Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* NMI cleanups (Bandan)
* RAMBlock/Memory cleanups and fixes (Dominik, Gonglei, Fam, me)
* first part of linuxboot support for fw_cfg DMA (Richard)
* IOAPIC fix (Peter Xu)
* iSCSI SG_IO fix (Vadim)
* Various infrastructure bug fixes (Zhijian, Peter M., Stefan)
* CVE fixes (Prasad)

# gpg: Signature made Mon 23 May 2016 16:06:18 BST using RSA key ID 78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"

* remotes/bonzini/tags/for-upstream: (24 commits)
  cpus: call the core nmi injection function
  nmi: remove x86 specific nmi handling
  target-i386: add a generic x86 nmi handler
  coccinelle: add g_assert_cmp* to macro file
  iscsi: pass SCSI status back for SG_IO
  esp: check dma length before reading scsi command(CVE-2016-4441)
  esp: check command buffer length before write(CVE-2016-4439)
  scripts/signrom.py: Check for magic in option ROMs.
  scripts/signrom.py: Allow option ROM checksum script to write the size header.
  Remove config-devices.mak on 'make clean'
  cpus.c: Use pthread_sigmask() rather than sigprocmask()
  memory: remove unnecessary masking of MemoryRegion ram_addr
  memory: Drop FlatRange.romd_mode
  memory: Remove code for mr->may_overlap
  exec: adjust rcu_read_lock requirement
  memory: drop find_ram_block()
  vl: change runstate only if new state is different from current state
  ioapic: clear remote irr bit for edge-triggered interrupts
  ioapic: keep RO bits for IOAPIC entry
  target-i386: key sfence availability on CPUID_SSE, not CPUID_SSE2
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

Makefile

@@ -356,6 +356,7 @@ clean:
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
         done
+	rm -f $(SUBDIR_DEVICES_MAK) config-all-devices.mak
 
 VERSION ?= $(shell cat VERSION)
 

block/iscsi.c

@@ -761,6 +761,7 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
     acb->ioh->driver_status = 0;
     acb->ioh->host_status   = 0;
     acb->ioh->resid         = 0;
+    acb->ioh->status        = status;
 
 #define SG_ERR_DRIVER_SENSE    0x08
 

configure

@@ -2985,7 +2985,7 @@ int main(void) {
 }
 EOF
 
-if ! compile_prog "-Werror $CFLAGS" "$LIBS" ; then
+if ! compile_prog "$CFLAGS" "$LIBS" ; then
     error_exit "sizeof(size_t) doesn't match GLIB_SIZEOF_SIZE_T."\
                "You probably need to set PKG_CONFIG_LIBDIR"\
 	       "to point to the right pkg-config files for your"\

cpus.c

@@ -780,7 +780,7 @@ static void sigbus_reraise(void)
         raise(SIGBUS);
         sigemptyset(&set);
         sigaddset(&set, SIGBUS);
-        sigprocmask(SIG_UNBLOCK, &set, NULL);
+        pthread_sigmask(SIG_UNBLOCK, &set, NULL);
     }
     perror("Failed to re-raise SIGBUS!\n");
     abort();
@@ -1693,21 +1693,7 @@ exit:
 
 void qmp_inject_nmi(Error **errp)
 {
-#if defined(TARGET_I386)
-    CPUState *cs;
-
-    CPU_FOREACH(cs) {
-        X86CPU *cpu = X86_CPU(cs);
-
-        if (!cpu->apic_state) {
-            cpu_interrupt(cs, CPU_INTERRUPT_NMI);
-        } else {
-            apic_deliver_nmi(cpu->apic_state);
-        }
-    }
-#else
     nmi_monitor_handle(monitor_get_cpu_index(), errp);
-#endif
 }
 
 void dump_drift_info(FILE *f, fprintf_function cpu_fprintf)

docs/atomics.txt

@@ -62,7 +62,7 @@ operations:
     typeof(*ptr) atomic_fetch_sub(ptr, val)
     typeof(*ptr) atomic_fetch_and(ptr, val)
     typeof(*ptr) atomic_fetch_or(ptr, val)
-    typeof(*ptr) atomic_xchg(ptr, val
+    typeof(*ptr) atomic_xchg(ptr, val)
     typeof(*ptr) atomic_cmpxchg(ptr, old, new)
 
 all of which return the old value of *ptr.  These operations are
@@ -328,7 +328,7 @@ and memory barriers, and the equivalents in QEMU:
 
 - atomic_read and atomic_set in Linux give no guarantee at all;
   atomic_read and atomic_set in QEMU include a compiler barrier
-  (similar to the ACCESS_ONCE macro in Linux).
+  (similar to the READ_ONCE/WRITE_ONCE macros in Linux).
 
 - most atomic read-modify-write operations in Linux return void;
   in QEMU, all of them return the old value of the variable.

exec.c

@@ -1046,8 +1046,7 @@ hwaddr memory_region_section_get_iotlb(CPUState *cpu,
 
     if (memory_region_is_ram(section->mr)) {
         /* Normal RAM.  */
-        iotlb = (memory_region_get_ram_addr(section->mr) & TARGET_PAGE_MASK)
-            + xlat;
+        iotlb = memory_region_get_ram_addr(section->mr) + xlat;
         if (!section->readonly) {
             iotlb |= PHYS_SECTION_NOTDIRTY;
         } else {
@@ -1299,7 +1298,7 @@ static void *file_ram_alloc(RAMBlock *block,
     }
 
     page_size = qemu_fd_getpagesize(fd);
-    block->mr->align = page_size;
+    block->mr->align = MAX(page_size, QEMU_VMALLOC_ALIGN);
 
     if (memory < page_size) {
         error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
@@ -1320,7 +1319,8 @@ static void *file_ram_alloc(RAMBlock *block,
         perror("ftruncate");
     }
 
-    area = qemu_ram_mmap(fd, memory, page_size, block->flags & RAM_SHARED);
+    area = qemu_ram_mmap(fd, memory, block->mr->align,
+                         block->flags & RAM_SHARED);
     if (area == MAP_FAILED) {
         error_setg_errno(errp, errno,
                          "unable to map backing store for guest RAM");
@@ -1410,34 +1410,16 @@ static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
     }
 }
 
-/* Called within an RCU critical section, or while the ramlist lock
- * is held.
- */
-static RAMBlock *find_ram_block(ram_addr_t addr)
-{
-    RAMBlock *block;
-
-    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-        if (block->offset == addr) {
-            return block;
-        }
-    }
-
-    return NULL;
-}
-
 const char *qemu_ram_get_idstr(RAMBlock *rb)
 {
     return rb->idstr;
 }
 
 /* Called with iothread lock held.  */
-void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
+void qemu_ram_set_idstr(RAMBlock *new_block, const char *name, DeviceState *dev)
 {
-    RAMBlock *new_block, *block;
+    RAMBlock *block;
 
-    rcu_read_lock();
-    new_block = find_ram_block(addr);
     assert(new_block);
     assert(!new_block->idstr[0]);
 
@@ -1450,8 +1432,10 @@ void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
     }
     pstrcat(new_block->idstr, sizeof(new_block->idstr), name);
 
+    rcu_read_lock();
     QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
-        if (block != new_block && !strcmp(block->idstr, new_block->idstr)) {
+        if (block != new_block &&
+            !strcmp(block->idstr, new_block->idstr)) {
             fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",
                     new_block->idstr);
             abort();
@@ -1461,21 +1445,15 @@ void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
 }
 
 /* Called with iothread lock held.  */
-void qemu_ram_unset_idstr(ram_addr_t addr)
+void qemu_ram_unset_idstr(RAMBlock *block)
 {
-    RAMBlock *block;
-
     /* FIXME: arch_init.c assumes that this is not called throughout
      * migration.  Ignore the problem since hot-unplug during migration
      * does not work anyway.
      */
-
-    rcu_read_lock();
-    block = find_ram_block(addr);
     if (block) {
         memset(block->idstr, 0, sizeof(block->idstr));
     }
-    rcu_read_unlock();
 }
 
 static int memory_try_enable_merging(void *addr, size_t len)
@@ -1495,10 +1473,8 @@ static int memory_try_enable_merging(void *addr, size_t len)
  * resize callback to update device state and/or add assertions to detect
  * misuse, if necessary.
  */
-int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp)
+int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
 {
-    RAMBlock *block = find_ram_block(base);
-
     assert(block);
 
     newsize = HOST_PAGE_ALIGN(newsize);
@@ -3102,9 +3078,7 @@ static inline uint32_t address_space_ldl_internal(AddressSpace *as, hwaddr addr,
     } else {
         /* RAM case */
         ptr = qemu_get_ram_ptr(mr->ram_block,
-                               (memory_region_get_ram_addr(mr)
-                                & TARGET_PAGE_MASK)
-                               + addr1);
+                               memory_region_get_ram_addr(mr) + addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             val = ldl_le_p(ptr);
@@ -3198,9 +3172,7 @@ static inline uint64_t address_space_ldq_internal(AddressSpace *as, hwaddr addr,
     } else {
         /* RAM case */
         ptr = qemu_get_ram_ptr(mr->ram_block,
-                               (memory_region_get_ram_addr(mr)
-                                & TARGET_PAGE_MASK)
-                               + addr1);
+                               memory_region_get_ram_addr(mr) + addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             val = ldq_le_p(ptr);
@@ -3314,9 +3286,7 @@ static inline uint32_t address_space_lduw_internal(AddressSpace *as,
     } else {
         /* RAM case */
         ptr = qemu_get_ram_ptr(mr->ram_block,
-                               (memory_region_get_ram_addr(mr)
-                                & TARGET_PAGE_MASK)
-                               + addr1);
+                               memory_region_get_ram_addr(mr) + addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             val = lduw_le_p(ptr);
@@ -3398,7 +3368,7 @@ void address_space_stl_notdirty(AddressSpace *as, hwaddr addr, uint32_t val,
 
         r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
     } else {
-        addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
+        addr1 += memory_region_get_ram_addr(mr);
         ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         stl_p(ptr, val);
 
@@ -3453,7 +3423,7 @@ static inline void address_space_stl_internal(AddressSpace *as,
         r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
     } else {
         /* RAM case */
-        addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
+        addr1 += memory_region_get_ram_addr(mr);
         ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
@@ -3563,7 +3533,7 @@ static inline void address_space_stw_internal(AddressSpace *as,
         r = memory_region_dispatch_write(mr, addr1, val, 2, attrs);
     } else {
         /* RAM case */
-        addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
+        addr1 += memory_region_get_ram_addr(mr);
         ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:

hw/core/nmi.c

@@ -20,16 +20,11 @@
  */
 
 #include "qemu/osdep.h"
-#include "qom/cpu.h"
 #include "hw/nmi.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "monitor/monitor.h"
 
-#if defined(TARGET_I386)
-#include "cpu.h"
-#endif
-
 struct do_nmi_s {
     int cpu_index;
     Error *err;
@@ -78,25 +73,6 @@ void nmi_monitor_handle(int cpu_index, Error **errp)
     }
 }
 
-void inject_nmi(void)
-{
-#if defined(TARGET_I386)
-    CPUState *cs;
-
-    CPU_FOREACH(cs) {
-        X86CPU *cpu = X86_CPU(cs);
-
-        if (!cpu->apic_state) {
-            cpu_interrupt(cs, CPU_INTERRUPT_NMI);
-        } else {
-            apic_deliver_nmi(cpu->apic_state);
-        }
-    }
-#else
-    nmi_monitor_handle(0, NULL);
-#endif
-}
-
 static const TypeInfo nmi_info = {
     .name          = TYPE_NMI,
     .parent        = TYPE_INTERFACE,

hw/i386/kvmvapic.c

@@ -397,7 +397,7 @@ static void patch_instruction(VAPICROMState *s, X86CPU *cpu, target_ulong ip)
     CPUX86State *env = &cpu->env;
     VAPICHandlers *handlers;
     uint8_t opcode[2];
-    uint32_t imm32;
+    uint32_t imm32 = 0;
     target_ulong current_pc = 0;
     target_ulong current_cs_base = 0;
     uint32_t current_flags = 0;

hw/i386/pc.c

@@ -67,6 +67,7 @@
 #include "qapi/visitor.h"
 #include "qapi-visit.h"
 #include "qom/cpu.h"
+#include "hw/nmi.h"
 
 /* debug PC/ISA interrupts */
 //#define DEBUG_IRQ
@@ -1963,11 +1964,28 @@ static CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *machine)
     return list;
 }
 
+static void x86_nmi(NMIState *n, int cpu_index, Error **errp)
+{
+    /* cpu index isn't used */
+    CPUState *cs;
+
+    CPU_FOREACH(cs) {
+        X86CPU *cpu = X86_CPU(cs);
+
+        if (!cpu->apic_state) {
+            cpu_interrupt(cs, CPU_INTERRUPT_NMI);
+        } else {
+            apic_deliver_nmi(cpu->apic_state);
+        }
+    }
+}
+
 static void pc_machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
     PCMachineClass *pcmc = PC_MACHINE_CLASS(oc);
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
+    NMIClass *nc = NMI_CLASS(oc);
 
     pcmc->get_hotplug_handler = mc->get_hotplug_handler;
     pcmc->pci_enabled = true;
@@ -1993,6 +2011,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     hc->plug = pc_machine_device_plug_cb;
     hc->unplug_request = pc_machine_device_unplug_request_cb;
     hc->unplug = pc_machine_device_unplug_cb;
+    nc->nmi_monitor_handler = x86_nmi;
 }
 
 static const TypeInfo pc_machine_info = {
@@ -2005,6 +2024,7 @@ static const TypeInfo pc_machine_info = {
     .class_init = pc_machine_class_init,
     .interfaces = (InterfaceInfo[]) {
          { TYPE_HOTPLUG_HANDLER },
+         { TYPE_NMI },
          { }
     },
 };

hw/intc/ioapic.c

@@ -255,6 +255,34 @@ ioapic_mem_read(void *opaque, hwaddr addr, unsigned int size)
     return val;
 }
 
+/*
+ * This is to satisfy the hack in Linux kernel. One hack of it is to
+ * simulate clearing the Remote IRR bit of IOAPIC entry using the
+ * following:
+ *
+ * "For IO-APIC's with EOI register, we use that to do an explicit EOI.
+ * Otherwise, we simulate the EOI message manually by changing the trigger
+ * mode to edge and then back to level, with RTE being masked during
+ * this."
+ *
+ * (See linux kernel __eoi_ioapic_pin() comment in commit c0205701)
+ *
+ * This is based on the assumption that, Remote IRR bit will be
+ * cleared by IOAPIC hardware when configured as edge-triggered
+ * interrupts.
+ *
+ * Without this, level-triggered interrupts in IR mode might fail to
+ * work correctly.
+ */
+static inline void
+ioapic_fix_edge_remote_irr(uint64_t *entry)
+{
+    if (!(*entry & IOAPIC_LVT_TRIGGER_MODE)) {
+        /* Edge-triggered interrupts, make sure remote IRR is zero */
+        *entry &= ~((uint64_t)IOAPIC_LVT_REMOTE_IRR);
+    }
+}
+
 static void
 ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val,
                  unsigned int size)
@@ -281,6 +309,7 @@ ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val,
         default:
             index = (s->ioregsel - IOAPIC_REG_REDTBL_BASE) >> 1;
             if (index >= 0 && index < IOAPIC_NUM_PINS) {
+                uint64_t ro_bits = s->ioredtbl[index] & IOAPIC_RO_BITS;
                 if (s->ioregsel & 1) {
                     s->ioredtbl[index] &= 0xffffffff;
                     s->ioredtbl[index] |= (uint64_t)val << 32;
@@ -288,6 +317,10 @@ ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val,
                     s->ioredtbl[index] &= ~0xffffffffULL;
                     s->ioredtbl[index] |= val;
                 }
+                /* restore RO bits */
+                s->ioredtbl[index] &= IOAPIC_RW_BITS;
+                s->ioredtbl[index] |= ro_bits;
+                ioapic_fix_edge_remote_irr(&s->ioredtbl[index]);
                 ioapic_service(s);
             }
         }

hw/scsi/esp.c

@@ -82,7 +82,7 @@ void esp_request_cancelled(SCSIRequest *req)
     }
 }
 
-static uint32_t get_cmd(ESPState *s, uint8_t *buf)
+static uint32_t get_cmd(ESPState *s, uint8_t *buf, uint8_t buflen)
 {
     uint32_t dmalen;
     int target;
@@ -92,6 +92,9 @@ static uint32_t get_cmd(ESPState *s, uint8_t *buf)
         dmalen = s->rregs[ESP_TCLO];
         dmalen |= s->rregs[ESP_TCMID] << 8;
         dmalen |= s->rregs[ESP_TCHI] << 16;
+        if (dmalen > buflen) {
+            return 0;
+        }
         s->dma_memory_read(s->dma_opaque, buf, dmalen);
     } else {
         dmalen = s->ti_size;
@@ -166,7 +169,7 @@ static void handle_satn(ESPState *s)
         s->dma_cb = handle_satn;
         return;
     }
-    len = get_cmd(s, buf);
+    len = get_cmd(s, buf, sizeof(buf));
     if (len)
         do_cmd(s, buf);
 }
@@ -180,7 +183,7 @@ static void handle_s_without_atn(ESPState *s)
         s->dma_cb = handle_s_without_atn;
         return;
     }
-    len = get_cmd(s, buf);
+    len = get_cmd(s, buf, sizeof(buf));
     if (len) {
         do_busid_cmd(s, buf, 0);
     }
@@ -192,7 +195,7 @@ static void handle_satn_stop(ESPState *s)
         s->dma_cb = handle_satn_stop;
         return;
     }
-    s->cmdlen = get_cmd(s, s->cmdbuf);
+    s->cmdlen = get_cmd(s, s->cmdbuf, sizeof(s->cmdbuf));
     if (s->cmdlen) {
         trace_esp_handle_satn_stop(s->cmdlen);
         s->do_cmd = 1;
@@ -448,7 +451,11 @@ void esp_reg_write(ESPState *s, uint32_t saddr, uint64_t val)
         break;
     case ESP_FIFO:
         if (s->do_cmd) {
-            s->cmdbuf[s->cmdlen++] = val & 0xff;
+            if (s->cmdlen < TI_BUFSZ) {
+                s->cmdbuf[s->cmdlen++] = val & 0xff;
+            } else {
+                trace_esp_error_fifo_overrun();
+            }
         } else if (s->ti_size == TI_BUFSZ - 1) {
             trace_esp_error_fifo_overrun();
         } else {

hw/watchdog/watchdog.c

@@ -143,7 +143,7 @@ void watchdog_perform_action(void)
     case WDT_NMI:
         qapi_event_send_watchdog(WATCHDOG_EXPIRATION_ACTION_INJECT_NMI,
                                  &error_abort);
-        inject_nmi();
+        nmi_monitor_handle(0, NULL);
         break;
     }
 }

include/exec/cpu-common.h

@@ -61,8 +61,8 @@ MemoryRegion *qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr);
 RAMBlock *qemu_ram_block_by_name(const char *name);
 RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset,
                                    ram_addr_t *ram_addr, ram_addr_t *offset);
-void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev);
-void qemu_ram_unset_idstr(ram_addr_t addr);
+void qemu_ram_set_idstr(RAMBlock *block, const char *name, DeviceState *dev);
+void qemu_ram_unset_idstr(RAMBlock *block);
 const char *qemu_ram_get_idstr(RAMBlock *rb);
 
 void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf,

include/exec/memory.h

@@ -187,7 +187,6 @@ struct MemoryRegion {
     MemoryRegion *alias;
     hwaddr alias_offset;
     int32_t priority;
-    bool may_overlap;
     QTAILQ_HEAD(subregions, MemoryRegion) subregions;
     QTAILQ_ENTRY(MemoryRegion) subregions_link;
     QTAILQ_HEAD(coalesced_ranges, CoalescedMemoryRange) coalesced;

include/exec/ram_addr.h

@@ -110,7 +110,7 @@ void qemu_set_ram_fd(ram_addr_t addr, int fd);
 void *qemu_get_ram_block_host_ptr(ram_addr_t addr);
 void qemu_ram_free(RAMBlock *block);
 
-int qemu_ram_resize(ram_addr_t base, ram_addr_t newsize, Error **errp);
+int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp);
 
 #define DIRTY_CLIENTS_ALL     ((1 << DIRTY_MEMORY_NUM) - 1)
 #define DIRTY_CLIENTS_NOCODE  (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE))

include/hw/i386/ioapic_internal.h

@@ -47,6 +47,11 @@
 #define IOAPIC_LVT_DEST_MODE            (1 << IOAPIC_LVT_DEST_MODE_SHIFT)
 #define IOAPIC_LVT_DELIV_MODE           (7 << IOAPIC_LVT_DELIV_MODE_SHIFT)
 
+/* Bits that are read-only for IOAPIC entry */
+#define IOAPIC_RO_BITS                  (IOAPIC_LVT_REMOTE_IRR | \
+                                         IOAPIC_LVT_DELIV_STATUS)
+#define IOAPIC_RW_BITS                  (~(uint64_t)IOAPIC_RO_BITS)
+
 #define IOAPIC_TRIGGER_EDGE             0
 #define IOAPIC_TRIGGER_LEVEL            1
 

include/hw/nmi.h

@@ -45,6 +45,5 @@ typedef struct NMIClass {
 } NMIClass;
 
 void nmi_monitor_handle(int cpu_index, Error **errp);
-void inject_nmi(void);
 
 #endif /* NMI_H */

include/qemu/osdep.h

@@ -263,6 +263,19 @@ void qemu_anon_ram_free(void *ptr, size_t size);
 
 #endif
 
+#if defined(__linux__) && \
+    (defined(__x86_64__) || defined(__arm__) || defined(__aarch64__))
+   /* Use 2 MiB alignment so transparent hugepages can be used by KVM.
+      Valgrind does not support alignments larger than 1 MiB,
+      therefore we need special code which handles running on Valgrind. */
+#  define QEMU_VMALLOC_ALIGN (512 * 4096)
+#elif defined(__linux__) && defined(__s390x__)
+   /* Use 1 MiB (segment size) alignment so gmap can be used by KVM. */
+#  define QEMU_VMALLOC_ALIGN (256 * 4096)
+#else
+#  define QEMU_VMALLOC_ALIGN getpagesize()
+#endif
+
 int qemu_madvise(void *addr, size_t len, int advice);
 
 int qemu_open(const char *name, int flags, ...);

memory.c

@@ -227,7 +227,6 @@ struct FlatRange {
     hwaddr offset_in_region;
     AddrRange addr;
     uint8_t dirty_log_mask;
-    bool romd_mode;
     bool readonly;
 };
 
@@ -252,7 +251,6 @@ static bool flatrange_equal(FlatRange *a, FlatRange *b)
     return a->mr == b->mr
         && addrrange_equal(a->addr, b->addr)
         && a->offset_in_region == b->offset_in_region
-        && a->romd_mode == b->romd_mode
         && a->readonly == b->readonly;
 }
 
@@ -312,7 +310,6 @@ static bool can_merge(FlatRange *r1, FlatRange *r2)
                                 r1->addr.size),
                      int128_make64(r2->offset_in_region))
         && r1->dirty_log_mask == r2->dirty_log_mask
-        && r1->romd_mode == r2->romd_mode
         && r1->readonly == r2->readonly;
 }
 
@@ -666,7 +663,6 @@ static void render_memory_region(FlatView *view,
 
     fr.mr = mr;
     fr.dirty_log_mask = memory_region_get_dirty_log_mask(mr);
-    fr.romd_mode = mr->romd_mode;
     fr.readonly = readonly;
 
     /* Render the region itself into any gaps left by the current view. */
@@ -1057,13 +1053,6 @@ static void memory_region_get_priority(Object *obj, Visitor *v,
     visit_type_int32(v, name, &value, errp);
 }
 
-static bool memory_region_get_may_overlap(Object *obj, Error **errp)
-{
-    MemoryRegion *mr = MEMORY_REGION(obj);
-
-    return mr->may_overlap;
-}
-
 static void memory_region_get_size(Object *obj, Visitor *v, const char *name,
                                    void *opaque, Error **errp)
 {
@@ -1101,10 +1090,6 @@ static void memory_region_initfn(Object *obj)
                         memory_region_get_priority,
                         NULL, /* memory_region_set_priority */
                         NULL, NULL, &error_abort);
-    object_property_add_bool(OBJECT(mr), "may-overlap",
-                             memory_region_get_may_overlap,
-                             NULL, /* memory_region_set_may_overlap */
-                             &error_abort);
     object_property_add(OBJECT(mr), "size", "uint64",
                         memory_region_get_size,
                         NULL, /* memory_region_set_size, */
@@ -1643,7 +1628,7 @@ int memory_region_get_fd(MemoryRegion *mr)
 
     assert(mr->ram_block);
 
-    return qemu_get_ram_fd(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK);
+    return qemu_get_ram_fd(memory_region_get_ram_addr(mr));
 }
 
 void *memory_region_get_ram_ptr(MemoryRegion *mr)
@@ -1657,8 +1642,7 @@ void *memory_region_get_ram_ptr(MemoryRegion *mr)
         mr = mr->alias;
     }
     assert(mr->ram_block);
-    ptr = qemu_get_ram_ptr(mr->ram_block,
-                           memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK);
+    ptr = qemu_get_ram_ptr(mr->ram_block, memory_region_get_ram_addr(mr));
     rcu_read_unlock();
 
     return ptr + offset;
@@ -1673,7 +1657,7 @@ void memory_region_ram_resize(MemoryRegion *mr, ram_addr_t newsize, Error **errp
 {
     assert(mr->ram_block);
 
-    qemu_ram_resize(memory_region_get_ram_addr(mr), newsize, errp);
+    qemu_ram_resize(mr->ram_block, newsize, errp);
 }
 
 static void memory_region_update_coalesced_range_as(MemoryRegion *mr, AddressSpace *as)
@@ -1864,34 +1848,12 @@ void memory_region_del_eventfd(MemoryRegion *mr,
 
 static void memory_region_update_container_subregions(MemoryRegion *subregion)
 {
-    hwaddr offset = subregion->addr;
     MemoryRegion *mr = subregion->container;
     MemoryRegion *other;
 
     memory_region_transaction_begin();
 
     memory_region_ref(subregion);
-    QTAILQ_FOREACH(other, &mr->subregions, subregions_link) {
-        if (subregion->may_overlap || other->may_overlap) {
-            continue;
-        }
-        if (int128_ge(int128_make64(offset),
-                      int128_add(int128_make64(other->addr), other->size))
-            || int128_le(int128_add(int128_make64(offset), subregion->size),
-                         int128_make64(other->addr))) {
-            continue;
-        }
-#if 0
-        printf("warning: subregion collision %llx/%llx (%s) "
-               "vs %llx/%llx (%s)\n",
-               (unsigned long long)offset,
-               (unsigned long long)int128_get64(subregion->size),
-               subregion->name,
-               (unsigned long long)other->addr,
-               (unsigned long long)int128_get64(other->size),
-               other->name);
-#endif
-    }
     QTAILQ_FOREACH(other, &mr->subregions, subregions_link) {
         if (subregion->priority >= other->priority) {
             QTAILQ_INSERT_BEFORE(other, subregion, subregions_link);
@@ -1918,7 +1880,6 @@ void memory_region_add_subregion(MemoryRegion *mr,
                                  hwaddr offset,
                                  MemoryRegion *subregion)
 {
-    subregion->may_overlap = false;
     subregion->priority = 0;
     memory_region_add_subregion_common(mr, offset, subregion);
 }
@@ -1928,7 +1889,6 @@ void memory_region_add_subregion_overlap(MemoryRegion *mr,
                                          MemoryRegion *subregion,
                                          int priority)
 {
-    subregion->may_overlap = true;
     subregion->priority = priority;
     memory_region_add_subregion_common(mr, offset, subregion);
 }

migration/ram.c

@@ -2478,7 +2478,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                     if (length != block->used_length) {
                         Error *local_err = NULL;
 
-                        ret = qemu_ram_resize(block->offset, length,
+                        ret = qemu_ram_resize(block, length,
                                               &local_err);
                         if (local_err) {
                             error_report_err(local_err);

migration/savevm.c

@@ -2229,13 +2229,13 @@ void hmp_info_snapshots(Monitor *mon, const QDict *qdict)
 
 void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev)
 {
-    qemu_ram_set_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK,
+    qemu_ram_set_idstr(mr->ram_block,
                        memory_region_name(mr), dev);
 }
 
 void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev)
 {
-    qemu_ram_unset_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK);
+    qemu_ram_unset_idstr(mr->ram_block);
 }
 
 void vmstate_register_ram_global(MemoryRegion *mr)

scripts/cocci-macro-file.h

@@ -117,3 +117,9 @@ struct {                                                                \
         type *tqe_next;       /* next element */                        \
         type **tqe_prev;      /* address of previous next element */    \
 }
+
+/* From glib */
+#define g_assert_cmpint(a, op, b)   g_assert(a op b)
+#define g_assert_cmpuint(a, op, b)   g_assert(a op b)
+#define g_assert_cmphex(a, op, b)   g_assert(a op b)
+#define g_assert_cmpstr(a, op, b)   g_assert(strcmp(a, b) op 0)

scripts/signrom.py

@@ -17,11 +17,33 @@ if len(sys.argv) < 3:
 fin = open(sys.argv[1], 'rb')
 fout = open(sys.argv[2], 'wb')
 
-fin.seek(2)
-size = ord(fin.read(1)) * 512 - 1
+magic = fin.read(2)
+if magic != '\x55\xaa':
+    sys.exit("%s: option ROM does not begin with magic 55 aa" % sys.argv[1])
 
+size_byte = ord(fin.read(1))
 fin.seek(0)
-data = fin.read(size)
+
+if size_byte == 0:
+    # If the caller left the size field blank then we will fill it in,
+    # also rounding the whole input to a multiple of 512 bytes.
+    data = fin.read()
+    # +1 because we need a byte to store the checksum.
+    size = len(data) + 1
+    # Round up to next multiple of 512.
+    size += 511
+    size -= size % 512
+    if size >= 65536:
+        sys.exit("%s: option ROM size too large" % sys.argv[1])
+    # size-1 because a final byte is added below to store the checksum.
+    data = data.ljust(size-1, '\0')
+    data = data[:2] + chr(size/512) + data[3:]
+else:
+    # Otherwise the input file specifies the size so use it.
+    # -1 because we overwrite the last byte of the file with the checksum.
+    size = size_byte * 512 - 1
+    data = fin.read(size)
+
 fout.write(data)
 
 checksum = 0

target-i386/translate.c

@@ -8008,6 +8008,11 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
             }
             /* fallthru */
         case 0xf9 ... 0xff: /* sfence */
+            if (!(s->cpuid_features & CPUID_SSE)
+                || (prefixes & PREFIX_LOCK)) {
+                goto illegal_op;
+            }
+            break;
         case 0xe8 ... 0xef: /* lfence */
         case 0xf0 ... 0xf7: /* mfence */
             if (!(s->cpuid_features & CPUID_SSE2)

translate-all.c

@@ -1555,8 +1555,7 @@ void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr)
         rcu_read_unlock();
         return;
     }
-    ram_addr = (memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK)
-        + addr;
+    ram_addr = memory_region_get_ram_addr(mr) + addr;
     tb_invalidate_phys_page_range(ram_addr, ram_addr + 1, 0);
     rcu_read_unlock();
 }

util/oslib-posix.c

@@ -26,19 +26,6 @@
  * THE SOFTWARE.
  */
 
-#if defined(__linux__) && \
-    (defined(__x86_64__) || defined(__arm__) || defined(__aarch64__))
-   /* Use 2 MiB alignment so transparent hugepages can be used by KVM.
-      Valgrind does not support alignments larger than 1 MiB,
-      therefore we need special code which handles running on Valgrind. */
-#  define QEMU_VMALLOC_ALIGN (512 * 4096)
-#elif defined(__linux__) && defined(__s390x__)
-   /* Use 1 MiB (segment size) alignment so gmap can be used by KVM. */
-#  define QEMU_VMALLOC_ALIGN (256 * 4096)
-#else
-#  define QEMU_VMALLOC_ALIGN getpagesize()
-#endif
-
 #include "qemu/osdep.h"
 #include <termios.h>
 #include <termios.h>

vl.c

@@ -690,6 +690,10 @@ void runstate_set(RunState new_state)
 {
     assert(new_state < RUN_STATE__MAX);
 
+    if (current_run_state == new_state) {
+        return;
+    }
+
     if (!runstate_valid_transitions[current_run_state][new_state]) {
         error_report("invalid runstate transition: '%s' -> '%s'",
                      RunState_lookup[current_run_state],