docs/system/arm/emulation.rst

   1 .. _Arm Emulation:
   2
   3 A-profile CPU architecture support
   4 ==================================
   5
   6 QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7 and
   7 Armv8 versions of the A-profile architecture. It also has support for
   8 the following architecture extensions:
   9
  10 - FEAT_AA32BF16 (AArch32 BFloat16 instructions)
  11 - FEAT_AA32HPD (AArch32 hierarchical permission disables)
  12 - FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions)
  13 - FEAT_AES (AESD and AESE instructions)
  14 - FEAT_BBM at level 2 (Translation table break-before-make levels)
  15 - FEAT_BF16 (AArch64 BFloat16 instructions)
  16 - FEAT_BTI (Branch Target Identification)
  17 - FEAT_CRC32 (CRC32 instructions)
  18 - FEAT_CSV2 (Cache speculation variant 2)
  19 - FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1)
  20 - FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2)
  21 - FEAT_CSV2_2 (Cache speculation variant 2, version 2)
  22 - FEAT_CSV3 (Cache speculation variant 3)
  23 - FEAT_DGH (Data gathering hint)
  24 - FEAT_DIT (Data Independent Timing instructions)
  25 - FEAT_DPB (DC CVAP instruction)
  26 - FEAT_Debugv8p2 (Debug changes for v8.2)
  27 - FEAT_Debugv8p4 (Debug changes for v8.4)
  28 - FEAT_DotProd (Advanced SIMD dot product instructions)
  29 - FEAT_DoubleFault (Double Fault Extension)
  30 - FEAT_E0PD (Preventing EL0 access to halves of address maps)
  31 - FEAT_EPAC (Enhanced pointer authentication)
  32 - FEAT_ETS (Enhanced Translation Synchronization)
  33 - FEAT_EVT (Enhanced Virtualization Traps)
  34 - FEAT_FCMA (Floating-point complex number instructions)
  35 - FEAT_FGT (Fine-Grained Traps)
  36 - FEAT_FHM (Floating-point half-precision multiplication instructions)
  37 - FEAT_FP16 (Half-precision floating-point data processing)
  38 - FEAT_FPAC (Faulting on AUT* instructions)
  39 - FEAT_FPACCOMBINE (Faulting on combined pointer authentication instructions)
  40 - FEAT_FRINTTS (Floating-point to integer instructions)
  41 - FEAT_FlagM (Flag manipulation instructions v2)
  42 - FEAT_FlagM2 (Enhancements to flag manipulation instructions)
  43 - FEAT_GTG (Guest translation granule size)
  44 - FEAT_HAFDBS (Hardware management of the access flag and dirty bit state)
  45 - FEAT_HBC (Hinted conditional branches)
  46 - FEAT_HCX (Support for the HCRX_EL2 register)
  47 - FEAT_HPDS (Hierarchical permission disables)
  48 - FEAT_HPDS2 (Translation table page-based hardware attributes)
  49 - FEAT_HPMN0 (Setting of MDCR_EL2.HPMN to zero)
  50 - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions)
  51 - FEAT_IDST (ID space trap handling)
  52 - FEAT_IESB (Implicit error synchronization event)
  53 - FEAT_JSCVT (JavaScript conversion instructions)
  54 - FEAT_LOR (Limited ordering regions)
  55 - FEAT_LPA (Large Physical Address space)
  56 - FEAT_LPA2 (Large Physical and virtual Address space v2)
  57 - FEAT_LRCPC (Load-acquire RCpc instructions)
  58 - FEAT_LRCPC2 (Load-acquire RCpc instructions v2)
  59 - FEAT_LSE (Large System Extensions)
  60 - FEAT_LSE2 (Large System Extensions v2)
  61 - FEAT_LVA (Large Virtual Address space)
  62 - FEAT_MOPS (Standardization of memory operations)
  63 - FEAT_MTE (Memory Tagging Extension)
  64 - FEAT_MTE2 (Memory Tagging Extension)
  65 - FEAT_MTE3 (MTE Asymmetric Fault Handling)
  66 - FEAT_PACIMP (Pointer authentication - IMPLEMENTATION DEFINED algorithm)
  67 - FEAT_PACQARMA3 (Pointer authentication - QARMA3 algorithm)
  68 - FEAT_PACQARMA5 (Pointer authentication - QARMA5 algorithm)
  69 - FEAT_PAN (Privileged access never)
  70 - FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN)
  71 - FEAT_PAN3 (Support for SCTLR_ELx.EPAN)
  72 - FEAT_PAuth (Pointer authentication)
  73 - FEAT_PAuth2 (Enhancements to pointer authentication)
  74 - FEAT_PMULL (PMULL, PMULL2 instructions)
  75 - FEAT_PMUv3p1 (PMU Extensions v3.1)
  76 - FEAT_PMUv3p4 (PMU Extensions v3.4)
  77 - FEAT_PMUv3p5 (PMU Extensions v3.5)
  78 - FEAT_RAS (Reliability, availability, and serviceability)
  79 - FEAT_RASv1p1 (RAS Extension v1.1)
  80 - FEAT_RDM (Advanced SIMD rounding double multiply accumulate instructions)
  81 - FEAT_RME (Realm Management Extension) (NB: support status in QEMU is experimental)
  82 - FEAT_RNG (Random number generator)
  83 - FEAT_S2FWB (Stage 2 forced Write-Back)
  84 - FEAT_SB (Speculation Barrier)
  85 - FEAT_SEL2 (Secure EL2)
  86 - FEAT_SHA1 (SHA1 instructions)
  87 - FEAT_SHA256 (SHA256 instructions)
  88 - FEAT_SHA3 (Advanced SIMD SHA3 instructions)
  89 - FEAT_SHA512 (Advanced SIMD SHA512 instructions)
  90 - FEAT_SM3 (Advanced SIMD SM3 instructions)
  91 - FEAT_SM4 (Advanced SIMD SM4 instructions)
  92 - FEAT_SME (Scalable Matrix Extension)
  93 - FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode)
  94 - FEAT_SME_F64F64 (Double-precision floating-point outer product instructions)
  95 - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions)
  96 - FEAT_SPECRES (Speculation restriction instructions)
  97 - FEAT_SSBS (Speculative Store Bypass Safe)
  98 - FEAT_TIDCP1 (EL0 use of IMPLEMENTATION DEFINED functionality)
  99 - FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain)
 100 - FEAT_TLBIRANGE (TLB invalidate range instructions)
 101 - FEAT_TTCNP (Translation table Common not private translations)
 102 - FEAT_TTL (Translation Table Level)
 103 - FEAT_TTST (Small translation tables)
 104 - FEAT_UAO (Unprivileged Access Override control)
 105 - FEAT_VHE (Virtualization Host Extensions)
 106 - FEAT_VMID16 (16-bit VMID)
 107 - FEAT_XNX (Translation table stage 2 Unprivileged Execute-never)
 108 - SVE (The Scalable Vector Extension)
 109 - SVE2 (The Scalable Vector Extension v2)
 110
 111 For information on the specifics of these extensions, please refer
 112 to the `Armv8-A Arm Architecture Reference Manual
 113 <https://developer.arm.com/documentation/ddi0487/latest>`_.
 114
 115 When a specific named CPU is being emulated, only those features which
 116 are present in hardware for that CPU are emulated. (If a feature is
 117 not in the list above then it is not supported, even if the real
 118 hardware should have it.) The ``max`` CPU enables all features.
 119
 120 R-profile CPU architecture support
 121 ==================================
 122
 123 QEMU's TCG emulation support for R-profile CPUs is currently limited.
 124 We emulate only the Cortex-R5 and Cortex-R5F CPUs.
 125
 126 M-profile CPU architecture support
 127 ==================================
 128
 129 QEMU's TCG emulation includes support for Armv6-M, Armv7-M, Armv8-M, and
 130 Armv8.1-M versions of the M-profile architucture.  It also has support
 131 for the following architecture extensions:
 132
 133 - FP (Floating-point Extension)
 134 - FPCXT (FPCXT access instructions)
 135 - HP (Half-precision floating-point instructions)
 136 - LOB (Low Overhead loops and Branch future)
 137 - M (Main Extension)
 138 - MPU (Memory Protection Unit Extension)
 139 - PXN (Privileged Execute Never)
 140 - RAS (Reliability, Serviceability and Availability): "minimum RAS Extension" only
 141 - S (Security Extension)
 142 - ST (System Timer Extension)
 143
 144 For information on the specifics of these extensions, please refer
 145 to the `Armv8-M Arm Architecture Reference Manual
 146 <https://developer.arm.com/documentation/ddi0553/latest>`_.
 147
 148 When a specific named CPU is being emulated, only those features which
 149 are present in hardware for that CPU are emulated. (If a feature is
 150 not in the list above then it is not supported, even if the real
 151 hardware should have it.) There is no equivalent of the ``max`` CPU for
 152 M-profile.