summary refs log tree commit diff stats
path: root/target
diff options
context:
space:
mode:
Diffstat (limited to 'target')
-rw-r--r--target/arm/cpu.c2
-rw-r--r--target/arm/helper.c9
-rw-r--r--target/arm/internals.h12
-rw-r--r--target/arm/ptw.c141
-rw-r--r--target/arm/tcg/cpu-v7m.c2
-rw-r--r--target/arm/tcg/m_helper.c8
-rw-r--r--target/arm/tcg/tlb_helper.c47
-rw-r--r--target/arm/tcg/translate-a64.c4
-rw-r--r--target/hppa/cpu.c2
-rw-r--r--target/hppa/cpu.h8
-rw-r--r--target/hppa/int_helper.c2
-rw-r--r--target/hppa/mem_helper.c55
-rw-r--r--target/hppa/op_helper.c2
-rw-r--r--target/i386/cpu.c1
-rw-r--r--target/i386/cpu.h1
-rw-r--r--target/i386/gdbstub.c102
-rw-r--r--target/mips/tcg/translate.c5
-rw-r--r--target/xtensa/translate.c2
18 files changed, 244 insertions, 161 deletions
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 19191c2391..1320fd8c8f 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -2663,7 +2663,7 @@ static const TCGCPUOps arm_tcg_ops = {
     .record_sigsegv = arm_cpu_record_sigsegv,
     .record_sigbus = arm_cpu_record_sigbus,
 #else
-    .tlb_fill = arm_cpu_tlb_fill,
+    .tlb_fill_align = arm_cpu_tlb_fill_align,
     .cpu_exec_interrupt = arm_cpu_exec_interrupt,
     .cpu_exec_halt = arm_cpu_exec_halt,
     .do_interrupt = arm_cpu_do_interrupt,
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 3f77b40734..0a731a38e8 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -3599,11 +3599,12 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
     GetPhysAddrResult res = {};
 
     /*
-     * I_MXTJT: Granule protection checks are not performed on the final address
-     * of a successful translation.
+     * I_MXTJT: Granule protection checks are not performed on the final
+     * address of a successful translation.  This is a translation not a
+     * memory reference, so "memop = none = 0".
      */
-    ret = get_phys_addr_with_space_nogpc(env, value, access_type, mmu_idx, ss,
-                                         &res, &fi);
+    ret = get_phys_addr_with_space_nogpc(env, value, access_type, 0,
+                                         mmu_idx, ss, &res, &fi);
 
     /*
      * ATS operations only do S1 or S1+S2 translations, so we never
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 1e5da81ce9..299a96a81a 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -816,9 +816,9 @@ void arm_cpu_record_sigsegv(CPUState *cpu, vaddr addr,
 void arm_cpu_record_sigbus(CPUState *cpu, vaddr addr,
                            MMUAccessType access_type, uintptr_t ra);
 #else
-bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
-                      MMUAccessType access_type, int mmu_idx,
-                      bool probe, uintptr_t retaddr);
+bool arm_cpu_tlb_fill_align(CPUState *cs, CPUTLBEntryFull *out, vaddr addr,
+                            MMUAccessType access_type, int mmu_idx,
+                            MemOp memop, int size, bool probe, uintptr_t ra);
 #endif
 
 static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx)
@@ -1432,6 +1432,7 @@ typedef struct GetPhysAddrResult {
  * @env: CPUARMState
  * @address: virtual address to get physical address for
  * @access_type: 0 for read, 1 for write, 2 for execute
+ * @memop: memory operation feeding this access, or 0 for none
  * @mmu_idx: MMU index indicating required translation regime
  * @result: set on translation success.
  * @fi: set to fault info if the translation fails
@@ -1450,7 +1451,7 @@ typedef struct GetPhysAddrResult {
  *    value.
  */
 bool get_phys_addr(CPUARMState *env, vaddr address,
-                   MMUAccessType access_type, ARMMMUIdx mmu_idx,
+                   MMUAccessType access_type, MemOp memop, ARMMMUIdx mmu_idx,
                    GetPhysAddrResult *result, ARMMMUFaultInfo *fi)
     __attribute__((nonnull));
 
@@ -1460,6 +1461,7 @@ bool get_phys_addr(CPUARMState *env, vaddr address,
  * @env: CPUARMState
  * @address: virtual address to get physical address for
  * @access_type: 0 for read, 1 for write, 2 for execute
+ * @memop: memory operation feeding this access, or 0 for none
  * @mmu_idx: MMU index indicating required translation regime
  * @space: security space for the access
  * @result: set on translation success.
@@ -1469,7 +1471,7 @@ bool get_phys_addr(CPUARMState *env, vaddr address,
  * a Granule Protection Check on the resulting address.
  */
 bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address,
-                                    MMUAccessType access_type,
+                                    MMUAccessType access_type, MemOp memop,
                                     ARMMMUIdx mmu_idx, ARMSecuritySpace space,
                                     GetPhysAddrResult *result,
                                     ARMMMUFaultInfo *fi)
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index 659855133c..dd40268397 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -75,13 +75,13 @@ typedef struct S1Translate {
 
 static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw,
                                 vaddr address,
-                                MMUAccessType access_type,
+                                MMUAccessType access_type, MemOp memop,
                                 GetPhysAddrResult *result,
                                 ARMMMUFaultInfo *fi);
 
 static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw,
                               vaddr address,
-                              MMUAccessType access_type,
+                              MMUAccessType access_type, MemOp memop,
                               GetPhysAddrResult *result,
                               ARMMMUFaultInfo *fi);
 
@@ -579,7 +579,7 @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw,
         };
         GetPhysAddrResult s2 = { };
 
-        if (get_phys_addr_gpc(env, &s2ptw, addr, MMU_DATA_LOAD, &s2, fi)) {
+        if (get_phys_addr_gpc(env, &s2ptw, addr, MMU_DATA_LOAD, 0, &s2, fi)) {
             goto fail;
         }
 
@@ -1684,12 +1684,13 @@ static bool nv_nv1_enabled(CPUARMState *env, S1Translate *ptw)
  * @ptw: Current and next stage parameters for the walk.
  * @address: virtual address to get physical address for
  * @access_type: MMU_DATA_LOAD, MMU_DATA_STORE or MMU_INST_FETCH
+ * @memop: memory operation feeding this access, or 0 for none
  * @result: set on translation success,
  * @fi: set to fault info if the translation fails
  */
 static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw,
                                uint64_t address,
-                               MMUAccessType access_type,
+                               MMUAccessType access_type, MemOp memop,
                                GetPhysAddrResult *result, ARMMMUFaultInfo *fi)
 {
     ARMCPU *cpu = env_archcpu(env);
@@ -2028,8 +2029,20 @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw,
             xn = extract64(attrs, 53, 2);
             result->f.prot = get_S2prot(env, ap, xn, ptw->in_s1_is_el0);
         }
+
+        result->cacheattrs.is_s2_format = true;
+        result->cacheattrs.attrs = extract32(attrs, 2, 4);
+        /*
+         * Security state does not really affect HCR_EL2.FWB;
+         * we only need to filter FWB for aa32 or other FEAT.
+         */
+        device = S2_attrs_are_device(arm_hcr_el2_eff(env),
+                                     result->cacheattrs.attrs);
     } else {
         int nse, ns = extract32(attrs, 5, 1);
+        uint8_t attrindx;
+        uint64_t mair;
+
         switch (out_space) {
         case ARMSS_Root:
             /*
@@ -2101,6 +2114,49 @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw,
          */
         result->f.prot = get_S1prot(env, mmu_idx, aarch64, ap, xn, pxn,
                                     result->f.attrs.space, out_space);
+
+        /* Index into MAIR registers for cache attributes */
+        attrindx = extract32(attrs, 2, 3);
+        mair = env->cp15.mair_el[regime_el(env, mmu_idx)];
+        assert(attrindx <= 7);
+        result->cacheattrs.is_s2_format = false;
+        result->cacheattrs.attrs = extract64(mair, attrindx * 8, 8);
+
+        /* When in aarch64 mode, and BTI is enabled, remember GP in the TLB. */
+        if (aarch64 && cpu_isar_feature(aa64_bti, cpu)) {
+            result->f.extra.arm.guarded = extract64(attrs, 50, 1); /* GP */
+        }
+        device = S1_attrs_are_device(result->cacheattrs.attrs);
+    }
+
+    /*
+     * Enable alignment checks on Device memory.
+     *
+     * Per R_XCHFJ, the correct ordering for alignment, permission,
+     * and stage 2 faults is:
+     *    - Alignment fault caused by the memory type
+     *    - Permission fault
+     *    - A stage 2 fault on the memory access
+     * Perform the alignment check now, so that we recognize it in
+     * the correct order.  Set TLB_CHECK_ALIGNED so that any subsequent
+     * softmmu tlb hit will also check the alignment; clear along the
+     * non-device path so that tlb_fill_flags is consistent in the
+     * event of restart_atomic_update.
+     *
+     * In v7, for a CPU without the Virtualization Extensions this
+     * access is UNPREDICTABLE; we choose to make it take the alignment
+     * fault as is required for a v7VE CPU. (QEMU doesn't emulate any
+     * CPUs with ARM_FEATURE_LPAE but not ARM_FEATURE_V7VE anyway.)
+     */
+    if (device) {
+        unsigned a_bits = memop_atomicity_bits(memop);
+        if (address & ((1 << a_bits) - 1)) {
+            fi->type = ARMFault_Alignment;
+            goto do_fault;
+        }
+        result->f.tlb_fill_flags = TLB_CHECK_ALIGNED;
+    } else {
+        result->f.tlb_fill_flags = 0;
     }
 
     if (!(result->f.prot & (1 << access_type))) {
@@ -2130,51 +2186,6 @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw,
     result->f.attrs.space = out_space;
     result->f.attrs.secure = arm_space_is_secure(out_space);
 
-    if (regime_is_stage2(mmu_idx)) {
-        result->cacheattrs.is_s2_format = true;
-        result->cacheattrs.attrs = extract32(attrs, 2, 4);
-        /*
-         * Security state does not really affect HCR_EL2.FWB;
-         * we only need to filter FWB for aa32 or other FEAT.
-         */
-        device = S2_attrs_are_device(arm_hcr_el2_eff(env),
-                                     result->cacheattrs.attrs);
-    } else {
-        /* Index into MAIR registers for cache attributes */
-        uint8_t attrindx = extract32(attrs, 2, 3);
-        uint64_t mair = env->cp15.mair_el[regime_el(env, mmu_idx)];
-        assert(attrindx <= 7);
-        result->cacheattrs.is_s2_format = false;
-        result->cacheattrs.attrs = extract64(mair, attrindx * 8, 8);
-
-        /* When in aarch64 mode, and BTI is enabled, remember GP in the TLB. */
-        if (aarch64 && cpu_isar_feature(aa64_bti, cpu)) {
-            result->f.extra.arm.guarded = extract64(attrs, 50, 1); /* GP */
-        }
-        device = S1_attrs_are_device(result->cacheattrs.attrs);
-    }
-
-    /*
-     * Enable alignment checks on Device memory.
-     *
-     * Per R_XCHFJ, this check is mis-ordered. The correct ordering
-     * for alignment, permission, and stage 2 faults should be:
-     *    - Alignment fault caused by the memory type
-     *    - Permission fault
-     *    - A stage 2 fault on the memory access
-     * but due to the way the TCG softmmu TLB operates, we will have
-     * implicitly done the permission check and the stage2 lookup in
-     * finding the TLB entry, so the alignment check cannot be done sooner.
-     *
-     * In v7, for a CPU without the Virtualization Extensions this
-     * access is UNPREDICTABLE; we choose to make it take the alignment
-     * fault as is required for a v7VE CPU. (QEMU doesn't emulate any
-     * CPUs with ARM_FEATURE_LPAE but not ARM_FEATURE_V7VE anyway.)
-     */
-    if (device) {
-        result->f.tlb_fill_flags |= TLB_CHECK_ALIGNED;
-    }
-
     /*
      * For FEAT_LPA2 and effective DS, the SH field in the attributes
      * was re-purposed for output address bits.  The SH attribute in
@@ -3301,7 +3312,7 @@ static bool get_phys_addr_disabled(CPUARMState *env,
 
 static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw,
                                    vaddr address,
-                                   MMUAccessType access_type,
+                                   MMUAccessType access_type, MemOp memop,
                                    GetPhysAddrResult *result,
                                    ARMMMUFaultInfo *fi)
 {
@@ -3313,7 +3324,8 @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw,
     ARMSecuritySpace ipa_space;
     uint64_t hcr;
 
-    ret = get_phys_addr_nogpc(env, ptw, address, access_type, result, fi);
+    ret = get_phys_addr_nogpc(env, ptw, address, access_type,
+                              memop, result, fi);
 
     /* If S1 fails, return early.  */
     if (ret) {
@@ -3339,7 +3351,8 @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw,
     cacheattrs1 = result->cacheattrs;
     memset(result, 0, sizeof(*result));
 
-    ret = get_phys_addr_nogpc(env, ptw, ipa, access_type, result, fi);
+    ret = get_phys_addr_nogpc(env, ptw, ipa, access_type,
+                              memop, result, fi);
     fi->s2addr = ipa;
 
     /* Combine the S1 and S2 perms.  */
@@ -3406,7 +3419,7 @@ static bool get_phys_addr_twostage(CPUARMState *env, S1Translate *ptw,
 
 static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw,
                                       vaddr address,
-                                      MMUAccessType access_type,
+                                      MMUAccessType access_type, MemOp memop,
                                       GetPhysAddrResult *result,
                                       ARMMMUFaultInfo *fi)
 {
@@ -3469,7 +3482,7 @@ static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw,
         if (arm_feature(env, ARM_FEATURE_EL2) &&
             !regime_translation_disabled(env, ARMMMUIdx_Stage2, ptw->in_space)) {
             return get_phys_addr_twostage(env, ptw, address, access_type,
-                                          result, fi);
+                                          memop, result, fi);
         }
         /* fall through */
 
@@ -3532,7 +3545,8 @@ static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw,
     }
 
     if (regime_using_lpae_format(env, mmu_idx)) {
-        return get_phys_addr_lpae(env, ptw, address, access_type, result, fi);
+        return get_phys_addr_lpae(env, ptw, address, access_type,
+                                  memop, result, fi);
     } else if (arm_feature(env, ARM_FEATURE_V7) ||
                regime_sctlr(env, mmu_idx) & SCTLR_XP) {
         return get_phys_addr_v6(env, ptw, address, access_type, result, fi);
@@ -3543,11 +3557,12 @@ static bool get_phys_addr_nogpc(CPUARMState *env, S1Translate *ptw,
 
 static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw,
                               vaddr address,
-                              MMUAccessType access_type,
+                              MMUAccessType access_type, MemOp memop,
                               GetPhysAddrResult *result,
                               ARMMMUFaultInfo *fi)
 {
-    if (get_phys_addr_nogpc(env, ptw, address, access_type, result, fi)) {
+    if (get_phys_addr_nogpc(env, ptw, address, access_type,
+                            memop, result, fi)) {
         return true;
     }
     if (!granule_protection_check(env, result->f.phys_addr,
@@ -3559,7 +3574,7 @@ static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw,
 }
 
 bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address,
-                                    MMUAccessType access_type,
+                                    MMUAccessType access_type, MemOp memop,
                                     ARMMMUIdx mmu_idx, ARMSecuritySpace space,
                                     GetPhysAddrResult *result,
                                     ARMMMUFaultInfo *fi)
@@ -3568,11 +3583,12 @@ bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address,
         .in_mmu_idx = mmu_idx,
         .in_space = space,
     };
-    return get_phys_addr_nogpc(env, &ptw, address, access_type, result, fi);
+    return get_phys_addr_nogpc(env, &ptw, address, access_type,
+                               memop, result, fi);
 }
 
 bool get_phys_addr(CPUARMState *env, vaddr address,
-                   MMUAccessType access_type, ARMMMUIdx mmu_idx,
+                   MMUAccessType access_type, MemOp memop, ARMMMUIdx mmu_idx,
                    GetPhysAddrResult *result, ARMMMUFaultInfo *fi)
 {
     S1Translate ptw = {
@@ -3641,7 +3657,8 @@ bool get_phys_addr(CPUARMState *env, vaddr address,
     }
 
     ptw.in_space = ss;
-    return get_phys_addr_gpc(env, &ptw, address, access_type, result, fi);
+    return get_phys_addr_gpc(env, &ptw, address, access_type,
+                             memop, result, fi);
 }
 
 hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr,
@@ -3660,7 +3677,7 @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr,
     ARMMMUFaultInfo fi = {};
     bool ret;
 
-    ret = get_phys_addr_gpc(env, &ptw, addr, MMU_DATA_LOAD, &res, &fi);
+    ret = get_phys_addr_gpc(env, &ptw, addr, MMU_DATA_LOAD, 0, &res, &fi);
     *attrs = res.f.attrs;
 
     if (ret) {
diff --git a/target/arm/tcg/cpu-v7m.c b/target/arm/tcg/cpu-v7m.c
index 5496f14dc1..58e54578d6 100644
--- a/target/arm/tcg/cpu-v7m.c
+++ b/target/arm/tcg/cpu-v7m.c
@@ -242,7 +242,7 @@ static const TCGCPUOps arm_v7m_tcg_ops = {
     .record_sigsegv = arm_cpu_record_sigsegv,
     .record_sigbus = arm_cpu_record_sigbus,
 #else
-    .tlb_fill = arm_cpu_tlb_fill,
+    .tlb_fill_align = arm_cpu_tlb_fill_align,
     .cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt,
     .cpu_exec_halt = arm_cpu_exec_halt,
     .do_interrupt = arm_v7m_cpu_do_interrupt,
diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index 23d7f73035..f7354f3c6e 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -222,7 +222,7 @@ static bool v7m_stack_write(ARMCPU *cpu, uint32_t addr, uint32_t value,
     int exc;
     bool exc_secure;
 
-    if (get_phys_addr(env, addr, MMU_DATA_STORE, mmu_idx, &res, &fi)) {
+    if (get_phys_addr(env, addr, MMU_DATA_STORE, 0, mmu_idx, &res, &fi)) {
         /* MPU/SAU lookup failed */
         if (fi.type == ARMFault_QEMU_SFault) {
             if (mode == STACK_LAZYFP) {
@@ -311,7 +311,7 @@ static bool v7m_stack_read(ARMCPU *cpu, uint32_t *dest, uint32_t addr,
     bool exc_secure;
     uint32_t value;
 
-    if (get_phys_addr(env, addr, MMU_DATA_LOAD, mmu_idx, &res, &fi)) {
+    if (get_phys_addr(env, addr, MMU_DATA_LOAD, 0, mmu_idx, &res, &fi)) {
         /* MPU/SAU lookup failed */
         if (fi.type == ARMFault_QEMU_SFault) {
             qemu_log_mask(CPU_LOG_INT,
@@ -2009,7 +2009,7 @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, bool secure,
                       "...really SecureFault with SFSR.INVEP\n");
         return false;
     }
-    if (get_phys_addr(env, addr, MMU_INST_FETCH, mmu_idx, &res, &fi)) {
+    if (get_phys_addr(env, addr, MMU_INST_FETCH, 0, mmu_idx, &res, &fi)) {
         /* the MPU lookup failed */
         env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_IACCVIOL_MASK;
         armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM, env->v7m.secure);
@@ -2045,7 +2045,7 @@ static bool v7m_read_sg_stack_word(ARMCPU *cpu, ARMMMUIdx mmu_idx,
     ARMMMUFaultInfo fi = {};
     uint32_t value;
 
-    if (get_phys_addr(env, addr, MMU_DATA_LOAD, mmu_idx, &res, &fi)) {
+    if (get_phys_addr(env, addr, MMU_DATA_LOAD, 0, mmu_idx, &res, &fi)) {
         /* MPU/SAU lookup failed */
         if (fi.type == ARMFault_QEMU_SFault) {
             qemu_log_mask(CPU_LOG_INT,
diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c
index 885bf4ec14..8841f039bc 100644
--- a/target/arm/tcg/tlb_helper.c
+++ b/target/arm/tcg/tlb_helper.c
@@ -318,14 +318,13 @@ void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
     arm_deliver_fault(cpu, addr, access_type, mmu_idx, &fi);
 }
 
-bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
-                      MMUAccessType access_type, int mmu_idx,
-                      bool probe, uintptr_t retaddr)
+bool arm_cpu_tlb_fill_align(CPUState *cs, CPUTLBEntryFull *out, vaddr address,
+                            MMUAccessType access_type, int mmu_idx,
+                            MemOp memop, int size, bool probe, uintptr_t ra)
 {
     ARMCPU *cpu = ARM_CPU(cs);
     GetPhysAddrResult res = {};
     ARMMMUFaultInfo local_fi, *fi;
-    int ret;
 
     /*
      * Allow S1_ptw_translate to see any fault generated here.
@@ -339,37 +338,27 @@ bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
     }
 
     /*
-     * 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.
+     * Per R_XCHFJ, alignment fault not due to memory type has
+     * highest precedence.  Otherwise, walk the page table and
+     * and collect the page description.
      */
-    ret = get_phys_addr(&cpu->env, address, access_type,
-                        core_to_arm_mmu_idx(&cpu->env, mmu_idx),
-                        &res, fi);
-    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 (res.f.lg_page_size >= TARGET_PAGE_BITS) {
-            res.f.phys_addr &= TARGET_PAGE_MASK;
-            address &= TARGET_PAGE_MASK;
-        }
-
+    if (address & ((1 << memop_alignment_bits(memop)) - 1)) {
+        fi->type = ARMFault_Alignment;
+    } else if (!get_phys_addr(&cpu->env, address, access_type, memop,
+                              core_to_arm_mmu_idx(&cpu->env, mmu_idx),
+                              &res, fi)) {
         res.f.extra.arm.pte_attrs = res.cacheattrs.attrs;
         res.f.extra.arm.shareability = res.cacheattrs.shareability;
-
-        tlb_set_page_full(cs, mmu_idx, address, &res.f);
+        *out = res.f;
         return true;
-    } else if (probe) {
+    }
+    if (probe) {
         return false;
-    } else {
-        /* now we have a real cpu fault */
-        cpu_restore_state(cs, retaddr);
-        arm_deliver_fault(cpu, address, access_type, mmu_idx, fi);
     }
+
+    /* Now we have a real cpu fault. */
+    cpu_restore_state(cs, ra);
+    arm_deliver_fault(cpu, address, access_type, mmu_idx, fi);
 }
 #else
 void arm_cpu_record_sigsegv(CPUState *cs, vaddr addr,
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 071b6349fc..ec0b1ee252 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -294,7 +294,7 @@ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr,
         desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid);
         desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma);
         desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write);
-        desc = FIELD_DP32(desc, MTEDESC, ALIGN, get_alignment_bits(memop));
+        desc = FIELD_DP32(desc, MTEDESC, ALIGN, memop_alignment_bits(memop));
         desc = FIELD_DP32(desc, MTEDESC, SIZEM1, memop_size(memop) - 1);
 
         ret = tcg_temp_new_i64();
@@ -326,7 +326,7 @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write,
         desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid);
         desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma);
         desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write);
-        desc = FIELD_DP32(desc, MTEDESC, ALIGN, get_alignment_bits(single_mop));
+        desc = FIELD_DP32(desc, MTEDESC, ALIGN, memop_alignment_bits(single_mop));
         desc = FIELD_DP32(desc, MTEDESC, SIZEM1, total_size - 1);
 
         ret = tcg_temp_new_i64();
diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c
index 7cf2e2f266..c38439c180 100644
--- a/target/hppa/cpu.c
+++ b/target/hppa/cpu.c
@@ -226,7 +226,7 @@ static const TCGCPUOps hppa_tcg_ops = {
     .restore_state_to_opc = hppa_restore_state_to_opc,
 
 #ifndef CONFIG_USER_ONLY
-    .tlb_fill = hppa_cpu_tlb_fill,
+    .tlb_fill_align = hppa_cpu_tlb_fill_align,
     .cpu_exec_interrupt = hppa_cpu_exec_interrupt,
     .cpu_exec_halt = hppa_cpu_has_work,
     .do_interrupt = hppa_cpu_do_interrupt,
diff --git a/target/hppa/cpu.h b/target/hppa/cpu.h
index f4e051f176..e45ba50a59 100644
--- a/target/hppa/cpu.h
+++ b/target/hppa/cpu.h
@@ -363,13 +363,13 @@ void hppa_cpu_dump_state(CPUState *cs, FILE *f, int);
 void hppa_ptlbe(CPUHPPAState *env);
 hwaddr hppa_cpu_get_phys_page_debug(CPUState *cs, vaddr addr);
 void hppa_set_ior_and_isr(CPUHPPAState *env, vaddr addr, bool mmu_disabled);
-bool hppa_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
-                       MMUAccessType access_type, int mmu_idx,
-                       bool probe, uintptr_t retaddr);
+bool hppa_cpu_tlb_fill_align(CPUState *cs, CPUTLBEntryFull *out, vaddr addr,
+                             MMUAccessType access_type, int mmu_idx,
+                             MemOp memop, int size, bool probe, uintptr_t ra);
 void hppa_cpu_do_interrupt(CPUState *cpu);
 bool hppa_cpu_exec_interrupt(CPUState *cpu, int int_req);
 int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
-                              int type, hwaddr *pphys, int *pprot);
+                              int type, MemOp mop, hwaddr *pphys, int *pprot);
 void hppa_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
                                      vaddr addr, unsigned size,
                                      MMUAccessType access_type,
diff --git a/target/hppa/int_helper.c b/target/hppa/int_helper.c
index 391f32f27d..58695def82 100644
--- a/target/hppa/int_helper.c
+++ b/target/hppa/int_helper.c
@@ -167,7 +167,7 @@ void hppa_cpu_do_interrupt(CPUState *cs)
 
                     vaddr = hppa_form_gva_psw(old_psw, env->iasq_f, vaddr);
                     t = hppa_get_physical_address(env, vaddr, MMU_KERNEL_IDX,
-                                                  0, &paddr, &prot);
+                                                  0, 0, &paddr, &prot);
                     if (t >= 0) {
                         /* We can't re-load the instruction.  */
                         env->cr[CR_IIR] = 0;
diff --git a/target/hppa/mem_helper.c b/target/hppa/mem_helper.c
index b984f730aa..b8c3e55170 100644
--- a/target/hppa/mem_helper.c
+++ b/target/hppa/mem_helper.c
@@ -197,7 +197,7 @@ static int match_prot_id64(CPUHPPAState *env, uint32_t access_id)
 }
 
 int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
-                              int type, hwaddr *pphys, int *pprot)
+                              int type, MemOp mop, hwaddr *pphys, int *pprot)
 {
     hwaddr phys;
     int prot, r_prot, w_prot, x_prot, priv;
@@ -221,7 +221,7 @@ int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
             g_assert_not_reached();
         }
         prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
-        goto egress;
+        goto egress_align;
     }
 
     /* Find a valid tlb entry that matches the virtual address.  */
@@ -267,6 +267,12 @@ int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
         goto egress;
     }
 
+    if (unlikely(!(prot & type))) {
+        /* Not allowed -- Inst/Data Memory Access Rights Fault. */
+        ret = (type & PAGE_EXEC) ? EXCP_IMP : EXCP_DMAR;
+        goto egress;
+    }
+
     /* access_id == 0 means public page and no check is performed */
     if (ent->access_id && MMU_IDX_TO_P(mmu_idx)) {
         int access_prot = (hppa_is_pa20(env)
@@ -281,14 +287,8 @@ int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
         prot &= access_prot;
     }
 
-    if (unlikely(!(prot & type))) {
-        /* Not allowed -- Inst/Data Memory Access Rights Fault. */
-        ret = (type & PAGE_EXEC) ? EXCP_IMP : EXCP_DMAR;
-        goto egress;
-    }
-
     /*
-     * In priority order, check for conditions which raise faults.
+     * In reverse priority order, check for conditions which raise faults.
      * Remove PROT bits that cover the condition we want to check,
      * so that the resulting PROT will force a re-check of the
      * architectural TLB entry for the next access.
@@ -299,13 +299,15 @@ int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
             /* The T bit is set -- Page Reference Fault.  */
             ret = EXCP_PAGE_REF;
         }
-    } else if (!ent->d) {
+    }
+    if (unlikely(!ent->d)) {
         prot &= PAGE_READ | PAGE_EXEC;
         if (type & PAGE_WRITE) {
             /* The D bit is not set -- TLB Dirty Bit Fault.  */
             ret = EXCP_TLB_DIRTY;
         }
-    } else if (unlikely(ent->b)) {
+    }
+    if (unlikely(ent->b)) {
         prot &= PAGE_READ | PAGE_EXEC;
         if (type & PAGE_WRITE) {
             /*
@@ -321,6 +323,11 @@ int hppa_get_physical_address(CPUHPPAState *env, vaddr addr, int mmu_idx,
         }
     }
 
+ egress_align:
+    if (addr & ((1u << memop_alignment_bits(mop)) - 1)) {
+        ret = EXCP_UNALIGN;
+    }
+
  egress:
     *pphys = phys;
     *pprot = prot;
@@ -340,7 +347,7 @@ hwaddr hppa_cpu_get_phys_page_debug(CPUState *cs, vaddr addr)
     mmu_idx = (cpu->env.psw & PSW_D ? MMU_KERNEL_IDX :
                cpu->env.psw & PSW_W ? MMU_ABS_W_IDX : MMU_ABS_IDX);
 
-    excp = hppa_get_physical_address(&cpu->env, addr, mmu_idx, 0,
+    excp = hppa_get_physical_address(&cpu->env, addr, mmu_idx, 0, 0,
                                      &phys, &prot);
 
     /* Since we're translating for debugging, the only error that is a
@@ -417,12 +424,11 @@ void hppa_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr,
     }
 }
 
-bool hppa_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
-                       MMUAccessType type, int mmu_idx,
-                       bool probe, uintptr_t retaddr)
+bool hppa_cpu_tlb_fill_align(CPUState *cs, CPUTLBEntryFull *out, vaddr addr,
+                             MMUAccessType type, int mmu_idx,
+                             MemOp memop, int size, bool probe, uintptr_t ra)
 {
-    HPPACPU *cpu = HPPA_CPU(cs);
-    CPUHPPAState *env = &cpu->env;
+    CPUHPPAState *env = cpu_env(cs);
     int prot, excp, a_prot;
     hwaddr phys;
 
@@ -438,7 +444,8 @@ bool hppa_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
         break;
     }
 
-    excp = hppa_get_physical_address(env, addr, mmu_idx, a_prot, &phys, &prot);
+    excp = hppa_get_physical_address(env, addr, mmu_idx, a_prot, memop,
+                                     &phys, &prot);
     if (unlikely(excp >= 0)) {
         if (probe) {
             return false;
@@ -446,7 +453,7 @@ bool hppa_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
         trace_hppa_tlb_fill_excp(env, addr, size, type, mmu_idx);
 
         /* Failure.  Raise the indicated exception.  */
-        raise_exception_with_ior(env, excp, retaddr, addr,
+        raise_exception_with_ior(env, excp, ra, addr,
                                  MMU_IDX_MMU_DISABLED(mmu_idx));
     }
 
@@ -460,8 +467,12 @@ bool hppa_cpu_tlb_fill(CPUState *cs, vaddr addr, int size,
      * the large page protection mask.  We do not require this,
      * because we record the large page here in the hppa tlb.
      */
-    tlb_set_page(cs, addr & TARGET_PAGE_MASK, phys & TARGET_PAGE_MASK,
-                 prot, mmu_idx, TARGET_PAGE_SIZE);
+    memset(out, 0, sizeof(*out));
+    out->phys_addr = phys;
+    out->prot = prot;
+    out->attrs = MEMTXATTRS_UNSPECIFIED;
+    out->lg_page_size = TARGET_PAGE_BITS;
+
     return true;
 }
 
@@ -678,7 +689,7 @@ target_ulong HELPER(lpa)(CPUHPPAState *env, target_ulong addr)
     hwaddr phys;
     int prot, excp;
 
-    excp = hppa_get_physical_address(env, addr, MMU_KERNEL_IDX, 0,
+    excp = hppa_get_physical_address(env, addr, MMU_KERNEL_IDX, 0, 0,
                                      &phys, &prot);
     if (excp >= 0) {
         if (excp == EXCP_DTLB_MISS) {
diff --git a/target/hppa/op_helper.c b/target/hppa/op_helper.c
index 7f79196fff..744325969f 100644
--- a/target/hppa/op_helper.c
+++ b/target/hppa/op_helper.c
@@ -334,7 +334,7 @@ target_ulong HELPER(probe)(CPUHPPAState *env, target_ulong addr,
     }
 
     mmu_idx = PRIV_P_TO_MMU_IDX(level, env->psw & PSW_P);
-    excp = hppa_get_physical_address(env, addr, mmu_idx, 0, &phys, &prot);
+    excp = hppa_get_physical_address(env, addr, mmu_idx, 0, 0, &phys, &prot);
     if (excp >= 0) {
         cpu_restore_state(env_cpu(env), GETPC());
         hppa_set_ior_and_isr(env, addr, MMU_IDX_MMU_DISABLED(mmu_idx));
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index ff227a8c5c..0d30191482 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -7831,6 +7831,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
 
     mce_init(cpu);
 
+    x86_cpu_gdb_init(cs);
     qemu_init_vcpu(cs);
 
     /*
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 9c39384ac0..4c63e7b045 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -2226,6 +2226,7 @@ void x86_cpu_dump_state(CPUState *cs, FILE *f, int flags);
 
 int x86_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg);
 int x86_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
+void x86_cpu_gdb_init(CPUState *cs);
 
 void x86_cpu_list(void);
 int cpu_x86_support_mca_broadcast(CPUX86State *env);
diff --git a/target/i386/gdbstub.c b/target/i386/gdbstub.c
index 4acf485879..04c49e802d 100644
--- a/target/i386/gdbstub.c
+++ b/target/i386/gdbstub.c
@@ -18,8 +18,13 @@
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "qemu/osdep.h"
+#include "accel/tcg/vcpu-state.h"
 #include "cpu.h"
+#include "exec/gdbstub.h"
 #include "gdbstub/helpers.h"
+#ifdef CONFIG_LINUX_USER
+#include "linux-user/qemu.h"
+#endif
 
 #ifdef TARGET_X86_64
 static const int gpr_map[16] = {
@@ -96,6 +101,19 @@ static int gdb_write_reg_cs64(uint32_t hflags, uint8_t *buf, target_ulong *val)
     return 4;
 }
 
+static int gdb_get_reg(CPUX86State *env, GByteArray *mem_buf, target_ulong val)
+{
+    if (TARGET_LONG_BITS == 64) {
+        if (env->hflags & HF_CS64_MASK) {
+            return gdb_get_reg64(mem_buf, val);
+        } else {
+            return gdb_get_reg64(mem_buf, val & 0xffffffffUL);
+        }
+    } else {
+        return gdb_get_reg32(mem_buf, val);
+    }
+}
+
 int x86_cpu_gdb_read_register(CPUState *cs, GByteArray *mem_buf, int n)
 {
     X86CPU *cpu = X86_CPU(cs);
@@ -137,15 +155,7 @@ int x86_cpu_gdb_read_register(CPUState *cs, GByteArray *mem_buf, int n)
     } else {
         switch (n) {
         case IDX_IP_REG:
-            if (TARGET_LONG_BITS == 64) {
-                if (env->hflags & HF_CS64_MASK) {
-                    return gdb_get_reg64(mem_buf, env->eip);
-                } else {
-                    return gdb_get_reg64(mem_buf, env->eip & 0xffffffffUL);
-                }
-            } else {
-                return gdb_get_reg32(mem_buf, env->eip);
-            }
+            return gdb_get_reg(env, mem_buf, env->eip);
         case IDX_FLAGS_REG:
             return gdb_get_reg32(mem_buf, env->eflags);
 
@@ -248,6 +258,21 @@ static int x86_cpu_gdb_load_seg(X86CPU *cpu, X86Seg sreg, uint8_t *mem_buf)
     return 4;
 }
 
+static int gdb_write_reg(CPUX86State *env, uint8_t *mem_buf, target_ulong *val)
+{
+    if (TARGET_LONG_BITS == 64) {
+        if (env->hflags & HF_CS64_MASK) {
+            *val = ldq_p(mem_buf);
+        } else {
+            *val = ldq_p(mem_buf) & 0xffffffffUL;
+        }
+        return 8;
+    } else {
+        *val = (uint32_t)ldl_p(mem_buf);
+        return 4;
+    }
+}
+
 int x86_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
 {
     X86CPU *cpu = X86_CPU(cs);
@@ -288,18 +313,7 @@ int x86_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
     } else {
         switch (n) {
         case IDX_IP_REG:
-            if (TARGET_LONG_BITS == 64) {
-                if (env->hflags & HF_CS64_MASK) {
-                    env->eip = ldq_p(mem_buf);
-                } else {
-                    env->eip = ldq_p(mem_buf) & 0xffffffffUL;
-                }
-                return 8;
-            } else {
-                env->eip &= ~0xffffffffUL;
-                env->eip |= (uint32_t)ldl_p(mem_buf);
-                return 4;
-            }
+            return gdb_write_reg(env, mem_buf, &env->eip);
         case IDX_FLAGS_REG:
             env->eflags = ldl_p(mem_buf);
             return 4;
@@ -397,3 +411,49 @@ int x86_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
     /* Unrecognised register.  */
     return 0;
 }
+
+#ifdef CONFIG_LINUX_USER
+
+#define IDX_ORIG_AX 0
+
+static int x86_cpu_gdb_read_linux_register(CPUState *cs, GByteArray *mem_buf,
+                                           int n)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    CPUX86State *env = &cpu->env;
+
+    switch (n) {
+    case IDX_ORIG_AX:
+        return gdb_get_reg(env, mem_buf, get_task_state(cs)->orig_ax);
+    }
+    return 0;
+}
+
+static int x86_cpu_gdb_write_linux_register(CPUState *cs, uint8_t *mem_buf,
+                                            int n)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    CPUX86State *env = &cpu->env;
+
+    switch (n) {
+    case IDX_ORIG_AX:
+        return gdb_write_reg(env, mem_buf, &get_task_state(cs)->orig_ax);
+    }
+    return 0;
+}
+
+#endif
+
+void x86_cpu_gdb_init(CPUState *cs)
+{
+#ifdef CONFIG_LINUX_USER
+    gdb_register_coprocessor(cs, x86_cpu_gdb_read_linux_register,
+                             x86_cpu_gdb_write_linux_register,
+#ifdef TARGET_X86_64
+                             gdb_find_static_feature("i386-64bit-linux.xml"),
+#else
+                             gdb_find_static_feature("i386-32bit-linux.xml"),
+#endif
+                             0);
+#endif
+}
diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c
index 333469b268..50d8537a3b 100644
--- a/target/mips/tcg/translate.c
+++ b/target/mips/tcg/translate.c
@@ -15362,7 +15362,8 @@ static void mips_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
      * hardware does (e.g. if a delay slot instruction faults, the
      * reported PC is the PC of the branch).
      */
-    if (ctx->base.singlestep_enabled && (ctx->hflags & MIPS_HFLAG_BMASK)) {
+    if ((tb_cflags(ctx->base.tb) & CF_SINGLE_STEP) &&
+        (ctx->hflags & MIPS_HFLAG_BMASK)) {
         ctx->base.max_insns = 2;
     }
 
@@ -15445,7 +15446,7 @@ static void mips_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs)
      * together with its delay slot.
      */
     if (ctx->base.pc_next - ctx->page_start >= TARGET_PAGE_SIZE
-        && !ctx->base.singlestep_enabled) {
+        && !(tb_cflags(ctx->base.tb) & CF_SINGLE_STEP)) {
         ctx->base.is_jmp = DISAS_TOO_MANY;
     }
 }
diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c
index 75b7bfda4c..f4da4a40f9 100644
--- a/target/xtensa/translate.c
+++ b/target/xtensa/translate.c
@@ -521,7 +521,7 @@ static MemOp gen_load_store_alignment(DisasContext *dc, MemOp mop,
         mop |= MO_ALIGN;
     }
     if (!option_enabled(dc, XTENSA_OPTION_UNALIGNED_EXCEPTION)) {
-        tcg_gen_andi_i32(addr, addr, ~0 << get_alignment_bits(mop));
+        tcg_gen_andi_i32(addr, addr, ~0 << memop_alignment_bits(mop));
     }
     return mop;
 }