You copied the Doc URL to your clipboard.

CPSR, Current Program Status Register

The CPSR characteristics are:

Purpose

Holds PE status and control information.

Configuration

Some or all RW fields of this register have defined reset values. These apply only if the PE resets into an Exception level that is using AArch32. Otherwise, RW fields in this register reset to architecturally UNKNOWN values.

Attributes

CPSR is a 32-bit register.

Field descriptions

The CPSR bit assignments are:

313029282726252423222120191817161514131211109876543210
NZCVQRES0SSBSPANDITRES0GERES0EAIFRES0RES1M

N, bit [31]

Negative condition flag. Set to bit[31] of the result of the last flag-setting instruction. If the result is regarded as a two's complement signed integer, then N is set to 1 if the result was negative, and N is set to 0 if the result was positive or zero.

Z, bit [30]

Zero condition flag. Set to 1 if the result of the last flag-setting instruction was zero, and to 0 otherwise. A result of zero often indicates an equal result from a comparison.

C, bit [29]

Carry condition flag. Set to 1 if the last flag-setting instruction resulted in a carry condition, for example an unsigned overflow on an addition.

V, bit [28]

Overflow condition flag. Set to 1 if the last flag-setting instruction resulted in an overflow condition, for example a signed overflow on an addition.

Q, bit [27]

Cumulative saturation bit. Set to 1 to indicate that overflow or saturation occurred in some instructions.

Bits [26:24]

Reserved, RES0.

SSBS, bit [23]

When ARMv8.0-SSBS is implemented:

Speculative Store Bypass Safe.

Prohibits speculative loads or stores which might practically allow a cache timing side channel.

A cache timing side channel might be exploited where a load or store uses an address that is derived from a register that is being loaded from memory using a load instruction speculatively read from a memory location. If PSTATE.SSBS is enabled, the address derived from the load instruction might be from earlier in the coherence order than the lastest store to that memory location with the same virtual address.

SSBSMeaning
0b0

Hardware is not permitted to load or store speculatively in the manner described.

0b1

Hardware is permitted to load or store speculatively in the manner described.

The value of this bit is usually set to the value described by the SCTLR.DSSBS bit on exceptions to any mode except Hyp mode, and the value described by HSCTLR.DSSBS on exceptions to Hyp mode.

This field resets to an IMPLEMENTATION DEFINED value.


Otherwise:

Reserved, RES0.

PAN, bit [22]

When ARMv8.1-PAN is implemented:

Privileged Access Never.

PANMeaning
0b0

The translation system is the same as Armv8.0.

0b1

Disables privileged read and write accesses to addresses accessible at EL0.

The value of this bit is usually preserved on taking an exception, except in the following situations:

  • When the target of the exception is EL1, and the value of the SCTLR.SPAN bit for the current Security state is 0, this bit is set to 1.
  • When the target of the exception is EL3, from Secure state, and the value of the Secure SCTLR.SPAN is 0, this bit is set to 1.
  • When the target of the exception is EL3, from Non-secure state, this bit is set to 0 regardless of the value of the Secure SCTLR.SPAN bit.


Otherwise:

Reserved, RES0.

DIT, bit [21]

When ARMv8.4-DIT is implemented:

Data Independent Timing.

DITMeaning
0b0

The architecture makes no statement about the timing properties of any instructions.

0b1

The architecture requires that:

  • The timing of every load and store instruction is insensitive to the value of the data being loaded or stored.

  • For certain data processing instructions, the instruction takes a time which is independent of:

    • The values of the data supplied in any of its registers.

    • The values of the NZCV flags.

  • For certain data processing instructions, the response of the instruction to asynchronous exceptions does not vary based on:

    • The values of the data supplied in any of its registers.

    • The values of the NZCV flags.

The data processing instructions affected by this bit are:

  • All cryptographic instructions. These instructions are:

    • AESD, AESE, AESIMC, AESMC, SHA1C, SHA1H, SHA1M, SHA1P, SHA1SU0, SHA1SU1, SHA256H, SHA256H2, SHA256SU0, and SHA256SU1.

  • A subset of those instructions which use the general-purpose register file. For these instructions, the effects of CPSR.DIT apply only if they do not use R15 as either their source or destination and pass their condition execution check. The instructions are:

    • BFI, BFC, CLZ, CMN, CMP, MLA, MLAS, MLS, MOVT, MUL, MULS, NOP, PKHBT, PKHTB, RBIT, REV, REV16, REVSH, RRX, SADD16, SADD8, SASX, SBFX, SHADD16, SHADD8, SHASX, SHSAX, SHSUB16, SHSUB8, SMLAL**, SMLAW*, SMLSD*, SMMLA*, SMMLS*, SMMUL*, SMUAD*, SMUL*, SSAX, SSUB16, SSUB8, SXTAB*, SXTAH, SXTB*, SXTH, TEQ, TST, UADD*, UASX, UBFX, UHADD*, UHASX, UHSAX, UHSUB*, UMAAL, UMLAL, UMLALS, UMULL, UMULLS, USADA8, USAX, USUB*, UXTAB*, UXTAH, UXTB*, UXTH, ADC (register-shifted register), ADCS (register-shifted register), ADD (register-shifted register), ADDS (register-shifted register), AND (register-shifted register), ANDS (register-shifted register), ASR (register-shifted register), ASRS (register-shifted register), BIC (register-shifted register), BICS (register-shifted register), EOR (register-shifted register), EORS (register-shifted register), LSL (register-shifted register), LSLS (register-shifted register), LSR (register-shifted register), LSRS (register-shifted register), MOV (register-shifted register), MOVS (register-shifted register), MVN (register-shifted register), MVNS (register-shifted register), ORR (register-shifted register), ORRS (register-shifted register), ROR (register-shifted register), RORS (register-shifted register), RSB (register-shifted register), RSBS (register-shifted register), RSC (register-shifted register), RSCS (register-shifted register), SBC (register-shifted register), SBCS (register-shifted register), SUB (register-shifted register), and SUBS (register-shifted register).

  • A subset of those instructions which use the general-purpose register file. For these instructions, the effects of CPSR.DIT apply only if they do not use R15 as either their source or destination. The effects of CPSR.DIT do not depend on these instructions passing their condition execution check. These instructions are:

    • ADC (immediate), ADC (register), ADCS (immediate), ADCS (register), ADD (immediate), ADD (register), ADDS (immediate), ADDS (register), AND (immediate), AND (register), ANDS (immediate), ANDS (register), ASR (immediate), ASR (register), ASRS (immediate), ASRS (register), BIC (immediate), BIC (register), BICS (immediate), BICS (register), EOR (immediate), EOR (register), EORS (immediate), EORS (register), LSL (immediate), LSL (register), LSLS (immediate), LSLS (register), LSR (immediate), LSR (register), LSRS (immediate), LSRS (register), MOV (immediate), MOV (register), MOVS (immediate), MOVS (register), MVN (immediate), MVN (register), MVNS (immediate), MVNS (register), ORR (immediate), ORR (register), ORRS (immediate), ORRS (register), ROR (immediate), ROR (register), RORS (immediate), RORS (register), RSB (immediate), RSB (register), RSBS (immediate), RSBS (register), RSC (immediate), RSC (register), RSCS (immediate), RSCS (register), SBC (immediate), SBC (register), SBCS (immediate), SBCS (register), SUB (immediate), SUB (register), SUBS (immediate), and SUBS (register).

  • A subset of those instructions which use the SIMD&FP register file. For these instructions, the effects of CPSR.DIT apply only if they pass their condition execution check. These instructions are:

    • CRC32B, CRC32H, CRC32W, CRC32CB, CRC32CH, CRC32CW, VABA*, VABD*, VABS, VACGE, VACGT, VACLE, VACLT, VADD (integer), VADDHN, VADDL, VADDW, VAND, VBIC, VBIF, VBIT, VBSL, VCGE, VCGT, VCLE, VCLS, VCLT, VCLZ, VCMP, VCMPE, VCNT, VDUP, VEOR, VEXT, VHADD, VHSUB, VMAX (integer), VMIN (integer), VMLA (integer), VMLAL, VMLS (integer), VMLSL, VMOV, VMOVL, VMOVN, VMUL (integer and polynomial), VMULL (integer and polynomial), VMVN, VNEG, VORN, VORR, VPADAL, VPADD (integer), VPADDL, VPMAX (integer), VPMIN (integer), VRADDHN, VREV*, VRHADD, VRSHL, VRSHR, VRSHRN, VRSRA, VRSUBHN, VSELEQ, VSELGE, VSELGT, VSELVS, VSHL, VSHLL, VSHR, VSLI, VSRA, VSRI, VSUB (integer), VSUBHN, VSUBL, VSUBW, VSWP, VTBL, VTBX, VTRN, VTST, VUZP, and VZIP

This field resets to 0.


Otherwise:

Reserved, RES0.

Bit [20]

Reserved, RES0.

GE, bits [19:16]

Greater than or Equal flags, for parallel addition and subtraction.

Bits [15:10]

Reserved, RES0.

E, bit [9]

Endianness state bit. Controls the load and store endianness for data accesses:

EMeaning
0b0

Little-endian operation

0b1

Big-endian operation.

Instruction fetches ignore this bit.

If an implementation does not provide Big-endian support, this bit is RES0. If it does not provide Little-endian support, this bit is RES1.

If an implementation provides Big-endian support but only at EL0, this bit is RES0 for an exception return to any Exception level other than EL0.

Likewise, if it provides Little-endian support only at EL0, this bit is RES1 for an exception return to any Exception level other than EL0.

When the reset value of the SCTLR.EE bit is defined by a configuration input signal, that value also applies to the CPSR.E bit on reset, and therefore applies to software execution from reset.

A, bit [8]

SError interrupt mask bit. The possible values of this bit are:

AMeaning
0b0

Exception not masked.

0b1

Exception masked.

I, bit [7]

IRQ mask bit. The possible values of this bit are:

IMeaning
0b0

Exception not masked.

0b1

Exception masked.

F, bit [6]

FIQ mask bit. The possible values of this bit are:

FMeaning
0b0

Exception not masked.

0b1

Exception masked.

Bit [5]

Reserved, RES0.

Bit [4]

Reserved, RES1.

M, bits [3:0]

Current PE mode. Possible values are:

MMeaning
0b0000

User.

0b0001

FIQ.

0b0010

IRQ.

0b0011

Supervisor.

0b0110

Monitor.

0b0111

Abort.

0b1010

Hyp.

0b1011

Undefined.

0b1111

System.

Accessing the CPSR

CPSR can be read using the MRS instruction and written using the MSR (register) or MSR (immediate) instructions. For more details, see MRS, MSR (register), and MSR (immediate) in the Arm® Architecture Reference Manual, Armv8, for Armv8-A architecture profile.



Previous Next
Was this page helpful? Yes No