +77,8 @@ MISMATCH_CHECK(QEMU_PSCI_0_1_FN_MIGRATE, KVM_PSCI_FN_MIGRATE);
 #define QEMU_PSCI_0_2_FN64_AFFINITY_INFO QEMU_PSCI_0_2_FN64(4)
 #define QEMU_PSCI_0_2_FN64_MIGRATE QEMU_PSCI_0_2_FN64(5)
 
+#define QEMU_PSCI_1_0_FN_PSCI_FEATURES QEMU_PSCI_0_2_FN(10)
+
 MISMATCH_CHECK(QEMU_PSCI_0_2_FN_CPU_SUSPEND, PSCI_0_2_FN_CPU_SUSPEND);
 MISMATCH_CHECK(QEMU_PSCI_0_2_FN_CPU_OFF, PSCI_0_2_FN_CPU_OFF);
 MISMATCH_CHECK(QEMU_PSCI_0_2_FN_CPU_ON, PSCI_0_2_FN_CPU_ON);
@@ -84,18 +86,22 @@ MISMATCH_CHECK(QEMU_PSCI_0_2_FN_MIGRATE, PSCI_0_2_FN_MIGRATE);
 MISMATCH_CHECK(QEMU_PSCI_0_2_FN64_CPU_SUSPEND, PSCI_0_2_FN64_CPU_SUSPEND);
 MISMATCH_CHECK(QEMU_PSCI_0_2_FN64_CPU_ON, PSCI_0_2_FN64_CPU_ON);
 MISMATCH_CHECK(QEMU_PSCI_0_2_FN64_MIGRATE, PSCI_0_2_FN64_MIGRATE);
+MISMATCH_CHECK(QEMU_PSCI_1_0_FN_PSCI_FEATURES, PSCI_1_0_FN_PSCI_FEATURES);
 
 /* PSCI v0.2 return values used by TCG emulation of PSCI */
 
 /* No Trusted OS migration to worry about when offlining CPUs */
 #define QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED        2
 
-/* We implement version 0.2 only */
-#define QEMU_PSCI_0_2_RET_VERSION_0_2                       2
+#define QEMU_PSCI_VERSION_0_1                     0x00001
+#define QEMU_PSCI_VERSION_0_2                     0x00002
+#define QEMU_PSCI_VERSION_1_0                     0x10000
+#define QEMU_PSCI_VERSION_1_1                     0x10001
 
 MISMATCH_CHECK(QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED, PSCI_0_2_TOS_MP);
-MISMATCH_CHECK(QEMU_PSCI_0_2_RET_VERSION_0_2,
-               (PSCI_VERSION_MAJOR(0) | PSCI_VERSION_MINOR(2)));
+/* We don't bother to check every possible version value */
+MISMATCH_CHECK(QEMU_PSCI_VERSION_0_2, PSCI_VERSION(0, 2));
+MISMATCH_CHECK(QEMU_PSCI_VERSION_1_1, PSCI_VERSION(1, 1));
 
 /* PSCI return values (inclusive of all PSCI versions) */
 #define QEMU_PSCI_RET_SUCCESS                     0
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
index 71c3ca6..ccadfbb 100644
--- a/target/arm/kvm64.c
+++ b/target/arm/kvm64.c
@@ -849,6 +849,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
     uint64_t mpidr;
     ARMCPU *cpu = ARM_CPU(cs);
     CPUARMState *env = &cpu->env;
+    uint64_t psciver;
 
     if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE ||
         !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) {
@@ -864,7 +865,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
         cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_POWER_OFF;
     }
     if (kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PSCI_0_2)) {
-        cpu->psci_version = 2;
+        cpu->psci_version = QEMU_PSCI_VERSION_0_2;
         cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2;
     }
     if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
@@ -905,6 +906,17 @@ int kvm_arch_init_vcpu(CPUState *cs)
     }
 
     /*
+     * KVM reports the exact PSCI version it is implementing via a
+     * special sysreg. If it is present, use its contents to determine
+     * what to report to the guest in the dtb (it is the PSCI version,
+     * in the same 15-bits major 16-bits minor format that PSCI_VERSION
+     * returns).
+     */
+    if (!kvm_get_one_reg(cs, KVM_REG_ARM_PSCI_VERSION, &psciver)) {
+        cpu->psci_version = psciver;
+    }
+
+    /*
      * When KVM is in use, PSCI is emulated in-kernel and not by qemu.
      * Currently KVM has its own idea about MPIDR assignment, so we
      * override our defaults with what we get from KVM.
diff --git a/target/arm/psci.c b/target/arm/psci.c
index b279c0b..6c1239b 100644
--- a/target/arm/psci.c
+++ b/target/arm/psci.c
@@ -57,7 +57,7 @@ void arm_handle_psci_call(ARMCPU *cpu)
 {
     /*
      * This function partially implements the logic for dispatching Power State
-     * Coordination Interface (PSCI) calls (as described in ARM DEN 0022B.b),
+     * Coordination Interface (PSCI) calls (as described in ARM DEN 0022D.b),
      * to the extent required for bringing up and taking down secondary cores,
      * and for handling reset and poweroff requests.
      * Additional information about the calling convention used is available in
@@ -80,7 +80,7 @@ void arm_handle_psci_call(ARMCPU *cpu)
     }
 
     if ((param[0] & QEMU_PSCI_0_2_64BIT) && !is_a64(env)) {
-        ret = QEMU_PSCI_RET_INVALID_PARAMS;
+        ret = QEMU_PSCI_RET_NOT_SUPPORTED;
         goto err;
     }
 
@@ -89,7 +89,7 @@ void arm_handle_psci_call(ARMCPU *cpu)
         ARMCPU *target_cpu;
 
     case QEMU_PSCI_0_2_FN_PSCI_VERSION:
-        ret = QEMU_PSCI_0_2_RET_VERSION_0_2;
+        ret = QEMU_PSCI_VERSION_1_1;
         break;
     case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE:
         ret = QEMU_PSCI_0_2_RET_TOS_MIGRATION_NOT_REQUIRED; /* No trusted OS */
@@ -170,6 +170,35 @@ void arm_handle_psci_call(ARMCPU *cpu)
         }
         helper_wfi(env, 4);
         break;
+    case QEMU_PSCI_1_0_FN_PSCI_FEATURES:
+        switch (param[1]) {
+        case QEMU_PSCI_0_2_FN_PSCI_VERSION:
+        case QEMU_PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+        case QEMU_PSCI_0_2_FN_AFFINITY_INFO:
+        case QEMU_PSCI_0_2_FN64_AFFINITY_INFO:
+        case QEMU_PSCI_0_2_FN_SYSTEM_RESET:
+        case QEMU_PSCI_0_2_FN_SYSTEM_OFF:
+        case QEMU_PSCI_0_1_FN_CPU_ON:
+        case QEMU_PSCI_0_2_FN_CPU_ON:
+        case QEMU_PSCI_0_2_FN64_CPU_ON:
+        case QEMU_PSCI_0_1_FN_CPU_OFF:
+        case QEMU_PSCI_0_2_FN_CPU_OFF:
+        case QEMU_PSCI_0_1_FN_CPU_SUSPEND:
+        case QEMU_PSCI_0_2_FN_CPU_SUSPEND:
+        case QEMU_PSCI_0_2_FN64_CPU_SUSPEND:
+        case QEMU_PSCI_1_0_FN_PSCI_FEATURES:
+            if (!(param[1] & QEMU_PSCI_0_2_64BIT) || is_a64(env)) {
+                ret = 0;
+                break;
+            }
+            /* fallthrough */
+        case QEMU_PSCI_0_1_FN_MIGRATE:
+        case QEMU_PSCI_0_2_FN_MIGRATE:
+        default:
+            ret = QEMU_PSCI_RET_NOT_SUPPORTED;
+            break;
+        }
+        break;
     case QEMU_PSCI_0_1_FN_MIGRATE:
     case QEMU_PSCI_0_2_FN_MIGRATE:
     default:
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 5a1df25..d1a59fa 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -9045,9 +9045,9 @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar,
         }
     }
 
-    tcg_temp_free_ptr(tcg_fpstatus);
     tcg_temp_free_i32(tcg_shift);
     gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus);
+    tcg_temp_free_ptr(tcg_fpstatus);
     tcg_temp_free_i32(tcg_rmode);
 }
 
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index f33d84d..721eafa 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -190,6 +190,7 @@ qtests_npcm7xx = \
    'npcm7xx_gpio-test',
    'npcm7xx_pwm-test',
    'npcm7xx_rng-test',
+   'npcm7xx_sdhci-test',
    'npcm7xx_smbus-test',
    'npcm7xx_timer-test',
    'npcm7xx_watchdog_timer-test'] + \
diff --git a/tests/qtest/npcm7xx_sdhci-test.c b/tests/qtest/npcm7xx_sdhci-test.c
new file mode 100644
index 0000000..c1f496f
--- /dev/null
+++ b/tests/qtest/npcm7xx_sdhci-test.c
@@ -0,0 +1,215 @@
+/*
+ * QTests for NPCM7xx SD-3.0 / MMC-4.51 Host Controller
+ *
+ * Copyright (c) 2022 Google LLC
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/sd/npcm7xx_sdhci.h"
+
+#include "libqos/libqtest.h"
+#include "libqtest-single.h"
+#include "libqos/sdhci-cmd.h"
+
+#define NPCM7XX_REG_SIZE 0x100
+#define NPCM7XX_MMC_BA 0xF0842000
+#define NPCM7XX_BLK_SIZE 512
+#define NPCM7XX_TEST_IMAGE_SIZE (1 << 30)
+
+char *sd_path;
+
+static QTestState *setup_sd_card(void)
+{
+    QTestState *qts = qtest_initf(
+        "-machine kudo-bmc "
+        "-device sd-card,drive=drive0 "
+        "-drive id=drive0,if=none,file=%s,format=raw,auto-read-only=off",
+        sd_path);
+
+    qtest_writew(qts, NPCM7XX_MMC_BA + SDHC_SWRST, SDHC_RESET_ALL);
+    qtest_writew(qts, NPCM7XX_MMC_BA + SDHC_CLKCON,
+                 SDHC_CLOCK_SDCLK_EN | SDHC_CLOCK_INT_STABLE |
+                     SDHC_CLOCK_INT_EN);
+    sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0, 0, SDHC_APP_CMD);
+    sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0x41200000, 0, (41 << 8));
+    sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0, 0, SDHC_ALL_SEND_CID);
+    sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0, 0, SDHC_SEND_RELATIVE_ADDR);
+    sdhci_cmd_regs(qts, NPCM7XX_MMC_BA, 0, 0, 0x45670000, 0,
+                   SDHC_SELECT_DESELECT_CARD);
+
+    return qts;
+}
+
+static void write_sdread(QTestState *qts, const char *msg)
+{
+    int fd, ret;
+    size_t len = strlen(msg);
+    char *rmsg = g_malloc(len);
+
+    /* write message to sd */
+    fd = open(sd_path, O_WRONLY);
+    g_assert(fd >= 0);
+    ret = write(fd, msg, len);
+    close(fd);
+    g_assert(ret == len);
+
+    /* read message using sdhci */
+    ret = sdhci_read_cmd(qts, NPCM7XX_MMC_BA, rmsg, len);
+    g_assert(ret == len);
+    g_assert(!memcmp(rmsg, msg, len));
+
+    g_free(rmsg);
+}
+
+/* Check MMC can read values from sd */
+static void test_read_sd(void)
+{
+    QTestState *qts = setup_sd_card();
+
+    write_sdread(qts, "hello world");
+    write_sdread(qts, "goodbye");
+
+    qtest_quit(qts);
+}
+
+static void sdwrite_read(QTestState *qts, const char *msg)
+{
+    int fd, ret;
+    size_t len = strlen(msg);
+    char *rmsg = g_malloc(len);
+
+    /* write message using sdhci */
+    sdhci_write_cmd(qts, NPCM7XX_MMC_BA, msg, len, NPCM7XX_BLK_SIZE);
+
+    /* read message from sd */
+    fd = open(sd_path, O_RDONLY);
+    g_assert(fd >= 0);
+    ret = read(fd, rmsg, len);
+    close(fd);
+    g_assert(ret == len);
+
+    g_assert(!memcmp(rmsg, msg, len));
+
+    g_free(rmsg);
+}
+
+/* Check MMC can write values to sd */
+static void test_write_sd(void)
+{
+    QTestState *qts = setup_sd_card();
+
+    sdwrite_read(qts, "hello world");
+    sdwrite_read(qts, "goodbye");
+
+    qtest_quit(qts);
+}
+
+/* Check SDHCI has correct default values. */
+static void test_reset(void)
+{
+    QTestState *qts = qtest_init("-machine kudo-bmc");
+    uint64_t addr = NPCM7XX_MMC_BA;
+    uint64_t end_addr = addr + NPCM7XX_REG_SIZE;
+    uint16_t prstvals_resets[] = {NPCM7XX_PRSTVALS_0_RESET,
+                                  NPCM7XX_PRSTVALS_1_RESET,
+                                  0,
+                                  NPCM7XX_PRSTVALS_3_RESET,
+                                  0,
+                                  0};
+    int i;
+    uint32_t mask;
+
+    while (addr < end_addr) {
+        switch (addr - NPCM7XX_MMC_BA) {
+        case SDHC_PRNSTS:
+            /*
+             * ignores bits 20 to 24: they are changed when reading registers
+             */
+            mask = 0x1f00000;
+            g_assert_cmphex(qtest_readl(qts, addr) | mask, ==,
+                            NPCM7XX_PRSNTS_RESET | mask);
+            addr += 4;
+            break;
+        case SDHC_BLKGAP:
+            g_assert_cmphex(qtest_readb(qts, addr), ==, NPCM7XX_BLKGAP_RESET);
+            addr += 1;
+            break;
+        case SDHC_CAPAB:
+            g_assert_cmphex(qtest_readq(qts, addr), ==, NPCM7XX_CAPAB_RESET);
+            addr += 8;
+            break;
+        case SDHC_MAXCURR:
+            g_assert_cmphex(qtest_readq(qts, addr), ==, NPCM7XX_MAXCURR_RESET);
+            addr += 8;
+            break;
+        case SDHC_HCVER:
+            g_assert_cmphex(qtest_readw(qts, addr), ==, NPCM7XX_HCVER_RESET);
+            addr += 2;
+            break;
+        case NPCM7XX_PRSTVALS:
+            for (i = 0; i < NPCM7XX_PRSTVALS_SIZE; ++i) {
+                g_assert_cmphex(qtest_readw(qts, addr + 2 * i), ==,
+                                prstvals_resets[i]);
+            }
+            addr += NPCM7XX_PRSTVALS_SIZE * 2;
+            break;
+        default:
+            g_assert_cmphex(qtest_readb(qts, addr), ==, 0);
+            addr += 1;
+        }
+    }
+
+    qtest_quit(qts);
+}
+
+static void drive_destroy(void)
+{
+    unlink(sd_path);
+    g_free(sd_path);
+}
+
+static void drive_create(void)
+{
+    int fd, ret;
+    GError *error = NULL;
+
+    /* Create a temporary raw image */
+    fd = g_file_open_tmp("sdhci_XXXXXX", &sd_path, &error);
+    if (fd == -1) {
+        fprintf(stderr, "unable to create sdhci file: %s\n", error->message);
+        g_error_free(error);
+    }
+    g_assert(sd_path != NULL);
+
+    ret = ftruncate(fd, NPCM7XX_TEST_IMAGE_SIZE);
+    g_assert_cmpint(ret, ==, 0);
+    g_message("%s", sd_path);
+    close(fd);
+}
+
+int main(int argc, char **argv)
+{
+    int ret;
+
+    drive_create();
+
+    g_test_init(&argc, &argv, NULL);
+
+    qtest_add_func("npcm7xx_sdhci/reset", test_reset);
+    qtest_add_func("npcm7xx_sdhci/write_sd", test_write_sd);
+    qtest_add_func("npcm7xx_sdhci/read_sd", test_read_sd);
+
+    ret = g_test_run();
+    drive_destroy();
+    return ret;
+}
diff --git a/ui/cocoa.m b/ui/cocoa.m
index a8f1cda..b6e70e9 100644
--- a/ui/cocoa.m
+++ b/ui/cocoa.m
@@ -522,8 +522,9 @@ QemuCocoaView *cocoaView;
     }
 }
 
-- (void) updateUIInfo
+- (void) updateUIInfoLocked
 {
+    /* Must be called with the iothread lock, i.e. via updateUIInfo */
     NSSize frameSize;
     QemuUIInfo info;
 
@@ -554,6 +555,25 @@ QemuCocoaView *cocoaView;
     dpy_set_ui_info(dcl.con, &info, TRUE);
 }
 
+- (void) updateUIInfo
+{
+    if (!allow_events) {
+        /*
+         * Don't try to tell QEMU about UI information in the application
+         * startup phase -- we haven't yet registered dcl with the QEMU UI
+         * layer, and also trying to take the iothread lock would deadlock.
+         * When cocoa_display_init() does register the dcl, the UI layer
+         * will call cocoa_switch(), which will call updateUIInfo, so
+         * we don't lose any information here.
+         */
+        return;
+    }
+
+    with_iothread_lock(^{
+        [self updateUIInfoLocked];
+    });
+}
+
 - (void)viewDidMoveToWindow
 {
     [self updateUIInfo];
@@ -1956,8 +1976,6 @@ int main (int argc, char **argv) {
 static void cocoa_update(DisplayChangeListener *dcl,
                          int x, int y, int w, int h)
 {
-    NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init];
-
     COCOA_DEBUG("qemu_cocoa: cocoa_update\n");
 
     dispatch_async(dispatch_get_main_queue(), ^{
@@ -1973,20 +1991,15 @@ static void cocoa_update(DisplayChangeListener *dcl,
         }
         [cocoaView setNeedsDisplayInRect:rect];
     });
-
-    [pool release];
 }
 
 static void cocoa_switch(DisplayChangeListener *dcl,
                          DisplaySurface *surface)
 {
-    NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init];
     pixman_image_t *image = surface->image;
 
     COCOA_DEBUG("qemu_cocoa: cocoa_switch\n");
 
-    [cocoaView updateUIInfo];
-
     // The DisplaySurface will be freed as soon as this callback returns.
     // We take a reference to the underlying pixman image here so it does
     // not disappear from under our feet; the switchSurface method will
@@ -1994,9 +2007,9 @@ static void cocoa_switch(DisplayChangeListener *dcl,
     pixman_image_ref(image);
 
     dispatch_async(dispatch_get_main_queue(), ^{
+        [cocoaView updateUIInfo];
         [cocoaView switchSurface:image];
     });
-    [pool release];
 }
 
 static void cocoa_refresh(DisplayChangeListener *dcl)