Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20190510' into staging

Add CPUClass::tlb_fill.
Improve tlb_vaddr_to_host for use by ARM SVE no-fault loads.

# gpg: Signature made Fri 10 May 2019 19:48:37 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth/tags/pull-tcg-20190510: (27 commits)
  tcg: Use tlb_fill probe from tlb_vaddr_to_host
  tcg: Remove CPUClass::handle_mmu_fault
  tcg: Use CPUClass::tlb_fill in cputlb.c
  target/xtensa: Convert to CPUClass::tlb_fill
  target/unicore32: Convert to CPUClass::tlb_fill
  target/tricore: Convert to CPUClass::tlb_fill
  target/tilegx: Convert to CPUClass::tlb_fill
  target/sparc: Convert to CPUClass::tlb_fill
  target/sh4: Convert to CPUClass::tlb_fill
  target/s390x: Convert to CPUClass::tlb_fill
  target/riscv: Convert to CPUClass::tlb_fill
  target/ppc: Convert to CPUClass::tlb_fill
  target/openrisc: Convert to CPUClass::tlb_fill
  target/nios2: Convert to CPUClass::tlb_fill
  target/moxie: Convert to CPUClass::tlb_fill
  target/mips: Convert to CPUClass::tlb_fill
  target/mips: Tidy control flow in mips_cpu_handle_mmu_fault
  target/mips: Pass a valid error to raise_mmu_exception for user-only
  target/microblaze: Convert to CPUClass::tlb_fill
  target/m68k: Convert to CPUClass::tlb_fill
  ...

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

83 files changed, 866 insertions, 1129 deletions

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index a083324768..cdcc377102 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -855,6 +855,25 @@ static inline ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr)
     return ram_addr;
 }
 
+/*
+ * Note: tlb_fill() can trigger a resize of the TLB. This means that all of the
+ * caller's prior references to the TLB table (e.g. CPUTLBEntry pointers) must
+ * be discarded and looked up again (e.g. via tlb_entry()).
+ */
+static void tlb_fill(CPUState *cpu, target_ulong addr, int size,
+                     MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
+{
+    CPUClass *cc = CPU_GET_CLASS(cpu);
+    bool ok;
+
+    /*
+     * This is not a probe, so only valid return is success; failure
+     * should result in exception + longjmp to the cpu loop.
+     */
+    ok = cc->tlb_fill(cpu, addr, size, access_type, mmu_idx, false, retaddr);
+    assert(ok);
+}
+
 static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                          int mmu_idx, target_ulong addr, uintptr_t retaddr,
                          MMUAccessType access_type, int size)
@@ -938,6 +957,16 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     }
 }
 
+static inline target_ulong tlb_read_ofs(CPUTLBEntry *entry, size_t ofs)
+{
+#if TCG_OVERSIZED_GUEST
+    return *(target_ulong *)((uintptr_t)entry + ofs);
+#else
+    /* ofs might correspond to .addr_write, so use atomic_read */
+    return atomic_read((target_ulong *)((uintptr_t)entry + ofs));
+#endif
+}
+
 /* Return true if ADDR is present in the victim tlb, and has been copied
    back to the main tlb.  */
 static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
@@ -948,14 +977,7 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
     assert_cpu_is_self(ENV_GET_CPU(env));
     for (vidx = 0; vidx < CPU_VTLB_SIZE; ++vidx) {
         CPUTLBEntry *vtlb = &env->tlb_v_table[mmu_idx][vidx];
-        target_ulong cmp;
-
-        /* elt_ofs might correspond to .addr_write, so use atomic_read */
-#if TCG_OVERSIZED_GUEST
-        cmp = *(target_ulong *)((uintptr_t)vtlb + elt_ofs);
-#else
-        cmp = atomic_read((target_ulong *)((uintptr_t)vtlb + elt_ofs));
-#endif
+        target_ulong cmp = tlb_read_ofs(vtlb, elt_ofs);
 
         if (cmp == page) {
             /* Found entry in victim tlb, swap tlb and iotlb.  */
@@ -1039,6 +1061,56 @@ void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx,
     }
 }
 
+void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
+                        MMUAccessType access_type, int mmu_idx)
+{
+    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
+    uintptr_t tlb_addr, page;
+    size_t elt_ofs;
+
+    switch (access_type) {
+    case MMU_DATA_LOAD:
+        elt_ofs = offsetof(CPUTLBEntry, addr_read);
+        break;
+    case MMU_DATA_STORE:
+        elt_ofs = offsetof(CPUTLBEntry, addr_write);
+        break;
+    case MMU_INST_FETCH:
+        elt_ofs = offsetof(CPUTLBEntry, addr_code);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    page = addr & TARGET_PAGE_MASK;
+    tlb_addr = tlb_read_ofs(entry, elt_ofs);
+
+    if (!tlb_hit_page(tlb_addr, page)) {
+        uintptr_t index = tlb_index(env, mmu_idx, addr);
+
+        if (!victim_tlb_hit(env, mmu_idx, index, elt_ofs, page)) {
+            CPUState *cs = ENV_GET_CPU(env);
+            CPUClass *cc = CPU_GET_CLASS(cs);
+
+            if (!cc->tlb_fill(cs, addr, 0, access_type, mmu_idx, true, 0)) {
+                /* Non-faulting page table read failed.  */
+                return NULL;
+            }
+
+            /* TLB resize via tlb_fill may have moved the entry.  */
+            entry = tlb_entry(env, mmu_idx, addr);
+        }
+        tlb_addr = tlb_read_ofs(entry, elt_ofs);
+    }
+
+    if (tlb_addr & ~TARGET_PAGE_MASK) {
+        /* IO access */
+        return NULL;
+    }
+
+    return (void *)((uintptr_t)addr + entry->addend);
+}
+
 /* Probe for a read-modify-write atomic operation.  Do not allow unaligned
  * operations, or io operations to proceed.  Return the host address.  */
 static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c
index 0789984fe6..8cfbeb1b56 100644
--- a/accel/tcg/user-exec.c
+++ b/accel/tcg/user-exec.c
@@ -63,8 +63,8 @@ static inline int handle_cpu_signal(uintptr_t pc, siginfo_t *info,
 {
     CPUState *cpu = current_cpu;
     CPUClass *cc;
-    int ret;
     unsigned long address = (unsigned long)info->si_addr;
+    MMUAccessType access_type;
 
     /* We must handle PC addresses from two different sources:
      * a call return address and a signal frame address.
@@ -147,35 +147,17 @@ static inline int handle_cpu_signal(uintptr_t pc, siginfo_t *info,
        are still valid segv ones */
     address = h2g_nocheck(address);
 
-    cc = CPU_GET_CLASS(cpu);
-    /* see if it is an MMU fault */
-    g_assert(cc->handle_mmu_fault);
-    ret = cc->handle_mmu_fault(cpu, address, 0, is_write, MMU_USER_IDX);
-
-    if (ret == 0) {
-        /* The MMU fault was handled without causing real CPU fault.
-         *  Retain helper_retaddr for a possible second fault.
-         */
-        return 1;
-    }
-
-    /* All other paths lead to cpu_exit; clear helper_retaddr
-     * for next execution.
+    /*
+     * There is no way the target can handle this other than raising
+     * an exception.  Undo signal and retaddr state prior to longjmp.
      */
-    helper_retaddr = 0;
-
-    if (ret < 0) {
-        return 0; /* not an MMU fault */
-    }
-
-    /* Now we have a real cpu fault.  */
-    cpu_restore_state(cpu, pc, true);
-
     sigprocmask(SIG_SETMASK, old_set, NULL);
-    cpu_loop_exit(cpu);
+    helper_retaddr = 0;
 
-    /* never comes here */
-    return 1;
+    cc = CPU_GET_CLASS(cpu);
+    access_type = is_write ? MMU_DATA_STORE : MMU_DATA_LOAD;
+    cc->tlb_fill(cpu, address, 0, access_type, MMU_USER_IDX, false, pc);
+    g_assert_not_reached();
 }
 
 #if defined(__i386__)
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index d78041d7a0..7b28a839d2 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -433,50 +433,20 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx,
  * @mmu_idx: MMU index to use for lookup
  *
  * Look up the specified guest virtual index in the TCG softmmu TLB.
- * If the TLB contains a host virtual address suitable for direct RAM
- * access, then return it. Otherwise (TLB miss, TLB entry is for an
- * I/O access, etc) return NULL.
- *
- * This is the equivalent of the initial fast-path code used by
- * TCG backends for guest load and store accesses.
+ * If we can translate a host virtual address suitable for direct RAM
+ * access, without causing a guest exception, then return it.
+ * Otherwise (TLB entry is for an I/O access, guest software
+ * TLB fill required, etc) return NULL.
  */
+#ifdef CONFIG_USER_ONLY
 static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
-                                      int access_type, int mmu_idx)
+                                      MMUAccessType access_type, int mmu_idx)
 {
-#if defined(CONFIG_USER_ONLY)
     return g2h(addr);
-#else
-    CPUTLBEntry *tlbentry = tlb_entry(env, mmu_idx, addr);
-    abi_ptr tlb_addr;
-    uintptr_t haddr;
-
-    switch (access_type) {
-    case 0:
-        tlb_addr = tlbentry->addr_read;
-        break;
-    case 1:
-        tlb_addr = tlb_addr_write(tlbentry);
-        break;
-    case 2:
-        tlb_addr = tlbentry->addr_code;
-        break;
-    default:
-        g_assert_not_reached();
-    }
-
-    if (!tlb_hit(tlb_addr, addr)) {
-        /* TLB entry is for a different page */
-        return NULL;
-    }
-
-    if (tlb_addr & ~TARGET_PAGE_MASK) {
-        /* IO access */
-        return NULL;
-    }
-
-    haddr = addr + tlbentry->addend;
-    return (void *)haddr;
-#endif /* defined(CONFIG_USER_ONLY) */
 }
+#else
+void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
+                        MMUAccessType access_type, int mmu_idx);
+#endif
 
 #endif /* CPU_LDST_H */
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 58e988b3b1..31f0ecc461 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -474,15 +474,6 @@ static inline void assert_no_pages_locked(void)
  */
 struct MemoryRegionSection *iotlb_to_section(CPUState *cpu,
                                              hwaddr index, MemTxAttrs attrs);
-
-/*
- * Note: tlb_fill() can trigger a resize of the TLB. This means that all of the
- * caller's prior references to the TLB table (e.g. CPUTLBEntry pointers) must
- * be discarded and looked up again (e.g. via tlb_entry()).
- */
-void tlb_fill(CPUState *cpu, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr);
-
 #endif
 
 #if defined(CONFIG_USER_ONLY)
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index 08abcbd3fe..32983f27c3 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -117,7 +117,12 @@ struct TranslationBlock;
  *       This always includes at least the program counter; some targets
  *       will need to do more. If this hook is not implemented then the
  *       default is to call @set_pc(tb->pc).
- * @handle_mmu_fault: Callback for handling an MMU fault.
+ * @tlb_fill: Callback for handling a softmmu tlb miss or user-only
+ *       address fault.  For system mode, if the access is valid, call
+ *       tlb_set_page and return true; if the access is invalid, and
+ *       probe is true, return false; otherwise raise an exception and
+ *       do not return.  For user-only mode, always raise an exception
+ *       and do not return.
  * @get_phys_page_debug: Callback for obtaining a physical address.
  * @get_phys_page_attrs_debug: Callback for obtaining a physical address and the
  *       associated memory transaction attributes to use for the access.
@@ -189,8 +194,9 @@ typedef struct CPUClass {
                                Error **errp);
     void (*set_pc)(CPUState *cpu, vaddr value);
     void (*synchronize_from_tb)(CPUState *cpu, struct TranslationBlock *tb);
-    int (*handle_mmu_fault)(CPUState *cpu, vaddr address, int size, int rw,
-                            int mmu_index);
+    bool (*tlb_fill)(CPUState *cpu, vaddr address, int size,
+                     MMUAccessType access_type, int mmu_idx,
+                     bool probe, uintptr_t retaddr);
     hwaddr (*get_phys_page_debug)(CPUState *cpu, vaddr addr);
     hwaddr (*get_phys_page_attrs_debug)(CPUState *cpu, vaddr addr,
                                         MemTxAttrs *attrs);
diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c
index ad3588a44a..7c81be4111 100644
--- a/target/alpha/cpu.c
+++ b/target/alpha/cpu.c
@@ -225,9 +225,8 @@ static void alpha_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = alpha_cpu_set_pc;
     cc->gdb_read_register = alpha_cpu_gdb_read_register;
     cc->gdb_write_register = alpha_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = alpha_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = alpha_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->do_transaction_failed = alpha_cpu_do_transaction_failed;
     cc->do_unaligned_access = alpha_cpu_do_unaligned_access;
     cc->get_phys_page_debug = alpha_cpu_get_phys_page_debug;
diff --git a/target/alpha/cpu.h b/target/alpha/cpu.h
index 63bf3618ff..cf09112b6a 100644
--- a/target/alpha/cpu.h
+++ b/target/alpha/cpu.h
@@ -475,8 +475,9 @@ void alpha_cpu_list(void);
    is returned if the signal was handled by the virtual CPU.  */
 int cpu_alpha_signal_handler(int host_signum, void *pinfo,
                              void *puc);
-int alpha_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                               int mmu_idx);
+bool alpha_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr);
 void QEMU_NORETURN dynamic_excp(CPUAlphaState *, uintptr_t, int, int);
 void QEMU_NORETURN arith_excp(CPUAlphaState *, uintptr_t, int, uint64_t);
 
diff --git a/target/alpha/helper.c b/target/alpha/helper.c
index 7201576aae..5fe9c87912 100644
--- a/target/alpha/helper.c
+++ b/target/alpha/helper.c
@@ -104,14 +104,15 @@ void cpu_alpha_store_gr(CPUAlphaState *env, unsigned reg, uint64_t val)
 }
 
 #if defined(CONFIG_USER_ONLY)
-int alpha_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                               int rw, int mmu_idx)
+bool alpha_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     AlphaCPU *cpu = ALPHA_CPU(cs);
 
     cs->exception_index = EXCP_MMFAULT;
     cpu->env.trap_arg0 = address;
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 #else
 /* Returns the OSF/1 entMM failure indication, or -1 on success.  */
@@ -248,26 +249,31 @@ hwaddr alpha_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
     return (fail >= 0 ? -1 : phys);
 }
 
-int alpha_cpu_handle_mmu_fault(CPUState *cs, vaddr addr, int size, int rw,
-                               int mmu_idx)
+bool alpha_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     AlphaCPU *cpu = ALPHA_CPU(cs);
     CPUAlphaState *env = &cpu->env;
     target_ulong phys;
     int prot, fail;
 
-    fail = get_physical_address(env, addr, 1 << rw, mmu_idx, &phys, &prot);
+    fail = get_physical_address(env, addr, 1 << access_type,
+                                mmu_idx, &phys, &prot);
     if (unlikely(fail >= 0)) {
+        if (probe) {
+            return false;
+        }
         cs->exception_index = EXCP_MMFAULT;
         env->trap_arg0 = addr;
         env->trap_arg1 = fail;
-        env->trap_arg2 = (rw == 2 ? -1 : rw);
-        return 1;
+        env->trap_arg2 = (access_type == MMU_INST_FETCH ? -1 : access_type);
+        cpu_loop_exit_restore(cs, retaddr);
     }
 
     tlb_set_page(cs, addr & TARGET_PAGE_MASK, phys & TARGET_PAGE_MASK,
                  prot, mmu_idx, TARGET_PAGE_SIZE);
-    return 0;
+    return true;
 }
 #endif /* USER_ONLY */
 
diff --git a/target/alpha/mem_helper.c b/target/alpha/mem_helper.c
index 011bc73dca..934faa1d6f 100644
--- a/target/alpha/mem_helper.c
+++ b/target/alpha/mem_helper.c
@@ -62,20 +62,4 @@ void alpha_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
     env->error_code = 0;
     cpu_loop_exit_restore(cs, retaddr);
 }
-
-/* try to fill the TLB and return an exception if error. If retaddr is
-   NULL, it means that the function was called in C code (i.e. not
-   from generated code or from helper.c) */
-/* XXX: fix it to restore all registers */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = alpha_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret != 0)) {
-        /* Exception index and error code are already set */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
 #endif /* CONFIG_USER_ONLY */
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index a181fa8dc1..8eee1d8c59 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2133,23 +2133,6 @@ static Property arm_cpu_properties[] = {
     DEFINE_PROP_END_OF_LIST()
 };
 
-#ifdef CONFIG_USER_ONLY
-static int arm_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                                    int rw, int mmu_idx)
-{
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
-
-    env->exception.vaddress = address;
-    if (rw == 2) {
-        cs->exception_index = EXCP_PREFETCH_ABORT;
-    } else {
-        cs->exception_index = EXCP_DATA_ABORT;
-    }
-    return 1;
-}
-#endif
-
 static gchar *arm_gdb_arch_name(CPUState *cs)
 {
     ARMCPU *cpu = ARM_CPU(cs);
@@ -2182,9 +2165,7 @@ static void arm_cpu_class_init(ObjectClass *oc, void *data)
     cc->synchronize_from_tb = arm_cpu_synchronize_from_tb;
     cc->gdb_read_register = arm_cpu_gdb_read_register;
     cc->gdb_write_register = arm_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = arm_cpu_handle_mmu_fault;
-#else
+#ifndef CONFIG_USER_ONLY
     cc->do_interrupt = arm_cpu_do_interrupt;
     cc->do_unaligned_access = arm_cpu_do_unaligned_access;
     cc->do_transaction_failed = arm_cpu_do_transaction_failed;
@@ -2209,6 +2190,7 @@ static void arm_cpu_class_init(ObjectClass *oc, void *data)
     cc->disas_set_info = arm_disas_set_info;
 #ifdef CONFIG_TCG
     cc->tcg_initialize = arm_translate_init;
+    cc->tlb_fill = arm_cpu_tlb_fill;
 #endif
 }
 
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 1e6eb0d0f3..e2d5c8e34f 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -12596,43 +12596,6 @@ static bool get_phys_addr(CPUARMState *env, target_ulong address,
     }
 }
 
-/* Walk the page table and (if the mapping exists) add the page
- * to the TLB. Return false on success, or true on failure. Populate
- * fsr with ARM DFSR/IFSR fault register format value on failure.
- */
-bool arm_tlb_fill(CPUState *cs, vaddr address,
-                  MMUAccessType access_type, int mmu_idx,
-                  ARMMMUFaultInfo *fi)
-{
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
-    hwaddr phys_addr;
-    target_ulong page_size;
-    int prot;
-    int ret;
-    MemTxAttrs attrs = {};
-
-    ret = get_phys_addr(env, address, access_type,
-                        core_to_arm_mmu_idx(env, mmu_idx), &phys_addr,
-                        &attrs, &prot, &page_size, fi, NULL);
-    if (!ret) {
-        /*
-         * Map a single [sub]page. Regions smaller than our declared
-         * target page size are handled specially, so for those we
-         * pass in the exact addresses.
-         */
-        if (page_size >= TARGET_PAGE_SIZE) {
-            phys_addr &= TARGET_PAGE_MASK;
-            address &= TARGET_PAGE_MASK;
-        }
-        tlb_set_page_with_attrs(cs, address, phys_addr, attrs,
-                                prot, mmu_idx, page_size);
-        return 0;
-    }
-
-    return ret;
-}
-
 hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr,
                                          MemTxAttrs *attrs)
 {
@@ -13111,6 +13074,59 @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op)
 
 #endif
 
+bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr)
+{
+    ARMCPU *cpu = ARM_CPU(cs);
+
+#ifdef CONFIG_USER_ONLY
+    cpu->env.exception.vaddress = address;
+    if (access_type == MMU_INST_FETCH) {
+        cs->exception_index = EXCP_PREFETCH_ABORT;
+    } else {
+        cs->exception_index = EXCP_DATA_ABORT;
+    }
+    cpu_loop_exit_restore(cs, retaddr);
+#else
+    hwaddr phys_addr;
+    target_ulong page_size;
+    int prot, ret;
+    MemTxAttrs attrs = {};
+    ARMMMUFaultInfo fi = {};
+
+    /*
+     * Walk the page table and (if the mapping exists) add the page
+     * to the TLB.  On success, return true.  Otherwise, if probing,
+     * return false.  Otherwise populate fsr with ARM DFSR/IFSR fault
+     * register format, and signal the fault.
+     */
+    ret = get_phys_addr(&cpu->env, address, access_type,
+                        core_to_arm_mmu_idx(&cpu->env, mmu_idx),
+                        &phys_addr, &attrs, &prot, &page_size, &fi, NULL);
+    if (likely(!ret)) {
+        /*
+         * Map a single [sub]page. Regions smaller than our declared
+         * target page size are handled specially, so for those we
+         * pass in the exact addresses.
+         */
+        if (page_size >= TARGET_PAGE_SIZE) {
+            phys_addr &= TARGET_PAGE_MASK;
+            address &= TARGET_PAGE_MASK;
+        }
+        tlb_set_page_with_attrs(cs, address, phys_addr, attrs,
+                                prot, mmu_idx, page_size);
+        return true;
+    } else if (probe) {
+        return false;
+    } else {
+        /* now we have a real cpu fault */
+        cpu_restore_state(cs, retaddr, true);
+        arm_deliver_fault(cpu, address, access_type, mmu_idx, &fi);
+    }
+#endif
+}
+
 void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in)
 {
     /* Implement DC ZVA, which zeroes a fixed-length block of memory.
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 587a1ddf58..5a02f458f3 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -761,10 +761,12 @@ static inline bool arm_extabort_type(MemTxResult result)
     return result != MEMTX_DECODE_ERROR;
 }
 
-/* Do a page table walk and add page to TLB if possible */
-bool arm_tlb_fill(CPUState *cpu, vaddr address,
-                  MMUAccessType access_type, int mmu_idx,
-                  ARMMMUFaultInfo *fi);
+bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr);
+
+void arm_deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type,
+                       int mmu_idx, ARMMMUFaultInfo *fi) QEMU_NORETURN;
 
 /* Return true if the stage 1 translation regime is using LPAE format page
  * tables */
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index 8698b4dc83..8ee15a4bd4 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -126,8 +126,8 @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn,
     return syn;
 }
 
-static void deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type,
-                          int mmu_idx, ARMMMUFaultInfo *fi)
+void arm_deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type,
+                       int mmu_idx, ARMMMUFaultInfo *fi)
 {
     CPUARMState *env = &cpu->env;
     int target_el;
@@ -179,27 +179,6 @@ static void deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type,
     raise_exception(env, exc, syn, target_el);
 }
 
-/* try to fill the TLB and return an exception if error. If retaddr is
- * NULL, it means that the function was called in C code (i.e. not
- * from generated code or from helper.c)
- */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    bool ret;
-    ARMMMUFaultInfo fi = {};
-
-    ret = arm_tlb_fill(cs, addr, access_type, mmu_idx, &fi);
-    if (unlikely(ret)) {
-        ARMCPU *cpu = ARM_CPU(cs);
-
-        /* now we have a real cpu fault */
-        cpu_restore_state(cs, retaddr, true);
-
-        deliver_fault(cpu, addr, access_type, mmu_idx, &fi);
-    }
-}
-
 /* Raise a data fault alignment exception for the specified virtual address */
 void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr,
                                  MMUAccessType access_type,
@@ -212,7 +191,7 @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr,
     cpu_restore_state(cs, retaddr, true);
 
     fi.type = ARMFault_Alignment;
-    deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi);
+    arm_deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi);
 }
 
 /* arm_cpu_do_transaction_failed: handle a memory system error response
@@ -233,7 +212,7 @@ void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
 
     fi.ea = arm_extabort_type(response);
     fi.type = ARMFault_SyncExternal;
-    deliver_fault(cpu, addr, access_type, mmu_idx, &fi);
+    arm_deliver_fault(cpu, addr, access_type, mmu_idx, &fi);
 }
 
 #endif /* !defined(CONFIG_USER_ONLY) */
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index bc847250dd..fd434c66ea 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -4598,11 +4598,7 @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
      * in the real world, obviously.)
      *
      * Then there are the annoying special cases with watchpoints...
-     *
-     * TODO: Add a form of tlb_fill that does not raise an exception,
-     * with a form of tlb_vaddr_to_host and a set of loads to match.
-     * The non_fault_vaddr_to_host would handle everything, usually,
-     * and the loads would handle the iomem path for watchpoints.
+     * TODO: Add a form of non-faulting loads using cc->tlb_fill(probe=true).
      */
     host = tlb_vaddr_to_host(env, addr + mem_off, MMU_DATA_LOAD, mmu_idx);
     split = max_for_page(addr, mem_off, mem_max);
diff --git a/target/cris/cpu.c b/target/cris/cpu.c
index 75729bfdd5..4e5288ae80 100644
--- a/target/cris/cpu.c
+++ b/target/cris/cpu.c
@@ -269,9 +269,8 @@ static void cris_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = cris_cpu_set_pc;
     cc->gdb_read_register = cris_cpu_gdb_read_register;
     cc->gdb_write_register = cris_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = cris_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = cris_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = cris_cpu_get_phys_page_debug;
     dc->vmsd = &vmstate_cris_cpu;
 #endif
diff --git a/target/cris/cpu.h b/target/cris/cpu.h
index 0fbe771639..857de79e24 100644
--- a/target/cris/cpu.h
+++ b/target/cris/cpu.h
@@ -281,8 +281,9 @@ static inline int cpu_mmu_index (CPUCRISState *env, bool ifetch)
 	return !!(env->pregs[PR_CCS] & U_FLAG);
 }
 
-int cris_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                              int mmu_idx);
+bool cris_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
 
 /* Support function regs.  */
 #define SFR_RW_GC_CFG      0][0
diff --git a/target/cris/helper.c b/target/cris/helper.c
index 3939603c73..b5159b8357 100644
--- a/target/cris/helper.c
+++ b/target/cris/helper.c
@@ -24,6 +24,7 @@
 #include "qemu/host-utils.h"
 #include "exec/exec-all.h"
 #include "exec/cpu_ldst.h"
+#include "exec/helper-proto.h"
 
 
 //#define CRIS_HELPER_DEBUG
@@ -53,15 +54,15 @@ void crisv10_cpu_do_interrupt(CPUState *cs)
     cris_cpu_do_interrupt(cs);
 }
 
-int cris_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                              int mmu_idx)
+bool cris_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     CRISCPU *cpu = CRIS_CPU(cs);
 
     cs->exception_index = 0xaa;
     cpu->env.pregs[PR_EDA] = address;
-    cpu_dump_state(cs, stderr, 0);
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #else /* !CONFIG_USER_ONLY */
@@ -76,33 +77,19 @@ static void cris_shift_ccs(CPUCRISState *env)
     env->pregs[PR_CCS] = ccs;
 }
 
-int cris_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                              int mmu_idx)
+bool cris_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     CRISCPU *cpu = CRIS_CPU(cs);
     CPUCRISState *env = &cpu->env;
     struct cris_mmu_result res;
     int prot, miss;
-    int r = -1;
     target_ulong phy;
 
-    qemu_log_mask(CPU_LOG_MMU, "%s addr=%" VADDR_PRIx " pc=%x rw=%x\n",
-            __func__, address, env->pc, rw);
     miss = cris_mmu_translate(&res, env, address & TARGET_PAGE_MASK,
-                              rw, mmu_idx, 0);
-    if (miss) {
-        if (cs->exception_index == EXCP_BUSFAULT) {
-            cpu_abort(cs,
-                      "CRIS: Illegal recursive bus fault."
-                      "addr=%" VADDR_PRIx " rw=%d\n",
-                      address, rw);
-        }
-
-        env->pregs[PR_EDA] = address;
-        cs->exception_index = EXCP_BUSFAULT;
-        env->fault_vector = res.bf_vec;
-        r = 1;
-    } else {
+                              access_type, mmu_idx, 0);
+    if (likely(!miss)) {
         /*
          * Mask off the cache selection bit. The ETRAX busses do not
          * see the top bit.
@@ -111,15 +98,29 @@ int cris_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
         prot = res.prot;
         tlb_set_page(cs, address & TARGET_PAGE_MASK, phy,
                      prot, mmu_idx, TARGET_PAGE_SIZE);
-        r = 0;
+        return true;
+    }
+
+    if (probe) {
+        return false;
     }
-    if (r > 0) {
-        qemu_log_mask(CPU_LOG_MMU,
-                "%s returns %d irqreq=%x addr=%" VADDR_PRIx " phy=%x vec=%x"
-                " pc=%x\n", __func__, r, cs->interrupt_request, address,
-                res.phy, res.bf_vec, env->pc);
+
+    if (cs->exception_index == EXCP_BUSFAULT) {
+        cpu_abort(cs, "CRIS: Illegal recursive bus fault."
+                      "addr=%" VADDR_PRIx " access_type=%d\n",
+                      address, access_type);
+    }
+
+    env->pregs[PR_EDA] = address;
+    cs->exception_index = EXCP_BUSFAULT;
+    env->fault_vector = res.bf_vec;
+    if (retaddr) {
+        if (cpu_restore_state(cs, retaddr, true)) {
+            /* Evaluate flags after retranslation. */
+            helper_top_evaluate_flags(env);
+        }
     }
-    return r;
+    cpu_loop_exit(cs);
 }
 
 void crisv10_cpu_do_interrupt(CPUState *cs)
diff --git a/target/cris/op_helper.c b/target/cris/op_helper.c
index 0ee3a3117b..26a395b413 100644
--- a/target/cris/op_helper.c
+++ b/target/cris/op_helper.c
@@ -37,34 +37,6 @@
 #define D_LOG(...) do { } while (0)
 #endif
 
-#if !defined(CONFIG_USER_ONLY)
-/* Try to fill the TLB and return an exception if error. If retaddr is
-   NULL, it means that the function was called in C code (i.e. not
-   from generated code or from helper.c) */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    CRISCPU *cpu = CRIS_CPU(cs);
-    CPUCRISState *env = &cpu->env;
-    int ret;
-
-    D_LOG("%s pc=%x tpc=%x ra=%p\n", __func__,
-          env->pc, env->pregs[PR_EDA], (void *)retaddr);
-    ret = cris_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        if (retaddr) {
-            /* now we have a real cpu fault */
-            if (cpu_restore_state(cs, retaddr, true)) {
-                /* Evaluate flags after retranslation. */
-                helper_top_evaluate_flags(env);
-            }
-        }
-        cpu_loop_exit(cs);
-    }
-}
-
-#endif
-
 void helper_raise_exception(CPUCRISState *env, uint32_t index)
 {
     CPUState *cs = CPU(cris_env_get_cpu(env));
diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c
index e64f48581e..9717ea1798 100644
--- a/target/hppa/cpu.c
+++ b/target/hppa/cpu.c
@@ -163,9 +163,8 @@ static void hppa_cpu_class_init(ObjectClass *oc, void *data)
     cc->synchronize_from_tb = hppa_cpu_synchronize_from_tb;
     cc->gdb_read_register = hppa_cpu_gdb_read_register;
     cc->gdb_write_register = hppa_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = hppa_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = hppa_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = hppa_cpu_get_phys_page_debug;
     dc->vmsd = &vmstate_hppa_cpu;
 #endif
diff --git a/target/hppa/cpu.h b/target/hppa/cpu.h
index 923346adb6..c1e0215e66 100644
--- a/target/hppa/cpu.h
+++ b/target/hppa/cpu.h
@@ -360,10 +360,10 @@ int hppa_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
 void hppa_cpu_do_interrupt(CPUState *cpu);
 bool hppa_cpu_exec_interrupt(CPUState *cpu, int int_req);
 void hppa_cpu_dump_state(CPUState *cs, FILE *f, int);
-#ifdef CONFIG_USER_ONLY
-int hppa_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size,
-                              int rw, int midx);
-#else
+bool hppa_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
+#ifndef CONFIG_USER_ONLY
 int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
                               int type, hwaddr *pphys, int *pprot);
 extern const MemoryRegionOps hppa_io_eir_ops;
diff --git a/target/hppa/mem_helper.c b/target/hppa/mem_helper.c
index 77fb544838..0fd3ac6645 100644
--- a/target/hppa/mem_helper.c
+++ b/target/hppa/mem_helper.c
@@ -25,8 +25,9 @@
 #include "trace.h"
 
 #ifdef CONFIG_USER_ONLY
-int hppa_cpu_handle_mmu_fault(CPUState *cs, vaddr address,
-                              int size, int rw, int mmu_idx)
+bool hppa_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     HPPACPU *cpu = HPPA_CPU(cs);
 
@@ -34,7 +35,7 @@ int hppa_cpu_handle_mmu_fault(CPUState *cs, vaddr address,
        which would affect si_code.  */
     cs->exception_index = EXCP_DMP;
     cpu->env.cr[CR_IOR] = address;
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 #else
 static hppa_tlb_entry *hppa_find_tlb(CPUHPPAState *env, vaddr addr)
@@ -213,8 +214,9 @@ hwaddr hppa_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
     return excp == EXCP_DTLB_MISS ? -1 : phys;
 }
 
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType type, int mmu_idx, uintptr_t retaddr)
+bool hppa_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
+                       MMUAccessType type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     HPPACPU *cpu = HPPA_CPU(cs);
     CPUHPPAState *env = &cpu->env;
@@ -236,6 +238,9 @@ void tlb_fill(CPUState *cs, target_ulong addr, int size,
     excp = hppa_get_physical_address(env, addr, mmu_idx,
                                      a_prot, &phys, &prot);
     if (unlikely(excp >= 0)) {
+        if (probe) {
+            return false;
+        }
         trace_hppa_tlb_fill_excp(env, addr, size, type, mmu_idx);
         /* Failure.  Raise the indicated exception.  */
         cs->exception_index = excp;
@@ -252,6 +257,7 @@ void tlb_fill(CPUState *cs, target_ulong addr, int size,
     /* Success!  Store the translation into the QEMU TLB.  */
     tlb_set_page(cs, addr & TARGET_PAGE_MASK, phys & TARGET_PAGE_MASK,
                  prot, mmu_idx, TARGET_PAGE_SIZE);
+    return true;
 }
 
 /* Insert (Insn/Data) TLB Address.  Note this is PA 1.1 only.  */
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 722c5514d4..2df56fa977 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -5915,9 +5915,7 @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data)
     cc->gdb_write_register = x86_cpu_gdb_write_register;
     cc->get_arch_id = x86_cpu_get_arch_id;
     cc->get_paging_enabled = x86_cpu_get_paging_enabled;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = x86_cpu_handle_mmu_fault;
-#else
+#ifndef CONFIG_USER_ONLY
     cc->asidx_from_attrs = x86_asidx_from_attrs;
     cc->get_memory_mapping = x86_cpu_get_memory_mapping;
     cc->get_phys_page_debug = x86_cpu_get_phys_page_debug;
@@ -5942,6 +5940,7 @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data)
     cc->cpu_exec_exit = x86_cpu_exec_exit;
 #ifdef CONFIG_TCG
     cc->tcg_initialize = tcg_x86_init;
+    cc->tlb_fill = x86_cpu_tlb_fill;
 #endif
     cc->disas_set_info = x86_disas_set_info;
 
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 0128910661..fce6660bac 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1656,8 +1656,9 @@ void host_cpuid(uint32_t function, uint32_t count,
 void host_vendor_fms(char *vendor, int *family, int *model, int *stepping);
 
 /* helper.c */
-int x86_cpu_handle_mmu_fault(CPUState *cpu, vaddr addr, int size,
-                             int is_write, int mmu_idx);
+bool x86_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr);
 void x86_cpu_set_a20(X86CPU *cpu, int a20_state);
 
 #ifndef CONFIG_USER_ONLY
diff --git a/target/i386/excp_helper.c b/target/i386/excp_helper.c
index 49231f6b69..fa1ead6404 100644
--- a/target/i386/excp_helper.c
+++ b/target/i386/excp_helper.c
@@ -137,26 +137,7 @@ void raise_exception_ra(CPUX86State *env, int exception_index, uintptr_t retaddr
     raise_interrupt2(env, exception_index, 0, 0, 0, retaddr);
 }
 
-#if defined(CONFIG_USER_ONLY)
-int x86_cpu_handle_mmu_fault(CPUState *cs, vaddr addr, int size,
-                             int is_write, int mmu_idx)
-{
-    X86CPU *cpu = X86_CPU(cs);
-    CPUX86State *env = &cpu->env;
-
-    /* user mode only emulation */
-    is_write &= 1;
-    env->cr[2] = addr;
-    env->error_code = (is_write << PG_ERROR_W_BIT);
-    env->error_code |= PG_ERROR_U_MASK;
-    cs->exception_index = EXCP0E_PAGE;
-    env->exception_is_int = 0;
-    env->exception_next_eip = -1;
-    return 1;
-}
-
-#else
-
+#if !defined(CONFIG_USER_ONLY)
 static hwaddr get_hphys(CPUState *cs, hwaddr gphys, MMUAccessType access_type,
                         int *prot)
 {
@@ -365,8 +346,8 @@ static hwaddr get_hphys(CPUState *cs, hwaddr gphys, MMUAccessType access_type,
  * 0  = nothing more to do
  * 1  = generate PF fault
  */
-int x86_cpu_handle_mmu_fault(CPUState *cs, vaddr addr, int size,
-                             int is_write1, int mmu_idx)
+static int handle_mmu_fault(CPUState *cs, vaddr addr, int size,
+                            int is_write1, int mmu_idx)
 {
     X86CPU *cpu = X86_CPU(cs);
     CPUX86State *env = &cpu->env;
@@ -691,3 +672,31 @@ do_check_protect_pse36:
     return 1;
 }
 #endif
+
+bool x86_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    CPUX86State *env = &cpu->env;
+
+#ifdef CONFIG_USER_ONLY
+    /* user mode only emulation */
+    env->cr[2] = addr;
+    env->error_code = (access_type == MMU_DATA_STORE) << PG_ERROR_W_BIT;
+    env->error_code |= PG_ERROR_U_MASK;
+    cs->exception_index = EXCP0E_PAGE;
+    env->exception_is_int = 0;
+    env->exception_next_eip = -1;
+    cpu_loop_exit_restore(cs, retaddr);
+#else
+    env->retaddr = retaddr;
+    if (handle_mmu_fault(cs, addr, size, access_type, mmu_idx)) {
+        /* FIXME: On error in get_hphys we have already jumped out.  */
+        g_assert(!probe);
+        raise_exception_err_ra(env, cs->exception_index,
+                               env->error_code, retaddr);
+    }
+    return true;
+#endif
+}
diff --git a/target/i386/mem_helper.c b/target/i386/mem_helper.c
index 6cc53bcb40..1885df29d2 100644
--- a/target/i386/mem_helper.c
+++ b/target/i386/mem_helper.c
@@ -191,24 +191,3 @@ void helper_boundl(CPUX86State *env, target_ulong a0, int v)
         raise_exception_ra(env, EXCP05_BOUND, GETPC());
     }
 }
-
-#if !defined(CONFIG_USER_ONLY)
-/* try to fill the TLB and return an exception if error. If retaddr is
- * NULL, it means that the function was called in C code (i.e. not
- * from generated code or from helper.c)
- */
-/* XXX: fix it to restore all registers */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    X86CPU *cpu = X86_CPU(cs);
-    CPUX86State *env = &cpu->env;
-    int ret;
-
-    env->retaddr = retaddr;
-    ret = x86_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (ret) {
-        raise_exception_err_ra(env, cs->exception_index, env->error_code, retaddr);
-    }
-}
-#endif
diff --git a/target/lm32/cpu.c b/target/lm32/cpu.c
index 282da19994..57c50c1578 100644
--- a/target/lm32/cpu.c
+++ b/target/lm32/cpu.c
@@ -231,9 +231,8 @@ static void lm32_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = lm32_cpu_set_pc;
     cc->gdb_read_register = lm32_cpu_gdb_read_register;
     cc->gdb_write_register = lm32_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = lm32_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = lm32_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = lm32_cpu_get_phys_page_debug;
     cc->vmsd = &vmstate_lm32_cpu;
 #endif
diff --git a/target/lm32/cpu.h b/target/lm32/cpu.h
index 9b1e6c2d58..d224d4426e 100644
--- a/target/lm32/cpu.h
+++ b/target/lm32/cpu.h
@@ -261,8 +261,9 @@ bool lm32_cpu_do_semihosting(CPUState *cs);
 #define cpu_list lm32_cpu_list
 #define cpu_signal_handler cpu_lm32_signal_handler
 
-int lm32_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                              int mmu_idx);
+bool lm32_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
 
 #include "exec/cpu-all.h"
 
diff --git a/target/lm32/helper.c b/target/lm32/helper.c
index a039a993ff..20ea17ba23 100644
--- a/target/lm32/helper.c
+++ b/target/lm32/helper.c
@@ -25,8 +25,9 @@
 #include "exec/semihost.h"
 #include "exec/log.h"
 
-int lm32_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                              int mmu_idx)
+bool lm32_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     LM32CPU *cpu = LM32_CPU(cs);
     CPULM32State *env = &cpu->env;
@@ -40,8 +41,7 @@ int lm32_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
     } else {
         tlb_set_page(cs, address, address, prot, mmu_idx, TARGET_PAGE_SIZE);
     }
-
-    return 0;
+    return true;
 }
 
 hwaddr lm32_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
diff --git a/target/lm32/op_helper.c b/target/lm32/op_helper.c
index 234d55e056..be12b11b02 100644
--- a/target/lm32/op_helper.c
+++ b/target/lm32/op_helper.c
@@ -143,21 +143,5 @@ uint32_t HELPER(rcsr_jrx)(CPULM32State *env)
 {
     return lm32_juart_get_jrx(env->juart_state);
 }
-
-/* Try to fill the TLB and return an exception if error. If retaddr is
- * NULL, it means that the function was called in C code (i.e. not
- * from generated code or from helper.c)
- */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = lm32_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        /* now we have a real cpu fault */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
 #endif
 
diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c
index 582e3a73b3..6f441bc973 100644
--- a/target/m68k/cpu.c
+++ b/target/m68k/cpu.c
@@ -269,7 +269,7 @@ static void m68k_cpu_class_init(ObjectClass *c, void *data)
     cc->set_pc = m68k_cpu_set_pc;
     cc->gdb_read_register = m68k_cpu_gdb_read_register;
     cc->gdb_write_register = m68k_cpu_gdb_write_register;
-    cc->handle_mmu_fault = m68k_cpu_handle_mmu_fault;
+    cc->tlb_fill = m68k_cpu_tlb_fill;
 #if defined(CONFIG_SOFTMMU)
     cc->do_unassigned_access = m68k_cpu_unassigned_access;
     cc->get_phys_page_debug = m68k_cpu_get_phys_page_debug;
diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h
index ad41608341..683d3e2f79 100644
--- a/target/m68k/cpu.h
+++ b/target/m68k/cpu.h
@@ -542,8 +542,9 @@ static inline int cpu_mmu_index (CPUM68KState *env, bool ifetch)
     return (env->sr & SR_S) == 0 ? 1 : 0;
 }
 
-int m68k_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                              int mmu_idx);
+bool m68k_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
 void m68k_cpu_unassigned_access(CPUState *cs, hwaddr addr,
                                 bool is_write, bool is_exec, int is_asi,
                                 unsigned size);
diff --git a/target/m68k/helper.c b/target/m68k/helper.c
index d958a34959..9fc9e646ff 100644
--- a/target/m68k/helper.c
+++ b/target/m68k/helper.c
@@ -353,20 +353,7 @@ void m68k_switch_sp(CPUM68KState *env)
     env->current_sp = new_sp;
 }
 
-#if defined(CONFIG_USER_ONLY)
-
-int m68k_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                              int mmu_idx)
-{
-    M68kCPU *cpu = M68K_CPU(cs);
-
-    cs->exception_index = EXCP_ACCESS;
-    cpu->env.mmu.ar = address;
-    return 1;
-}
-
-#else
-
+#if !defined(CONFIG_USER_ONLY)
 /* MMU: 68040 only */
 
 static void print_address_zone(uint32_t logical, uint32_t physical,
@@ -795,11 +782,36 @@ hwaddr m68k_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
     return phys_addr;
 }
 
-int m68k_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                              int mmu_idx)
+/*
+ * Notify CPU of a pending interrupt.  Prioritization and vectoring should
+ * be handled by the interrupt controller.  Real hardware only requests
+ * the vector when the interrupt is acknowledged by the CPU.  For
+ * simplicity we calculate it when the interrupt is signalled.
+ */
+void m68k_set_irq_level(M68kCPU *cpu, int level, uint8_t vector)
+{
+    CPUState *cs = CPU(cpu);
+    CPUM68KState *env = &cpu->env;
+
+    env->pending_level = level;
+    env->pending_vector = vector;
+    if (level) {
+        cpu_interrupt(cs, CPU_INTERRUPT_HARD);
+    } else {
+        cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
+    }
+}
+
+#endif
+
+bool m68k_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType qemu_access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     M68kCPU *cpu = M68K_CPU(cs);
     CPUM68KState *env = &cpu->env;
+
+#ifndef CONFIG_USER_ONLY
     hwaddr physical;
     int prot;
     int access_type;
@@ -812,32 +824,35 @@ int m68k_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
                      address & TARGET_PAGE_MASK,
                      PAGE_READ | PAGE_WRITE | PAGE_EXEC,
                      mmu_idx, TARGET_PAGE_SIZE);
-        return 0;
+        return true;
     }
 
-    if (rw == 2) {
+    if (qemu_access_type == MMU_INST_FETCH) {
         access_type = ACCESS_CODE;
-        rw = 0;
     } else {
         access_type = ACCESS_DATA;
-        if (rw) {
+        if (qemu_access_type == MMU_DATA_STORE) {
             access_type |= ACCESS_STORE;
         }
     }
-
     if (mmu_idx != MMU_USER_IDX) {
         access_type |= ACCESS_SUPER;
     }
 
     ret = get_physical_address(&cpu->env, &physical, &prot,
                                address, access_type, &page_size);
-    if (ret == 0) {
+    if (likely(ret == 0)) {
         address &= TARGET_PAGE_MASK;
         physical += address & (page_size - 1);
         tlb_set_page(cs, address, physical,
                      prot, mmu_idx, TARGET_PAGE_SIZE);
-        return 0;
+        return true;
     }
+
+    if (probe) {
+        return false;
+    }
+
     /* page fault */
     env->mmu.ssw = M68K_ATC_040;
     switch (size) {
@@ -862,31 +877,13 @@ int m68k_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
     if (!(access_type & ACCESS_STORE)) {
         env->mmu.ssw |= M68K_RW_040;
     }
-    env->mmu.ar = address;
-    cs->exception_index = EXCP_ACCESS;
-    return 1;
-}
-
-/* Notify CPU of a pending interrupt.  Prioritization and vectoring should
-   be handled by the interrupt controller.  Real hardware only requests
-   the vector when the interrupt is acknowledged by the CPU.  For
-   simplicitly we calculate it when the interrupt is signalled.  */
-void m68k_set_irq_level(M68kCPU *cpu, int level, uint8_t vector)
-{
-    CPUState *cs = CPU(cpu);
-    CPUM68KState *env = &cpu->env;
+#endif
 
-    env->pending_level = level;
-    env->pending_vector = vector;
-    if (level) {
-        cpu_interrupt(cs, CPU_INTERRUPT_HARD);
-    } else {
-        cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
-    }
+    cs->exception_index = EXCP_ACCESS;
+    env->mmu.ar = address;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
-#endif
-
 uint32_t HELPER(bitrev)(uint32_t x)
 {
     x = ((x >> 1) & 0x55555555u) | ((x << 1) & 0xaaaaaaaau);
diff --git a/target/m68k/op_helper.c b/target/m68k/op_helper.c
index 76f439985a..d421614727 100644
--- a/target/m68k/op_helper.c
+++ b/target/m68k/op_helper.c
@@ -36,21 +36,6 @@ static inline void do_interrupt_m68k_hardirq(CPUM68KState *env)
 
 #else
 
-/* Try to fill the TLB and return an exception if error. If retaddr is
-   NULL, it means that the function was called in C code (i.e. not
-   from generated code or from helper.c) */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = m68k_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        /* now we have a real cpu fault */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-
 static void cf_rte(CPUM68KState *env)
 {
     uint32_t sp;
diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c
index 5596cd5485..0ea549910b 100644
--- a/target/microblaze/cpu.c
+++ b/target/microblaze/cpu.c
@@ -304,9 +304,8 @@ static void mb_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = mb_cpu_set_pc;
     cc->gdb_read_register = mb_cpu_gdb_read_register;
     cc->gdb_write_register = mb_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = mb_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = mb_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->do_transaction_failed = mb_cpu_transaction_failed;
     cc->get_phys_page_debug = mb_cpu_get_phys_page_debug;
 #endif
diff --git a/target/microblaze/cpu.h b/target/microblaze/cpu.h
index f20e796865..7a9fb8f4aa 100644
--- a/target/microblaze/cpu.h
+++ b/target/microblaze/cpu.h
@@ -374,8 +374,9 @@ static inline int cpu_mmu_index (CPUMBState *env, bool ifetch)
     return MMU_KERNEL_IDX;
 }
 
-int mb_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                            int mmu_idx);
+bool mb_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                     MMUAccessType access_type, int mmu_idx,
+                     bool probe, uintptr_t retaddr);
 
 #include "exec/cpu-all.h"
 
diff --git a/target/microblaze/helper.c b/target/microblaze/helper.c
index 9848e31d7f..ab2ceeb055 100644
--- a/target/microblaze/helper.c
+++ b/target/microblaze/helper.c
@@ -38,73 +38,74 @@ void mb_cpu_do_interrupt(CPUState *cs)
     env->regs[14] = env->sregs[SR_PC];
 }
 
-int mb_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                            int mmu_idx)
+bool mb_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                     MMUAccessType access_type, int mmu_idx,
+                     bool probe, uintptr_t retaddr)
 {
     cs->exception_index = 0xaa;
-    cpu_dump_state(cs, stderr, 0);
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #else /* !CONFIG_USER_ONLY */
 
-int mb_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                            int mmu_idx)
+bool mb_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                     MMUAccessType access_type, int mmu_idx,
+                     bool probe, uintptr_t retaddr)
 {
     MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs);
     CPUMBState *env = &cpu->env;
+    struct microblaze_mmu_lookup lu;
     unsigned int hit;
-    int r = 1;
     int prot;
 
-    /* Translate if the MMU is available and enabled.  */
-    if (mmu_idx != MMU_NOMMU_IDX) {
-        uint32_t vaddr, paddr;
-        struct microblaze_mmu_lookup lu;
-
-        hit = mmu_translate(&env->mmu, &lu, address, rw, mmu_idx);
-        if (hit) {
-            vaddr = address & TARGET_PAGE_MASK;
-            paddr = lu.paddr + vaddr - lu.vaddr;
-
-            qemu_log_mask(CPU_LOG_MMU, "MMU map mmu=%d v=%x p=%x prot=%x\n",
-                    mmu_idx, vaddr, paddr, lu.prot);
-            tlb_set_page(cs, vaddr, paddr, lu.prot, mmu_idx, TARGET_PAGE_SIZE);
-            r = 0;
-        } else {
-            env->sregs[SR_EAR] = address;
-            qemu_log_mask(CPU_LOG_MMU, "mmu=%d miss v=%" VADDR_PRIx "\n",
-                                        mmu_idx, address);
-
-            switch (lu.err) {
-                case ERR_PROT:
-                    env->sregs[SR_ESR] = rw == 2 ? 17 : 16;
-                    env->sregs[SR_ESR] |= (rw == 1) << 10;
-                    break;
-                case ERR_MISS:
-                    env->sregs[SR_ESR] = rw == 2 ? 19 : 18;
-                    env->sregs[SR_ESR] |= (rw == 1) << 10;
-                    break;
-                default:
-                    abort();
-                    break;
-            }
-
-            if (cs->exception_index == EXCP_MMU) {
-                cpu_abort(cs, "recursive faults\n");
-            }
-
-            /* TLB miss.  */
-            cs->exception_index = EXCP_MMU;
-        }
-    } else {
+    if (mmu_idx == MMU_NOMMU_IDX) {
         /* MMU disabled or not available.  */
         address &= TARGET_PAGE_MASK;
         prot = PAGE_BITS;
         tlb_set_page(cs, address, address, prot, mmu_idx, TARGET_PAGE_SIZE);
-        r = 0;
+        return true;
     }
-    return r;
+
+    hit = mmu_translate(&env->mmu, &lu, address, access_type, mmu_idx);
+    if (likely(hit)) {
+        uint32_t vaddr = address & TARGET_PAGE_MASK;
+        uint32_t paddr = lu.paddr + vaddr - lu.vaddr;
+
+        qemu_log_mask(CPU_LOG_MMU, "MMU map mmu=%d v=%x p=%x prot=%x\n",
+                      mmu_idx, vaddr, paddr, lu.prot);
+        tlb_set_page(cs, vaddr, paddr, lu.prot, mmu_idx, TARGET_PAGE_SIZE);
+        return true;
+    }
+
+    /* TLB miss.  */
+    if (probe) {
+        return false;
+    }
+
+    qemu_log_mask(CPU_LOG_MMU, "mmu=%d miss v=%" VADDR_PRIx "\n",
+                  mmu_idx, address);
+
+    env->sregs[SR_EAR] = address;
+    switch (lu.err) {
+    case ERR_PROT:
+        env->sregs[SR_ESR] = access_type == MMU_INST_FETCH ? 17 : 16;
+        env->sregs[SR_ESR] |= (access_type == MMU_DATA_STORE) << 10;
+        break;
+    case ERR_MISS:
+        env->sregs[SR_ESR] = access_type == MMU_INST_FETCH ? 19 : 18;
+        env->sregs[SR_ESR] |= (access_type == MMU_DATA_STORE) << 10;
+        break;
+    default:
+        abort();
+    }
+
+    if (cs->exception_index == EXCP_MMU) {
+        cpu_abort(cs, "recursive faults\n");
+    }
+
+    /* TLB miss.  */
+    cs->exception_index = EXCP_MMU;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 void mb_cpu_do_interrupt(CPUState *cs)
diff --git a/target/microblaze/op_helper.c b/target/microblaze/op_helper.c
index e23dcfdc20..b5dbb90d05 100644
--- a/target/microblaze/op_helper.c
+++ b/target/microblaze/op_helper.c
@@ -28,25 +28,6 @@
 
 #define D(x)
 
-#if !defined(CONFIG_USER_ONLY)
-
-/* Try to fill the TLB and return an exception if error. If retaddr is
- * NULL, it means that the function was called in C code (i.e. not
- * from generated code or from helper.c)
- */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = mb_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        /* now we have a real cpu fault */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-#endif
-
 void helper_put(uint32_t id, uint32_t ctrl, uint32_t data)
 {
     int test = ctrl & STREAM_TEST;
diff --git a/target/mips/cpu.c b/target/mips/cpu.c
index e217fb3e36..a33058609a 100644
--- a/target/mips/cpu.c
+++ b/target/mips/cpu.c
@@ -197,9 +197,7 @@ static void mips_cpu_class_init(ObjectClass *c, void *data)
     cc->synchronize_from_tb = mips_cpu_synchronize_from_tb;
     cc->gdb_read_register = mips_cpu_gdb_read_register;
     cc->gdb_write_register = mips_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = mips_cpu_handle_mmu_fault;
-#else
+#ifndef CONFIG_USER_ONLY
     cc->do_unassigned_access = mips_cpu_unassigned_access;
     cc->do_unaligned_access = mips_cpu_do_unaligned_access;
     cc->get_phys_page_debug = mips_cpu_get_phys_page_debug;
@@ -208,6 +206,7 @@ static void mips_cpu_class_init(ObjectClass *c, void *data)
     cc->disas_set_info = mips_cpu_disas_set_info;
 #ifdef CONFIG_TCG
     cc->tcg_initialize = mips_tcg_init;
+    cc->tlb_fill = mips_cpu_tlb_fill;
 #endif
 
     cc->gdb_num_core_regs = 73;
diff --git a/target/mips/helper.c b/target/mips/helper.c
index c44cdca3b5..9799f2ede1 100644
--- a/target/mips/helper.c
+++ b/target/mips/helper.c
@@ -874,31 +874,25 @@ refill:
 #endif
 #endif
 
-int mips_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                              int mmu_idx)
+bool mips_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     MIPSCPU *cpu = MIPS_CPU(cs);
     CPUMIPSState *env = &cpu->env;
 #if !defined(CONFIG_USER_ONLY)
     hwaddr physical;
     int prot;
-    int access_type;
+    int mips_access_type;
 #endif
-    int ret = 0;
-
-#if 0
-    log_cpu_state(cs, 0);
-#endif
-    qemu_log_mask(CPU_LOG_MMU,
-              "%s pc " TARGET_FMT_lx " ad %" VADDR_PRIx " rw %d mmu_idx %d\n",
-              __func__, env->active_tc.PC, address, rw, mmu_idx);
+    int ret = TLBRET_BADADDR;
 
     /* data access */
 #if !defined(CONFIG_USER_ONLY)
     /* XXX: put correct access by using cpu_restore_state() correctly */
-    access_type = ACCESS_INT;
-    ret = get_physical_address(env, &physical, &prot,
-                               address, rw, access_type, mmu_idx);
+    mips_access_type = ACCESS_INT;
+    ret = get_physical_address(env, &physical, &prot, address,
+                               access_type, mips_access_type, mmu_idx);
     switch (ret) {
     case TLBRET_MATCH:
         qemu_log_mask(CPU_LOG_MMU,
@@ -915,44 +909,41 @@ int mips_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
         tlb_set_page(cs, address & TARGET_PAGE_MASK,
                      physical & TARGET_PAGE_MASK, prot | PAGE_EXEC,
                      mmu_idx, TARGET_PAGE_SIZE);
-        ret = 0;
-    } else if (ret < 0)
-#endif
-    {
-#if !defined(CONFIG_USER_ONLY)
+        return true;
+    }
 #if !defined(TARGET_MIPS64)
-        if ((ret == TLBRET_NOMATCH) && (env->tlb->nb_tlb > 1)) {
-            /*
-             * Memory reads during hardware page table walking are performed
-             * as if they were kernel-mode load instructions.
-             */
-            int mode = (env->hflags & MIPS_HFLAG_KSU);
-            bool ret_walker;
-            env->hflags &= ~MIPS_HFLAG_KSU;
-            ret_walker = page_table_walk_refill(env, address, rw, mmu_idx);
-            env->hflags |= mode;
-            if (ret_walker) {
-                ret = get_physical_address(env, &physical, &prot,
-                                           address, rw, access_type, mmu_idx);
-                if (ret == TLBRET_MATCH) {
-                    tlb_set_page(cs, address & TARGET_PAGE_MASK,
-                            physical & TARGET_PAGE_MASK, prot | PAGE_EXEC,
-                            mmu_idx, TARGET_PAGE_SIZE);
-                    ret = 0;
-                    return ret;
-                }
+    if ((ret == TLBRET_NOMATCH) && (env->tlb->nb_tlb > 1)) {
+        /*
+         * Memory reads during hardware page table walking are performed
+         * as if they were kernel-mode load instructions.
+         */
+        int mode = (env->hflags & MIPS_HFLAG_KSU);
+        bool ret_walker;
+        env->hflags &= ~MIPS_HFLAG_KSU;
+        ret_walker = page_table_walk_refill(env, address, access_type, mmu_idx);
+        env->hflags |= mode;
+        if (ret_walker) {
+            ret = get_physical_address(env, &physical, &prot, address,
+                                       access_type, mips_access_type, mmu_idx);
+            if (ret == TLBRET_MATCH) {
+                tlb_set_page(cs, address & TARGET_PAGE_MASK,
+                             physical & TARGET_PAGE_MASK, prot | PAGE_EXEC,
+                             mmu_idx, TARGET_PAGE_SIZE);
+                return true;
             }
         }
+    }
 #endif
-#endif
-        raise_mmu_exception(env, address, rw, ret);
-        ret = 1;
+    if (probe) {
+        return false;
     }
+#endif
 
-    return ret;
+    raise_mmu_exception(env, address, access_type, ret);
+    do_raise_exception_err(env, cs->exception_index, env->error_code, retaddr);
 }
 
-#if !defined(CONFIG_USER_ONLY)
+#ifndef CONFIG_USER_ONLY
 hwaddr cpu_mips_translate_address(CPUMIPSState *env, target_ulong address, int rw)
 {
     hwaddr physical;
diff --git a/target/mips/internal.h b/target/mips/internal.h
index 286e3888ab..b2b41a51ab 100644
--- a/target/mips/internal.h
+++ b/target/mips/internal.h
@@ -202,8 +202,9 @@ void cpu_mips_start_count(CPUMIPSState *env);
 void cpu_mips_stop_count(CPUMIPSState *env);
 
 /* helper.c */
-int mips_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                              int mmu_idx);
+bool mips_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
 
 /* op_helper.c */
 uint32_t float_class_s(uint32_t arg, float_status *fst);
diff --git a/target/mips/op_helper.c b/target/mips/op_helper.c
index 0f272a5b93..6d86912958 100644
--- a/target/mips/op_helper.c
+++ b/target/mips/op_helper.c
@@ -2669,21 +2669,6 @@ void mips_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
     do_raise_exception_err(env, excp, error_code, retaddr);
 }
 
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = mips_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (ret) {
-        MIPSCPU *cpu = MIPS_CPU(cs);
-        CPUMIPSState *env = &cpu->env;
-
-        do_raise_exception_err(env, cs->exception_index,
-                               env->error_code, retaddr);
-    }
-}
-
 void mips_cpu_unassigned_access(CPUState *cs, hwaddr addr,
                                 bool is_write, bool is_exec, int unused,
                                 unsigned size)
diff --git a/target/moxie/cpu.c b/target/moxie/cpu.c
index 46434e65ba..02b2b47574 100644
--- a/target/moxie/cpu.c
+++ b/target/moxie/cpu.c
@@ -112,9 +112,8 @@ static void moxie_cpu_class_init(ObjectClass *oc, void *data)
     cc->do_interrupt = moxie_cpu_do_interrupt;
     cc->dump_state = moxie_cpu_dump_state;
     cc->set_pc = moxie_cpu_set_pc;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = moxie_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = moxie_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = moxie_cpu_get_phys_page_debug;
     cc->vmsd = &vmstate_moxie_cpu;
 #endif
diff --git a/target/moxie/cpu.h b/target/moxie/cpu.h
index f3b6d83ae7..a63a96bc05 100644
--- a/target/moxie/cpu.h
+++ b/target/moxie/cpu.h
@@ -139,7 +139,8 @@ static inline void cpu_get_tb_cpu_state(CPUMoxieState *env, target_ulong *pc,
     *flags = 0;
 }
 
-int moxie_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size,
-                               int rw, int mmu_idx);
+bool moxie_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr);
 
 #endif /* MOXIE_CPU_H */
diff --git a/target/moxie/helper.c b/target/moxie/helper.c
index 287a45232c..f5c1d4181c 100644
--- a/target/moxie/helper.c
+++ b/target/moxie/helper.c
@@ -26,20 +26,6 @@
 #include "qemu/host-utils.h"
 #include "exec/helper-proto.h"
 
-/* Try to fill the TLB and return an exception if error. If retaddr is
-   NULL, it means that the function was called in C code (i.e. not
-   from generated code or from helper.c) */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = moxie_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-
 void helper_raise_exception(CPUMoxieState *env, int ex)
 {
     CPUState *cs = CPU(moxie_env_get_cpu(env));
@@ -85,53 +71,29 @@ void helper_debug(CPUMoxieState *env)
     cpu_loop_exit(cs);
 }
 
-#if defined(CONFIG_USER_ONLY)
-
-void moxie_cpu_do_interrupt(CPUState *cs)
-{
-    CPUState *cs = CPU(moxie_env_get_cpu(env));
-
-    cs->exception_index = -1;
-}
-
-int moxie_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                               int rw, int mmu_idx)
-{
-    MoxieCPU *cpu = MOXIE_CPU(cs);
-
-    cs->exception_index = 0xaa;
-    cpu->env.debug1 = address;
-    cpu_dump_state(cs, stderr, 0);
-    return 1;
-}
-
-#else /* !CONFIG_USER_ONLY */
-
-int moxie_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                               int rw, int mmu_idx)
+bool moxie_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     MoxieCPU *cpu = MOXIE_CPU(cs);
     CPUMoxieState *env = &cpu->env;
     MoxieMMUResult res;
     int prot, miss;
-    target_ulong phy;
-    int r = 1;
 
     address &= TARGET_PAGE_MASK;
     prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
-    miss = moxie_mmu_translate(&res, env, address, rw, mmu_idx);
-    if (miss) {
-        /* handle the miss.  */
-        phy = 0;
-        cs->exception_index = MOXIE_EX_MMU_MISS;
-    } else {
-        phy = res.phy;
-        r = 0;
+    miss = moxie_mmu_translate(&res, env, address, access_type, mmu_idx);
+    if (likely(!miss)) {
+        tlb_set_page(cs, address, res.phy, prot, mmu_idx, TARGET_PAGE_SIZE);
+        return true;
+    }
+    if (probe) {
+        return false;
     }
-    tlb_set_page(cs, address, phy, prot, mmu_idx, TARGET_PAGE_SIZE);
-    return r;
-}
 
+    cs->exception_index = MOXIE_EX_MMU_MISS;
+    cpu_loop_exit_restore(cs, retaddr);
+}
 
 void moxie_cpu_do_interrupt(CPUState *cs)
 {
@@ -156,4 +118,3 @@ hwaddr moxie_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
     }
     return phy;
 }
-#endif
diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c
index fbfaa2ce26..186af4913d 100644
--- a/target/nios2/cpu.c
+++ b/target/nios2/cpu.c
@@ -200,9 +200,8 @@ static void nios2_cpu_class_init(ObjectClass *oc, void *data)
     cc->dump_state = nios2_cpu_dump_state;
     cc->set_pc = nios2_cpu_set_pc;
     cc->disas_set_info = nios2_cpu_disas_set_info;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = nios2_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = nios2_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->do_unaligned_access = nios2_cpu_do_unaligned_access;
     cc->get_phys_page_debug = nios2_cpu_get_phys_page_debug;
 #endif
diff --git a/target/nios2/cpu.h b/target/nios2/cpu.h
index adc90722c6..35d3886dc2 100644
--- a/target/nios2/cpu.h
+++ b/target/nios2/cpu.h
@@ -253,8 +253,9 @@ static inline int cpu_mmu_index(CPUNios2State *env, bool ifetch)
                                                   MMU_SUPERVISOR_IDX;
 }
 
-int nios2_cpu_handle_mmu_fault(CPUState *env, vaddr address, int size,
-                               int rw, int mmu_idx);
+bool nios2_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr);
 
 static inline int cpu_interrupts_enabled(CPUNios2State *env)
 {
diff --git a/target/nios2/helper.c b/target/nios2/helper.c
index e01fc1ff3e..ffb83fc104 100644
--- a/target/nios2/helper.c
+++ b/target/nios2/helper.c
@@ -38,15 +38,12 @@ void nios2_cpu_do_interrupt(CPUState *cs)
     env->regs[R_EA] = env->regs[R_PC] + 4;
 }
 
-int nios2_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                               int rw, int mmu_idx)
+bool nios2_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     cs->exception_index = 0xaa;
-    /* Page 0x1000 is kuser helper */
-    if (address < 0x1000 || address >= 0x2000) {
-        cpu_dump_state(cs, stderr, 0);
-    }
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #else /* !CONFIG_USER_ONLY */
@@ -203,89 +200,6 @@ void nios2_cpu_do_interrupt(CPUState *cs)
     }
 }
 
-static int cpu_nios2_handle_virtual_page(
-    CPUState *cs, target_ulong address, int rw, int mmu_idx)
-{
-    Nios2CPU *cpu = NIOS2_CPU(cs);
-    CPUNios2State *env = &cpu->env;
-    target_ulong vaddr, paddr;
-    Nios2MMULookup lu;
-    unsigned int hit;
-    hit = mmu_translate(env, &lu, address, rw, mmu_idx);
-    if (hit) {
-        vaddr = address & TARGET_PAGE_MASK;
-        paddr = lu.paddr + vaddr - lu.vaddr;
-
-        if (((rw == 0) && (lu.prot & PAGE_READ)) ||
-            ((rw == 1) && (lu.prot & PAGE_WRITE)) ||
-            ((rw == 2) && (lu.prot & PAGE_EXEC))) {
-
-            tlb_set_page(cs, vaddr, paddr, lu.prot,
-                         mmu_idx, TARGET_PAGE_SIZE);
-            return 0;
-        } else {
-            /* Permission violation */
-            cs->exception_index = (rw == 0) ? EXCP_TLBR :
-                                               ((rw == 1) ? EXCP_TLBW :
-                                                            EXCP_TLBX);
-        }
-    } else {
-        cs->exception_index = EXCP_TLBD;
-    }
-
-    if (rw == 2) {
-        env->regs[CR_TLBMISC] &= ~CR_TLBMISC_D;
-    } else {
-        env->regs[CR_TLBMISC] |= CR_TLBMISC_D;
-    }
-    env->regs[CR_PTEADDR] &= CR_PTEADDR_PTBASE_MASK;
-    env->regs[CR_PTEADDR] |= (address >> 10) & CR_PTEADDR_VPN_MASK;
-    env->mmu.pteaddr_wr = env->regs[CR_PTEADDR];
-    env->regs[CR_BADADDR] = address;
-    return 1;
-}
-
-int nios2_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                               int rw, int mmu_idx)
-{
-    Nios2CPU *cpu = NIOS2_CPU(cs);
-    CPUNios2State *env = &cpu->env;
-
-    if (cpu->mmu_present) {
-        if (MMU_SUPERVISOR_IDX == mmu_idx) {
-            if (address >= 0xC0000000) {
-                /* Kernel physical page - TLB bypassed */
-                address &= TARGET_PAGE_MASK;
-                tlb_set_page(cs, address, address, PAGE_BITS,
-                             mmu_idx, TARGET_PAGE_SIZE);
-            } else if (address >= 0x80000000) {
-                /* Kernel virtual page */
-                return cpu_nios2_handle_virtual_page(cs, address, rw, mmu_idx);
-            } else {
-                /* User virtual page */
-                return cpu_nios2_handle_virtual_page(cs, address, rw, mmu_idx);
-            }
-        } else {
-            if (address >= 0x80000000) {
-                /* Illegal access from user mode */
-                cs->exception_index = EXCP_SUPERA;
-                env->regs[CR_BADADDR] = address;
-                return 1;
-            } else {
-                /* User virtual page */
-                return cpu_nios2_handle_virtual_page(cs, address, rw, mmu_idx);
-            }
-        }
-    } else {
-        /* No MMU */
-        address &= TARGET_PAGE_MASK;
-        tlb_set_page(cs, address, address, PAGE_BITS,
-                     mmu_idx, TARGET_PAGE_SIZE);
-    }
-
-    return 0;
-}
-
 hwaddr nios2_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
 {
     Nios2CPU *cpu = NIOS2_CPU(cs);
@@ -321,4 +235,80 @@ void nios2_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
     env->regs[CR_EXCEPTION] = EXCP_UNALIGN << 2;
     helper_raise_exception(env, EXCP_UNALIGN);
 }
+
+bool nios2_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
+{
+    Nios2CPU *cpu = NIOS2_CPU(cs);
+    CPUNios2State *env = &cpu->env;
+    unsigned int excp = EXCP_TLBD;
+    target_ulong vaddr, paddr;
+    Nios2MMULookup lu;
+    unsigned int hit;
+
+    if (!cpu->mmu_present) {
+        /* No MMU */
+        address &= TARGET_PAGE_MASK;
+        tlb_set_page(cs, address, address, PAGE_BITS,
+                     mmu_idx, TARGET_PAGE_SIZE);
+        return true;
+    }
+
+    if (MMU_SUPERVISOR_IDX == mmu_idx) {
+        if (address >= 0xC0000000) {
+            /* Kernel physical page - TLB bypassed */
+            address &= TARGET_PAGE_MASK;
+            tlb_set_page(cs, address, address, PAGE_BITS,
+                         mmu_idx, TARGET_PAGE_SIZE);
+            return true;
+        }
+    } else {
+        if (address >= 0x80000000) {
+            /* Illegal access from user mode */
+            if (probe) {
+                return false;
+            }
+            cs->exception_index = EXCP_SUPERA;
+            env->regs[CR_BADADDR] = address;
+            cpu_loop_exit_restore(cs, retaddr);
+        }
+    }
+
+    /* Virtual page.  */
+    hit = mmu_translate(env, &lu, address, access_type, mmu_idx);
+    if (hit) {
+        vaddr = address & TARGET_PAGE_MASK;
+        paddr = lu.paddr + vaddr - lu.vaddr;
+
+        if (((access_type == MMU_DATA_LOAD) && (lu.prot & PAGE_READ)) ||
+            ((access_type == MMU_DATA_STORE) && (lu.prot & PAGE_WRITE)) ||
+            ((access_type == MMU_INST_FETCH) && (lu.prot & PAGE_EXEC))) {
+            tlb_set_page(cs, vaddr, paddr, lu.prot,
+                         mmu_idx, TARGET_PAGE_SIZE);
+            return true;
+        }
+
+        /* Permission violation */
+        excp = (access_type == MMU_DATA_LOAD ? EXCP_TLBR :
+                access_type == MMU_DATA_STORE ? EXCP_TLBW : EXCP_TLBX);
+    }
+
+    if (probe) {
+        return false;
+    }
+
+    if (access_type == MMU_INST_FETCH) {
+        env->regs[CR_TLBMISC] &= ~CR_TLBMISC_D;
+    } else {
+        env->regs[CR_TLBMISC] |= CR_TLBMISC_D;
+    }
+    env->regs[CR_PTEADDR] &= CR_PTEADDR_PTBASE_MASK;
+    env->regs[CR_PTEADDR] |= (address >> 10) & CR_PTEADDR_VPN_MASK;
+    env->mmu.pteaddr_wr = env->regs[CR_PTEADDR];
+
+    cs->exception_index = excp;
+    env->regs[CR_BADADDR] = address;
+    cpu_loop_exit_restore(cs, retaddr);
+}
 #endif /* !CONFIG_USER_ONLY */
diff --git a/target/nios2/mmu.c b/target/nios2/mmu.c
index 5acf442d8b..47fa474efb 100644
--- a/target/nios2/mmu.c
+++ b/target/nios2/mmu.c
@@ -36,18 +36,6 @@
 #define MMU_LOG(x)
 #endif
 
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = nios2_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        /* now we have a real cpu fault */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-
 void mmu_read_debug(CPUNios2State *env, uint32_t rn)
 {
     switch (rn) {
diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c
index d125236977..3816baee70 100644
--- a/target/openrisc/cpu.c
+++ b/target/openrisc/cpu.c
@@ -149,9 +149,8 @@ static void openrisc_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = openrisc_cpu_set_pc;
     cc->gdb_read_register = openrisc_cpu_gdb_read_register;
     cc->gdb_write_register = openrisc_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = openrisc_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = openrisc_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = openrisc_cpu_get_phys_page_debug;
     dc->vmsd = &vmstate_openrisc_cpu;
 #endif
diff --git a/target/openrisc/cpu.h b/target/openrisc/cpu.h
index 88a8c70092..9473d94d0c 100644
--- a/target/openrisc/cpu.h
+++ b/target/openrisc/cpu.h
@@ -344,8 +344,9 @@ hwaddr openrisc_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr);
 int openrisc_cpu_gdb_read_register(CPUState *cpu, uint8_t *buf, int reg);
 int openrisc_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
 void openrisc_translate_init(void);
-int openrisc_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size,
-                                  int rw, int mmu_idx);
+bool openrisc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                           MMUAccessType access_type, int mmu_idx,
+                           bool probe, uintptr_t retaddr);
 int cpu_openrisc_signal_handler(int host_signum, void *pinfo, void *puc);
 int print_insn_or1k(bfd_vma addr, disassemble_info *info);
 
diff --git a/target/openrisc/mmu.c b/target/openrisc/mmu.c
index 5dec68dcff..a73b12af03 100644
--- a/target/openrisc/mmu.c
+++ b/target/openrisc/mmu.c
@@ -107,16 +107,42 @@ static void raise_mmu_exception(OpenRISCCPU *cpu, target_ulong address,
     cpu->env.lock_addr = -1;
 }
 
-int openrisc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                                  int rw, int mmu_idx)
+bool openrisc_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
+                           MMUAccessType access_type, int mmu_idx,
+                           bool probe, uintptr_t retaddr)
 {
-#ifdef CONFIG_USER_ONLY
     OpenRISCCPU *cpu = OPENRISC_CPU(cs);
-    raise_mmu_exception(cpu, address, EXCP_DPF);
-    return 1;
-#else
-    g_assert_not_reached();
+    int excp = EXCP_DPF;
+
+#ifndef CONFIG_USER_ONLY
+    int prot;
+    hwaddr phys_addr;
+
+    if (mmu_idx == MMU_NOMMU_IDX) {
+        /* The mmu is disabled; lookups never fail.  */
+        get_phys_nommu(&phys_addr, &prot, addr);
+        excp = 0;
+    } else {
+        bool super = mmu_idx == MMU_SUPERVISOR_IDX;
+        int need = (access_type == MMU_INST_FETCH ? PAGE_EXEC
+                    : access_type == MMU_DATA_STORE ? PAGE_WRITE
+                    : PAGE_READ);
+        excp = get_phys_mmu(cpu, &phys_addr, &prot, addr, need, super);
+    }
+
+    if (likely(excp == 0)) {
+        tlb_set_page(cs, addr & TARGET_PAGE_MASK,
+                     phys_addr & TARGET_PAGE_MASK, prot,
+                     mmu_idx, TARGET_PAGE_SIZE);
+        return true;
+    }
+    if (probe) {
+        return false;
+    }
 #endif
+
+    raise_mmu_exception(cpu, addr, excp);
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #ifndef CONFIG_USER_ONLY
@@ -152,33 +178,4 @@ hwaddr openrisc_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
         return phys_addr;
     }
 }
-
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    OpenRISCCPU *cpu = OPENRISC_CPU(cs);
-    int prot, excp;
-    hwaddr phys_addr;
-
-    if (mmu_idx == MMU_NOMMU_IDX) {
-        /* The mmu is disabled; lookups never fail.  */
-        get_phys_nommu(&phys_addr, &prot, addr);
-        excp = 0;
-    } else {
-        bool super = mmu_idx == MMU_SUPERVISOR_IDX;
-        int need = (access_type == MMU_INST_FETCH ? PAGE_EXEC
-                    : access_type == MMU_DATA_STORE ? PAGE_WRITE
-                    : PAGE_READ);
-        excp = get_phys_mmu(cpu, &phys_addr, &prot, addr, need, super);
-    }
-
-    if (unlikely(excp)) {
-        raise_mmu_exception(cpu, addr, excp);
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-
-    tlb_set_page(cs, addr & TARGET_PAGE_MASK,
-                 phys_addr & TARGET_PAGE_MASK, prot,
-                 mmu_idx, TARGET_PAGE_SIZE);
-}
 #endif
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 5e7cf54b2f..d7f23ad5e0 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -1311,10 +1311,9 @@ void ppc_translate_init(void);
  * is returned if the signal was handled by the virtual CPU.
  */
 int cpu_ppc_signal_handler(int host_signum, void *pinfo, void *puc);
-#if defined(CONFIG_USER_ONLY)
-int ppc_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                             int mmu_idx);
-#endif
+bool ppc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr);
 
 #if !defined(CONFIG_USER_ONLY)
 void ppc_store_sdr1(CPUPPCState *env, target_ulong value);
diff --git a/target/ppc/mmu_helper.c b/target/ppc/mmu_helper.c
index 1dbc9acb75..e605efa883 100644
--- a/target/ppc/mmu_helper.c
+++ b/target/ppc/mmu_helper.c
@@ -3057,15 +3057,9 @@ void helper_check_tlb_flush_global(CPUPPCState *env)
 
 /*****************************************************************************/
 
-/*
- * try to fill the TLB and return an exception if error. If retaddr is
- * NULL, it means that the function was called in C code (i.e. not
- * from generated code or from helper.c)
- *
- * XXX: fix it to restore all registers
- */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
+bool ppc_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
     PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
@@ -3078,7 +3072,11 @@ void tlb_fill(CPUState *cs, target_ulong addr, int size,
         ret = cpu_ppc_handle_mmu_fault(env, addr, access_type, mmu_idx);
     }
     if (unlikely(ret != 0)) {
+        if (probe) {
+            return false;
+        }
         raise_exception_err_ra(env, cs->exception_index, env->error_code,
                                retaddr);
     }
+    return true;
 }
diff --git a/target/ppc/translate_init.inc.c b/target/ppc/translate_init.inc.c
index 0394a9ddad..ad5e14b16f 100644
--- a/target/ppc/translate_init.inc.c
+++ b/target/ppc/translate_init.inc.c
@@ -10592,9 +10592,7 @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_read_register = ppc_cpu_gdb_read_register;
     cc->gdb_write_register = ppc_cpu_gdb_write_register;
     cc->do_unaligned_access = ppc_cpu_do_unaligned_access;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = ppc_cpu_handle_mmu_fault;
-#else
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = ppc_cpu_get_phys_page_debug;
     cc->vmsd = &vmstate_ppc_cpu;
 #endif
@@ -10624,6 +10622,7 @@ static void ppc_cpu_class_init(ObjectClass *oc, void *data)
 #endif
 #ifdef CONFIG_TCG
     cc->tcg_initialize = ppc_translate_init;
+    cc->tlb_fill = ppc_cpu_tlb_fill;
 #endif
     cc->disas_set_info = ppc_disas_set_info;
 
diff --git a/target/ppc/user_only_helper.c b/target/ppc/user_only_helper.c
index 2f1477f102..683c03390d 100644
--- a/target/ppc/user_only_helper.c
+++ b/target/ppc/user_only_helper.c
@@ -20,21 +20,24 @@
 
 #include "qemu/osdep.h"
 #include "cpu.h"
+#include "exec/exec-all.h"
 
-int ppc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                             int mmu_idx)
+
+bool ppc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                      MMUAccessType access_type, int mmu_idx,
+                      bool probe, uintptr_t retaddr)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
     CPUPPCState *env = &cpu->env;
     int exception, error_code;
 
-    if (rw == 2) {
+    if (access_type == MMU_INST_FETCH) {
         exception = POWERPC_EXCP_ISI;
         error_code = 0x40000000;
     } else {
         exception = POWERPC_EXCP_DSI;
         error_code = 0x40000000;
-        if (rw) {
+        if (access_type == MMU_DATA_STORE) {
             error_code |= 0x02000000;
         }
         env->spr[SPR_DAR] = address;
@@ -42,6 +45,5 @@ int ppc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
     }
     cs->exception_index = exception;
     env->error_code = error_code;
-
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index 1bcf4eaeb8..b7675707e0 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -355,14 +355,13 @@ static void riscv_cpu_class_init(ObjectClass *c, void *data)
 #endif
     cc->gdb_stop_before_watchpoint = true;
     cc->disas_set_info = riscv_cpu_disas_set_info;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = riscv_cpu_handle_mmu_fault;
-#else
+#ifndef CONFIG_USER_ONLY
     cc->do_unaligned_access = riscv_cpu_do_unaligned_access;
     cc->get_phys_page_debug = riscv_cpu_get_phys_page_debug;
 #endif
 #ifdef CONFIG_TCG
     cc->tcg_initialize = riscv_translate_init;
+    cc->tlb_fill = riscv_cpu_tlb_fill;
 #endif
     /* For now, mark unmigratable: */
     cc->vmsd = &vmstate_riscv_cpu;
diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 7d9f48973f..c17184f4e4 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -261,8 +261,9 @@ hwaddr riscv_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr);
 void  riscv_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
                                     MMUAccessType access_type, int mmu_idx,
                                     uintptr_t retaddr);
-int riscv_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size,
-                              int rw, int mmu_idx);
+bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr);
 char *riscv_isa_string(RISCVCPU *cpu);
 void riscv_cpu_list(void);
 
diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index b17f169681..41d6db41c3 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -378,54 +378,44 @@ void riscv_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
     env->badaddr = addr;
     riscv_raise_exception(env, cs->exception_index, retaddr);
 }
-
-/* called by qemu's softmmu to fill the qemu tlb */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-        MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-    ret = riscv_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (ret == TRANSLATE_FAIL) {
-        RISCVCPU *cpu = RISCV_CPU(cs);
-        CPURISCVState *env = &cpu->env;
-        riscv_raise_exception(env, cs->exception_index, retaddr);
-    }
-}
-
 #endif
 
-int riscv_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-        int rw, int mmu_idx)
+bool riscv_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
+#ifndef CONFIG_USER_ONLY
     RISCVCPU *cpu = RISCV_CPU(cs);
     CPURISCVState *env = &cpu->env;
-#if !defined(CONFIG_USER_ONLY)
     hwaddr pa = 0;
     int prot;
-#endif
     int ret = TRANSLATE_FAIL;
 
-    qemu_log_mask(CPU_LOG_MMU,
-            "%s pc " TARGET_FMT_lx " ad %" VADDR_PRIx " rw %d mmu_idx \
-             %d\n", __func__, env->pc, address, rw, mmu_idx);
+    qemu_log_mask(CPU_LOG_MMU, "%s ad %" VADDR_PRIx " rw %d mmu_idx %d\n",
+                  __func__, address, access_type, mmu_idx);
+
+    ret = get_physical_address(env, &pa, &prot, address, access_type, mmu_idx);
 
-#if !defined(CONFIG_USER_ONLY)
-    ret = get_physical_address(env, &pa, &prot, address, rw, mmu_idx);
     qemu_log_mask(CPU_LOG_MMU,
-            "%s address=%" VADDR_PRIx " ret %d physical " TARGET_FMT_plx
-             " prot %d\n", __func__, address, ret, pa, prot);
+                  "%s address=%" VADDR_PRIx " ret %d physical " TARGET_FMT_plx
+                  " prot %d\n", __func__, address, ret, pa, prot);
+
     if (riscv_feature(env, RISCV_FEATURE_PMP) &&
-        !pmp_hart_has_privs(env, pa, TARGET_PAGE_SIZE, 1 << rw)) {
+        !pmp_hart_has_privs(env, pa, TARGET_PAGE_SIZE, 1 << access_type)) {
         ret = TRANSLATE_FAIL;
     }
     if (ret == TRANSLATE_SUCCESS) {
         tlb_set_page(cs, address & TARGET_PAGE_MASK, pa & TARGET_PAGE_MASK,
                      prot, mmu_idx, TARGET_PAGE_SIZE);
-    } else if (ret == TRANSLATE_FAIL) {
-        raise_mmu_exception(env, address, rw);
+        return true;
+    } else if (probe) {
+        return false;
+    } else {
+        raise_mmu_exception(env, address, access_type);
+        riscv_raise_exception(env, cs->exception_index, retaddr);
     }
 #else
-    switch (rw) {
+    switch (access_type) {
     case MMU_INST_FETCH:
         cs->exception_index = RISCV_EXCP_INST_PAGE_FAULT;
         break;
@@ -436,8 +426,8 @@ int riscv_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
         cs->exception_index = RISCV_EXCP_STORE_PAGE_FAULT;
         break;
     }
+    cpu_loop_exit_restore(cs, retaddr);
 #endif
-    return ret;
 }
 
 /*
diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c
index b58ef0a8ef..b1df63d82c 100644
--- a/target/s390x/cpu.c
+++ b/target/s390x/cpu.c
@@ -478,9 +478,7 @@ static void s390_cpu_class_init(ObjectClass *oc, void *data)
     cc->set_pc = s390_cpu_set_pc;
     cc->gdb_read_register = s390_cpu_gdb_read_register;
     cc->gdb_write_register = s390_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = s390_cpu_handle_mmu_fault;
-#else
+#ifndef CONFIG_USER_ONLY
     cc->get_phys_page_debug = s390_cpu_get_phys_page_debug;
     cc->vmsd = &vmstate_s390_cpu;
     cc->write_elf64_note = s390_cpu_write_elf64_note;
@@ -493,6 +491,7 @@ static void s390_cpu_class_init(ObjectClass *oc, void *data)
     cc->disas_set_info = s390_cpu_disas_set_info;
 #ifdef CONFIG_TCG
     cc->tcg_initialize = s390x_translate_init;
+    cc->tlb_fill = s390_cpu_tlb_fill;
 #endif
 
     cc->gdb_num_core_regs = S390_NUM_CORE_REGS;
diff --git a/target/s390x/excp_helper.c b/target/s390x/excp_helper.c
index f84bfb1284..3a467b72c5 100644
--- a/target/s390x/excp_helper.c
+++ b/target/s390x/excp_helper.c
@@ -74,8 +74,9 @@ void s390_cpu_do_interrupt(CPUState *cs)
     cs->exception_index = -1;
 }
 
-int s390_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                              int rw, int mmu_idx)
+bool s390_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     S390CPU *cpu = S390_CPU(cs);
 
@@ -83,7 +84,7 @@ int s390_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
     /* On real machines this value is dropped into LowMem.  Since this
        is userland, simply put this someplace that cpu_loop can find it.  */
     cpu->env.__excp_addr = address;
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #else /* !CONFIG_USER_ONLY */
@@ -102,19 +103,20 @@ static inline uint64_t cpu_mmu_idx_to_asc(int mmu_idx)
     }
 }
 
-int s390_cpu_handle_mmu_fault(CPUState *cs, vaddr orig_vaddr, int size,
-                              int rw, int mmu_idx)
+bool s390_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     S390CPU *cpu = S390_CPU(cs);
     CPUS390XState *env = &cpu->env;
     target_ulong vaddr, raddr;
     uint64_t asc;
-    int prot;
+    int prot, fail;
 
     qemu_log_mask(CPU_LOG_MMU, "%s: addr 0x%" VADDR_PRIx " rw %d mmu_idx %d\n",
-                  __func__, orig_vaddr, rw, mmu_idx);
+                  __func__, address, access_type, mmu_idx);
 
-    vaddr = orig_vaddr;
+    vaddr = address;
 
     if (mmu_idx < MMU_REAL_IDX) {
         asc = cpu_mmu_idx_to_asc(mmu_idx);
@@ -122,39 +124,58 @@ int s390_cpu_handle_mmu_fault(CPUState *cs, vaddr orig_vaddr, int size,
         if (!(env->psw.mask & PSW_MASK_64)) {
             vaddr &= 0x7fffffff;
         }
-        if (mmu_translate(env, vaddr, rw, asc, &raddr, &prot, true)) {
-            return 1;
-        }
+        fail = mmu_translate(env, vaddr, access_type, asc, &raddr, &prot, true);
     } else if (mmu_idx == MMU_REAL_IDX) {
         /* 31-Bit mode */
         if (!(env->psw.mask & PSW_MASK_64)) {
             vaddr &= 0x7fffffff;
         }
-        if (mmu_translate_real(env, vaddr, rw, &raddr, &prot)) {
-            return 1;
-        }
+        fail = mmu_translate_real(env, vaddr, access_type, &raddr, &prot);
     } else {
-        abort();
+        g_assert_not_reached();
     }
 
     /* check out of RAM access */
-    if (!address_space_access_valid(&address_space_memory, raddr,
-                                    TARGET_PAGE_SIZE, rw,
+    if (!fail &&
+        !address_space_access_valid(&address_space_memory, raddr,
+                                    TARGET_PAGE_SIZE, access_type,
                                     MEMTXATTRS_UNSPECIFIED)) {
         qemu_log_mask(CPU_LOG_MMU,
                       "%s: raddr %" PRIx64 " > ram_size %" PRIx64 "\n",
                       __func__, (uint64_t)raddr, (uint64_t)ram_size);
         trigger_pgm_exception(env, PGM_ADDRESSING, ILEN_AUTO);
-        return 1;
+        fail = 1;
     }
 
-    qemu_log_mask(CPU_LOG_MMU, "%s: set tlb %" PRIx64 " -> %" PRIx64 " (%x)\n",
-            __func__, (uint64_t)vaddr, (uint64_t)raddr, prot);
+    if (!fail) {
+        qemu_log_mask(CPU_LOG_MMU,
+                      "%s: set tlb %" PRIx64 " -> %" PRIx64 " (%x)\n",
+                      __func__, (uint64_t)vaddr, (uint64_t)raddr, prot);
+        tlb_set_page(cs, address & TARGET_PAGE_MASK, raddr, prot,
+                     mmu_idx, TARGET_PAGE_SIZE);
+        return true;
+    }
+    if (probe) {
+        return false;
+    }
 
-    tlb_set_page(cs, orig_vaddr & TARGET_PAGE_MASK, raddr, prot,
-                 mmu_idx, TARGET_PAGE_SIZE);
+    cpu_restore_state(cs, retaddr, true);
+
+    /*
+     * The ILC value for code accesses is undefined.  The important
+     * thing here is to *not* leave env->int_pgm_ilen set to ILEN_AUTO,
+     * which would cause do_program_interrupt to attempt to read from
+     * env->psw.addr again.  C.f. the condition in trigger_page_fault,
+     * but is not universally applied.
+     *
+     * ??? If we remove ILEN_AUTO, by moving the computation of ILEN
+     * into cpu_restore_state, then we may remove this entirely.
+     */
+    if (access_type == MMU_INST_FETCH) {
+        env->int_pgm_ilen = 2;
+    }
 
-    return 0;
+    cpu_loop_exit(cs);
 }
 
 static void do_program_interrupt(CPUS390XState *env)
diff --git a/target/s390x/internal.h b/target/s390x/internal.h
index 26575f2130..56534b38e0 100644
--- a/target/s390x/internal.h
+++ b/target/s390x/internal.h
@@ -263,8 +263,9 @@ ObjectClass *s390_cpu_class_by_name(const char *name);
 void s390x_cpu_debug_excp_handler(CPUState *cs);
 void s390_cpu_do_interrupt(CPUState *cpu);
 bool s390_cpu_exec_interrupt(CPUState *cpu, int int_req);
-int s390_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                              int mmu_idx);
+bool s390_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
 void s390x_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
                                    MMUAccessType access_type,
                                    int mmu_idx, uintptr_t retaddr);
diff --git a/target/s390x/mem_helper.c b/target/s390x/mem_helper.c
index 3f76a8abfd..ffd5f02fbe 100644
--- a/target/s390x/mem_helper.c
+++ b/target/s390x/mem_helper.c
@@ -33,22 +33,6 @@
 
 /*****************************************************************************/
 /* Softmmu support */
-#if !defined(CONFIG_USER_ONLY)
-
-/* try to fill the TLB and return an exception if error. If retaddr is
-   NULL, it means that the function was called in C code (i.e. not
-   from generated code or from helper.c) */
-/* XXX: fix it to restore all registers */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret = s390_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret != 0)) {
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-
-#endif
 
 /* #define DEBUG_HELPER */
 #ifdef DEBUG_HELPER
diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c
index da2799082e..c4736a0a73 100644
--- a/target/sh4/cpu.c
+++ b/target/sh4/cpu.c
@@ -229,9 +229,8 @@ static void superh_cpu_class_init(ObjectClass *oc, void *data)
     cc->synchronize_from_tb = superh_cpu_synchronize_from_tb;
     cc->gdb_read_register = superh_cpu_gdb_read_register;
     cc->gdb_write_register = superh_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = superh_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = superh_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->do_unaligned_access = superh_cpu_do_unaligned_access;
     cc->get_phys_page_debug = superh_cpu_get_phys_page_debug;
 #endif
diff --git a/target/sh4/cpu.h b/target/sh4/cpu.h
index 1be36fe875..547194aac7 100644
--- a/target/sh4/cpu.h
+++ b/target/sh4/cpu.h
@@ -243,8 +243,9 @@ void superh_cpu_do_unaligned_access(CPUState *cpu, vaddr addr,
 void sh4_translate_init(void);
 int cpu_sh4_signal_handler(int host_signum, void *pinfo,
                            void *puc);
-int superh_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                                int mmu_idx);
+bool superh_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                         MMUAccessType access_type, int mmu_idx,
+                         bool probe, uintptr_t retaddr);
 
 void sh4_cpu_list(void);
 #if !defined(CONFIG_USER_ONLY)
diff --git a/target/sh4/helper.c b/target/sh4/helper.c
index fa51269fb1..fda195e7cb 100644
--- a/target/sh4/helper.c
+++ b/target/sh4/helper.c
@@ -27,43 +27,6 @@
 #include "hw/sh4/sh_intc.h"
 #endif
 
-#if defined(CONFIG_USER_ONLY)
-
-void superh_cpu_do_interrupt(CPUState *cs)
-{
-    cs->exception_index = -1;
-}
-
-int superh_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                                int mmu_idx)
-{
-    SuperHCPU *cpu = SUPERH_CPU(cs);
-    CPUSH4State *env = &cpu->env;
-
-    env->tea = address;
-    cs->exception_index = -1;
-    switch (rw) {
-    case 0:
-        cs->exception_index = 0x0a0;
-        break;
-    case 1:
-        cs->exception_index = 0x0c0;
-        break;
-    case 2:
-        cs->exception_index = 0x0a0;
-        break;
-    }
-    return 1;
-}
-
-int cpu_sh4_is_cached(CPUSH4State * env, target_ulong addr)
-{
-    /* For user mode, only U0 area is cacheable. */
-    return !(addr & 0x80000000);
-}
-
-#else /* !CONFIG_USER_ONLY */
-
 #define MMU_OK                   0
 #define MMU_ITLB_MISS            (-1)
 #define MMU_ITLB_MULTIPLE        (-2)
@@ -79,6 +42,21 @@ int cpu_sh4_is_cached(CPUSH4State * env, target_ulong addr)
 #define MMU_DADDR_ERROR_READ     (-12)
 #define MMU_DADDR_ERROR_WRITE    (-13)
 
+#if defined(CONFIG_USER_ONLY)
+
+void superh_cpu_do_interrupt(CPUState *cs)
+{
+    cs->exception_index = -1;
+}
+
+int cpu_sh4_is_cached(CPUSH4State *env, target_ulong addr)
+{
+    /* For user mode, only U0 area is cacheable. */
+    return !(addr & 0x80000000);
+}
+
+#else /* !CONFIG_USER_ONLY */
+
 void superh_cpu_do_interrupt(CPUState *cs)
 {
     SuperHCPU *cpu = SUPERH_CPU(cs);
@@ -458,69 +436,6 @@ static int get_physical_address(CPUSH4State * env, target_ulong * physical,
     return get_mmu_address(env, physical, prot, address, rw, access_type);
 }
 
-int superh_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                                int mmu_idx)
-{
-    SuperHCPU *cpu = SUPERH_CPU(cs);
-    CPUSH4State *env = &cpu->env;
-    target_ulong physical;
-    int prot, ret, access_type;
-
-    access_type = ACCESS_INT;
-    ret =
-	get_physical_address(env, &physical, &prot, address, rw,
-			     access_type);
-
-    if (ret != MMU_OK) {
-	env->tea = address;
-	if (ret != MMU_DTLB_MULTIPLE && ret != MMU_ITLB_MULTIPLE) {
-	    env->pteh = (env->pteh & PTEH_ASID_MASK) |
-		    (address & PTEH_VPN_MASK);
-	}
-	switch (ret) {
-	case MMU_ITLB_MISS:
-	case MMU_DTLB_MISS_READ:
-            cs->exception_index = 0x040;
-	    break;
-	case MMU_DTLB_MULTIPLE:
-	case MMU_ITLB_MULTIPLE:
-            cs->exception_index = 0x140;
-	    break;
-	case MMU_ITLB_VIOLATION:
-            cs->exception_index = 0x0a0;
-	    break;
-	case MMU_DTLB_MISS_WRITE:
-            cs->exception_index = 0x060;
-	    break;
-	case MMU_DTLB_INITIAL_WRITE:
-            cs->exception_index = 0x080;
-	    break;
-	case MMU_DTLB_VIOLATION_READ:
-            cs->exception_index = 0x0a0;
-	    break;
-	case MMU_DTLB_VIOLATION_WRITE:
-            cs->exception_index = 0x0c0;
-	    break;
-	case MMU_IADDR_ERROR:
-	case MMU_DADDR_ERROR_READ:
-            cs->exception_index = 0x0e0;
-	    break;
-	case MMU_DADDR_ERROR_WRITE:
-            cs->exception_index = 0x100;
-	    break;
-	default:
-            cpu_abort(cs, "Unhandled MMU fault");
-	}
-	return 1;
-    }
-
-    address &= TARGET_PAGE_MASK;
-    physical &= TARGET_PAGE_MASK;
-
-    tlb_set_page(cs, address, physical, prot, mmu_idx, TARGET_PAGE_SIZE);
-    return 0;
-}
-
 hwaddr superh_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
 {
     SuperHCPU *cpu = SUPERH_CPU(cs);
@@ -745,7 +660,6 @@ void cpu_sh4_write_mmaped_utlb_addr(CPUSH4State *s, hwaddr addr,
         if (needs_tlb_flush) {
             tlb_flush_page(CPU(sh_env_get_cpu(s)), vpn << 10);
         }
-        
     } else {
         int index = (addr & 0x00003f00) >> 8;
         tlb_t * entry = &s->utlb[index];
@@ -885,3 +799,76 @@ bool superh_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
     }
     return false;
 }
+
+bool superh_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                         MMUAccessType access_type, int mmu_idx,
+                         bool probe, uintptr_t retaddr)
+{
+    SuperHCPU *cpu = SUPERH_CPU(cs);
+    CPUSH4State *env = &cpu->env;
+    int ret;
+
+#ifdef CONFIG_USER_ONLY
+    ret = (access_type == MMU_DATA_STORE ? MMU_DTLB_VIOLATION_WRITE :
+           access_type == MMU_INST_FETCH ? MMU_ITLB_VIOLATION :
+           MMU_DTLB_VIOLATION_READ);
+#else
+    target_ulong physical;
+    int prot, sh_access_type;
+
+    sh_access_type = ACCESS_INT;
+    ret = get_physical_address(env, &physical, &prot, address,
+                               access_type, sh_access_type);
+
+    if (ret == MMU_OK) {
+        address &= TARGET_PAGE_MASK;
+        physical &= TARGET_PAGE_MASK;
+        tlb_set_page(cs, address, physical, prot, mmu_idx, TARGET_PAGE_SIZE);
+        return true;
+    }
+    if (probe) {
+        return false;
+    }
+
+    if (ret != MMU_DTLB_MULTIPLE && ret != MMU_ITLB_MULTIPLE) {
+        env->pteh = (env->pteh & PTEH_ASID_MASK) | (address & PTEH_VPN_MASK);
+    }
+#endif
+
+    env->tea = address;
+    switch (ret) {
+    case MMU_ITLB_MISS:
+    case MMU_DTLB_MISS_READ:
+        cs->exception_index = 0x040;
+        break;
+    case MMU_DTLB_MULTIPLE:
+    case MMU_ITLB_MULTIPLE:
+        cs->exception_index = 0x140;
+        break;
+    case MMU_ITLB_VIOLATION:
+        cs->exception_index = 0x0a0;
+        break;
+    case MMU_DTLB_MISS_WRITE:
+        cs->exception_index = 0x060;
+        break;
+    case MMU_DTLB_INITIAL_WRITE:
+        cs->exception_index = 0x080;
+        break;
+    case MMU_DTLB_VIOLATION_READ:
+        cs->exception_index = 0x0a0;
+        break;
+    case MMU_DTLB_VIOLATION_WRITE:
+        cs->exception_index = 0x0c0;
+        break;
+    case MMU_IADDR_ERROR:
+    case MMU_DADDR_ERROR_READ:
+        cs->exception_index = 0x0e0;
+        break;
+    case MMU_DADDR_ERROR_WRITE:
+        cs->exception_index = 0x100;
+        break;
+    default:
+        cpu_abort(cs, "Unhandled MMU fault");
+    }
+    cpu_loop_exit_restore(cs, retaddr);
+}
diff --git a/target/sh4/op_helper.c b/target/sh4/op_helper.c
index 28027f9e0b..bd5d782b50 100644
--- a/target/sh4/op_helper.c
+++ b/target/sh4/op_helper.c
@@ -41,18 +41,6 @@ void superh_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
     cpu_loop_exit_restore(cs, retaddr);
 }
 
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = superh_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (ret) {
-        /* now we have a real cpu fault */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-
 #endif
 
 void helper_ldtlb(CPUSH4State *env)
diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c
index 4654c2a6a0..f93ce72eb9 100644
--- a/target/sparc/cpu.c
+++ b/target/sparc/cpu.c
@@ -875,9 +875,8 @@ static void sparc_cpu_class_init(ObjectClass *oc, void *data)
     cc->synchronize_from_tb = sparc_cpu_synchronize_from_tb;
     cc->gdb_read_register = sparc_cpu_gdb_read_register;
     cc->gdb_write_register = sparc_cpu_gdb_write_register;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = sparc_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = sparc_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->do_unassigned_access = sparc_cpu_unassigned_access;
     cc->do_unaligned_access = sparc_cpu_do_unaligned_access;
     cc->get_phys_page_debug = sparc_cpu_get_phys_page_debug;
diff --git a/target/sparc/cpu.h b/target/sparc/cpu.h
index 85b9665ccc..f31e8535df 100644
--- a/target/sparc/cpu.h
+++ b/target/sparc/cpu.h
@@ -579,8 +579,9 @@ void cpu_raise_exception_ra(CPUSPARCState *, int, uintptr_t) QEMU_NORETURN;
 void cpu_sparc_set_id(CPUSPARCState *env, unsigned int cpu);
 void sparc_cpu_list(void);
 /* mmu_helper.c */
-int sparc_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                               int mmu_idx);
+bool sparc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr);
 target_ulong mmu_probe(CPUSPARCState *env, target_ulong address, int mmulev);
 void dump_mmu(CPUSPARCState *env);
 
diff --git a/target/sparc/ldst_helper.c b/target/sparc/ldst_helper.c
index a7fcb84ac0..b4bf6faf41 100644
--- a/target/sparc/ldst_helper.c
+++ b/target/sparc/ldst_helper.c
@@ -1924,19 +1924,4 @@ void QEMU_NORETURN sparc_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
 #endif
     cpu_raise_exception_ra(env, TT_UNALIGNED, retaddr);
 }
-
-/* try to fill the TLB and return an exception if error. If retaddr is
-   NULL, it means that the function was called in C code (i.e. not
-   from generated code or from helper.c) */
-/* XXX: fix it to restore all registers */
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = sparc_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (ret) {
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
 #endif
diff --git a/target/sparc/mmu_helper.c b/target/sparc/mmu_helper.c
index afcc5b617d..facc0c60e9 100644
--- a/target/sparc/mmu_helper.c
+++ b/target/sparc/mmu_helper.c
@@ -27,13 +27,14 @@
 
 #if defined(CONFIG_USER_ONLY)
 
-int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                               int mmu_idx)
+bool sparc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     SPARCCPU *cpu = SPARC_CPU(cs);
     CPUSPARCState *env = &cpu->env;
 
-    if (rw & 2) {
+    if (access_type == MMU_INST_FETCH) {
         cs->exception_index = TT_TFAULT;
     } else {
         cs->exception_index = TT_DFAULT;
@@ -43,7 +44,7 @@ int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
         env->mmuregs[4] = address;
 #endif
     }
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #else
@@ -208,8 +209,9 @@ static int get_physical_address(CPUSPARCState *env, hwaddr *physical,
 }
 
 /* Perform address translation */
-int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                               int mmu_idx)
+bool sparc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     SPARCCPU *cpu = SPARC_CPU(cs);
     CPUSPARCState *env = &cpu->env;
@@ -218,16 +220,26 @@ int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
     target_ulong page_size;
     int error_code = 0, prot, access_index;
 
+    /*
+     * TODO: If we ever need tlb_vaddr_to_host for this target,
+     * then we must figure out how to manipulate FSR and FAR
+     * when both MMU_NF and probe are set.  In the meantime,
+     * do not support this use case.
+     */
+    assert(!probe);
+
     address &= TARGET_PAGE_MASK;
     error_code = get_physical_address(env, &paddr, &prot, &access_index,
-                                      address, rw, mmu_idx, &page_size);
+                                      address, access_type,
+                                      mmu_idx, &page_size);
     vaddr = address;
-    if (error_code == 0) {
+    if (likely(error_code == 0)) {
         qemu_log_mask(CPU_LOG_MMU,
-                "Translate at %" VADDR_PRIx " -> " TARGET_FMT_plx ", vaddr "
-                TARGET_FMT_lx "\n", address, paddr, vaddr);
+                      "Translate at %" VADDR_PRIx " -> "
+                      TARGET_FMT_plx ", vaddr " TARGET_FMT_lx "\n",
+                      address, paddr, vaddr);
         tlb_set_page(cs, vaddr, paddr, prot, mmu_idx, page_size);
-        return 0;
+        return true;
     }
 
     if (env->mmuregs[3]) { /* Fault status register */
@@ -243,14 +255,14 @@ int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
            switching to normal mode. */
         prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
         tlb_set_page(cs, vaddr, paddr, prot, mmu_idx, TARGET_PAGE_SIZE);
-        return 0;
+        return true;
     } else {
-        if (rw & 2) {
+        if (access_type == MMU_INST_FETCH) {
             cs->exception_index = TT_TFAULT;
         } else {
             cs->exception_index = TT_DFAULT;
         }
-        return 1;
+        cpu_loop_exit_restore(cs, retaddr);
     }
 }
 
@@ -713,8 +725,9 @@ static int get_physical_address(CPUSPARCState *env, hwaddr *physical,
 }
 
 /* Perform address translation */
-int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                               int mmu_idx)
+bool sparc_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                        MMUAccessType access_type, int mmu_idx,
+                        bool probe, uintptr_t retaddr)
 {
     SPARCCPU *cpu = SPARC_CPU(cs);
     CPUSPARCState *env = &cpu->env;
@@ -725,8 +738,9 @@ int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
 
     address &= TARGET_PAGE_MASK;
     error_code = get_physical_address(env, &paddr, &prot, &access_index,
-                                      address, rw, mmu_idx, &page_size);
-    if (error_code == 0) {
+                                      address, access_type,
+                                      mmu_idx, &page_size);
+    if (likely(error_code == 0)) {
         vaddr = address;
 
         trace_mmu_helper_mmu_fault(address, paddr, mmu_idx, env->tl,
@@ -734,10 +748,12 @@ int sparc_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
                                    env->dmmu.mmu_secondary_context);
 
         tlb_set_page(cs, vaddr, paddr, prot, mmu_idx, page_size);
-        return 0;
+        return true;
     }
-    /* XXX */
-    return 1;
+    if (probe) {
+        return false;
+    }
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 void dump_mmu(CPUSPARCState *env)
diff --git a/target/tilegx/cpu.c b/target/tilegx/cpu.c
index b9d37105fa..b209c55387 100644
--- a/target/tilegx/cpu.c
+++ b/target/tilegx/cpu.c
@@ -25,6 +25,7 @@
 #include "hw/qdev-properties.h"
 #include "linux-user/syscall_defs.h"
 #include "qemu/qemu-print.h"
+#include "exec/exec-all.h"
 
 static void tilegx_cpu_dump_state(CPUState *cs, FILE *f, int flags)
 {
@@ -111,8 +112,9 @@ static void tilegx_cpu_do_interrupt(CPUState *cs)
     cs->exception_index = -1;
 }
 
-static int tilegx_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                                       int rw, int mmu_idx)
+static bool tilegx_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                                MMUAccessType access_type, int mmu_idx,
+                                bool probe, uintptr_t retaddr)
 {
     TileGXCPU *cpu = TILEGX_CPU(cs);
 
@@ -122,7 +124,7 @@ static int tilegx_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
     cpu->env.signo = TARGET_SIGSEGV;
     cpu->env.sigcode = 0;
 
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 static bool tilegx_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
@@ -152,7 +154,7 @@ static void tilegx_cpu_class_init(ObjectClass *oc, void *data)
     cc->cpu_exec_interrupt = tilegx_cpu_exec_interrupt;
     cc->dump_state = tilegx_cpu_dump_state;
     cc->set_pc = tilegx_cpu_set_pc;
-    cc->handle_mmu_fault = tilegx_cpu_handle_mmu_fault;
+    cc->tlb_fill = tilegx_cpu_tlb_fill;
     cc->gdb_num_core_regs = 0;
     cc->tcg_initialize = tilegx_tcg_init;
 }
diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c
index e8d37e4040..ea1199d27e 100644
--- a/target/tricore/cpu.c
+++ b/target/tricore/cpu.c
@@ -166,6 +166,7 @@ static void tricore_cpu_class_init(ObjectClass *c, void *data)
     cc->synchronize_from_tb = tricore_cpu_synchronize_from_tb;
     cc->get_phys_page_attrs_debug = tricore_cpu_get_phys_page_attrs_debug;
     cc->tcg_initialize = tricore_tcg_init;
+    cc->tlb_fill = tricore_cpu_tlb_fill;
 }
 
 #define DEFINE_TRICORE_CPU_TYPE(cpu_model, initfn) \
diff --git a/target/tricore/cpu.h b/target/tricore/cpu.h
index 64d1a9c75e..287f4328a3 100644
--- a/target/tricore/cpu.h
+++ b/target/tricore/cpu.h
@@ -417,8 +417,8 @@ static inline void cpu_get_tb_cpu_state(CPUTriCoreState *env, target_ulong *pc,
 #define CPU_RESOLVING_TYPE TYPE_TRICORE_CPU
 
 /* helpers.c */
-int cpu_tricore_handle_mmu_fault(CPUState *cpu, target_ulong address,
-                                 int rw, int mmu_idx);
-#define cpu_handle_mmu_fault cpu_tricore_handle_mmu_fault
+bool tricore_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                          MMUAccessType access_type, int mmu_idx,
+                          bool probe, uintptr_t retaddr);
 
 #endif /* TRICORE_CPU_H */
diff --git a/target/tricore/helper.c b/target/tricore/helper.c
index 78ee87c9ea..a680336850 100644
--- a/target/tricore/helper.c
+++ b/target/tricore/helper.c
@@ -50,8 +50,9 @@ static void raise_mmu_exception(CPUTriCoreState *env, target_ulong address,
 {
 }
 
-int cpu_tricore_handle_mmu_fault(CPUState *cs, target_ulong address,
-                                 int rw, int mmu_idx)
+bool tricore_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                          MMUAccessType rw, int mmu_idx,
+                          bool probe, uintptr_t retaddr)
 {
     TriCoreCPU *cpu = TRICORE_CPU(cs);
     CPUTriCoreState *env = &cpu->env;
@@ -64,20 +65,24 @@ int cpu_tricore_handle_mmu_fault(CPUState *cs, target_ulong address,
     access_type = ACCESS_INT;
     ret = get_physical_address(env, &physical, &prot,
                                address, rw, access_type);
-    qemu_log_mask(CPU_LOG_MMU, "%s address=" TARGET_FMT_lx " ret %d physical " TARGET_FMT_plx
-                  " prot %d\n", __func__, address, ret, physical, prot);
+
+    qemu_log_mask(CPU_LOG_MMU, "%s address=" TARGET_FMT_lx " ret %d physical "
+                  TARGET_FMT_plx " prot %d\n",
+                  __func__, (target_ulong)address, ret, physical, prot);
 
     if (ret == TLBRET_MATCH) {
         tlb_set_page(cs, address & TARGET_PAGE_MASK,
                      physical & TARGET_PAGE_MASK, prot | PAGE_EXEC,
                      mmu_idx, TARGET_PAGE_SIZE);
-        ret = 0;
-    } else if (ret < 0) {
+        return true;
+    } else {
+        assert(ret < 0);
+        if (probe) {
+            return false;
+        }
         raise_mmu_exception(env, address, rw, ret);
-        ret = 1;
+        cpu_loop_exit_restore(cs, retaddr);
     }
-
-    return ret;
 }
 
 static void tricore_cpu_list_entry(gpointer data, gpointer user_data)
diff --git a/target/tricore/op_helper.c b/target/tricore/op_helper.c
index ed9dc0c83e..601e92f92a 100644
--- a/target/tricore/op_helper.c
+++ b/target/tricore/op_helper.c
@@ -2793,29 +2793,3 @@ uint32_t helper_psw_read(CPUTriCoreState *env)
 {
     return psw_read(env);
 }
-
-
-static inline void QEMU_NORETURN do_raise_exception_err(CPUTriCoreState *env,
-                                                        uint32_t exception,
-                                                        int error_code,
-                                                        uintptr_t pc)
-{
-    CPUState *cs = CPU(tricore_env_get_cpu(env));
-    cs->exception_index = exception;
-    env->error_code = error_code;
-    /* now we have a real cpu fault */
-    cpu_loop_exit_restore(cs, pc);
-}
-
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-    ret = cpu_tricore_handle_mmu_fault(cs, addr, access_type, mmu_idx);
-    if (ret) {
-        TriCoreCPU *cpu = TRICORE_CPU(cs);
-        CPUTriCoreState *env = &cpu->env;
-        do_raise_exception_err(env, cs->exception_index,
-                               env->error_code, retaddr);
-    }
-}
diff --git a/target/unicore32/cpu.c b/target/unicore32/cpu.c
index 2b49d1ca40..3f57c508a0 100644
--- a/target/unicore32/cpu.c
+++ b/target/unicore32/cpu.c
@@ -138,11 +138,8 @@ static void uc32_cpu_class_init(ObjectClass *oc, void *data)
     cc->cpu_exec_interrupt = uc32_cpu_exec_interrupt;
     cc->dump_state = uc32_cpu_dump_state;
     cc->set_pc = uc32_cpu_set_pc;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = uc32_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = uc32_cpu_tlb_fill;
     cc->get_phys_page_debug = uc32_cpu_get_phys_page_debug;
-#endif
     cc->tcg_initialize = uc32_translate_init;
     dc->vmsd = &vmstate_uc32_cpu;
 }
diff --git a/target/unicore32/cpu.h b/target/unicore32/cpu.h
index 24abe5e5c0..f052ee08bf 100644
--- a/target/unicore32/cpu.h
+++ b/target/unicore32/cpu.h
@@ -178,8 +178,9 @@ static inline void cpu_get_tb_cpu_state(CPUUniCore32State *env, target_ulong *pc
     }
 }
 
-int uc32_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw,
-                              int mmu_idx);
+bool uc32_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr);
 void uc32_translate_init(void);
 void switch_mode(CPUUniCore32State *, int);
 
diff --git a/target/unicore32/helper.c b/target/unicore32/helper.c
index a5ff2ddb74..0d4914b48d 100644
--- a/target/unicore32/helper.c
+++ b/target/unicore32/helper.c
@@ -215,29 +215,6 @@ void helper_cp1_putc(target_ulong x)
 }
 #endif
 
-#ifdef CONFIG_USER_ONLY
-void switch_mode(CPUUniCore32State *env, int mode)
-{
-    UniCore32CPU *cpu = uc32_env_get_cpu(env);
-
-    if (mode != ASR_MODE_USER) {
-        cpu_abort(CPU(cpu), "Tried to switch out of user mode\n");
-    }
-}
-
-void uc32_cpu_do_interrupt(CPUState *cs)
-{
-    cpu_abort(cs, "NO interrupt in user mode\n");
-}
-
-int uc32_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                              int access_type, int mmu_idx)
-{
-    cpu_abort(cs, "NO mmu fault in user mode\n");
-    return 1;
-}
-#endif
-
 bool uc32_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 {
     if (interrupt_request & CPU_INTERRUPT_HARD) {
diff --git a/target/unicore32/op_helper.c b/target/unicore32/op_helper.c
index e0a15882d3..797ba60dc9 100644
--- a/target/unicore32/op_helper.c
+++ b/target/unicore32/op_helper.c
@@ -242,17 +242,3 @@ uint32_t HELPER(ror_cc)(CPUUniCore32State *env, uint32_t x, uint32_t i)
         return ((uint32_t)x >> shift) | (x << (32 - shift));
     }
 }
-
-#ifndef CONFIG_USER_ONLY
-void tlb_fill(CPUState *cs, target_ulong addr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
-{
-    int ret;
-
-    ret = uc32_cpu_handle_mmu_fault(cs, addr, size, access_type, mmu_idx);
-    if (unlikely(ret)) {
-        /* now we have a real cpu fault */
-        cpu_loop_exit_restore(cs, retaddr);
-    }
-}
-#endif
diff --git a/target/unicore32/softmmu.c b/target/unicore32/softmmu.c
index 00c7e0d028..27f218abf0 100644
--- a/target/unicore32/softmmu.c
+++ b/target/unicore32/softmmu.c
@@ -215,8 +215,9 @@ do_fault:
     return code;
 }
 
-int uc32_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
-                              int access_type, int mmu_idx)
+bool uc32_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                       MMUAccessType access_type, int mmu_idx,
+                       bool probe, uintptr_t retaddr)
 {
     UniCore32CPU *cpu = UNICORE32_CPU(cs);
     CPUUniCore32State *env = &cpu->env;
@@ -257,7 +258,11 @@ int uc32_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
         phys_addr &= TARGET_PAGE_MASK;
         address &= TARGET_PAGE_MASK;
         tlb_set_page(cs, address, phys_addr, prot, mmu_idx, page_size);
-        return 0;
+        return true;
+    }
+
+    if (probe) {
+        return false;
     }
 
     env->cp0.c3_faultstatus = ret;
@@ -267,7 +272,7 @@ int uc32_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size,
     } else {
         cs->exception_index = UC32_EXCP_DTRAP;
     }
-    return ret;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 hwaddr uc32_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c
index a54dbe4260..da1236377e 100644
--- a/target/xtensa/cpu.c
+++ b/target/xtensa/cpu.c
@@ -181,9 +181,8 @@ static void xtensa_cpu_class_init(ObjectClass *oc, void *data)
     cc->gdb_read_register = xtensa_cpu_gdb_read_register;
     cc->gdb_write_register = xtensa_cpu_gdb_write_register;
     cc->gdb_stop_before_watchpoint = true;
-#ifdef CONFIG_USER_ONLY
-    cc->handle_mmu_fault = xtensa_cpu_handle_mmu_fault;
-#else
+    cc->tlb_fill = xtensa_cpu_tlb_fill;
+#ifndef CONFIG_USER_ONLY
     cc->do_unaligned_access = xtensa_cpu_do_unaligned_access;
     cc->get_phys_page_debug = xtensa_cpu_get_phys_page_debug;
     cc->do_transaction_failed = xtensa_cpu_do_transaction_failed;
diff --git a/target/xtensa/cpu.h b/target/xtensa/cpu.h
index 5d23e1345b..68d89f8faf 100644
--- a/target/xtensa/cpu.h
+++ b/target/xtensa/cpu.h
@@ -552,8 +552,9 @@ static inline XtensaCPU *xtensa_env_get_cpu(const CPUXtensaState *env)
 #define ENV_OFFSET offsetof(XtensaCPU, env)
 
 
-int xtensa_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int rw, int size,
-                                int mmu_idx);
+bool xtensa_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                         MMUAccessType access_type, int mmu_idx,
+                         bool probe, uintptr_t retaddr);
 void xtensa_cpu_do_interrupt(CPUState *cpu);
 bool xtensa_cpu_exec_interrupt(CPUState *cpu, int interrupt_request);
 void xtensa_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, vaddr addr,
diff --git a/target/xtensa/helper.c b/target/xtensa/helper.c
index 5f37f378a3..efb966b3bf 100644
--- a/target/xtensa/helper.c
+++ b/target/xtensa/helper.c
@@ -240,19 +240,21 @@ void xtensa_cpu_list(void)
 
 #ifdef CONFIG_USER_ONLY
 
-int xtensa_cpu_handle_mmu_fault(CPUState *cs, vaddr address, int size, int rw,
-                                int mmu_idx)
+bool xtensa_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                         MMUAccessType access_type, int mmu_idx,
+                         bool probe, uintptr_t retaddr)
 {
     XtensaCPU *cpu = XTENSA_CPU(cs);
     CPUXtensaState *env = &cpu->env;
 
     qemu_log_mask(CPU_LOG_INT,
                   "%s: rw = %d, address = 0x%08" VADDR_PRIx ", size = %d\n",
-                  __func__, rw, address, size);
+                  __func__, access_type, address, size);
     env->sregs[EXCVADDR] = address;
-    env->sregs[EXCCAUSE] = rw ? STORE_PROHIBITED_CAUSE : LOAD_PROHIBITED_CAUSE;
+    env->sregs[EXCCAUSE] = (access_type == MMU_DATA_STORE ?
+                            STORE_PROHIBITED_CAUSE : LOAD_PROHIBITED_CAUSE);
     cs->exception_index = EXC_USER;
-    return 1;
+    cpu_loop_exit_restore(cs, retaddr);
 }
 
 #else
@@ -273,28 +275,33 @@ void xtensa_cpu_do_unaligned_access(CPUState *cs,
     }
 }
 
-void tlb_fill(CPUState *cs, target_ulong vaddr, int size,
-              MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
+bool xtensa_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
+                         MMUAccessType access_type, int mmu_idx,
+                         bool probe, uintptr_t retaddr)
 {
     XtensaCPU *cpu = XTENSA_CPU(cs);
     CPUXtensaState *env = &cpu->env;
     uint32_t paddr;
     uint32_t page_size;
     unsigned access;
-    int ret = xtensa_get_physical_addr(env, true, vaddr, access_type, mmu_idx,
-                                       &paddr, &page_size, &access);
+    int ret = xtensa_get_physical_addr(env, true, address, access_type,
+                                       mmu_idx, &paddr, &page_size, &access);
 
-    qemu_log_mask(CPU_LOG_MMU, "%s(%08x, %d, %d) -> %08x, ret = %d\n",
-                  __func__, vaddr, access_type, mmu_idx, paddr, ret);
+    qemu_log_mask(CPU_LOG_MMU, "%s(%08" VADDR_PRIx
+                  ", %d, %d) -> %08x, ret = %d\n",
+                  __func__, address, access_type, mmu_idx, paddr, ret);
 
     if (ret == 0) {
         tlb_set_page(cs,
-                     vaddr & TARGET_PAGE_MASK,
+                     address & TARGET_PAGE_MASK,
                      paddr & TARGET_PAGE_MASK,
                      access, mmu_idx, page_size);
+        return true;
+    } else if (probe) {
+        return false;
     } else {
         cpu_restore_state(cs, retaddr, true);
-        HELPER(exception_cause_vaddr)(env, env->pc, ret, vaddr);
+        HELPER(exception_cause_vaddr)(env, env->pc, ret, address);
     }
 }