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

* minor patches here and there
* MTTCG: lock-free TB lookup
* SCSI: bugfixes for MPTSAS, MegaSAS, LSI53c, vmw_pvscsi
* buffer_is_zero rewrite (except for one patch)
* chardev: qemu_chr_fe_write checks
* checkpatch improvement for markdown preformatted text
* default-configs cleanups
* atomics cleanups

# gpg: Signature made Tue 13 Sep 2016 18:14:30 BST
# gpg:                using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (58 commits)
  cutils: Add generic prefetch
  cutils: Add SSE4 version
  cutils: Add test for buffer_is_zero
  cutils: Remove ppc buffer zero checking
  cutils: Remove aarch64 buffer zero checking
  cutils: Rearrange buffer_is_zero acceleration
  cutils: Export only buffer_is_zero
  cutils: Remove SPLAT macro
  cutils: Move buffer_is_zero and subroutines to a new file
  ppc: do not redefine CPUPPCState
  x86/lapic: Load LAPIC state at post_load
  optionrom: do not rely on compiler's bswap optimization
  checkpatch: Fix whitespace checks for documentation code blocks
  atomics: Use __atomic_*_n() variant primitives
  atomics: Remove redundant barrier()'s
  kvm-all: drop kvm_setup_guest_memory
  i8257: Make device "i8257" unavailable with -device
  Revert "megasas: remove useless check for cmd->frame"
  char: convert qemu_chr_fe_write to qemu_chr_fe_write_all
  hw: replace most use of qemu_chr_fe_write with qemu_chr_fe_write_all
  ...

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

 Conflicts:
	cpus.c
	tests/Makefile.include

7 files changed, 24 insertions, 39 deletions

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index d008296c1b..a0e87be88f 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -225,6 +225,8 @@ struct TranslationBlock {
 #define CF_USE_ICOUNT  0x20000
 #define CF_IGNORE_ICOUNT 0x40000 /* Do not generate icount code */
 
+    uint16_t invalid;
+
     void *tc_ptr;    /* pointer to the translated code */
     uint8_t *tc_search;  /* pointer to search data */
     /* original tb when cflags has CF_NOCACHE */
diff --git a/include/hw/ppc/fdt.h b/include/hw/ppc/fdt.h
index 2c68d1616f..0cabb6af04 100644
--- a/include/hw/ppc/fdt.h
+++ b/include/hw/ppc/fdt.h
@@ -11,8 +11,7 @@
 #define PPC_FDT_H
 
 #include "qemu/error-report.h"
-
-typedef struct CPUPPCState CPUPPCState;
+#include "target-ppc/cpu-qom.h"
 
 #define _FDT(exp)                                                  \
     do {                                                           \
diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h
index 43b06458f1..0cce246ea9 100644
--- a/include/qemu/atomic.h
+++ b/include/qemu/atomic.h
@@ -72,16 +72,16 @@
  * Add one here, and similarly in smp_rmb() and smp_read_barrier_depends().
  */
 
-#define smp_mb()    ({ barrier(); __atomic_thread_fence(__ATOMIC_SEQ_CST); barrier(); })
-#define smp_wmb()   ({ barrier(); __atomic_thread_fence(__ATOMIC_RELEASE); barrier(); })
-#define smp_rmb()   ({ barrier(); __atomic_thread_fence(__ATOMIC_ACQUIRE); barrier(); })
+#define smp_mb()    ({ barrier(); __atomic_thread_fence(__ATOMIC_SEQ_CST); })
+#define smp_wmb()   ({ barrier(); __atomic_thread_fence(__ATOMIC_RELEASE); })
+#define smp_rmb()   ({ barrier(); __atomic_thread_fence(__ATOMIC_ACQUIRE); })
 
 /* Most compilers currently treat consume and acquire the same, but really
  * no processors except Alpha need a barrier here.  Leave it in if
  * using Thread Sanitizer to avoid warnings, otherwise optimize it away.
  */
 #if defined(__SANITIZE_THREAD__)
-#define smp_read_barrier_depends() ({ barrier(); __atomic_thread_fence(__ATOMIC_CONSUME); barrier(); })
+#define smp_read_barrier_depends() ({ barrier(); __atomic_thread_fence(__ATOMIC_CONSUME); })
 #elsif defined(__alpha__)
 #define smp_read_barrier_depends()   asm volatile("mb":::"memory")
 #else
@@ -96,15 +96,12 @@
 #define atomic_read(ptr)                              \
     ({                                                \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *)); \
-    typeof_strip_qual(*ptr) _val;                     \
-     __atomic_load(ptr, &_val, __ATOMIC_RELAXED);     \
-    _val;                                             \
+    __atomic_load_n(ptr, __ATOMIC_RELAXED);           \
     })
 
 #define atomic_set(ptr, i)  do {                      \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *)); \
-    typeof(*ptr) _val = (i);                          \
-    __atomic_store(ptr, &_val, __ATOMIC_RELAXED);     \
+    __atomic_store_n(ptr, i, __ATOMIC_RELAXED);       \
 } while(0)
 
 /* See above: most compilers currently treat consume and acquire the
@@ -129,8 +126,7 @@
 
 #define atomic_rcu_set(ptr, i) do {                   \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *)); \
-    typeof(*ptr) _val = (i);                          \
-    __atomic_store(ptr, &_val, __ATOMIC_RELEASE);     \
+    __atomic_store_n(ptr, i, __ATOMIC_RELEASE);       \
 } while(0)
 
 /* atomic_mb_read/set semantics map Java volatile variables. They are
@@ -153,9 +149,8 @@
 
 #define atomic_mb_set(ptr, i)  do {                     \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *));   \
-    typeof(*ptr) _val = (i);                            \
     smp_wmb();                                          \
-    __atomic_store(ptr, &_val, __ATOMIC_RELAXED);       \
+    __atomic_store_n(ptr, i, __ATOMIC_RELAXED);         \
     smp_mb();                                           \
 } while(0)
 #else
@@ -169,8 +164,7 @@
 
 #define atomic_mb_set(ptr, i)  do {                     \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *));   \
-    typeof(*ptr) _val = (i);                            \
-    __atomic_store(ptr, &_val, __ATOMIC_SEQ_CST);       \
+    __atomic_store_n(ptr, i, __ATOMIC_SEQ_CST);         \
 } while(0)
 #endif
 
@@ -179,17 +173,15 @@
 
 #define atomic_xchg(ptr, i)    ({                           \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *));       \
-    typeof_strip_qual(*ptr) _new = (i), _old;               \
-    __atomic_exchange(ptr, &_new, &_old, __ATOMIC_SEQ_CST); \
-    _old;                                                   \
+    __atomic_exchange_n(ptr, i, __ATOMIC_SEQ_CST);          \
 })
 
 /* Returns the eventual value, failed or not */
 #define atomic_cmpxchg(ptr, old, new)                                   \
     ({                                                                  \
     QEMU_BUILD_BUG_ON(sizeof(*ptr) > sizeof(void *));                   \
-    typeof_strip_qual(*ptr) _old = (old), _new = (new);                 \
-    __atomic_compare_exchange(ptr, &_old, &_new, false,                 \
+    typeof_strip_qual(*ptr) _old = (old);                               \
+    __atomic_compare_exchange_n(ptr, &_old, new, false,                 \
                               __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST);      \
     _old;                                                               \
     })
diff --git a/include/qemu/cutils.h b/include/qemu/cutils.h
index 3e4ea236f0..8033929139 100644
--- a/include/qemu/cutils.h
+++ b/include/qemu/cutils.h
@@ -168,9 +168,8 @@ int64_t qemu_strtosz_suffix_unit(const char *nptr, char **end,
 /* used to print char* safely */
 #define STR_OR_NULL(str) ((str) ? (str) : "null")
 
-bool can_use_buffer_find_nonzero_offset(const void *buf, size_t len);
-size_t buffer_find_nonzero_offset(const void *buf, size_t len);
 bool buffer_is_zero(const void *buf, size_t len);
+bool test_buffer_is_zero_next_accel(void);
 
 /*
  * Implementation of ULEB128 (http://en.wikipedia.org/wiki/LEB128)
diff --git a/include/qemu/queue.h b/include/qemu/queue.h
index c2b6c8149d..342073fb4d 100644
--- a/include/qemu/queue.h
+++ b/include/qemu/queue.h
@@ -407,6 +407,7 @@ struct {                                                                \
         else                                                            \
                 (head)->tqh_last = (elm)->field.tqe_prev;               \
         *(elm)->field.tqe_prev = (elm)->field.tqe_next;                 \
+        (elm)->field.tqe_prev = NULL;                                   \
 } while (/*CONSTCOND*/0)
 
 #define QTAILQ_FOREACH(var, head, field)                                \
@@ -430,6 +431,7 @@ struct {                                                                \
 #define QTAILQ_EMPTY(head)               ((head)->tqh_first == NULL)
 #define QTAILQ_FIRST(head)               ((head)->tqh_first)
 #define QTAILQ_NEXT(elm, field)          ((elm)->field.tqe_next)
+#define QTAILQ_IN_USE(elm, field)        ((elm)->field.tqe_prev != NULL)
 
 #define QTAILQ_LAST(head, headname) \
         (*(((struct headname *)((head)->tqh_last))->tqh_last))
diff --git a/include/qemu/timer.h b/include/qemu/timer.h
index 4bfcd35560..bdfae004e4 100644
--- a/include/qemu/timer.h
+++ b/include/qemu/timer.h
@@ -22,23 +22,20 @@
  * @QEMU_CLOCK_REALTIME: Real time clock
  *
  * The real time clock should be used only for stuff which does not
- * change the virtual machine state, as it is run even if the virtual
- * machine is stopped. The real time clock has a frequency of 1000
- * Hz.
+ * change the virtual machine state, as it runs even if the virtual
+ * machine is stopped.
  *
  * @QEMU_CLOCK_VIRTUAL: virtual clock
  *
- * The virtual clock is only run during the emulation. It is stopped
- * when the virtual machine is stopped. Virtual timers use a high
- * precision clock, usually cpu cycles (use ticks_per_sec).
+ * The virtual clock only runs during the emulation. It stops
+ * when the virtual machine is stopped.
  *
  * @QEMU_CLOCK_HOST: host clock
  *
- * The host clock should be use for device models that emulate accurate
+ * The host clock should be used for device models that emulate accurate
  * real time sources. It will continue to run when the virtual machine
  * is suspended, and it will reflect system time changes the host may
- * undergo (e.g. due to NTP). The host clock has the same precision as
- * the virtual clock.
+ * undergo (e.g. due to NTP).
  *
  * @QEMU_CLOCK_VIRTUAL_RT: realtime clock used for icount warp
  *
@@ -77,10 +74,6 @@ struct QEMUTimer {
 extern QEMUTimerListGroup main_loop_tlg;
 
 /*
- * QEMUClockType
- */
-
-/*
  * qemu_clock_get_ns;
  * @type: the clock type
  *
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index c9c243631e..f2a7b3b8fe 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -221,7 +221,6 @@ int kvm_destroy_vcpu(CPUState *cpu);
 #ifdef NEED_CPU_H
 #include "cpu.h"
 
-void kvm_setup_guest_memory(void *start, size_t size);
 void kvm_flush_coalesced_mmio_buffer(void);
 
 int kvm_insert_breakpoint(CPUState *cpu, target_ulong addr,
@@ -372,7 +371,6 @@ int kvm_irqchip_send_msi(KVMState *s, MSIMessage msg);
 
 void kvm_irqchip_add_irq_route(KVMState *s, int gsi, int irqchip, int pin);
 
-void kvm_put_apic_state(DeviceState *d, struct kvm_lapic_state *kapic);
 void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic);
 
 struct kvm_guest_debug;