Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20181016-1' into staging

target-arm queue:
 * hw/arm/virt: add DT property /secure-chosen/stdout-path indicating secure UART
 * target/arm: Fix aarch64_sve_change_el wrt EL0
 * target/arm: Define fields of ISAR registers
 * target/arm: Align cortex-r5 id_isar0
 * target/arm: Fix cortex-a7 id_isar0
 * net/cadence_gem: Fix various bugs, add support for new
   features that will be used by the Xilinx Versal board
 * target-arm: powerctl: Enable HVC when starting CPUs to EL2
 * target/arm: Add the Cortex-A72
 * target/arm: Mark PMINTENCLR and PMINTENCLR_EL1 accesses as possibly doing IO
 * target/arm: Mask PMOVSR writes based on supported counters
 * target/arm: Initialize ARMMMUFaultInfo in v7m_stack_read/write
 * coccinelle: new inplace-byteswaps.cocci to remove inplace-byteswapping calls

# gpg: Signature made Tue 16 Oct 2018 17:42:01 BST
# gpg:                using RSA key 3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20181016-1:
  coccinelle: new inplace-byteswaps.cocci to remove inplace-byteswapping calls
  target/arm: Initialize ARMMMUFaultInfo in v7m_stack_read/write
  target/arm: Mask PMOVSR writes based on supported counters
  target/arm: Mark PMINTENCLR and PMINTENCLR_EL1 accesses as possibly doing IO
  target/arm: Add the Cortex-A72
  target-arm: powerctl: Enable HVC when starting CPUs to EL2
  net: cadence_gem: Implement support for 64bit descriptor addresses
  net: cadence_gem: Add support for selecting the DMA MemoryRegion
  net: cadence_gem: Add support for extended descriptors
  net: cadence_gem: Add macro with max number of descriptor words
  net: cadence_gem: Use uint32_t for 32bit descriptor words
  net: cadence_gem: Disable TSU feature bit
  target/arm: Fix cortex-a7 id_isar0
  target/arm: Align cortex-r5 id_isar0
  target/arm: Define fields of ISAR registers
  target/arm: Fix aarch64_sve_change_el wrt EL0
  hw/arm/virt: add DT property /secure-chosen/stdout-path indicating secure UART
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

hw/arm/virt.c

@@ -712,6 +712,10 @@ static void create_uart(const VirtMachineState *vms, qemu_irq *pic, int uart,
         /* Mark as not usable by the normal world */
         qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled");
         qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay");
+
+        qemu_fdt_add_subnode(vms->fdt, "/secure-chosen");
+        qemu_fdt_setprop_string(vms->fdt, "/secure-chosen", "stdout-path",
+                                nodename);
     }
 
     g_free(nodename);

hw/net/cadence_gem.c

@@ -28,6 +28,7 @@
 #include "hw/net/cadence_gem.h"
 #include "qapi/error.h"
 #include "qemu/log.h"
+#include "sysemu/dma.h"
 #include "net/checksum.h"
 
 #ifdef CADENCE_GEM_ERR_DEBUG
@@ -152,6 +153,9 @@
 #define GEM_RECEIVE_Q1_PTR              (0x00000480 / 4)
 #define GEM_RECEIVE_Q7_PTR              (GEM_RECEIVE_Q1_PTR + 6)
 
+#define GEM_TBQPH                       (0x000004C8 / 4)
+#define GEM_RBQPH                       (0x000004D4 / 4)
+
 #define GEM_INT_Q1_ENABLE               (0x00000600 / 4)
 #define GEM_INT_Q7_ENABLE               (GEM_INT_Q1_ENABLE + 6)
 
@@ -207,6 +211,9 @@
 #define GEM_NWCFG_BCAST_REJ    0x00000020 /* Reject broadcast packets */
 #define GEM_NWCFG_PROMISC      0x00000010 /* Accept all packets */
 
+#define GEM_DMACFG_ADDR_64B    (1U << 30)
+#define GEM_DMACFG_TX_BD_EXT   (1U << 29)
+#define GEM_DMACFG_RX_BD_EXT   (1U << 28)
 #define GEM_DMACFG_RBUFSZ_M    0x00FF0000 /* DMA RX Buffer Size mask */
 #define GEM_DMACFG_RBUFSZ_S    16         /* DMA RX Buffer Size shift */
 #define GEM_DMACFG_RBUFSZ_MUL  64         /* DMA RX Buffer Size multiplier */
@@ -302,42 +309,47 @@
 
 #define GEM_MODID_VALUE 0x00020118
 
-static inline unsigned tx_desc_get_buffer(unsigned *desc)
+static inline uint64_t tx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc)
 {
-    return desc[0];
+    uint64_t ret = desc[0];
+
+    if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) {
+        ret |= (uint64_t)desc[2] << 32;
+    }
+    return ret;
 }
 
-static inline unsigned tx_desc_get_used(unsigned *desc)
+static inline unsigned tx_desc_get_used(uint32_t *desc)
 {
     return (desc[1] & DESC_1_USED) ? 1 : 0;
 }
 
-static inline void tx_desc_set_used(unsigned *desc)
+static inline void tx_desc_set_used(uint32_t *desc)
 {
     desc[1] |= DESC_1_USED;
 }
 
-static inline unsigned tx_desc_get_wrap(unsigned *desc)
+static inline unsigned tx_desc_get_wrap(uint32_t *desc)
 {
     return (desc[1] & DESC_1_TX_WRAP) ? 1 : 0;
 }
 
-static inline unsigned tx_desc_get_last(unsigned *desc)
+static inline unsigned tx_desc_get_last(uint32_t *desc)
 {
     return (desc[1] & DESC_1_TX_LAST) ? 1 : 0;
 }
 
-static inline void tx_desc_set_last(unsigned *desc)
+static inline void tx_desc_set_last(uint32_t *desc)
 {
     desc[1] |= DESC_1_TX_LAST;
 }
 
-static inline unsigned tx_desc_get_length(unsigned *desc)
+static inline unsigned tx_desc_get_length(uint32_t *desc)
 {
     return desc[1] & DESC_1_LENGTH;
 }
 
-static inline void print_gem_tx_desc(unsigned *desc, uint8_t queue)
+static inline void print_gem_tx_desc(uint32_t *desc, uint8_t queue)
 {
     DB_PRINT("TXDESC (queue %" PRId8 "):\n", queue);
     DB_PRINT("bufaddr: 0x%08x\n", *desc);
@@ -347,58 +359,79 @@ static inline void print_gem_tx_desc(unsigned *desc, uint8_t queue)
     DB_PRINT("length:  %d\n", tx_desc_get_length(desc));
 }
 
-static inline unsigned rx_desc_get_buffer(unsigned *desc)
+static inline uint64_t rx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc)
+{
+    uint64_t ret = desc[0] & ~0x3UL;
+
+    if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) {
+        ret |= (uint64_t)desc[2] << 32;
+    }
+    return ret;
+}
+
+static inline int gem_get_desc_len(CadenceGEMState *s, bool rx_n_tx)
 {
-    return desc[0] & ~0x3UL;
+    int ret = 2;
+
+    if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) {
+        ret += 2;
+    }
+    if (s->regs[GEM_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT
+                                       : GEM_DMACFG_TX_BD_EXT)) {
+        ret += 2;
+    }
+
+    assert(ret <= DESC_MAX_NUM_WORDS);
+    return ret;
 }
 
-static inline unsigned rx_desc_get_wrap(unsigned *desc)
+static inline unsigned rx_desc_get_wrap(uint32_t *desc)
 {
     return desc[0] & DESC_0_RX_WRAP ? 1 : 0;
 }
 
-static inline unsigned rx_desc_get_ownership(unsigned *desc)
+static inline unsigned rx_desc_get_ownership(uint32_t *desc)
 {
     return desc[0] & DESC_0_RX_OWNERSHIP ? 1 : 0;
 }
 
-static inline void rx_desc_set_ownership(unsigned *desc)
+static inline void rx_desc_set_ownership(uint32_t *desc)
 {
     desc[0] |= DESC_0_RX_OWNERSHIP;
 }
 
-static inline void rx_desc_set_sof(unsigned *desc)
+static inline void rx_desc_set_sof(uint32_t *desc)
 {
     desc[1] |= DESC_1_RX_SOF;
 }
 
-static inline void rx_desc_set_eof(unsigned *desc)
+static inline void rx_desc_set_eof(uint32_t *desc)
 {
     desc[1] |= DESC_1_RX_EOF;
 }
 
-static inline void rx_desc_set_length(unsigned *desc, unsigned len)
+static inline void rx_desc_set_length(uint32_t *desc, unsigned len)
 {
     desc[1] &= ~DESC_1_LENGTH;
     desc[1] |= len;
 }
 
-static inline void rx_desc_set_broadcast(unsigned *desc)
+static inline void rx_desc_set_broadcast(uint32_t *desc)
 {
     desc[1] |= R_DESC_1_RX_BROADCAST;
 }
 
-static inline void rx_desc_set_unicast_hash(unsigned *desc)
+static inline void rx_desc_set_unicast_hash(uint32_t *desc)
 {
     desc[1] |= R_DESC_1_RX_UNICAST_HASH;
 }
 
-static inline void rx_desc_set_multicast_hash(unsigned *desc)
+static inline void rx_desc_set_multicast_hash(uint32_t *desc)
 {
     desc[1] |= R_DESC_1_RX_MULTICAST_HASH;
 }
 
-static inline void rx_desc_set_sar(unsigned *desc, int sar_idx)
+static inline void rx_desc_set_sar(uint32_t *desc, int sar_idx)
 {
     desc[1] = deposit32(desc[1], R_DESC_1_RX_SAR_SHIFT, R_DESC_1_RX_SAR_LENGTH,
                         sar_idx);
@@ -419,7 +452,7 @@ static void gem_init_register_masks(CadenceGEMState *s)
     memset(&s->regs_ro[0], 0, sizeof(s->regs_ro));
     s->regs_ro[GEM_NWCTRL]   = 0xFFF80000;
     s->regs_ro[GEM_NWSTATUS] = 0xFFFFFFFF;
-    s->regs_ro[GEM_DMACFG]   = 0xFE00F000;
+    s->regs_ro[GEM_DMACFG]   = 0x8E00F000;
     s->regs_ro[GEM_TXSTATUS] = 0xFFFFFE08;
     s->regs_ro[GEM_RXQBASE]  = 0x00000003;
     s->regs_ro[GEM_TXQBASE]  = 0x00000003;
@@ -802,17 +835,42 @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr,
     return 0;
 }
 
+static hwaddr gem_get_desc_addr(CadenceGEMState *s, bool tx, int q)
+{
+    hwaddr desc_addr = 0;
+
+    if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) {
+        desc_addr = s->regs[tx ? GEM_TBQPH : GEM_RBQPH];
+    }
+    desc_addr <<= 32;
+    desc_addr |= tx ? s->tx_desc_addr[q] : s->rx_desc_addr[q];
+    return desc_addr;
+}
+
+static hwaddr gem_get_tx_desc_addr(CadenceGEMState *s, int q)
+{
+    return gem_get_desc_addr(s, true, q);
+}
+
+static hwaddr gem_get_rx_desc_addr(CadenceGEMState *s, int q)
+{
+    return gem_get_desc_addr(s, false, q);
+}
+
 static void gem_get_rx_desc(CadenceGEMState *s, int q)
 {
-    DB_PRINT("read descriptor 0x%x\n", (unsigned)s->rx_desc_addr[q]);
+    hwaddr desc_addr = gem_get_rx_desc_addr(s, q);
+
+    DB_PRINT("read descriptor 0x%" HWADDR_PRIx "\n", desc_addr);
+
     /* read current descriptor */
-    cpu_physical_memory_read(s->rx_desc_addr[q],
-                             (uint8_t *)s->rx_desc[q], sizeof(s->rx_desc[q]));
+    address_space_read(&s->dma_as, desc_addr, MEMTXATTRS_UNSPECIFIED,
+                       (uint8_t *)s->rx_desc[q],
+                       sizeof(uint32_t) * gem_get_desc_len(s, true));
 
     /* Descriptor owned by software ? */
     if (rx_desc_get_ownership(s->rx_desc[q]) == 1) {
-        DB_PRINT("descriptor 0x%x owned by sw.\n",
-                 (unsigned)s->rx_desc_addr[q]);
+        DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr);
         s->regs[GEM_RXSTATUS] |= GEM_RXSTATUS_NOBUF;
         s->regs[GEM_ISR] |= GEM_INT_RXUSED & ~(s->regs[GEM_IMR]);
         /* Handle interrupt consequences */
@@ -916,6 +974,8 @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size)
     q = get_queue_from_screen(s, rxbuf_ptr, rxbufsize);
 
     while (bytes_to_copy) {
+        hwaddr desc_addr;
+
         /* Do nothing if receive is not enabled. */
         if (!gem_can_receive(nc)) {
             assert(!first_desc);
@@ -926,9 +986,10 @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size)
                 rx_desc_get_buffer(s->rx_desc[q]));
 
         /* Copy packet data to emulated DMA buffer */
-        cpu_physical_memory_write(rx_desc_get_buffer(s->rx_desc[q]) +
-                                                                 rxbuf_offset,
-                                  rxbuf_ptr, MIN(bytes_to_copy, rxbufsize));
+        address_space_write(&s->dma_as, rx_desc_get_buffer(s, s->rx_desc[q]) +
+                                                                  rxbuf_offset,
+                            MEMTXATTRS_UNSPECIFIED, rxbuf_ptr,
+                            MIN(bytes_to_copy, rxbufsize));
         rxbuf_ptr += MIN(bytes_to_copy, rxbufsize);
         bytes_to_copy -= MIN(bytes_to_copy, rxbufsize);
 
@@ -962,9 +1023,11 @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size)
         }
 
         /* Descriptor write-back.  */
-        cpu_physical_memory_write(s->rx_desc_addr[q],
-                                  (uint8_t *)s->rx_desc[q],
-                                  sizeof(s->rx_desc[q]));
+        desc_addr = gem_get_rx_desc_addr(s, q);
+        address_space_write(&s->dma_as, desc_addr,
+                            MEMTXATTRS_UNSPECIFIED,
+                            (uint8_t *)s->rx_desc[q],
+                            sizeof(uint32_t) * gem_get_desc_len(s, true));
 
         /* Next descriptor */
         if (rx_desc_get_wrap(s->rx_desc[q])) {
@@ -972,7 +1035,7 @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size)
             s->rx_desc_addr[q] = s->regs[GEM_RXQBASE];
         } else {
             DB_PRINT("incrementing RX descriptor list\n");
-            s->rx_desc_addr[q] += 8;
+            s->rx_desc_addr[q] += 4 * gem_get_desc_len(s, true);
         }
 
         gem_get_rx_desc(s, q);
@@ -1042,7 +1105,7 @@ static void gem_transmit_updatestats(CadenceGEMState *s, const uint8_t *packet,
  */
 static void gem_transmit(CadenceGEMState *s)
 {
-    unsigned    desc[2];
+    uint32_t desc[DESC_MAX_NUM_WORDS];
     hwaddr packet_desc_addr;
     uint8_t     tx_packet[2048];
     uint8_t     *p;
@@ -1065,11 +1128,12 @@ static void gem_transmit(CadenceGEMState *s)
 
     for (q = s->num_priority_queues - 1; q >= 0; q--) {
         /* read current descriptor */
-        packet_desc_addr = s->tx_desc_addr[q];
+        packet_desc_addr = gem_get_tx_desc_addr(s, q);
 
         DB_PRINT("read descriptor 0x%" HWADDR_PRIx "\n", packet_desc_addr);
-        cpu_physical_memory_read(packet_desc_addr,
-                                 (uint8_t *)desc, sizeof(desc));
+        address_space_read(&s->dma_as, packet_desc_addr,
+                           MEMTXATTRS_UNSPECIFIED, (uint8_t *)desc,
+                           sizeof(uint32_t) * gem_get_desc_len(s, false));
         /* Handle all descriptors owned by hardware */
         while (tx_desc_get_used(desc) == 0) {
 
@@ -1082,7 +1146,7 @@ static void gem_transmit(CadenceGEMState *s)
             /* The real hardware would eat this (and possibly crash).
              * For QEMU let's lend a helping hand.
              */
-            if ((tx_desc_get_buffer(desc) == 0) ||
+            if ((tx_desc_get_buffer(s, desc) == 0) ||
                 (tx_desc_get_length(desc) == 0)) {
                 DB_PRINT("Invalid TX descriptor @ 0x%x\n",
                          (unsigned)packet_desc_addr);
@@ -1101,30 +1165,35 @@ static void gem_transmit(CadenceGEMState *s)
             /* Gather this fragment of the packet from "dma memory" to our
              * contig buffer.
              */
-            cpu_physical_memory_read(tx_desc_get_buffer(desc), p,
-                                     tx_desc_get_length(desc));
+            address_space_read(&s->dma_as, tx_desc_get_buffer(s, desc),
+                               MEMTXATTRS_UNSPECIFIED,
+                               p, tx_desc_get_length(desc));
             p += tx_desc_get_length(desc);
             total_bytes += tx_desc_get_length(desc);
 
             /* Last descriptor for this packet; hand the whole thing off */
             if (tx_desc_get_last(desc)) {
-                unsigned    desc_first[2];
+                uint32_t desc_first[DESC_MAX_NUM_WORDS];
+                hwaddr desc_addr = gem_get_tx_desc_addr(s, q);
 
                 /* Modify the 1st descriptor of this packet to be owned by
                  * the processor.
                  */
-                cpu_physical_memory_read(s->tx_desc_addr[q],
-                                         (uint8_t *)desc_first,
-                                         sizeof(desc_first));
+                address_space_read(&s->dma_as, desc_addr,
+                                   MEMTXATTRS_UNSPECIFIED,
+                                   (uint8_t *)desc_first,
+                                   sizeof(desc_first));
                 tx_desc_set_used(desc_first);
-                cpu_physical_memory_write(s->tx_desc_addr[q],
-                                          (uint8_t *)desc_first,
-                                          sizeof(desc_first));
+                address_space_write(&s->dma_as, desc_addr,
+                                  MEMTXATTRS_UNSPECIFIED,
+                                  (uint8_t *)desc_first,
+                                   sizeof(desc_first));
                 /* Advance the hardware current descriptor past this packet */
                 if (tx_desc_get_wrap(desc)) {
                     s->tx_desc_addr[q] = s->regs[GEM_TXQBASE];
                 } else {
-                    s->tx_desc_addr[q] = packet_desc_addr + 8;
+                    s->tx_desc_addr[q] = packet_desc_addr +
+                                         4 * gem_get_desc_len(s, false);
                 }
                 DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]);
 
@@ -1168,11 +1237,12 @@ static void gem_transmit(CadenceGEMState *s)
                 tx_desc_set_last(desc);
                 packet_desc_addr = s->regs[GEM_TXQBASE];
             } else {
-                packet_desc_addr += 8;
+                packet_desc_addr += 4 * gem_get_desc_len(s, false);
             }
             DB_PRINT("read descriptor 0x%" HWADDR_PRIx "\n", packet_desc_addr);
-            cpu_physical_memory_read(packet_desc_addr,
-                                     (uint8_t *)desc, sizeof(desc));
+            address_space_read(&s->dma_as, packet_desc_addr,
+                              MEMTXATTRS_UNSPECIFIED, (uint8_t *)desc,
+                              sizeof(uint32_t) * gem_get_desc_len(s, false));
         }
 
         if (tx_desc_get_used(desc)) {
@@ -1228,7 +1298,7 @@ static void gem_reset(DeviceState *d)
     s->regs[GEM_MODID] = s->revision;
     s->regs[GEM_DESCONF] = 0x02500111;
     s->regs[GEM_DESCONF2] = 0x2ab13fff;
-    s->regs[GEM_DESCONF5] = 0x002f2145;
+    s->regs[GEM_DESCONF5] = 0x002f2045;
     s->regs[GEM_DESCONF6] = 0x00000200;
 
     /* Set MAC address */
@@ -1463,6 +1533,9 @@ static void gem_realize(DeviceState *dev, Error **errp)
     CadenceGEMState *s = CADENCE_GEM(dev);
     int i;
 
+    address_space_init(&s->dma_as,
+                       s->dma_mr ? s->dma_mr : get_system_memory(), "dma");
+
     if (s->num_priority_queues == 0 ||
         s->num_priority_queues > MAX_PRIORITY_QUEUES) {
         error_setg(errp, "Invalid num-priority-queues value: %" PRIx8,
@@ -1500,6 +1573,12 @@ static void gem_init(Object *obj)
                           "enet", sizeof(s->regs));
 
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem);
+
+    object_property_add_link(obj, "dma", TYPE_MEMORY_REGION,
+                             (Object **)&s->dma_mr,
+                             qdev_prop_allow_set_link_before_realize,
+                             OBJ_PROP_LINK_STRONG,
+                             &error_abort);
 }
 
 static const VMStateDescription vmstate_cadence_gem = {

include/hw/net/cadence_gem.h

@@ -32,6 +32,9 @@
 
 #define CADENCE_GEM_MAXREG        (0x00000800 / 4) /* Last valid GEM address */
 
+/* Max number of words in a DMA descriptor.  */
+#define DESC_MAX_NUM_WORDS              6
+
 #define MAX_PRIORITY_QUEUES             8
 #define MAX_TYPE1_SCREENERS             16
 #define MAX_TYPE2_SCREENERS             16
@@ -42,6 +45,8 @@ typedef struct CadenceGEMState {
 
     /*< public >*/
     MemoryRegion iomem;
+    MemoryRegion *dma_mr;
+    AddressSpace dma_as;
     NICState *nic;
     NICConf conf;
     qemu_irq irq[MAX_PRIORITY_QUEUES];
@@ -74,7 +79,7 @@ typedef struct CadenceGEMState {
 
     uint8_t can_rx_state; /* Debug only */
 
-    unsigned rx_desc[MAX_PRIORITY_QUEUES][2];
+    uint32_t rx_desc[MAX_PRIORITY_QUEUES][DESC_MAX_NUM_WORDS];
 
     bool sar_active[4];
 } CadenceGEMState;

scripts/coccinelle/inplace-byteswaps.cocci

+// Replace uses of in-place byteswapping functions with calls to the
+// equivalent not-in-place functions.  This is necessary to avoid
+// undefined behaviour if the expression being swapped is a field in a
+// packed struct.
+
+@@
+expression E;
+@@
+-be16_to_cpus(&E);
++E = be16_to_cpu(E);
+@@
+expression E;
+@@
+-be32_to_cpus(&E);
++E = be32_to_cpu(E);
+@@
+expression E;
+@@
+-be64_to_cpus(&E);
++E = be64_to_cpu(E);
+@@
+expression E;
+@@
+-cpu_to_be16s(&E);
++E = cpu_to_be16(E);
+@@
+expression E;
+@@
+-cpu_to_be32s(&E);
++E = cpu_to_be32(E);
+@@
+expression E;
+@@
+-cpu_to_be64s(&E);
++E = cpu_to_be64(E);
+@@
+expression E;
+@@
+-le16_to_cpus(&E);
++E = le16_to_cpu(E);
+@@
+expression E;
+@@
+-le32_to_cpus(&E);
++E = le32_to_cpu(E);
+@@
+expression E;
+@@
+-le64_to_cpus(&E);
++E = le64_to_cpu(E);
+@@
+expression E;
+@@
+-cpu_to_le16s(&E);
++E = cpu_to_le16(E);
+@@
+expression E;
+@@
+-cpu_to_le32s(&E);
++E = cpu_to_le32(E);
+@@
+expression E;
+@@
+-cpu_to_le64s(&E);
++E = cpu_to_le64(E);

target/arm/arm-powerctl.c

@@ -103,6 +103,16 @@ static void arm_set_cpu_on_async_work(CPUState *target_cpu_state,
     } else {
         /* Processor is not in secure mode */
         target_cpu->env.cp15.scr_el3 |= SCR_NS;
+
+        /*
+         * If QEMU is providing the equivalent of EL3 firmware, then we need
+         * to make sure a CPU targeting EL2 comes out of reset with a
+         * functional HVC insn.
+         */
+        if (arm_feature(&target_cpu->env, ARM_FEATURE_EL3)
+            && info->target_el == 2) {
+            target_cpu->env.cp15.scr_el3 |= SCR_HCE;
+        }
     }
 
     /* We check if the started CPU is now at the correct level */

target/arm/cpu.c

@@ -1397,7 +1397,7 @@ static void cortex_r5_initfn(Object *obj)
     cpu->id_mmfr1 = 0x00000000;
     cpu->id_mmfr2 = 0x01200000;
     cpu->id_mmfr3 = 0x0211;
-    cpu->id_isar0 = 0x2101111;
+    cpu->id_isar0 = 0x02101111;
     cpu->id_isar1 = 0x13112111;
     cpu->id_isar2 = 0x21232141;
     cpu->id_isar3 = 0x01112131;
@@ -1587,7 +1587,10 @@ static void cortex_a7_initfn(Object *obj)
     cpu->id_mmfr1 = 0x40000000;
     cpu->id_mmfr2 = 0x01240000;
     cpu->id_mmfr3 = 0x02102211;
-    cpu->id_isar0 = 0x01101110;
+    /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but
+     * table 4-41 gives 0x02101110, which includes the arm div insns.
+     */
+    cpu->id_isar0 = 0x02101110;
     cpu->id_isar1 = 0x13112111;
     cpu->id_isar2 = 0x21232041;
     cpu->id_isar3 = 0x11112131;

target/arm/cpu.h

@@ -911,10 +911,13 @@ int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
 int aarch64_cpu_gdb_read_register(CPUState *cpu, uint8_t *buf, int reg);
 int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
 void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq);
-void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el);
+void aarch64_sve_change_el(CPUARMState *env, int old_el,
+                           int new_el, bool el0_a64);
 #else
 static inline void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) { }
-static inline void aarch64_sve_change_el(CPUARMState *env, int o, int n) { }
+static inline void aarch64_sve_change_el(CPUARMState *env, int o,
+                                         int n, bool a)
+{ }
 #endif
 
 target_ulong do_arm_semihosting(CPUARMState *env);
@@ -1440,6 +1443,94 @@ FIELD(V7M_CSSELR, LEVEL, 1, 3)
  */
 FIELD(V7M_CSSELR, INDEX, 0, 4)
 
+/*
+ * System register ID fields.
+ */
+FIELD(ID_ISAR0, SWAP, 0, 4)
+FIELD(ID_ISAR0, BITCOUNT, 4, 4)
+FIELD(ID_ISAR0, BITFIELD, 8, 4)
+FIELD(ID_ISAR0, CMPBRANCH, 12, 4)
+FIELD(ID_ISAR0, COPROC, 16, 4)
+FIELD(ID_ISAR0, DEBUG, 20, 4)
+FIELD(ID_ISAR0, DIVIDE, 24, 4)
+
+FIELD(ID_ISAR1, ENDIAN, 0, 4)
+FIELD(ID_ISAR1, EXCEPT, 4, 4)
+FIELD(ID_ISAR1, EXCEPT_AR, 8, 4)
+FIELD(ID_ISAR1, EXTEND, 12, 4)
+FIELD(ID_ISAR1, IFTHEN, 16, 4)
+FIELD(ID_ISAR1, IMMEDIATE, 20, 4)
+FIELD(ID_ISAR1, INTERWORK, 24, 4)
+FIELD(ID_ISAR1, JAZELLE, 28, 4)
+
+FIELD(ID_ISAR2, LOADSTORE, 0, 4)
+FIELD(ID_ISAR2, MEMHINT, 4, 4)
+FIELD(ID_ISAR2, MULTIACCESSINT, 8, 4)
+FIELD(ID_ISAR2, MULT, 12, 4)
+FIELD(ID_ISAR2, MULTS, 16, 4)
+FIELD(ID_ISAR2, MULTU, 20, 4)
+FIELD(ID_ISAR2, PSR_AR, 24, 4)
+FIELD(ID_ISAR2, REVERSAL, 28, 4)
+
+FIELD(ID_ISAR3, SATURATE, 0, 4)
+FIELD(ID_ISAR3, SIMD, 4, 4)
+FIELD(ID_ISAR3, SVC, 8, 4)
+FIELD(ID_ISAR3, SYNCHPRIM, 12, 4)
+FIELD(ID_ISAR3, TABBRANCH, 16, 4)
+FIELD(ID_ISAR3, T32COPY, 20, 4)
+FIELD(ID_ISAR3, TRUENOP, 24, 4)
+FIELD(ID_ISAR3, T32EE, 28, 4)
+
+FIELD(ID_ISAR4, UNPRIV, 0, 4)
+FIELD(ID_ISAR4, WITHSHIFTS, 4, 4)
+FIELD(ID_ISAR4, WRITEBACK, 8, 4)
+FIELD(ID_ISAR4, SMC, 12, 4)
+FIELD(ID_ISAR4, BARRIER, 16, 4)
+FIELD(ID_ISAR4, SYNCHPRIM_FRAC, 20, 4)
+FIELD(ID_ISAR4, PSR_M, 24, 4)
+FIELD(ID_ISAR4, SWP_FRAC, 28, 4)
+
+FIELD(ID_ISAR5, SEVL, 0, 4)
+FIELD(ID_ISAR5, AES, 4, 4)
+FIELD(ID_ISAR5, SHA1, 8, 4)
+FIELD(ID_ISAR5, SHA2, 12, 4)
+FIELD(ID_ISAR5, CRC32, 16, 4)
+FIELD(ID_ISAR5, RDM, 24, 4)
+FIELD(ID_ISAR5, VCMA, 28, 4)
+
+FIELD(ID_ISAR6, JSCVT, 0, 4)
+FIELD(ID_ISAR6, DP, 4, 4)
+FIELD(ID_ISAR6, FHM, 8, 4)
+FIELD(ID_ISAR6, SB, 12, 4)
+FIELD(ID_ISAR6, SPECRES, 16, 4)
+
+FIELD(ID_AA64ISAR0, AES, 4, 4)
+FIELD(ID_AA64ISAR0, SHA1, 8, 4)
+FIELD(ID_AA64ISAR0, SHA2, 12, 4)
+FIELD(ID_AA64ISAR0, CRC32, 16, 4)
+FIELD(ID_AA64ISAR0, ATOMIC, 20, 4)
+FIELD(ID_AA64ISAR0, RDM, 28, 4)
+FIELD(ID_AA64ISAR0, SHA3, 32, 4)
+FIELD(ID_AA64ISAR0, SM3, 36, 4)
+FIELD(ID_AA64ISAR0, SM4, 40, 4)
+FIELD(ID_AA64ISAR0, DP, 44, 4)
+FIELD(ID_AA64ISAR0, FHM, 48, 4)
+FIELD(ID_AA64ISAR0, TS, 52, 4)
+FIELD(ID_AA64ISAR0, TLB, 56, 4)
+FIELD(ID_AA64ISAR0, RNDR, 60, 4)
+
+FIELD(ID_AA64ISAR1, DPB, 0, 4)
+FIELD(ID_AA64ISAR1, APA, 4, 4)
+FIELD(ID_AA64ISAR1, API, 8, 4)
+FIELD(ID_AA64ISAR1, JSCVT, 12, 4)
+FIELD(ID_AA64ISAR1, FCMA, 16, 4)
+FIELD(ID_AA64ISAR1, LRCPC, 20, 4)
+FIELD(ID_AA64ISAR1, GPA, 24, 4)
+FIELD(ID_AA64ISAR1, GPI, 28, 4)
+FIELD(ID_AA64ISAR1, FRINTTS, 32, 4)
+FIELD(ID_AA64ISAR1, SB, 36, 4)
+FIELD(ID_AA64ISAR1, SPECRES, 40, 4)
+
 QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK);
 
 /* If adding a feature bit which corresponds to a Linux ELF

target/arm/cpu64.c

@@ -51,7 +51,7 @@ static uint64_t a57_a53_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri)
 }
 #endif
 
-static const ARMCPRegInfo cortex_a57_a53_cp_reginfo[] = {
+static const ARMCPRegInfo cortex_a72_a57_a53_cp_reginfo[] = {
 #ifndef CONFIG_USER_ONLY
     { .name = "L2CTLR_EL1", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 2,
@@ -156,7 +156,7 @@ static void aarch64_a57_initfn(Object *obj)
     cpu->gic_num_lrs = 4;
     cpu->gic_vpribits = 5;
     cpu->gic_vprebits = 5;
-    define_arm_cp_regs(cpu, cortex_a57_a53_cp_reginfo);
+    define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
 }
 
 static void aarch64_a53_initfn(Object *obj)
@@ -215,7 +215,66 @@ static void aarch64_a53_initfn(Object *obj)
     cpu->gic_num_lrs = 4;
     cpu->gic_vpribits = 5;
     cpu->gic_vprebits = 5;
-    define_arm_cp_regs(cpu, cortex_a57_a53_cp_reginfo);
+    define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
+}
+
+static void aarch64_a72_initfn(Object *obj)
+{
+    ARMCPU *cpu = ARM_CPU(obj);
+
+    cpu->dtb_compatible = "arm,cortex-a72";
+    set_feature(&cpu->env, ARM_FEATURE_V8);
+    set_feature(&cpu->env, ARM_FEATURE_VFP4);
+    set_feature(&cpu->env, ARM_FEATURE_NEON);
+    set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER);
+    set_feature(&cpu->env, ARM_FEATURE_AARCH64);
+    set_feature(&cpu->env, ARM_FEATURE_CBAR_RO);
+    set_feature(&cpu->env, ARM_FEATURE_V8_AES);
+    set_feature(&cpu->env, ARM_FEATURE_V8_SHA1);
+    set_feature(&cpu->env, ARM_FEATURE_V8_SHA256);
+    set_feature(&cpu->env, ARM_FEATURE_V8_PMULL);
+    set_feature(&cpu->env, ARM_FEATURE_CRC);
+    set_feature(&cpu->env, ARM_FEATURE_EL2);
+    set_feature(&cpu->env, ARM_FEATURE_EL3);
+    set_feature(&cpu->env, ARM_FEATURE_PMU);
+    cpu->midr = 0x410fd083;
+    cpu->revidr = 0x00000000;
+    cpu->reset_fpsid = 0x41034080;
+    cpu->mvfr0 = 0x10110222;
+    cpu->mvfr1 = 0x12111111;
+    cpu->mvfr2 = 0x00000043;
+    cpu->ctr = 0x8444c004;
+    cpu->reset_sctlr = 0x00c50838;
+    cpu->id_pfr0 = 0x00000131;
+    cpu->id_pfr1 = 0x00011011;
+    cpu->id_dfr0 = 0x03010066;
+    cpu->id_afr0 = 0x00000000;
+    cpu->id_mmfr0 = 0x10201105;
+    cpu->id_mmfr1 = 0x40000000;
+    cpu->id_mmfr2 = 0x01260000;
+    cpu->id_mmfr3 = 0x02102211;
+    cpu->id_isar0 = 0x02101110;
+    cpu->id_isar1 = 0x13112111;
+    cpu->id_isar2 = 0x21232042;
+    cpu->id_isar3 = 0x01112131;
+    cpu->id_isar4 = 0x00011142;
+    cpu->id_isar5 = 0x00011121;
+    cpu->id_aa64pfr0 = 0x00002222;
+    cpu->id_aa64dfr0 = 0x10305106;
+    cpu->pmceid0 = 0x00000000;
+    cpu->pmceid1 = 0x00000000;
+    cpu->id_aa64isar0 = 0x00011120;
+    cpu->id_aa64mmfr0 = 0x00001124;
+    cpu->dbgdidr = 0x3516d000;
+    cpu->clidr = 0x0a200023;
+    cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
+    cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */
+    cpu->ccsidr[2] = 0x707fe07a; /* 1MB L2 cache */
+    cpu->dcz_blocksize = 4; /* 64 bytes */
+    cpu->gic_num_lrs = 4;
+    cpu->gic_vpribits = 5;
+    cpu->gic_vprebits = 5;
+    define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
 }
 
 static void cpu_max_get_sve_vq(Object *obj, Visitor *v, const char *name,
@@ -293,6 +352,7 @@ typedef struct ARMCPUInfo {
 static const ARMCPUInfo aarch64_cpus[] = {
     { .name = "cortex-a57",         .initfn = aarch64_a57_initfn },
     { .name = "cortex-a53",         .initfn = aarch64_a53_initfn },
+    { .name = "cortex-a72",         .initfn = aarch64_a72_initfn },
     { .name = "max",                .initfn = aarch64_max_initfn },
     { .name = NULL }
 };

target/arm/helper.c

@@ -1179,6 +1179,7 @@ static void pmcntenclr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                          uint64_t value)
 {
+    value &= pmu_counter_mask(env);
     env->cp15.c9_pmovsr &= ~value;
 }
 
@@ -1423,12 +1424,14 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
       .writefn = pmintenset_write, .raw_writefn = raw_write,
       .resetvalue = 0x0 },
     { .name = "PMINTENCLR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 2,
-      .access = PL1_RW, .accessfn = access_tpm, .type = ARM_CP_ALIAS,
+      .access = PL1_RW, .accessfn = access_tpm,
+      .type = ARM_CP_ALIAS | ARM_CP_IO,
       .fieldoffset = offsetof(CPUARMState, cp15.c9_pminten),
       .writefn = pmintenclr_write, },
     { .name = "PMINTENCLR_EL1", .state = ARM_CP_STATE_AA64,
       .opc0 = 3, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 2,
-      .access = PL1_RW, .accessfn = access_tpm, .type = ARM_CP_ALIAS,
+      .access = PL1_RW, .accessfn = access_tpm,
+      .type = ARM_CP_ALIAS | ARM_CP_IO,
       .fieldoffset = offsetof(CPUARMState, cp15.c9_pminten),
       .writefn = pmintenclr_write },
     { .name = "CCSIDR", .state = ARM_CP_STATE_BOTH,
@@ -6469,7 +6472,7 @@ static bool v7m_stack_write(ARMCPU *cpu, uint32_t addr, uint32_t value,
     target_ulong page_size;
     hwaddr physaddr;
     int prot;
-    ARMMMUFaultInfo fi;
+    ARMMMUFaultInfo fi = {};
     bool secure = mmu_idx & ARM_MMU_IDX_M_S;
     int exc;
     bool exc_secure;
@@ -6531,7 +6534,7 @@ static bool v7m_stack_read(ARMCPU *cpu, uint32_t *dest, uint32_t addr,
     target_ulong page_size;
     hwaddr physaddr;
     int prot;
-    ARMMMUFaultInfo fi;
+    ARMMMUFaultInfo fi = {};
     bool secure = mmu_idx & ARM_MMU_IDX_M_S;
     int exc;
     bool exc_secure;
@@ -8374,7 +8377,11 @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs)
     unsigned int new_mode = aarch64_pstate_mode(new_el, true);
     unsigned int cur_el = arm_current_el(env);
 
-    aarch64_sve_change_el(env, cur_el, new_el);
+    /*
+     * Note that new_el can never be 0.  If cur_el is 0, then
+     * el0_a64 is is_a64(), else el0_a64 is ignored.
+     */
+    aarch64_sve_change_el(env, cur_el, new_el, is_a64(env));
 
     if (cur_el < new_el) {
         /* Entry vector offset depends on whether the implemented EL
@@ -12791,9 +12798,11 @@ void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq)
 /*
  * Notice a change in SVE vector size when changing EL.
  */
-void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el)
+void aarch64_sve_change_el(CPUARMState *env, int old_el,
+                           int new_el, bool el0_a64)
 {
     int old_len, new_len;
+    bool old_a64, new_a64;
 
     /* Nothing to do if no SVE.  */
     if (!arm_feature(env, ARM_FEATURE_SVE)) {
@@ -12817,9 +12826,11 @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el)
      * we already have the correct register contents when encountering the
      * vq0->vq0 transition between EL0->EL1.
      */
-    old_len = (arm_el_is_aa64(env, old_el) && !sve_exception_el(env, old_el)
+    old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64;
+    old_len = (old_a64 && !sve_exception_el(env, old_el)
                ? sve_zcr_len_for_el(env, old_el) : 0);
-    new_len = (arm_el_is_aa64(env, new_el) && !sve_exception_el(env, new_el)
+    new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64;
+    new_len = (new_a64 && !sve_exception_el(env, new_el)
                ? sve_zcr_len_for_el(env, new_el) : 0);
 
     /* When changing vector length, clear inaccessible state.  */

target/arm/op_helper.c

@@ -1101,7 +1101,11 @@ void HELPER(exception_return)(CPUARMState *env)
                       "AArch64 EL%d PC 0x%" PRIx64 "\n",
                       cur_el, new_el, env->pc);
     }
-    aarch64_sve_change_el(env, cur_el, new_el);
+    /*
+     * Note that cur_el can never be 0.  If new_el is 0, then
+     * el0_a64 is return_to_aa64, else el0_a64 is ignored.
+     */
+    aarch64_sve_change_el(env, cur_el, new_el, return_to_aa64);
 
     qemu_mutex_lock_iothread();
     arm_call_el_change_hook(arm_env_get_cpu(env));