Merge tag 'pull-target-arm-20230306' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * allwinner-h3: Fix I2C controller model for Sun6i SoCs
 * allwinner-h3: Add missing i2c controllers
 * Expose M-profile system registers to gdbstub
 * Expose pauth information to gdbstub
 * Support direct boot for Linux/arm64 EFI zboot images
 * Fix incorrect stage 2 MMU setup validation

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmQGB+wZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3gdQEACVfgbs77mxbOb6u8yWHKGZ
# tVnQr9KZMv2lmwt5H3ROJPXznchrIIAwdMeRgKnbI+lC5jTq9L+Q8RJch3t/EbAd
# f0VMyiPe3DzCbCrAR9cW6EWzbYnEVo3Ioj4k7qjxK6u1BIKhXz99DLYd1KRdTxnx
# BAYmcl857Uir1q2FrBVMZ/ItCLbk4ejn+YaDIawNue2/s1oGa+we473x9rosCFvp
# L9bzT3R46e0o+Mfkn1OYRmgCmURTalWPpWAxyOUFR9YbrzXleLgAKEB3o3PPcvls
# u26uxztyRMqje1q06VjUzwaLw7zN9XPhmir+NXX7KXp2/x9PZjApOpPtt0kl+6qe
# FbByKfl24O9w/OKewsJw+udCBYdYrRPm6tWv2D71iAwjBUzBJgNGe5VPRdPFtPDn
# uSRO65o34w1nPzRpAheUciZueiabYrVmIgVltFxj0JlrKGfgiYHPLVyU0Uu0K/A7
# F2kUEQIzIcWdo+c8SlvlWOEA2ojVd/KoLVLgndqr40Tk5pbc65TRS08kkVVl4cMT
# jUGscl7Dyxe+yo8+nHdycAJpnKYDllJOh2JbGv3r2FqCy5FMuIqW4hHeuUxwpE+O
# nxm7lzjnaVHSAFHdzhk9x4E4uH/GTcdWzX1EsmpgGqe5oejLJOrCINb+Dj44+Y8h
# 8aGRvE7kxMs11upxc7BcAw==
# =KIMt
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 06 Mar 2023 15:34:04 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]
# gpg:                 aka "Peter Maydell <peter@archaic.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* tag 'pull-target-arm-20230306' of https://git.linaro.org/people/pmaydell/qemu-arm: (21 commits)
  hw: arm: allwinner-h3: Fix and complete H3 i2c devices
  hw: allwinner-i2c: Fix TWI_CNTR_INT_FLAG on SUN6i SoCs
  hw: arm: Support direct boot for Linux/arm64 EFI zboot images
  target/arm: Rewrite check_s2_mmu_setup
  target/arm: Diagnose incorrect usage of arm_is_secure subroutines
  target/arm: Stub arm_hcr_el2_eff for m-profile
  target/arm: Handle m-profile in arm_is_secure
  target/arm: Implement gdbstub m-profile systemreg and secext
  target/arm: Export arm_v7m_get_sp_ptr
  target/arm: Export arm_v7m_mrs_control
  target/arm: Implement gdbstub pauth extension
  target/arm: Create pauth_ptr_mask
  target/arm: Simplify iteration over bit widths
  target/arm: Add name argument to output_vector_union_type
  target/arm: Fix svep width in arm_gen_dynamic_svereg_xml
  target/arm: Hoist pred_width in arm_gen_dynamic_svereg_xml
  target/arm: Simplify register counting in arm_gen_dynamic_svereg_xml
  target/arm: Split out output_vector_union_type
  target/arm: Move arm_gen_dynamic_svereg_xml to gdbstub64.c
  target/arm: Unexport arm_gen_dynamic_sysreg_xml
  ...

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

19 files changed, 739 insertions, 255 deletions

diff --git a/configs/targets/aarch64-linux-user.mak b/configs/targets/aarch64-linux-user.mak
index db552f1839..ba8bc5fe3f 100644
--- a/configs/targets/aarch64-linux-user.mak
+++ b/configs/targets/aarch64-linux-user.mak
@@ -1,6 +1,6 @@
 TARGET_ARCH=aarch64
 TARGET_BASE_ARCH=arm
-TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml
+TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/aarch64-pauth.xml
 TARGET_HAS_BFLT=y
 CONFIG_SEMIHOSTING=y
 CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y
diff --git a/configs/targets/aarch64-softmmu.mak b/configs/targets/aarch64-softmmu.mak
index d489e6da83..b4338e9568 100644
--- a/configs/targets/aarch64-softmmu.mak
+++ b/configs/targets/aarch64-softmmu.mak
@@ -1,5 +1,5 @@
 TARGET_ARCH=aarch64
 TARGET_BASE_ARCH=arm
 TARGET_SUPPORTS_MTTCG=y
-TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/arm-core.xml gdb-xml/arm-vfp.xml gdb-xml/arm-vfp3.xml gdb-xml/arm-vfp-sysregs.xml gdb-xml/arm-neon.xml gdb-xml/arm-m-profile.xml gdb-xml/arm-m-profile-mve.xml
+TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/arm-core.xml gdb-xml/arm-vfp.xml gdb-xml/arm-vfp3.xml gdb-xml/arm-vfp-sysregs.xml gdb-xml/arm-neon.xml gdb-xml/arm-m-profile.xml gdb-xml/arm-m-profile-mve.xml gdb-xml/aarch64-pauth.xml
 TARGET_NEED_FDT=y
diff --git a/configs/targets/aarch64_be-linux-user.mak b/configs/targets/aarch64_be-linux-user.mak
index dc78044fb1..acb5620cdb 100644
--- a/configs/targets/aarch64_be-linux-user.mak
+++ b/configs/targets/aarch64_be-linux-user.mak
@@ -1,7 +1,7 @@
 TARGET_ARCH=aarch64
 TARGET_BASE_ARCH=arm
 TARGET_BIG_ENDIAN=y
-TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml
+TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/aarch64-pauth.xml
 TARGET_HAS_BFLT=y
 CONFIG_SEMIHOSTING=y
 CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y
diff --git a/gdb-xml/aarch64-pauth.xml b/gdb-xml/aarch64-pauth.xml
new file mode 100644
index 0000000000..24af5f903c
--- /dev/null
+++ b/gdb-xml/aarch64-pauth.xml
@@ -0,0 +1,15 @@
+<?xml version="1.0"?>
+<!-- Copyright (C) 2018-2022 Free Software Foundation, Inc.
+
+     Copying and distribution of this file, with or without modification,
+     are permitted in any medium without royalty provided the copyright
+     notice and this notice are preserved.  -->
+
+<!DOCTYPE feature SYSTEM "gdb-target.dtd">
+<feature name="org.gnu.gdb.aarch64.pauth">
+  <reg name="pauth_dmask" bitsize="64"/>
+  <reg name="pauth_cmask" bitsize="64"/>
+  <reg name="pauth_dmask_high" bitsize="64"/>
+  <reg name="pauth_cmask_high" bitsize="64"/>
+</feature>
+
diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c
index bfce3c8d92..69d0ad6f50 100644
--- a/hw/arm/allwinner-h3.c
+++ b/hw/arm/allwinner-h3.c
@@ -54,6 +54,8 @@ const hwaddr allwinner_h3_memmap[] = {
     [AW_H3_DEV_UART2]      = 0x01c28800,
     [AW_H3_DEV_UART3]      = 0x01c28c00,
     [AW_H3_DEV_TWI0]       = 0x01c2ac00,
+    [AW_H3_DEV_TWI1]       = 0x01c2b000,
+    [AW_H3_DEV_TWI2]       = 0x01c2b400,
     [AW_H3_DEV_EMAC]       = 0x01c30000,
     [AW_H3_DEV_DRAMCOM]    = 0x01c62000,
     [AW_H3_DEV_DRAMCTL]    = 0x01c63000,
@@ -64,6 +66,7 @@ const hwaddr allwinner_h3_memmap[] = {
     [AW_H3_DEV_GIC_VCPU]   = 0x01c86000,
     [AW_H3_DEV_RTC]        = 0x01f00000,
     [AW_H3_DEV_CPUCFG]     = 0x01f01c00,
+    [AW_H3_DEV_R_TWI]      = 0x01f02400,
     [AW_H3_DEV_SDRAM]      = 0x40000000
 };
 
@@ -107,8 +110,6 @@ struct AwH3Unimplemented {
     { "uart1",     0x01c28400, 1 * KiB },
     { "uart2",     0x01c28800, 1 * KiB },
     { "uart3",     0x01c28c00, 1 * KiB },
-    { "twi1",      0x01c2b000, 1 * KiB },
-    { "twi2",      0x01c2b400, 1 * KiB },
     { "scr",       0x01c2c400, 1 * KiB },
     { "gpu",       0x01c40000, 64 * KiB },
     { "hstmr",     0x01c60000, 4 * KiB },
@@ -123,7 +124,6 @@ struct AwH3Unimplemented {
     { "r_prcm",    0x01f01400, 1 * KiB },
     { "r_twd",     0x01f01800, 1 * KiB },
     { "r_cir-rx",  0x01f02000, 1 * KiB },
-    { "r_twi",     0x01f02400, 1 * KiB },
     { "r_uart",    0x01f02800, 1 * KiB },
     { "r_pio",     0x01f02c00, 1 * KiB },
     { "r_pwm",     0x01f03800, 1 * KiB },
@@ -151,8 +151,11 @@ enum {
     AW_H3_GIC_SPI_UART2     =  2,
     AW_H3_GIC_SPI_UART3     =  3,
     AW_H3_GIC_SPI_TWI0      =  6,
+    AW_H3_GIC_SPI_TWI1      =  7,
+    AW_H3_GIC_SPI_TWI2      =  8,
     AW_H3_GIC_SPI_TIMER0    = 18,
     AW_H3_GIC_SPI_TIMER1    = 19,
+    AW_H3_GIC_SPI_R_TWI     = 44,
     AW_H3_GIC_SPI_MMC0      = 60,
     AW_H3_GIC_SPI_EHCI0     = 72,
     AW_H3_GIC_SPI_OHCI0     = 73,
@@ -227,7 +230,10 @@ static void allwinner_h3_init(Object *obj)
 
     object_initialize_child(obj, "rtc", &s->rtc, TYPE_AW_RTC_SUN6I);
 
-    object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C);
+    object_initialize_child(obj, "twi0",  &s->i2c0,  TYPE_AW_I2C_SUN6I);
+    object_initialize_child(obj, "twi1",  &s->i2c1,  TYPE_AW_I2C_SUN6I);
+    object_initialize_child(obj, "twi2",  &s->i2c2,  TYPE_AW_I2C_SUN6I);
+    object_initialize_child(obj, "r_twi", &s->r_twi, TYPE_AW_I2C_SUN6I);
 }
 
 static void allwinner_h3_realize(DeviceState *dev, Error **errp)
@@ -432,6 +438,21 @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0,
                        qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI0));
 
+    sysbus_realize(SYS_BUS_DEVICE(&s->i2c1), &error_fatal);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c1), 0, s->memmap[AW_H3_DEV_TWI1]);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c1), 0,
+                       qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI1));
+
+    sysbus_realize(SYS_BUS_DEVICE(&s->i2c2), &error_fatal);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c2), 0, s->memmap[AW_H3_DEV_TWI2]);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c2), 0,
+                       qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI2));
+
+    sysbus_realize(SYS_BUS_DEVICE(&s->r_twi), &error_fatal);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->r_twi), 0, s->memmap[AW_H3_DEV_R_TWI]);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->r_twi), 0,
+                       qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_R_TWI));
+
     /* Unimplemented devices */
     for (i = 0; i < ARRAY_SIZE(unimplemented); i++) {
         create_unimplemented_device(unimplemented[i].device_name,
diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index 1e021c4a34..50e5141116 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -926,6 +926,12 @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base,
             return -1;
         }
         size = len;
+
+        /* Unpack the image if it is a EFI zboot image */
+        if (unpack_efi_zboot_image(&buffer, &size) < 0) {
+            g_free(buffer);
+            return -1;
+        }
     }
 
     /* check the arm64 magic header value -- very old kernels may not have it */
diff --git a/hw/core/loader.c b/hw/core/loader.c
index 173f8f67f6..cd53235fed 100644
--- a/hw/core/loader.c
+++ b/hw/core/loader.c
@@ -857,6 +857,97 @@ ssize_t load_image_gzipped(const char *filename, hwaddr addr, uint64_t max_sz)
     return bytes;
 }
 
+/* The PE/COFF MS-DOS stub magic number */
+#define EFI_PE_MSDOS_MAGIC        "MZ"
+
+/*
+ * The Linux header magic number for a EFI PE/COFF
+ * image targetting an unspecified architecture.
+ */
+#define EFI_PE_LINUX_MAGIC        "\xcd\x23\x82\x81"
+
+/*
+ * Bootable Linux kernel images may be packaged as EFI zboot images, which are
+ * self-decompressing executables when loaded via EFI. The compressed payload
+ * can also be extracted from the image and decompressed by a non-EFI loader.
+ *
+ * The de facto specification for this format is at the following URL:
+ *
+ * https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/firmware/efi/libstub/zboot-header.S
+ *
+ * This definition is based on Linux upstream commit 29636a5ce87beba.
+ */
+struct linux_efi_zboot_header {
+    uint8_t     msdos_magic[2];         /* PE/COFF 'MZ' magic number */
+    uint8_t     reserved0[2];
+    uint8_t     zimg[4];                /* "zimg" for Linux EFI zboot images */
+    uint32_t    payload_offset;         /* LE offset to compressed payload */
+    uint32_t    payload_size;           /* LE size of the compressed payload */
+    uint8_t     reserved1[8];
+    char        compression_type[32];   /* Compression type, NUL terminated */
+    uint8_t     linux_magic[4];         /* Linux header magic */
+    uint32_t    pe_header_offset;       /* LE offset to the PE header */
+};
+
+/*
+ * Check whether *buffer points to a Linux EFI zboot image in memory.
+ *
+ * If it does, attempt to decompress it to a new buffer, and free the old one.
+ * If any of this fails, return an error to the caller.
+ *
+ * If the image is not a Linux EFI zboot image, do nothing and return success.
+ */
+ssize_t unpack_efi_zboot_image(uint8_t **buffer, int *size)
+{
+    const struct linux_efi_zboot_header *header;
+    uint8_t *data = NULL;
+    int ploff, plsize;
+    ssize_t bytes;
+
+    /* ignore if this is too small to be a EFI zboot image */
+    if (*size < sizeof(*header)) {
+        return 0;
+    }
+
+    header = (struct linux_efi_zboot_header *)*buffer;
+
+    /* ignore if this is not a Linux EFI zboot image */
+    if (memcmp(&header->msdos_magic, EFI_PE_MSDOS_MAGIC, 2) != 0 ||
+        memcmp(&header->zimg, "zimg", 4) != 0 ||
+        memcmp(&header->linux_magic, EFI_PE_LINUX_MAGIC, 4) != 0) {
+        return 0;
+    }
+
+    if (strcmp(header->compression_type, "gzip") != 0) {
+        fprintf(stderr,
+                "unable to handle EFI zboot image with \"%.*s\" compression\n",
+                (int)sizeof(header->compression_type) - 1,
+                header->compression_type);
+        return -1;
+    }
+
+    ploff = ldl_le_p(&header->payload_offset);
+    plsize = ldl_le_p(&header->payload_size);
+
+    if (ploff < 0 || plsize < 0 || ploff + plsize > *size) {
+        fprintf(stderr, "unable to handle corrupt EFI zboot image\n");
+        return -1;
+    }
+
+    data = g_malloc(LOAD_IMAGE_MAX_GUNZIP_BYTES);
+    bytes = gunzip(data, LOAD_IMAGE_MAX_GUNZIP_BYTES, *buffer + ploff, plsize);
+    if (bytes < 0) {
+        fprintf(stderr, "failed to decompress EFI zboot image\n");
+        g_free(data);
+        return -1;
+    }
+
+    g_free(*buffer);
+    *buffer = g_realloc(data, bytes);
+    *size = bytes;
+    return bytes;
+}
+
 /*
  * Functions for reboot-persistent memory regions.
  *  - used for vga bios and option roms.
diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c
index a435965836..f24c3ac6f0 100644
--- a/hw/i2c/allwinner-i2c.c
+++ b/hw/i2c/allwinner-i2c.c
@@ -357,10 +357,16 @@ static void allwinner_i2c_write(void *opaque, hwaddr offset,
                 s->stat = STAT_FROM_STA(STAT_IDLE);
                 s->cntr &= ~TWI_CNTR_M_STP;
             }
-            if ((s->cntr & TWI_CNTR_INT_FLAG) == 0) {
-                /* Interrupt flag cleared */
+
+            if (!s->irq_clear_inverted && !(s->cntr & TWI_CNTR_INT_FLAG)) {
+                /* Write 0 to clear this flag */
+                qemu_irq_lower(s->irq);
+            } else if (s->irq_clear_inverted && (s->cntr & TWI_CNTR_INT_FLAG)) {
+                /* Write 1 to clear this flag */
+                s->cntr &= ~TWI_CNTR_INT_FLAG;
                 qemu_irq_lower(s->irq);
             }
+
             if ((s->cntr & TWI_CNTR_A_ACK) == 0) {
                 if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) {
                     s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK);
@@ -451,9 +457,25 @@ static const TypeInfo allwinner_i2c_type_info = {
     .class_init = allwinner_i2c_class_init,
 };
 
+static void allwinner_i2c_sun6i_init(Object *obj)
+{
+    AWI2CState *s = AW_I2C(obj);
+
+    s->irq_clear_inverted = true;
+}
+
+static const TypeInfo allwinner_i2c_sun6i_type_info = {
+    .name = TYPE_AW_I2C_SUN6I,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(AWI2CState),
+    .instance_init = allwinner_i2c_sun6i_init,
+    .class_init = allwinner_i2c_class_init,
+};
+
 static void allwinner_i2c_register_types(void)
 {
     type_register_static(&allwinner_i2c_type_info);
+    type_register_static(&allwinner_i2c_sun6i_type_info);
 }
 
 type_init(allwinner_i2c_register_types)
diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h
index 1d7ce20589..59e0f822d2 100644
--- a/include/hw/arm/allwinner-h3.h
+++ b/include/hw/arm/allwinner-h3.h
@@ -84,6 +84,8 @@ enum {
     AW_H3_DEV_UART3,
     AW_H3_DEV_EMAC,
     AW_H3_DEV_TWI0,
+    AW_H3_DEV_TWI1,
+    AW_H3_DEV_TWI2,
     AW_H3_DEV_DRAMCOM,
     AW_H3_DEV_DRAMCTL,
     AW_H3_DEV_DRAMPHY,
@@ -93,6 +95,7 @@ enum {
     AW_H3_DEV_GIC_VCPU,
     AW_H3_DEV_RTC,
     AW_H3_DEV_CPUCFG,
+    AW_H3_DEV_R_TWI,
     AW_H3_DEV_SDRAM
 };
 
@@ -133,6 +136,9 @@ struct AwH3State {
     AwSidState sid;
     AwSdHostState mmc0;
     AWI2CState i2c0;
+    AWI2CState i2c1;
+    AWI2CState i2c2;
+    AWI2CState r_twi;
     AwSun8iEmacState emac;
     AwRtcState rtc;
     GICState gic;
diff --git a/include/hw/i2c/allwinner-i2c.h b/include/hw/i2c/allwinner-i2c.h
index 4f378b86ba..0e325d265e 100644
--- a/include/hw/i2c/allwinner-i2c.h
+++ b/include/hw/i2c/allwinner-i2c.h
@@ -28,6 +28,10 @@
 #include "qom/object.h"
 
 #define TYPE_AW_I2C "allwinner.i2c"
+
+/** Allwinner I2C sun6i family and newer (A31, H2+, H3, etc) */
+#define TYPE_AW_I2C_SUN6I    TYPE_AW_I2C "-sun6i"
+
 OBJECT_DECLARE_SIMPLE_TYPE(AWI2CState, AW_I2C)
 
 #define AW_I2C_MEM_SIZE         0x24
@@ -50,6 +54,8 @@ struct AWI2CState {
     uint8_t srst;
     uint8_t efr;
     uint8_t lcr;
+
+    bool irq_clear_inverted;
 };
 
 #endif /* ALLWINNER_I2C_H */
diff --git a/include/hw/loader.h b/include/hw/loader.h
index 1384796a4b..c4c14170ea 100644
--- a/include/hw/loader.h
+++ b/include/hw/loader.h
@@ -86,6 +86,25 @@ ssize_t load_image_gzipped_buffer(const char *filename, uint64_t max_sz,
                                   uint8_t **buffer);
 ssize_t load_image_gzipped(const char *filename, hwaddr addr, uint64_t max_sz);
 
+/**
+ * unpack_efi_zboot_image:
+ * @buffer: pointer to a variable holding the address of a buffer containing the
+ *          image
+ * @size: pointer to a variable holding the size of the buffer
+ *
+ * Check whether the buffer contains a EFI zboot image, and if it does, extract
+ * the compressed payload and decompress it into a new buffer. If successful,
+ * the old buffer is freed, and the *buffer and size variables pointed to by the
+ * function arguments are updated to refer to the newly populated buffer.
+ *
+ * Returns 0 if the image could not be identified as a EFI zboot image.
+ * Returns -1 if the buffer contents were identified as a EFI zboot image, but
+ * unpacking failed for any reason.
+ * Returns the size of the decompressed payload if decompression was performed
+ * successfully.
+ */
+ssize_t unpack_efi_zboot_image(uint8_t **buffer, int *size);
+
 #define ELF_LOAD_FAILED       -1
 #define ELF_LOAD_NOT_ELF      -2
 #define ELF_LOAD_WRONG_ARCH   -3
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 787121694c..c097cae988 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -869,6 +869,8 @@ struct ArchCPU {
 
     DynamicGDBXMLInfo dyn_sysreg_xml;
     DynamicGDBXMLInfo dyn_svereg_xml;
+    DynamicGDBXMLInfo dyn_m_systemreg_xml;
+    DynamicGDBXMLInfo dyn_m_secextreg_xml;
 
     /* Timers used by the generic (architected) timer */
     QEMUTimer *gt_timer[NUM_GTIMERS];
@@ -1112,13 +1114,6 @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr,
 int arm_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg);
 int arm_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
 
-/*
- * Helpers to dynamically generates XML descriptions of the sysregs
- * and SVE registers. Returns the number of registers in each set.
- */
-int arm_gen_dynamic_sysreg_xml(CPUState *cpu, int base_reg);
-int arm_gen_dynamic_svereg_xml(CPUState *cpu, int base_reg);
-
 /* Returns the dynamically generated XML for the gdb stub.
  * Returns a pointer to the XML contents for the specified XML file or NULL
  * if the XML name doesn't match the predefined one.
@@ -2389,7 +2384,8 @@ static inline int arm_feature(CPUARMState *env, int feature)
 void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp);
 
 #if !defined(CONFIG_USER_ONLY)
-/* Return true if exception levels below EL3 are in secure state,
+/*
+ * Return true if exception levels below EL3 are in secure state,
  * or would be following an exception return to that level.
  * Unlike arm_is_secure() (which is always a question about the
  * _current_ state of the CPU) this doesn't care about the current
@@ -2397,6 +2393,7 @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp);
  */
 static inline bool arm_is_secure_below_el3(CPUARMState *env)
 {
+    assert(!arm_feature(env, ARM_FEATURE_M));
     if (arm_feature(env, ARM_FEATURE_EL3)) {
         return !(env->cp15.scr_el3 & SCR_NS);
     } else {
@@ -2410,6 +2407,7 @@ static inline bool arm_is_secure_below_el3(CPUARMState *env)
 /* Return true if the CPU is AArch64 EL3 or AArch32 Mon */
 static inline bool arm_is_el3_or_mon(CPUARMState *env)
 {
+    assert(!arm_feature(env, ARM_FEATURE_M));
     if (arm_feature(env, ARM_FEATURE_EL3)) {
         if (is_a64(env) && extract32(env->pstate, 2, 2) == 3) {
             /* CPU currently in AArch64 state and EL3 */
@@ -2426,6 +2424,9 @@ static inline bool arm_is_el3_or_mon(CPUARMState *env)
 /* Return true if the processor is in secure state */
 static inline bool arm_is_secure(CPUARMState *env)
 {
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        return env->v7m.secure;
+    }
     if (arm_is_el3_or_mon(env)) {
         return true;
     }
diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c
index 2f806512d0..3f799f5d05 100644
--- a/target/arm/gdbstub.c
+++ b/target/arm/gdbstub.c
@@ -305,7 +305,7 @@ static void arm_register_sysreg_for_xml(gpointer key, gpointer value,
     }
 }
 
-int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg)
+static int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg)
 {
     ARMCPU *cpu = ARM_CPU(cs);
     GString *s = g_string_new(NULL);
@@ -322,125 +322,163 @@ int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg)
     return cpu->dyn_sysreg_xml.num;
 }
 
-struct TypeSize {
-    const char *gdb_type;
-    int  size;
-    const char sz, suffix;
+typedef enum {
+    M_SYSREG_MSP,
+    M_SYSREG_PSP,
+    M_SYSREG_PRIMASK,
+    M_SYSREG_CONTROL,
+    M_SYSREG_BASEPRI,
+    M_SYSREG_FAULTMASK,
+    M_SYSREG_MSPLIM,
+    M_SYSREG_PSPLIM,
+} MProfileSysreg;
+
+static const struct {
+    const char *name;
+    int feature;
+} m_sysreg_def[] = {
+    [M_SYSREG_MSP] = { "msp", ARM_FEATURE_M },
+    [M_SYSREG_PSP] = { "psp", ARM_FEATURE_M },
+    [M_SYSREG_PRIMASK] = { "primask", ARM_FEATURE_M },
+    [M_SYSREG_CONTROL] = { "control", ARM_FEATURE_M },
+    [M_SYSREG_BASEPRI] = { "basepri", ARM_FEATURE_M_MAIN },
+    [M_SYSREG_FAULTMASK] = { "faultmask", ARM_FEATURE_M_MAIN },
+    [M_SYSREG_MSPLIM] = { "msplim", ARM_FEATURE_V8 },
+    [M_SYSREG_PSPLIM] = { "psplim", ARM_FEATURE_V8 },
 };
 
-static const struct TypeSize vec_lanes[] = {
-    /* quads */
-    { "uint128", 128, 'q', 'u' },
-    { "int128", 128, 'q', 's' },
-    /* 64 bit */
-    { "ieee_double", 64, 'd', 'f' },
-    { "uint64", 64, 'd', 'u' },
-    { "int64", 64, 'd', 's' },
-    /* 32 bit */
-    { "ieee_single", 32, 's', 'f' },
-    { "uint32", 32, 's', 'u' },
-    { "int32", 32, 's', 's' },
-    /* 16 bit */
-    { "ieee_half", 16, 'h', 'f' },
-    { "uint16", 16, 'h', 'u' },
-    { "int16", 16, 'h', 's' },
-    /* bytes */
-    { "uint8", 8, 'b', 'u' },
-    { "int8", 8, 'b', 's' },
-};
+static uint32_t *m_sysreg_ptr(CPUARMState *env, MProfileSysreg reg, bool sec)
+{
+    uint32_t *ptr;
+
+    switch (reg) {
+    case M_SYSREG_MSP:
+        ptr = arm_v7m_get_sp_ptr(env, sec, false, true);
+        break;
+    case M_SYSREG_PSP:
+        ptr = arm_v7m_get_sp_ptr(env, sec, true, true);
+        break;
+    case M_SYSREG_MSPLIM:
+        ptr = &env->v7m.msplim[sec];
+        break;
+    case M_SYSREG_PSPLIM:
+        ptr = &env->v7m.psplim[sec];
+        break;
+    case M_SYSREG_PRIMASK:
+        ptr = &env->v7m.primask[sec];
+        break;
+    case M_SYSREG_BASEPRI:
+        ptr = &env->v7m.basepri[sec];
+        break;
+    case M_SYSREG_FAULTMASK:
+        ptr = &env->v7m.faultmask[sec];
+        break;
+    case M_SYSREG_CONTROL:
+        ptr = &env->v7m.control[sec];
+        break;
+    default:
+        return NULL;
+    }
+    return arm_feature(env, m_sysreg_def[reg].feature) ? ptr : NULL;
+}
+
+static int m_sysreg_get(CPUARMState *env, GByteArray *buf,
+                        MProfileSysreg reg, bool secure)
+{
+    uint32_t *ptr = m_sysreg_ptr(env, reg, secure);
+
+    if (ptr == NULL) {
+        return 0;
+    }
+    return gdb_get_reg32(buf, *ptr);
+}
+
+static int arm_gdb_get_m_systemreg(CPUARMState *env, GByteArray *buf, int reg)
+{
+    /*
+     * Here, we emulate MRS instruction, where CONTROL has a mix of
+     * banked and non-banked bits.
+     */
+    if (reg == M_SYSREG_CONTROL) {
+        return gdb_get_reg32(buf, arm_v7m_mrs_control(env, env->v7m.secure));
+    }
+    return m_sysreg_get(env, buf, reg, env->v7m.secure);
+}
 
+static int arm_gdb_set_m_systemreg(CPUARMState *env, uint8_t *buf, int reg)
+{
+    return 0; /* TODO */
+}
 
-int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg)
+static int arm_gen_dynamic_m_systemreg_xml(CPUState *cs, int orig_base_reg)
 {
     ARMCPU *cpu = ARM_CPU(cs);
+    CPUARMState *env = &cpu->env;
     GString *s = g_string_new(NULL);
-    DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml;
-    g_autoptr(GString) ts = g_string_new("");
-    int i, j, bits, reg_width = (cpu->sve_max_vq * 128);
-    info->num = 0;
+    int base_reg = orig_base_reg;
+    int i;
+
     g_string_printf(s, "<?xml version=\"1.0\"?>");
     g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">");
-    g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">");
+    g_string_append_printf(s, "<feature name=\"org.gnu.gdb.arm.m-system\">\n");
 
-    /* First define types and totals in a whole VL */
-    for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) {
-        int count = reg_width / vec_lanes[i].size;
-        g_string_printf(ts, "svev%c%c", vec_lanes[i].sz, vec_lanes[i].suffix);
-        g_string_append_printf(s,
-                               "<vector id=\"%s\" type=\"%s\" count=\"%d\"/>",
-                               ts->str, vec_lanes[i].gdb_type, count);
-    }
-    /*
-     * Now define a union for each size group containing unsigned and
-     * signed and potentially float versions of each size from 128 to
-     * 8 bits.
-     */
-    for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) {
-        const char suf[] = { 'q', 'd', 's', 'h', 'b' };
-        g_string_append_printf(s, "<union id=\"svevn%c\">", suf[i]);
-        for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) {
-            if (vec_lanes[j].size == bits) {
-                g_string_append_printf(s, "<field name=\"%c\" type=\"svev%c%c\"/>",
-                                       vec_lanes[j].suffix,
-                                       vec_lanes[j].sz, vec_lanes[j].suffix);
-            }
+    for (i = 0; i < ARRAY_SIZE(m_sysreg_def); i++) {
+        if (arm_feature(env, m_sysreg_def[i].feature)) {
+            g_string_append_printf(s,
+                "<reg name=\"%s\" bitsize=\"32\" regnum=\"%d\"/>\n",
+                m_sysreg_def[i].name, base_reg++);
         }
-        g_string_append(s, "</union>");
     }
-    /* And now the final union of unions */
-    g_string_append(s, "<union id=\"svev\">");
-    for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) {
-        const char suf[] = { 'q', 'd', 's', 'h', 'b' };
-        g_string_append_printf(s, "<field name=\"%c\" type=\"svevn%c\"/>",
-                               suf[i], suf[i]);
-    }
-    g_string_append(s, "</union>");
 
-    /* Finally the sve prefix type */
-    g_string_append_printf(s,
-                           "<vector id=\"svep\" type=\"uint8\" count=\"%d\"/>",
-                           reg_width / 8);
+    g_string_append_printf(s, "</feature>");
+    cpu->dyn_m_systemreg_xml.desc = g_string_free(s, false);
+    cpu->dyn_m_systemreg_xml.num = base_reg - orig_base_reg;
+
+    return cpu->dyn_m_systemreg_xml.num;
+}
+
+#ifndef CONFIG_USER_ONLY
+/*
+ * For user-only, we see the non-secure registers via m_systemreg above.
+ * For secext, encode the non-secure view as even and secure view as odd.
+ */
+static int arm_gdb_get_m_secextreg(CPUARMState *env, GByteArray *buf, int reg)
+{
+    return m_sysreg_get(env, buf, reg >> 1, reg & 1);
+}
+
+static int arm_gdb_set_m_secextreg(CPUARMState *env, uint8_t *buf, int reg)
+{
+    return 0; /* TODO */
+}
+
+static int arm_gen_dynamic_m_secextreg_xml(CPUState *cs, int orig_base_reg)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+    GString *s = g_string_new(NULL);
+    int base_reg = orig_base_reg;
+    int i;
+
+    g_string_printf(s, "<?xml version=\"1.0\"?>");
+    g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">");
+    g_string_append_printf(s, "<feature name=\"org.gnu.gdb.arm.secext\">\n");
 
-    /* Then define each register in parts for each vq */
-    for (i = 0; i < 32; i++) {
+    for (i = 0; i < ARRAY_SIZE(m_sysreg_def); i++) {
         g_string_append_printf(s,
-                               "<reg name=\"z%d\" bitsize=\"%d\""
-                               " regnum=\"%d\" type=\"svev\"/>",
-                               i, reg_width, base_reg++);
-        info->num++;
-    }
-    /* fpscr & status registers */
-    g_string_append_printf(s, "<reg name=\"fpsr\" bitsize=\"32\""
-                           " regnum=\"%d\" group=\"float\""
-                           " type=\"int\"/>", base_reg++);
-    g_string_append_printf(s, "<reg name=\"fpcr\" bitsize=\"32\""
-                           " regnum=\"%d\" group=\"float\""
-                           " type=\"int\"/>", base_reg++);
-    info->num += 2;
-
-    for (i = 0; i < 16; i++) {
+            "<reg name=\"%s_ns\" bitsize=\"32\" regnum=\"%d\"/>\n",
+            m_sysreg_def[i].name, base_reg++);
         g_string_append_printf(s,
-                               "<reg name=\"p%d\" bitsize=\"%d\""
-                               " regnum=\"%d\" type=\"svep\"/>",
-                               i, cpu->sve_max_vq * 16, base_reg++);
-        info->num++;
+            "<reg name=\"%s_s\" bitsize=\"32\" regnum=\"%d\"/>\n",
+            m_sysreg_def[i].name, base_reg++);
     }
-    g_string_append_printf(s,
-                           "<reg name=\"ffr\" bitsize=\"%d\""
-                           " regnum=\"%d\" group=\"vector\""
-                           " type=\"svep\"/>",
-                           cpu->sve_max_vq * 16, base_reg++);
-    g_string_append_printf(s,
-                           "<reg name=\"vg\" bitsize=\"64\""
-                           " regnum=\"%d\" type=\"int\"/>",
-                           base_reg++);
-    info->num += 2;
+
     g_string_append_printf(s, "</feature>");
-    cpu->dyn_svereg_xml.desc = g_string_free(s, false);
+    cpu->dyn_m_secextreg_xml.desc = g_string_free(s, false);
+    cpu->dyn_m_secextreg_xml.num = base_reg - orig_base_reg;
 
-    return cpu->dyn_svereg_xml.num;
+    return cpu->dyn_m_secextreg_xml.num;
 }
-
+#endif
 
 const char *arm_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname)
 {
@@ -450,6 +488,12 @@ const char *arm_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname)
         return cpu->dyn_sysreg_xml.desc;
     } else if (strcmp(xmlname, "sve-registers.xml") == 0) {
         return cpu->dyn_svereg_xml.desc;
+    } else if (strcmp(xmlname, "arm-m-system.xml") == 0) {
+        return cpu->dyn_m_systemreg_xml.desc;
+#ifndef CONFIG_USER_ONLY
+    } else if (strcmp(xmlname, "arm-m-secext.xml") == 0) {
+        return cpu->dyn_m_secextreg_xml.desc;
+#endif
     }
     return NULL;
 }
@@ -466,14 +510,20 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu)
          */
 #ifdef TARGET_AARCH64
         if (isar_feature_aa64_sve(&cpu->isar)) {
-            gdb_register_coprocessor(cs, arm_gdb_get_svereg, arm_gdb_set_svereg,
-                                     arm_gen_dynamic_svereg_xml(cs, cs->gdb_num_regs),
+            int nreg = arm_gen_dynamic_svereg_xml(cs, cs->gdb_num_regs);
+            gdb_register_coprocessor(cs, aarch64_gdb_get_sve_reg,
+                                     aarch64_gdb_set_sve_reg, nreg,
                                      "sve-registers.xml", 0);
         } else {
-            gdb_register_coprocessor(cs, aarch64_fpu_gdb_get_reg,
-                                     aarch64_fpu_gdb_set_reg,
+            gdb_register_coprocessor(cs, aarch64_gdb_get_fpu_reg,
+                                     aarch64_gdb_set_fpu_reg,
                                      34, "aarch64-fpu.xml", 0);
         }
+        if (isar_feature_aa64_pauth(&cpu->isar)) {
+            gdb_register_coprocessor(cs, aarch64_gdb_get_pauth_reg,
+                                     aarch64_gdb_set_pauth_reg,
+                                     4, "aarch64-pauth.xml", 0);
+        }
 #endif
     } else {
         if (arm_feature(env, ARM_FEATURE_NEON)) {
@@ -503,4 +553,18 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu)
                              arm_gen_dynamic_sysreg_xml(cs, cs->gdb_num_regs),
                              "system-registers.xml", 0);
 
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        gdb_register_coprocessor(cs,
+            arm_gdb_get_m_systemreg, arm_gdb_set_m_systemreg,
+            arm_gen_dynamic_m_systemreg_xml(cs, cs->gdb_num_regs),
+            "arm-m-system.xml", 0);
+#ifndef CONFIG_USER_ONLY
+        if (arm_feature(env, ARM_FEATURE_M_SECURITY)) {
+            gdb_register_coprocessor(cs,
+                arm_gdb_get_m_secextreg, arm_gdb_set_m_secextreg,
+                arm_gen_dynamic_m_secextreg_xml(cs, cs->gdb_num_regs),
+                "arm-m-secext.xml", 0);
+        }
+#endif
+    }
 }
diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c
index 07a6746944..3bee892fb7 100644
--- a/target/arm/gdbstub64.c
+++ b/target/arm/gdbstub64.c
@@ -72,7 +72,7 @@ int aarch64_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
     return 0;
 }
 
-int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg)
+int aarch64_gdb_get_fpu_reg(CPUARMState *env, GByteArray *buf, int reg)
 {
     switch (reg) {
     case 0 ... 31:
@@ -92,7 +92,7 @@ int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg)
     }
 }
 
-int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg)
+int aarch64_gdb_set_fpu_reg(CPUARMState *env, uint8_t *buf, int reg)
 {
     switch (reg) {
     case 0 ... 31:
@@ -116,7 +116,7 @@ int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg)
     }
 }
 
-int arm_gdb_get_svereg(CPUARMState *env, GByteArray *buf, int reg)
+int aarch64_gdb_get_sve_reg(CPUARMState *env, GByteArray *buf, int reg)
 {
     ARMCPU *cpu = env_archcpu(env);
 
@@ -164,7 +164,7 @@ int arm_gdb_get_svereg(CPUARMState *env, GByteArray *buf, int reg)
     return 0;
 }
 
-int arm_gdb_set_svereg(CPUARMState *env, uint8_t *buf, int reg)
+int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg)
 {
     ARMCPU *cpu = env_archcpu(env);
 
@@ -209,3 +209,170 @@ int arm_gdb_set_svereg(CPUARMState *env, uint8_t *buf, int reg)
 
     return 0;
 }
+
+int aarch64_gdb_get_pauth_reg(CPUARMState *env, GByteArray *buf, int reg)
+{
+    switch (reg) {
+    case 0: /* pauth_dmask */
+    case 1: /* pauth_cmask */
+    case 2: /* pauth_dmask_high */
+    case 3: /* pauth_cmask_high */
+        /*
+         * Note that older versions of this feature only contained
+         * pauth_{d,c}mask, for use with Linux user processes, and
+         * thus exclusively in the low half of the address space.
+         *
+         * To support system mode, and to debug kernels, two new regs
+         * were added to cover the high half of the address space.
+         * For the purpose of pauth_ptr_mask, we can use any well-formed
+         * address within the address space half -- here, 0 and -1.
+         */
+        {
+            bool is_data = !(reg & 1);
+            bool is_high = reg & 2;
+            uint64_t mask = pauth_ptr_mask(env, -is_high, is_data);
+            return gdb_get_reg64(buf, mask);
+        }
+    default:
+        return 0;
+    }
+}
+
+int aarch64_gdb_set_pauth_reg(CPUARMState *env, uint8_t *buf, int reg)
+{
+    /* All pseudo registers are read-only. */
+    return 0;
+}
+
+static void output_vector_union_type(GString *s, int reg_width,
+                                     const char *name)
+{
+    struct TypeSize {
+        const char *gdb_type;
+        short size;
+        char sz, suffix;
+    };
+
+    static const struct TypeSize vec_lanes[] = {
+        /* quads */
+        { "uint128", 128, 'q', 'u' },
+        { "int128", 128, 'q', 's' },
+        /* 64 bit */
+        { "ieee_double", 64, 'd', 'f' },
+        { "uint64", 64, 'd', 'u' },
+        { "int64", 64, 'd', 's' },
+        /* 32 bit */
+        { "ieee_single", 32, 's', 'f' },
+        { "uint32", 32, 's', 'u' },
+        { "int32", 32, 's', 's' },
+        /* 16 bit */
+        { "ieee_half", 16, 'h', 'f' },
+        { "uint16", 16, 'h', 'u' },
+        { "int16", 16, 'h', 's' },
+        /* bytes */
+        { "uint8", 8, 'b', 'u' },
+        { "int8", 8, 'b', 's' },
+    };
+
+    static const char suf[] = { 'b', 'h', 's', 'd', 'q' };
+    int i, j;
+
+    /* First define types and totals in a whole VL */
+    for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) {
+        g_string_append_printf(s,
+                               "<vector id=\"%s%c%c\" type=\"%s\" count=\"%d\"/>",
+                               name, vec_lanes[i].sz, vec_lanes[i].suffix,
+                               vec_lanes[i].gdb_type, reg_width / vec_lanes[i].size);
+    }
+
+    /*
+     * Now define a union for each size group containing unsigned and
+     * signed and potentially float versions of each size from 128 to
+     * 8 bits.
+     */
+    for (i = 0; i < ARRAY_SIZE(suf); i++) {
+        int bits = 8 << i;
+
+        g_string_append_printf(s, "<union id=\"%sn%c\">", name, suf[i]);
+        for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) {
+            if (vec_lanes[j].size == bits) {
+                g_string_append_printf(s, "<field name=\"%c\" type=\"%s%c%c\"/>",
+                                       vec_lanes[j].suffix, name,
+                                       vec_lanes[j].sz, vec_lanes[j].suffix);
+            }
+        }
+        g_string_append(s, "</union>");
+    }
+
+    /* And now the final union of unions */
+    g_string_append_printf(s, "<union id=\"%s\">", name);
+    for (i = ARRAY_SIZE(suf) - 1; i >= 0; i--) {
+        g_string_append_printf(s, "<field name=\"%c\" type=\"%sn%c\"/>",
+                               suf[i], name, suf[i]);
+    }
+    g_string_append(s, "</union>");
+}
+
+int arm_gen_dynamic_svereg_xml(CPUState *cs, int orig_base_reg)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+    GString *s = g_string_new(NULL);
+    DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml;
+    int reg_width = cpu->sve_max_vq * 128;
+    int pred_width = cpu->sve_max_vq * 16;
+    int base_reg = orig_base_reg;
+    int i;
+
+    g_string_printf(s, "<?xml version=\"1.0\"?>");
+    g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">");
+    g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">");
+
+    /* Create the vector union type. */
+    output_vector_union_type(s, reg_width, "svev");
+
+    /* Create the predicate vector type. */
+    g_string_append_printf(s,
+                           "<vector id=\"svep\" type=\"uint8\" count=\"%d\"/>",
+                           pred_width / 8);
+
+    /* Define the vector registers. */
+    for (i = 0; i < 32; i++) {
+        g_string_append_printf(s,
+                               "<reg name=\"z%d\" bitsize=\"%d\""
+                               " regnum=\"%d\" type=\"svev\"/>",
+                               i, reg_width, base_reg++);
+    }
+
+    /* fpscr & status registers */
+    g_string_append_printf(s, "<reg name=\"fpsr\" bitsize=\"32\""
+                           " regnum=\"%d\" group=\"float\""
+                           " type=\"int\"/>", base_reg++);
+    g_string_append_printf(s, "<reg name=\"fpcr\" bitsize=\"32\""
+                           " regnum=\"%d\" group=\"float\""
+                           " type=\"int\"/>", base_reg++);
+
+    /* Define the predicate registers. */
+    for (i = 0; i < 16; i++) {
+        g_string_append_printf(s,
+                               "<reg name=\"p%d\" bitsize=\"%d\""
+                               " regnum=\"%d\" type=\"svep\"/>",
+                               i, pred_width, base_reg++);
+    }
+    g_string_append_printf(s,
+                           "<reg name=\"ffr\" bitsize=\"%d\""
+                           " regnum=\"%d\" group=\"vector\""
+                           " type=\"svep\"/>",
+                           pred_width, base_reg++);
+
+    /* Define the vector length pseudo-register. */
+    g_string_append_printf(s,
+                           "<reg name=\"vg\" bitsize=\"64\""
+                           " regnum=\"%d\" type=\"int\"/>",
+                           base_reg++);
+
+    g_string_append_printf(s, "</feature>");
+
+    info->desc = g_string_free(s, false);
+    info->num = base_reg - orig_base_reg;
+    return info->num;
+}
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 82c546f11a..2297626bfb 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -5787,6 +5787,9 @@ uint64_t arm_hcr_el2_eff_secstate(CPUARMState *env, bool secure)
 
 uint64_t arm_hcr_el2_eff(CPUARMState *env)
 {
+    if (arm_feature(env, ARM_FEATURE_M)) {
+        return 0;
+    }
     return arm_hcr_el2_eff_secstate(env, arm_is_secure_below_el3(env));
 }
 
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 3c7341e774..b1ef05963f 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -1344,16 +1344,32 @@ static inline uint64_t pmu_counter_mask(CPUARMState *env)
 }
 
 #ifdef TARGET_AARCH64
-int arm_gdb_get_svereg(CPUARMState *env, GByteArray *buf, int reg);
-int arm_gdb_set_svereg(CPUARMState *env, uint8_t *buf, int reg);
-int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg);
-int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg);
+int arm_gen_dynamic_svereg_xml(CPUState *cpu, int base_reg);
+int aarch64_gdb_get_sve_reg(CPUARMState *env, GByteArray *buf, int reg);
+int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg);
+int aarch64_gdb_get_fpu_reg(CPUARMState *env, GByteArray *buf, int reg);
+int aarch64_gdb_set_fpu_reg(CPUARMState *env, uint8_t *buf, int reg);
+int aarch64_gdb_get_pauth_reg(CPUARMState *env, GByteArray *buf, int reg);
+int aarch64_gdb_set_pauth_reg(CPUARMState *env, uint8_t *buf, int reg);
 void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp);
 void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp);
 void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp);
 void arm_cpu_lpa2_finalize(ARMCPU *cpu, Error **errp);
 #endif
 
+/* Read the CONTROL register as the MRS instruction would. */
+uint32_t arm_v7m_mrs_control(CPUARMState *env, uint32_t secure);
+
+/*
+ * Return a pointer to the location where we currently store the
+ * stack pointer for the requested security state and thread mode.
+ * This pointer will become invalid if the CPU state is updated
+ * such that the stack pointers are switched around (eg changing
+ * the SPSEL control bit).
+ */
+uint32_t *arm_v7m_get_sp_ptr(CPUARMState *env, bool secure,
+                             bool threadmode, bool spsel);
+
 #ifdef CONFIG_USER_ONLY
 static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { }
 #else
@@ -1367,6 +1383,16 @@ int exception_target_el(CPUARMState *env);
 bool arm_singlestep_active(CPUARMState *env);
 bool arm_generate_debug_exceptions(CPUARMState *env);
 
+/**
+ * pauth_ptr_mask:
+ * @env: cpu context
+ * @ptr: selects between TTBR0 and TTBR1
+ * @data: selects between TBI and TBID
+ *
+ * Return a mask of the bits of @ptr that contain the authentication code.
+ */
+uint64_t pauth_ptr_mask(CPUARMState *env, uint64_t ptr, bool data);
+
 /* Add the cpreg definitions for debug related system registers */
 void define_debug_regs(ARMCPU *cpu);
 
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index 8541ef56d6..ec3f51782a 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -1081,70 +1081,119 @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va,
  * check_s2_mmu_setup
  * @cpu:        ARMCPU
  * @is_aa64:    True if the translation regime is in AArch64 state
- * @startlevel: Suggested starting level
- * @inputsize:  Bitsize of IPAs
+ * @tcr:        VTCR_EL2 or VSTCR_EL2
+ * @ds:         Effective value of TCR.DS.
+ * @iasize:     Bitsize of IPAs
  * @stride:     Page-table stride (See the ARM ARM)
  *
- * Returns true if the suggested S2 translation parameters are OK and
- * false otherwise.
+ * Decode the starting level of the S2 lookup, returning INT_MIN if
+ * the configuration is invalid.
  */
-static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level,
-                               int inputsize, int stride, int outputsize)
+static int check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, uint64_t tcr,
+                              bool ds, int iasize, int stride)
 {
-    const int grainsize = stride + 3;
-    int startsizecheck;
-
-    /*
-     * 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;
-    }
-
-    startsizecheck = inputsize - ((3 - level) * stride + grainsize);
-    if (startsizecheck < 1 || startsizecheck > stride + 4) {
-        return false;
-    }
+    int sl0, sl2, startlevel, granulebits, levels;
+    int s1_min_iasize, s1_max_iasize;
 
+    sl0 = extract32(tcr, 6, 2);
     if (is_aa64) {
+        /*
+         * AArch64.S2InvalidTxSZ: While we checked tsz_oob near the top of
+         * get_phys_addr_lpae, that used aa64_va_parameters which apply
+         * to aarch64.  If Stage1 is aarch32, the min_txsz is larger.
+         * See AArch64.S2MinTxSZ, where min_tsz is 24, translated to
+         * inputsize is 64 - 24 = 40.
+         */
+        if (iasize < 40 && !arm_el_is_aa64(&cpu->env, 1)) {
+            goto fail;
+        }
+
+        /*
+         * AArch64.S2InvalidSL: Interpretation of SL depends on the page size,
+         * so interleave AArch64.S2StartLevel.
+         */
         switch (stride) {
-        case 13: /* 64KB Pages.  */
-            if (level == 0 || (level == 1 && outputsize <= 42)) {
-                return false;
+        case 9: /* 4KB */
+            /* SL2 is RES0 unless DS=1 & 4KB granule. */
+            sl2 = extract64(tcr, 33, 1);
+            if (ds && sl2) {
+                if (sl0 != 0) {
+                    goto fail;
+                }
+                startlevel = -1;
+            } else {
+                startlevel = 2 - sl0;
+                switch (sl0) {
+                case 2:
+                    if (arm_pamax(cpu) < 44) {
+                        goto fail;
+                    }
+                    break;
+                case 3:
+                    if (!cpu_isar_feature(aa64_st, cpu)) {
+                        goto fail;
+                    }
+                    startlevel = 3;
+                    break;
+                }
             }
             break;
-        case 11: /* 16KB Pages.  */
-            if (level == 0 || (level == 1 && outputsize <= 40)) {
-                return false;
+        case 11: /* 16KB */
+            switch (sl0) {
+            case 2:
+                if (arm_pamax(cpu) < 42) {
+                    goto fail;
+                }
+                break;
+            case 3:
+                if (!ds) {
+                    goto fail;
+                }
+                break;
             }
+            startlevel = 3 - sl0;
             break;
-        case 9: /* 4KB Pages.  */
-            if (level == 0 && outputsize <= 42) {
-                return false;
+        case 13: /* 64KB */
+            switch (sl0) {
+            case 2:
+                if (arm_pamax(cpu) < 44) {
+                    goto fail;
+                }
+                break;
+            case 3:
+                goto fail;
             }
+            startlevel = 3 - sl0;
             break;
         default:
             g_assert_not_reached();
         }
-
-        /* Inputsize checks.  */
-        if (inputsize > outputsize &&
-            (arm_el_is_aa64(&cpu->env, 1) || inputsize > 40)) {
-            /* This is CONSTRAINED UNPREDICTABLE and we choose to fault.  */
-            return false;
-        }
     } else {
-        /* AArch32 only supports 4KB pages. Assert on that.  */
+        /*
+         * Things are simpler for AArch32 EL2, with only 4k pages.
+         * There is no separate S2InvalidSL function, but AArch32.S2Walk
+         * begins with walkparms.sl0 in {'1x'}.
+         */
         assert(stride == 9);
-
-        if (level == 0) {
-            return false;
+        if (sl0 >= 2) {
+            goto fail;
         }
+        startlevel = 2 - sl0;
     }
-    return true;
+
+    /* AArch{64,32}.S2InconsistentSL are functionally equivalent.  */
+    levels = 3 - startlevel;
+    granulebits = stride + 3;
+
+    s1_min_iasize = levels * stride + granulebits + 1;
+    s1_max_iasize = s1_min_iasize + (stride - 1) + 4;
+
+    if (iasize >= s1_min_iasize && iasize <= s1_max_iasize) {
+        return startlevel;
+    }
+
+ fail:
+    return INT_MIN;
 }
 
 /**
@@ -1300,38 +1349,10 @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw,
          */
         level = 4 - (inputsize - 4) / stride;
     } else {
-        /*
-         * For stage 2 translations the starting level is specified by the
-         * VTCR_EL2.SL0 field (whose interpretation depends on the page size)
-         */
-        uint32_t sl0 = extract32(tcr, 6, 2);
-        uint32_t sl2 = extract64(tcr, 33, 1);
-        int32_t startlevel;
-        bool ok;
-
-        /* SL2 is RES0 unless DS=1 & 4kb granule. */
-        if (param.ds && stride == 9 && sl2) {
-            if (sl0 != 0) {
-                level = 0;
-                goto do_translation_fault;
-            }
-            startlevel = -1;
-        } else if (!aarch64 || stride == 9) {
-            /* AArch32 or 4KB pages */
-            startlevel = 2 - sl0;
-
-            if (cpu_isar_feature(aa64_st, cpu)) {
-                startlevel &= 3;
-            }
-        } else {
-            /* 16KB or 64KB pages */
-            startlevel = 3 - sl0;
-        }
-
-        /* Check that the starting level is valid. */
-        ok = check_s2_mmu_setup(cpu, aarch64, startlevel,
-                                inputsize, stride, outputsize);
-        if (!ok) {
+        int startlevel = check_s2_mmu_setup(cpu, aarch64, tcr, param.ds,
+                                            inputsize, stride);
+        if (startlevel == INT_MIN) {
+            level = 0;
             goto do_translation_fault;
         }
         level = startlevel;
diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index f94e87e728..081fc3f5f7 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -56,7 +56,7 @@ static uint32_t v7m_mrs_xpsr(CPUARMState *env, uint32_t reg, unsigned el)
     return xpsr_read(env) & mask;
 }
 
-static uint32_t v7m_mrs_control(CPUARMState *env, uint32_t secure)
+uint32_t arm_v7m_mrs_control(CPUARMState *env, uint32_t secure)
 {
     uint32_t value = env->v7m.control[secure];
 
@@ -93,7 +93,7 @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg)
     case 0 ... 7: /* xPSR sub-fields */
         return v7m_mrs_xpsr(env, reg, 0);
     case 20: /* CONTROL */
-        return v7m_mrs_control(env, 0);
+        return arm_v7m_mrs_control(env, 0);
     default:
         /* Unprivileged reads others as zero.  */
         return 0;
@@ -650,42 +650,6 @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
     arm_rebuild_hflags(env);
 }
 
-static uint32_t *get_v7m_sp_ptr(CPUARMState *env, bool secure, bool threadmode,
-                                bool spsel)
-{
-    /*
-     * Return a pointer to the location where we currently store the
-     * stack pointer for the requested security state and thread mode.
-     * This pointer will become invalid if the CPU state is updated
-     * such that the stack pointers are switched around (eg changing
-     * the SPSEL control bit).
-     * Compare the v8M ARM ARM pseudocode LookUpSP_with_security_mode().
-     * Unlike that pseudocode, we require the caller to pass us in the
-     * SPSEL control bit value; this is because we also use this
-     * function in handling of pushing of the callee-saves registers
-     * part of the v8M stack frame (pseudocode PushCalleeStack()),
-     * and in the tailchain codepath the SPSEL bit comes from the exception
-     * return magic LR value from the previous exception. The pseudocode
-     * opencodes the stack-selection in PushCalleeStack(), but we prefer
-     * to make this utility function generic enough to do the job.
-     */
-    bool want_psp = threadmode && spsel;
-
-    if (secure == env->v7m.secure) {
-        if (want_psp == v7m_using_psp(env)) {
-            return &env->regs[13];
-        } else {
-            return &env->v7m.other_sp;
-        }
-    } else {
-        if (want_psp) {
-            return &env->v7m.other_ss_psp;
-        } else {
-            return &env->v7m.other_ss_msp;
-        }
-    }
-}
-
 static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure,
                                 uint32_t *pvec)
 {
@@ -810,8 +774,8 @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain,
             !mode;
 
         mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, M_REG_S, priv);
-        frame_sp_p = get_v7m_sp_ptr(env, M_REG_S, mode,
-                                    lr & R_V7M_EXCRET_SPSEL_MASK);
+        frame_sp_p = arm_v7m_get_sp_ptr(env, M_REG_S, mode,
+                                        lr & R_V7M_EXCRET_SPSEL_MASK);
         want_psp = mode && (lr & R_V7M_EXCRET_SPSEL_MASK);
         if (want_psp) {
             limit = env->v7m.psplim[M_REG_S];
@@ -1656,10 +1620,8 @@ static void do_v7m_exception_exit(ARMCPU *cpu)
          * use 'frame_sp_p' after we do something that makes it invalid.
          */
         bool spsel = env->v7m.control[return_to_secure] & R_V7M_CONTROL_SPSEL_MASK;
-        uint32_t *frame_sp_p = get_v7m_sp_ptr(env,
-                                              return_to_secure,
-                                              !return_to_handler,
-                                              spsel);
+        uint32_t *frame_sp_p = arm_v7m_get_sp_ptr(env, return_to_secure,
+                                                  !return_to_handler, spsel);
         uint32_t frameptr = *frame_sp_p;
         bool pop_ok = true;
         ARMMMUIdx mmu_idx;
@@ -1965,7 +1927,7 @@ static bool do_v7m_function_return(ARMCPU *cpu)
         threadmode = !arm_v7m_is_handler_mode(env);
         spsel = env->v7m.control[M_REG_S] & R_V7M_CONTROL_SPSEL_MASK;
 
-        frame_sp_p = get_v7m_sp_ptr(env, true, threadmode, spsel);
+        frame_sp_p = arm_v7m_get_sp_ptr(env, true, threadmode, spsel);
         frameptr = *frame_sp_p;
 
         /*
@@ -2465,7 +2427,7 @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg)
     case 0 ... 7: /* xPSR sub-fields */
         return v7m_mrs_xpsr(env, reg, el);
     case 20: /* CONTROL */
-        return v7m_mrs_control(env, env->v7m.secure);
+        return arm_v7m_mrs_control(env, env->v7m.secure);
     case 0x94: /* CONTROL_NS */
         /*
          * We have to handle this here because unprivileged Secure code
@@ -2900,3 +2862,39 @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op)
 }
 
 #endif /* !CONFIG_USER_ONLY */
+
+uint32_t *arm_v7m_get_sp_ptr(CPUARMState *env, bool secure, bool threadmode,
+                             bool spsel)
+{
+    /*
+     * Return a pointer to the location where we currently store the
+     * stack pointer for the requested security state and thread mode.
+     * This pointer will become invalid if the CPU state is updated
+     * such that the stack pointers are switched around (eg changing
+     * the SPSEL control bit).
+     * Compare the v8M ARM ARM pseudocode LookUpSP_with_security_mode().
+     * Unlike that pseudocode, we require the caller to pass us in the
+     * SPSEL control bit value; this is because we also use this
+     * function in handling of pushing of the callee-saves registers
+     * part of the v8M stack frame (pseudocode PushCalleeStack()),
+     * and in the tailchain codepath the SPSEL bit comes from the exception
+     * return magic LR value from the previous exception. The pseudocode
+     * opencodes the stack-selection in PushCalleeStack(), but we prefer
+     * to make this utility function generic enough to do the job.
+     */
+    bool want_psp = threadmode && spsel;
+
+    if (secure == env->v7m.secure) {
+        if (want_psp == v7m_using_psp(env)) {
+            return &env->regs[13];
+        } else {
+            return &env->v7m.other_sp;
+        }
+    } else {
+        if (want_psp) {
+            return &env->v7m.other_ss_psp;
+        } else {
+            return &env->v7m.other_ss_msp;
+        }
+    }
+}
diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c
index d0483bf051..20f347332d 100644
--- a/target/arm/tcg/pauth_helper.c
+++ b/target/arm/tcg/pauth_helper.c
@@ -339,14 +339,32 @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier,
     return pac | ext | ptr;
 }
 
-static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param)
+static uint64_t pauth_ptr_mask_internal(ARMVAParameters param)
 {
-    /* Note that bit 55 is used whether or not the regime has 2 ranges. */
-    uint64_t extfield = sextract64(ptr, 55, 1);
     int bot_pac_bit = 64 - param.tsz;
     int top_pac_bit = 64 - 8 * param.tbi;
 
-    return deposit64(ptr, bot_pac_bit, top_pac_bit - bot_pac_bit, extfield);
+    return MAKE_64BIT_MASK(bot_pac_bit, top_pac_bit - bot_pac_bit);
+}
+
+static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param)
+{
+    uint64_t mask = pauth_ptr_mask_internal(param);
+
+    /* Note that bit 55 is used whether or not the regime has 2 ranges. */
+    if (extract64(ptr, 55, 1)) {
+        return ptr | mask;
+    } else {
+        return ptr & ~mask;
+    }
+}
+
+uint64_t pauth_ptr_mask(CPUARMState *env, uint64_t ptr, bool data)
+{
+    ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env);
+    ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data);
+
+    return pauth_ptr_mask_internal(param);
 }
 
 static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier,