Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20181018' into staging

Queued tcg patches.

# gpg: Signature made Fri 19 Oct 2018 07:03:20 BST
# gpg:                using RSA key 64DF38E8AF7E215F
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>"
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth/tags/pull-tcg-20181018: (21 commits)
  cputlb: read CPUTLBEntry.addr_write atomically
  target/s390x: Check HAVE_ATOMIC128 and HAVE_CMPXCHG128 at translate
  target/s390x: Skip wout, cout helpers if op helper does not return
  target/s390x: Split do_cdsg, do_lpq, do_stpq
  target/s390x: Convert to HAVE_CMPXCHG128 and HAVE_ATOMIC128
  target/ppc: Convert to HAVE_CMPXCHG128 and HAVE_ATOMIC128
  target/arm: Check HAVE_CMPXCHG128 at translate time
  target/arm: Convert to HAVE_CMPXCHG128
  target/i386: Convert to HAVE_CMPXCHG128
  tcg: Split CONFIG_ATOMIC128
  tcg: Add tlb_index and tlb_entry helpers
  cputlb: serialize tlb updates with env->tlb_lock
  cputlb: fix assert_cpu_is_self macro
  exec: introduce tlb_init
  target/unicore32: remove tlb_flush from uc32_init_fn
  target/alpha: remove tlb_flush from alpha_cpu_initfn
  tcg: distribute tcg_time into TCG contexts
  tcg: plug holes in struct TCGProfile
  tcg: fix use of uninitialized variable under CONFIG_PROFILER
  tcg: access cpu->icount_decr.u16.high with atomics
  ...

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

7 files changed, 214 insertions, 17 deletions

diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index a171ffc..4ff62f3 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -24,6 +24,7 @@
 #endif
 
 #include "qemu/host-utils.h"
+#include "qemu/thread.h"
 #include "qemu/queue.h"
 #ifdef CONFIG_TCG
 #include "tcg-target.h"
@@ -142,6 +143,8 @@ typedef struct CPUIOTLBEntry {
 
 #define CPU_COMMON_TLB \
     /* The meaning of the MMU modes is defined in the target code. */   \
+    /* tlb_lock serializes updates to tlb_table and tlb_v_table */      \
+    QemuSpin tlb_lock;                                                  \
     CPUTLBEntry tlb_table[NB_MMU_MODES][CPU_TLB_SIZE];                  \
     CPUTLBEntry tlb_v_table[NB_MMU_MODES][CPU_VTLB_SIZE];               \
     CPUIOTLBEntry iotlb[NB_MMU_MODES][CPU_TLB_SIZE];                    \
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index 41ed052..9590684 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -126,6 +126,29 @@ extern __thread uintptr_t helper_retaddr;
 /* The memory helpers for tcg-generated code need tcg_target_long etc.  */
 #include "tcg.h"
 
+static inline target_ulong tlb_addr_write(const CPUTLBEntry *entry)
+{
+#if TCG_OVERSIZED_GUEST
+    return entry->addr_write;
+#else
+    return atomic_read(&entry->addr_write);
+#endif
+}
+
+/* Find the TLB index corresponding to the mmu_idx + address pair.  */
+static inline uintptr_t tlb_index(CPUArchState *env, uintptr_t mmu_idx,
+                                  target_ulong addr)
+{
+    return (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+}
+
+/* Find the TLB entry corresponding to the mmu_idx + address pair.  */
+static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx,
+                                     target_ulong addr)
+{
+    return &env->tlb_table[mmu_idx][tlb_index(env, mmu_idx, addr)];
+}
+
 #ifdef MMU_MODE0_SUFFIX
 #define CPU_MMU_INDEX 0
 #define MEMSUFFIX MMU_MODE0_SUFFIX
@@ -416,8 +439,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
 #if defined(CONFIG_USER_ONLY)
     return g2h(addr);
 #else
-    int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
-    CPUTLBEntry *tlbentry = &env->tlb_table[mmu_idx][index];
+    CPUTLBEntry *tlbentry = tlb_entry(env, mmu_idx, addr);
     abi_ptr tlb_addr;
     uintptr_t haddr;
 
@@ -426,7 +448,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
         tlb_addr = tlbentry->addr_read;
         break;
     case 1:
-        tlb_addr = tlbentry->addr_write;
+        tlb_addr = tlb_addr_write(tlbentry);
         break;
     case 2:
         tlb_addr = tlbentry->addr_code;
@@ -445,7 +467,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
         return NULL;
     }
 
-    haddr = addr + env->tlb_table[mmu_idx][index].addend;
+    haddr = addr + tlbentry->addend;
     return (void *)haddr;
 #endif /* defined(CONFIG_USER_ONLY) */
 }
diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h
index 4db2302..0f061d4 100644
--- a/include/exec/cpu_ldst_template.h
+++ b/include/exec/cpu_ldst_template.h
@@ -81,7 +81,7 @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env,
                                                   target_ulong ptr,
                                                   uintptr_t retaddr)
 {
-    int page_index;
+    CPUTLBEntry *entry;
     RES_TYPE res;
     target_ulong addr;
     int mmu_idx;
@@ -94,15 +94,15 @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX), _ra)(CPUArchState *env,
 #endif
 
     addr = ptr;
-    page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = CPU_MMU_INDEX;
-    if (unlikely(env->tlb_table[mmu_idx][page_index].ADDR_READ !=
+    entry = tlb_entry(env, mmu_idx, addr);
+    if (unlikely(entry->ADDR_READ !=
                  (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) {
         oi = make_memop_idx(SHIFT, mmu_idx);
         res = glue(glue(helper_ret_ld, URETSUFFIX), MMUSUFFIX)(env, addr,
                                                             oi, retaddr);
     } else {
-        uintptr_t hostaddr = addr + env->tlb_table[mmu_idx][page_index].addend;
+        uintptr_t hostaddr = addr + entry->addend;
         res = glue(glue(ld, USUFFIX), _p)((uint8_t *)hostaddr);
     }
     return res;
@@ -120,7 +120,8 @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env,
                                                   target_ulong ptr,
                                                   uintptr_t retaddr)
 {
-    int res, page_index;
+    CPUTLBEntry *entry;
+    int res;
     target_ulong addr;
     int mmu_idx;
     TCGMemOpIdx oi;
@@ -132,15 +133,15 @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env,
 #endif
 
     addr = ptr;
-    page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = CPU_MMU_INDEX;
-    if (unlikely(env->tlb_table[mmu_idx][page_index].ADDR_READ !=
+    entry = tlb_entry(env, mmu_idx, addr);
+    if (unlikely(entry->ADDR_READ !=
                  (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) {
         oi = make_memop_idx(SHIFT, mmu_idx);
         res = (DATA_STYPE)glue(glue(helper_ret_ld, SRETSUFFIX),
                                MMUSUFFIX)(env, addr, oi, retaddr);
     } else {
-        uintptr_t hostaddr = addr + env->tlb_table[mmu_idx][page_index].addend;
+        uintptr_t hostaddr = addr + entry->addend;
         res = glue(glue(lds, SUFFIX), _p)((uint8_t *)hostaddr);
     }
     return res;
@@ -162,7 +163,7 @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env,
                                                  target_ulong ptr,
                                                  RES_TYPE v, uintptr_t retaddr)
 {
-    int page_index;
+    CPUTLBEntry *entry;
     target_ulong addr;
     int mmu_idx;
     TCGMemOpIdx oi;
@@ -174,15 +175,15 @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX), _ra)(CPUArchState *env,
 #endif
 
     addr = ptr;
-    page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = CPU_MMU_INDEX;
-    if (unlikely(env->tlb_table[mmu_idx][page_index].addr_write !=
+    entry = tlb_entry(env, mmu_idx, addr);
+    if (unlikely(tlb_addr_write(entry) !=
                  (addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) {
         oi = make_memop_idx(SHIFT, mmu_idx);
         glue(glue(helper_ret_st, SUFFIX), MMUSUFFIX)(env, addr, v, oi,
                                                      retaddr);
     } else {
-        uintptr_t hostaddr = addr + env->tlb_table[mmu_idx][page_index].addend;
+        uintptr_t hostaddr = addr + entry->addend;
         glue(glue(st, SUFFIX), _p)((uint8_t *)hostaddr, v);
     }
 }
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 5f78125..815e5b1 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -100,6 +100,11 @@ void cpu_address_space_init(CPUState *cpu, int asidx,
 #if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG)
 /* cputlb.c */
 /**
+ * tlb_init - initialize a CPU's TLB
+ * @cpu: CPU whose TLB should be initialized
+ */
+void tlb_init(CPUState *cpu);
+/**
  * tlb_flush_page:
  * @cpu: CPU whose TLB should be flushed
  * @addr: virtual address of page to be flushed
@@ -258,6 +263,9 @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr,
 void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx,
                  uintptr_t retaddr);
 #else
+static inline void tlb_init(CPUState *cpu)
+{
+}
 static inline void tlb_flush_page(CPUState *cpu, target_ulong addr)
 {
 }
diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h
new file mode 100644
index 0000000..a6af22f
--- /dev/null
+++ b/include/qemu/atomic128.h
@@ -0,0 +1,153 @@
+/*
+ * Simple interface for 128-bit atomic operations.
+ *
+ * Copyright (C) 2018 Linaro, Ltd.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ * See docs/devel/atomics.txt for discussion about the guarantees each
+ * atomic primitive is meant to provide.
+ */
+
+#ifndef QEMU_ATOMIC128_H
+#define QEMU_ATOMIC128_H
+
+/*
+ * GCC is a house divided about supporting large atomic operations.
+ *
+ * For hosts that only have large compare-and-swap, a legalistic reading
+ * of the C++ standard means that one cannot implement __atomic_read on
+ * read-only memory, and thus all atomic operations must synchronize
+ * through libatomic.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80878
+ *
+ * This interpretation is not especially helpful for QEMU.
+ * For softmmu, all RAM is always read/write from the hypervisor.
+ * For user-only, if the guest doesn't implement such an __atomic_read
+ * then the host need not worry about it either.
+ *
+ * Moreover, using libatomic is not an option, because its interface is
+ * built for std::atomic<T>, and requires that *all* accesses to such an
+ * object go through the library.  In our case we do not have an object
+ * in the C/C++ sense, but a view of memory as seen by the guest.
+ * The guest may issue a large atomic operation and then access those
+ * pieces using word-sized accesses.  From the hypervisor, we have no
+ * way to connect those two actions.
+ *
+ * Therefore, special case each platform.
+ */
+
+#if defined(CONFIG_ATOMIC128)
+static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
+{
+    return atomic_cmpxchg__nocheck(ptr, cmp, new);
+}
+# define HAVE_CMPXCHG128 1
+#elif defined(CONFIG_CMPXCHG128)
+static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
+{
+    return __sync_val_compare_and_swap_16(ptr, cmp, new);
+}
+# define HAVE_CMPXCHG128 1
+#elif defined(__aarch64__)
+/* Through gcc 8, aarch64 has no support for 128-bit at all.  */
+static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
+{
+    uint64_t cmpl = int128_getlo(cmp), cmph = int128_gethi(cmp);
+    uint64_t newl = int128_getlo(new), newh = int128_gethi(new);
+    uint64_t oldl, oldh;
+    uint32_t tmp;
+
+    asm("0: ldaxp %[oldl], %[oldh], %[mem]\n\t"
+        "cmp %[oldl], %[cmpl]\n\t"
+        "ccmp %[oldh], %[cmph], #0, eq\n\t"
+        "b.ne 1f\n\t"
+        "stlxp %w[tmp], %[newl], %[newh], %[mem]\n\t"
+        "cbnz %w[tmp], 0b\n"
+        "1:"
+        : [mem] "+m"(*ptr), [tmp] "=&r"(tmp),
+          [oldl] "=&r"(oldl), [oldh] "=r"(oldh)
+        : [cmpl] "r"(cmpl), [cmph] "r"(cmph),
+          [newl] "r"(newl), [newh] "r"(newh)
+        : "memory", "cc");
+
+    return int128_make128(oldl, oldh);
+}
+# define HAVE_CMPXCHG128 1
+#else
+/* Fallback definition that must be optimized away, or error.  */
+Int128 QEMU_ERROR("unsupported atomic")
+    atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new);
+# define HAVE_CMPXCHG128 0
+#endif /* Some definition for HAVE_CMPXCHG128 */
+
+
+#if defined(CONFIG_ATOMIC128)
+static inline Int128 atomic16_read(Int128 *ptr)
+{
+    return atomic_read__nocheck(ptr);
+}
+
+static inline void atomic16_set(Int128 *ptr, Int128 val)
+{
+    atomic_set__nocheck(ptr, val);
+}
+
+# define HAVE_ATOMIC128 1
+#elif !defined(CONFIG_USER_ONLY) && defined(__aarch64__)
+/* We can do better than cmpxchg for AArch64.  */
+static inline Int128 atomic16_read(Int128 *ptr)
+{
+    uint64_t l, h;
+    uint32_t tmp;
+
+    /* The load must be paired with the store to guarantee not tearing.  */
+    asm("0: ldxp %[l], %[h], %[mem]\n\t"
+        "stxp %w[tmp], %[l], %[h], %[mem]\n\t"
+        "cbnz %w[tmp], 0b"
+        : [mem] "+m"(*ptr), [tmp] "=r"(tmp), [l] "=r"(l), [h] "=r"(h));
+
+    return int128_make128(l, h);
+}
+
+static inline void atomic16_set(Int128 *ptr, Int128 val)
+{
+    uint64_t l = int128_getlo(val), h = int128_gethi(val);
+    uint64_t t1, t2;
+
+    /* Load into temporaries to acquire the exclusive access lock.  */
+    asm("0: ldxp %[t1], %[t2], %[mem]\n\t"
+        "stxp %w[t1], %[l], %[h], %[mem]\n\t"
+        "cbnz %w[t1], 0b"
+        : [mem] "+m"(*ptr), [t1] "=&r"(t1), [t2] "=&r"(t2)
+        : [l] "r"(l), [h] "r"(h));
+}
+
+# define HAVE_ATOMIC128 1
+#elif !defined(CONFIG_USER_ONLY) && HAVE_CMPXCHG128
+static inline Int128 atomic16_read(Int128 *ptr)
+{
+    /* Maybe replace 0 with 0, returning the old value.  */
+    return atomic16_cmpxchg(ptr, 0, 0);
+}
+
+static inline void atomic16_set(Int128 *ptr, Int128 val)
+{
+    Int128 old = *ptr, cmp;
+    do {
+        cmp = old;
+        old = atomic16_cmpxchg(ptr, cmp, val);
+    } while (old != cmp);
+}
+
+# define HAVE_ATOMIC128 1
+#else
+/* Fallback definitions that must be optimized away, or error.  */
+Int128 QEMU_ERROR("unsupported atomic") atomic16_read(Int128 *ptr);
+void QEMU_ERROR("unsupported atomic") atomic16_set(Int128 *ptr, Int128 val);
+# define HAVE_ATOMIC128 0
+#endif /* Some definition for HAVE_ATOMIC128 */
+
+#endif /* QEMU_ATOMIC128_H */
diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h
index 66f8c24..6b92710 100644
--- a/include/qemu/compiler.h
+++ b/include/qemu/compiler.h
@@ -146,6 +146,17 @@
 # define QEMU_FLATTEN
 #endif
 
+/*
+ * If __attribute__((error)) is present, use it to produce an error at
+ * compile time.  Otherwise, one must wait for the linker to diagnose
+ * the missing symbol.
+ */
+#if __has_attribute(error)
+# define QEMU_ERROR(X) __attribute__((error(X)))
+#else
+# define QEMU_ERROR(X)
+#endif
+
 /* Implement C11 _Generic via GCC builtins.  Example:
  *
  *    QEMU_GENERIC(x, (float, sinf), (long double, sinl), sin) (x)
diff --git a/include/qemu/timer.h b/include/qemu/timer.h
index a005ed2..dfecd03 100644
--- a/include/qemu/timer.h
+++ b/include/qemu/timer.h
@@ -1046,7 +1046,6 @@ static inline int64_t profile_getclock(void)
     return get_clock();
 }
 
-extern int64_t tcg_time;
 extern int64_t dev_time;
 #endif