arm: add DCZID_EL0 to idregs array
PATCH v2 1/1 arm: add DCZID_EL0 to idregs array
This requires a bit of care, since we still have to handle the EL specific part (DCZID_EL0.DZP). Callers can set/access dcz_blocksize via a wrapper working on DCZID_EL.BS.
KVM currently does not support DCZID_EL0 via ONE_REG, assert that we're not trying to do anything with it until it does.
---
Changes v1 -> v2:
- use extract64/deposit64, tweak helper names
- assert that we're not using the reg while running under kvm, instead of providing an incorrect dummy value
--- target/arm/cpu-sysregs.h.inc | 1 + target/arm/cpu.c | 2 +- target/arm/cpu.h | 14 ++++++++++++-- target/arm/cpu64.c | 4 ++-- target/arm/helper.c | 5 ++++- target/arm/tcg/cpu64.c | 22 +++++++++++----------- target/arm/tcg/helper-a64.c | 2 +- target/arm/tcg/mte_helper.c | 4 ++-- target/arm/tcg/translate-a64.c | 2 +- target/arm/tcg/translate.h | 2 +- 10 files changed, 36 insertions(+), 22 deletions(-)
target/arm/cpu-sysregs.h.inc +1 -0
@@ -39,3 +39,4 @@ DEF(ID_MMFR5_EL1, 3, 0, 0, 3, 6) DEF(CLIDR_EL1, 3, 1, 0, 0, 1) DEF(ID_AA64ZFR0_EL1, 3, 0, 0, 4, 4) DEF(CTR_EL0, 3, 3, 0, 0, 1) +DEF(DCZID_EL0, 3, 3, 0, 0, 7)
target/arm/cpu.c +1 -1
@@ -2184,7 +2184,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)#endif if (tcg_enabled ()) { -int dcz_blocklen =4 << cpu->dcz_blocksize; +int dcz_blocklen =4 <<get_dczid_bs (cpu);/* * We only support DCZ blocklen that fits on one page.
target/arm/cpu.h +12 -2
@@ -1111,8 +1111,6 @@ struct ArchCPU {bool prop_pauth_qarma5;bool prop_lpa2; -/* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ -uint8_t dcz_blocksize;/* GM blocksize, in log_2(words), ie low 4 bits of GMID_EL0 */ uint8_t gm_blocksize;
@@ -1178,6 +1176,18 @@ struct ARMCPUClass {ResettablePhases parent_phases; }; +static inline uint8_t get_dczid_bs (ARMCPU *cpu) +{ +return extract64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 ); +} + +static inline void set_dczid_bs (ARMCPU *cpu,uint8_t bs) +{ +/* keep dzp unchanged */ + cpu->isar.idregs[DCZID_EL0_IDX ] = +deposit64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 , bs); +} +/* Callback functions for the generic timer's timers. */ void arm_gt_ptimer_cb (void *opaque);void arm_gt_vtimer_cb (void *opaque);
target/arm/cpu64.c +2 -2
@@ -689,7 +689,7 @@ static void aarch64_a57_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,3 ,64 ,48 * KiB,2 );/* 2048KB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,64 ,2 * MiB,7 ); - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;
@@ -751,7 +751,7 @@ static void aarch64_a53_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,1 ,64 ,32 * KiB,2 );/* 1024KB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,64 ,1 * MiB,7 ); - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;
target/arm/helper.c +4 -1
@@ -3320,11 +3320,14 @@ static uint64_t aa64_dczid_read(CPUARMState *env, const ARMCPRegInfo *ri)ARMCPU *cpu =env_archcpu (env);int dzp_bit =1 <<4 ; +assert (!kvm_enabled ()); +/* DZP indicates whether DC ZVA access is allowed */ if (aa64_zva_access (env,NULL , false) ==CP_ACCESS_OK ) { dzp_bit =0 ; } -return cpu->dcz_blocksize | dzp_bit; + +return cpu->isar.idregs[DCZID_EL0_IDX ] | dzp_bit; } static CPAccessResult sp_el0_access(CPUARMState *env, const ARMCPRegInfo *ri,
target/arm/tcg/cpu64.c +11 -11
@@ -72,7 +72,7 @@ static void aarch64_a35_initfn(Object *obj)SET_IDREG (isar,ID_AA64MMFR0 ,0x00101122 );SET_IDREG (isar,ID_AA64MMFR1 ,0 );SET_IDREG (isar,CLIDR ,0x0a200023 ); - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );/* From B2.4 AArch64 Virtual Memory control registers */ cpu->reset_sctlr =0x00c50838 ;
@@ -219,7 +219,7 @@ static void aarch64_a55_initfn(Object *obj)/* Ordered by B2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x84448004 ;/* L1Ip = VIPT */ - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ SET_IDREG (isar,ID_AA64DFR0 ,0x0000000010305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0000100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000000100001ull );
@@ -325,7 +325,7 @@ static void aarch64_a72_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,3 ,64 ,48 * KiB,2 );/* 1MB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,64 ,1 * MiB,7 ); - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;
@@ -352,7 +352,7 @@ static void aarch64_a76_initfn(Object *obj)/* Ordered by B2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x8444C004 ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64DFR0 ,0x0000000010305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0000100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000000100001ull );
@@ -424,7 +424,7 @@ static void aarch64_a78ae_initfn(Object *obj)/* Ordered by 3.2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x9444c004 ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64DFR0 ,0x0000000110305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0010100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000001200031ull );
@@ -517,7 +517,7 @@ static void aarch64_a64fx_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,4 ,256 ,64 * KiB,2 );/* 8MB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,256 ,8 * MiB,7 ); - cpu->dcz_blocksize =6 ;/* 256 bytes */ +set_dczid_bs (cpu,6 );/* 256 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;
@@ -673,7 +673,7 @@ static void aarch64_neoverse_n1_initfn(Object *obj)/* Ordered by B2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x8444c004 ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64DFR0 ,0x0000000110305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0000100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000000100001ull );
@@ -749,7 +749,7 @@ static void aarch64_neoverse_v1_initfn(Object *obj)/* Ordered by 3.2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0xb444c004 ;/* With DIC and IDC set */ - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64AFR0 ,0x00000000 );SET_IDREG (isar,ID_AA64AFR1 ,0x00000000 );SET_IDREG (isar,ID_AA64DFR0 ,0x000001f210305519ull );
@@ -1011,7 +1011,7 @@ static void aarch64_a710_initfn(Object *obj)SET_IDREG (isar,CLIDR ,0x0000001482000023ull ); cpu->gm_blocksize =4 ; cpu->ctr =0x000000049444c004ull ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );/* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_0006_003f */ /* Section B.5.2: PMCR_EL0 */
@@ -1113,7 +1113,7 @@ static void aarch64_neoverse_n2_initfn(Object *obj)SET_IDREG (isar,CLIDR ,0x0000001482000023ull ); cpu->gm_blocksize =4 ; cpu->ctr =0x00000004b444c004ull ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );/* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_001e_01ff */ /* Section B.7.2: PMCR_EL0 */
@@ -1377,7 +1377,7 @@ void aarch64_max_tcg_initfn(Object *obj)* blocksize since we don't have to follow what the hardware does. */ cpu->ctr =0x80038003 ;/* 32 byte I and D cacheline size, VIPT icache */ - cpu->dcz_blocksize =7 ;/* 512 bytes */ +set_dczid_bs (cpu,7 );/* 512 bytes */ #endif cpu->gm_blocksize =6 ;/* 256 bytes */
target/arm/tcg/helper-a64.c +1 -1
@@ -792,7 +792,7 @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in)* (which matches the usual QEMU behaviour of not implementing either * alignment faults or any memory attribute handling). */ -int blocklen =4 <<env_archcpu (env)->dcz_blocksize; +int blocklen =4 <<get_dczid_bs (env_archcpu (env));uint64_t vaddr = vaddr_in & ~(blocklen -1 );int mmu_idx =arm_env_mmu_index (env);void *mem;
target/arm/tcg/mte_helper.c +2 -2
@@ -545,7 +545,7 @@ void HELPER(stzgm_tags)(CPUARMState *env, uint64_t ptr, uint64_t val)* i.e. 32 bytes, which is an unreasonably small dcz anyway, * to make sure that we can access one complete tag byte here. */ - log2_dcz_bytes =env_archcpu (env)->dcz_blocksize +2 ; + log2_dcz_bytes =get_dczid_bs (env_archcpu (env)) +2 ; log2_tag_bytes = log2_dcz_bytes - (LOG2_TAG_GRANULE +1 ); dcz_bytes = (intptr_t )1 << log2_dcz_bytes; tag_bytes = (intptr_t )1 << log2_tag_bytes;
@@ -945,7 +945,7 @@ uint64_t HELPER(mte_check_zva)(CPUARMState *env, uint32_t desc, uint64_t ptr)* i.e. 32 bytes, which is an unreasonably small dcz anyway, to make * sure that we can access one complete tag byte here. */ - log2_dcz_bytes =env_archcpu (env)->dcz_blocksize +2 ; + log2_dcz_bytes =get_dczid_bs (env_archcpu (env)) +2 ; log2_tag_bytes = log2_dcz_bytes - (LOG2_TAG_GRANULE +1 ); dcz_bytes = (intptr_t )1 << log2_dcz_bytes; tag_bytes = (intptr_t )1 << log2_tag_bytes;
target/arm/tcg/translate-a64.c +1 -1
@@ -10712,7 +10712,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->vec_stride =0 ; dc->cp_regs = arm_cpu->cp_regs; dc->features = env->features; - dc->dcz_blocksize = arm_cpu->dcz_blocksize; + dc->dcz_blocksize =get_dczid_bs (arm_cpu); dc->gm_blocksize = arm_cpu->gm_blocksize;#ifdef CONFIG_USER_ONLY
target/arm/tcg/translate.h +1 -1
@@ -193,7 +193,7 @@ typedef struct DisasContext {* < 0, set by the current instruction. */ int8_t btype; -/* A copy of cpu->dcz_blocksize. */ +/* A copy of DCZID_EL0.BS. */ uint8_t dcz_blocksize;/* A copy of cpu->gm_blocksize. */ uint8_t gm_blocksize;
Signature · 1 line
2.51.1
Quoted 8 lines · Cornelia Huck
This requires a bit of care, since we still have to handle the EL specific part (DCZID_EL0.DZP). Callers can set/access
dcz_blocksizevia a wrapper working on DCZID_EL.BS.KVM currently does not support
DCZID_EL0viaONE_REG, assert that we're not trying to do anything with it until it does.Signed-off-by Cornelia Huck <[email protected]>
Oh, it's been some time... the new year might be a good occasion for a friendly ping :)
Quoted 280 lines
---
Changes v1 -> v2:
- use extract64/deposit64, tweak helper names
- assert that we're not using the reg while running under kvm, instead of providing an incorrect dummy value--- target/arm/cpu-sysregs.h.inc | 1 + target/arm/cpu.c | 2 +- target/arm/cpu.h | 14 ++++++++++++-- target/arm/cpu64.c | 4 ++-- target/arm/helper.c | 5 ++++- target/arm/tcg/cpu64.c | 22 +++++++++++----------- target/arm/tcg/helper-a64.c | 2 +- target/arm/tcg/mte_helper.c | 4 ++-- target/arm/tcg/translate-a64.c | 2 +- target/arm/tcg/translate.h | 2 +- 10 files changed, 36 insertions(+), 22 deletions(-)target/arm/cpu-sysregs.h.inc +1
-0@@ -39,3 +39,4 @@ DEF(ID_MMFR5_EL1, 3, 0, 0, 3, 6) DEF(CLIDR_EL1, 3, 1, 0, 0, 1) DEF(ID_AA64ZFR0_EL1, 3, 0, 0, 4, 4) DEF(CTR_EL0, 3, 3, 0, 0, 1) +DEF(DCZID_EL0, 3, 3, 0, 0, 7)target/arm/cpu.c +1
-1@@ -2184,7 +2184,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)#endif if (tcg_enabled ()) { -int dcz_blocklen =4 << cpu->dcz_blocksize; +int dcz_blocklen =4 <<get_dczid_bs (cpu);/* * We only support DCZ blocklen that fits on one page. target/arm/cpu.h +12
-2@@ -1111,8 +1111,6 @@ struct ArchCPU {bool prop_pauth_qarma5;bool prop_lpa2; -/* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ -uint8_t dcz_blocksize;/* GM blocksize, in log_2(words), ie low 4 bits of GMID_EL0 */ uint8_t gm_blocksize;@@ -1178,6 +1176,18 @@ struct ARMCPUClass {ResettablePhases parent_phases; }; +static inline uint8_t get_dczid_bs (ARMCPU *cpu) +{ +return extract64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 ); +} + +static inline void set_dczid_bs (ARMCPU *cpu,uint8_t bs) +{ +/* keep dzp unchanged */ + cpu->isar.idregs[DCZID_EL0_IDX ] = +deposit64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 , bs); +} +/* Callback functions for the generic timer's timers. */ void arm_gt_ptimer_cb (void *opaque);void arm_gt_vtimer_cb (void *opaque);target/arm/cpu64.c +2
-2@@ -689,7 +689,7 @@ static void aarch64_a57_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,3 ,64 ,48 * KiB,2 );/* 2048KB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,64 ,2 * MiB,7 ); - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;@@ -751,7 +751,7 @@ static void aarch64_a53_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,1 ,64 ,32 * KiB,2 );/* 1024KB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,64 ,1 * MiB,7 ); - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;target/arm/helper.c +4
-1@@ -3320,11 +3320,14 @@ static uint64_t aa64_dczid_read(CPUARMState *env, const ARMCPRegInfo *ri)ARMCPU *cpu =env_archcpu (env);int dzp_bit =1 <<4 ; +assert (!kvm_enabled ()); +/* DZP indicates whether DC ZVA access is allowed */ if (aa64_zva_access (env,NULL , false) ==CP_ACCESS_OK ) { dzp_bit =0 ; } -return cpu->dcz_blocksize | dzp_bit; + +return cpu->isar.idregs[DCZID_EL0_IDX ] | dzp_bit; } static CPAccessResult sp_el0_access(CPUARMState *env, const ARMCPRegInfo *ri,target/arm/tcg/cpu64.c +11
-11@@ -72,7 +72,7 @@ static void aarch64_a35_initfn(Object *obj)SET_IDREG (isar,ID_AA64MMFR0 ,0x00101122 );SET_IDREG (isar,ID_AA64MMFR1 ,0 );SET_IDREG (isar,CLIDR ,0x0a200023 ); - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );/* From B2.4 AArch64 Virtual Memory control registers */ cpu->reset_sctlr =0x00c50838 ;@@ -219,7 +219,7 @@ static void aarch64_a55_initfn(Object *obj)/* Ordered by B2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x84448004 ;/* L1Ip = VIPT */ - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ SET_IDREG (isar,ID_AA64DFR0 ,0x0000000010305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0000100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000000100001ull );@@ -325,7 +325,7 @@ static void aarch64_a72_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,3 ,64 ,48 * KiB,2 );/* 1MB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,64 ,1 * MiB,7 ); - cpu->dcz_blocksize =4 ;/* 64 bytes */ +set_dczid_bs (cpu,4 );/* 64 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;@@ -352,7 +352,7 @@ static void aarch64_a76_initfn(Object *obj)/* Ordered by B2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x8444C004 ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64DFR0 ,0x0000000010305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0000100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000000100001ull );@@ -424,7 +424,7 @@ static void aarch64_a78ae_initfn(Object *obj)/* Ordered by 3.2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x9444c004 ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64DFR0 ,0x0000000110305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0010100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000001200031ull );@@ -517,7 +517,7 @@ static void aarch64_a64fx_initfn(Object *obj) cpu->ccsidr[1 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,4 ,256 ,64 * KiB,2 );/* 8MB L2 cache */ cpu->ccsidr[2 ] =make_ccsidr (CCSIDR_FORMAT_LEGACY ,16 ,256 ,8 * MiB,7 ); - cpu->dcz_blocksize =6 ;/* 256 bytes */ +set_dczid_bs (cpu,6 );/* 256 bytes */ cpu->gic_num_lrs =4 ; cpu->gic_vpribits =5 ; cpu->gic_vprebits =5 ;@@ -673,7 +673,7 @@ static void aarch64_neoverse_n1_initfn(Object *obj)/* Ordered by B2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0x8444c004 ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64DFR0 ,0x0000000110305408ull );SET_IDREG (isar,ID_AA64ISAR0 ,0x0000100010211120ull );SET_IDREG (isar,ID_AA64ISAR1 ,0x0000000000100001ull );@@ -749,7 +749,7 @@ static void aarch64_neoverse_v1_initfn(Object *obj)/* Ordered by 3.2.4 AArch64 registers by functional group */ SET_IDREG (isar,CLIDR ,0x82000023 ); cpu->ctr =0xb444c004 ;/* With DIC and IDC set */ - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );SET_IDREG (isar,ID_AA64AFR0 ,0x00000000 );SET_IDREG (isar,ID_AA64AFR1 ,0x00000000 );SET_IDREG (isar,ID_AA64DFR0 ,0x000001f210305519ull );@@ -1011,7 +1011,7 @@ static void aarch64_a710_initfn(Object *obj)SET_IDREG (isar,CLIDR ,0x0000001482000023ull ); cpu->gm_blocksize =4 ; cpu->ctr =0x000000049444c004ull ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );/* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_0006_003f */ /* Section B.5.2: PMCR_EL0 */ @@ -1113,7 +1113,7 @@ static void aarch64_neoverse_n2_initfn(Object *obj)SET_IDREG (isar,CLIDR ,0x0000001482000023ull ); cpu->gm_blocksize =4 ; cpu->ctr =0x00000004b444c004ull ; - cpu->dcz_blocksize =4 ; +set_dczid_bs (cpu,4 );/* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_001e_01ff */ /* Section B.7.2: PMCR_EL0 */ @@ -1377,7 +1377,7 @@ void aarch64_max_tcg_initfn(Object *obj)* blocksize since we don't have to follow what the hardware does. */ cpu->ctr =0x80038003 ;/* 32 byte I and D cacheline size, VIPT icache */ - cpu->dcz_blocksize =7 ;/* 512 bytes */ +set_dczid_bs (cpu,7 );/* 512 bytes */ #endif cpu->gm_blocksize =6 ;/* 256 bytes */ target/arm/tcg/helper-a64.c +1
-1@@ -792,7 +792,7 @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in)* (which matches the usual QEMU behaviour of not implementing either * alignment faults or any memory attribute handling). */ -int blocklen =4 <<env_archcpu (env)->dcz_blocksize; +int blocklen =4 <<get_dczid_bs (env_archcpu (env));uint64_t vaddr = vaddr_in & ~(blocklen -1 );int mmu_idx =arm_env_mmu_index (env);void *mem;target/arm/tcg/mte_helper.c +2
-2@@ -545,7 +545,7 @@ void HELPER(stzgm_tags)(CPUARMState *env, uint64_t ptr, uint64_t val)* i.e. 32 bytes, which is an unreasonably small dcz anyway, * to make sure that we can access one complete tag byte here. */ - log2_dcz_bytes =env_archcpu (env)->dcz_blocksize +2 ; + log2_dcz_bytes =get_dczid_bs (env_archcpu (env)) +2 ; log2_tag_bytes = log2_dcz_bytes - (LOG2_TAG_GRANULE +1 ); dcz_bytes = (intptr_t )1 << log2_dcz_bytes; tag_bytes = (intptr_t )1 << log2_tag_bytes;@@ -945,7 +945,7 @@ uint64_t HELPER(mte_check_zva)(CPUARMState *env, uint32_t desc, uint64_t ptr)* i.e. 32 bytes, which is an unreasonably small dcz anyway, to make * sure that we can access one complete tag byte here. */ - log2_dcz_bytes =env_archcpu (env)->dcz_blocksize +2 ; + log2_dcz_bytes =get_dczid_bs (env_archcpu (env)) +2 ; log2_tag_bytes = log2_dcz_bytes - (LOG2_TAG_GRANULE +1 ); dcz_bytes = (intptr_t )1 << log2_dcz_bytes; tag_bytes = (intptr_t )1 << log2_tag_bytes;target/arm/tcg/translate-a64.c +1
-1@@ -10712,7 +10712,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->vec_stride =0 ; dc->cp_regs = arm_cpu->cp_regs; dc->features = env->features; - dc->dcz_blocksize = arm_cpu->dcz_blocksize; + dc->dcz_blocksize =get_dczid_bs (arm_cpu); dc->gm_blocksize = arm_cpu->gm_blocksize;#ifdef CONFIG_USER_ONLY target/arm/tcg/translate.h +1
-1@@ -193,7 +193,7 @@ typedef struct DisasContext {* < 0, set by the current instruction. */ int8_t btype; -/* A copy of cpu->dcz_blocksize. */ +/* A copy of DCZID_EL0.BS. */ uint8_t dcz_blocksize;/* A copy of cpu->gm_blocksize. */ uint8_t gm_blocksize;Signature · 1 line
2.51.1
Quoted 66 lines · Cornelia Huck
This requires a bit of care, since we still have to handle the EL specific part (DCZID_EL0.DZP). Callers can set/access
dcz_blocksizevia a wrapper working on DCZID_EL.BS.KVM currently does not support
DCZID_EL0viaONE_REG, assert that we're not trying to do anything with it until it does.Signed-off-by Cornelia Huck <[email protected]>---
Changes v1 -> v2:
- use extract64/deposit64, tweak helper names
- assert that we're not using the reg while running under kvm, instead of providing an incorrect dummy value--- target/arm/cpu-sysregs.h.inc | 1 + target/arm/cpu.c | 2 +- target/arm/cpu.h | 14 ++++++++++++-- target/arm/cpu64.c | 4 ++-- target/arm/helper.c | 5 ++++- target/arm/tcg/cpu64.c | 22 +++++++++++----------- target/arm/tcg/helper-a64.c | 2 +- target/arm/tcg/mte_helper.c | 4 ++-- target/arm/tcg/translate-a64.c | 2 +- target/arm/tcg/translate.h | 2 +- 10 files changed, 36 insertions(+), 22 deletions(-)target/arm/cpu-sysregs.h.inc +1
-0@@ -39,3 +39,4 @@ DEF(ID_MMFR5_EL1, 3, 0, 0, 3, 6) DEF(CLIDR_EL1, 3, 1, 0, 0, 1) DEF(ID_AA64ZFR0_EL1, 3, 0, 0, 4, 4) DEF(CTR_EL0, 3, 3, 0, 0, 1) +DEF(DCZID_EL0, 3, 3, 0, 0, 7)target/arm/cpu.c +1
-1@@ -2184,7 +2184,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)#endif if (tcg_enabled ()) { -int dcz_blocklen =4 << cpu->dcz_blocksize; +int dcz_blocklen =4 <<get_dczid_bs (cpu);/* * We only support DCZ blocklen that fits on one page. target/arm/cpu.h +1
-2@@ -1111,8 +1111,6 @@ struct ArchCPU {bool prop_pauth_qarma5;bool prop_lpa2; -/* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ -uint8_t dcz_blocksize;/* GM blocksize, in log_2(words), ie low 4 bits of GMID_EL0 */ uint8_t gm_blocksize;@@ -1178,6 +1176,18 @@ struct ARMCPUClass {ResettablePhases parent_phases; }; +static inline uint8_t get_dczid_bs (ARMCPU *cpu)
target/arm/cpu.h struct ARMCPUClass { · line 1189
Quoted 10 lines
target/arm/cpu.h +10
-0+{ +return extract64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 ); +} + +static inline void set_dczid_bs (ARMCPU *cpu,uint8_t bs) +{ +/* keep dzp unchanged */ + cpu->isar.idregs[DCZID_EL0_IDX ] = +deposit64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 , bs); +}
Given that dzp is always computed, I don't see the point of this. Or... is the point that KVM *will* eventually support DCZID_EL0, and we won't be computing DZP along the KVM trap-and-read path?
You could usefully split this patch, introducing the get/set helpers before changing the representation.
r~
Quoted 66 lines · Richard Henderson
Quoted 65 lines · Cornelia Huck
This requires a bit of care, since we still have to handle the EL specific part (DCZID_EL0.DZP). Callers can set/access
dcz_blocksizevia a wrapper working on DCZID_EL.BS.KVM currently does not support
DCZID_EL0viaONE_REG, assert that we're not trying to do anything with it until it does.Signed-off-by Cornelia Huck <[email protected]>---
Changes v1 -> v2:
- use extract64/deposit64, tweak helper names
- assert that we're not using the reg while running under kvm, instead of providing an incorrect dummy value--- target/arm/cpu-sysregs.h.inc | 1 + target/arm/cpu.c | 2 +- target/arm/cpu.h | 14 ++++++++++++-- target/arm/cpu64.c | 4 ++-- target/arm/helper.c | 5 ++++- target/arm/tcg/cpu64.c | 22 +++++++++++----------- target/arm/tcg/helper-a64.c | 2 +- target/arm/tcg/mte_helper.c | 4 ++-- target/arm/tcg/translate-a64.c | 2 +- target/arm/tcg/translate.h | 2 +- 10 files changed, 36 insertions(+), 22 deletions(-)target/arm/cpu-sysregs.h.inc +1
-0@@ -39,3 +39,4 @@ DEF(ID_MMFR5_EL1, 3, 0, 0, 3, 6) DEF(CLIDR_EL1, 3, 1, 0, 0, 1) DEF(ID_AA64ZFR0_EL1, 3, 0, 0, 4, 4) DEF(CTR_EL0, 3, 3, 0, 0, 1) +DEF(DCZID_EL0, 3, 3, 0, 0, 7)target/arm/cpu.c +1
-1@@ -2184,7 +2184,7 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)#endif if (tcg_enabled ()) { -int dcz_blocklen =4 << cpu->dcz_blocksize; +int dcz_blocklen =4 <<get_dczid_bs (cpu);/* * We only support DCZ blocklen that fits on one page. target/arm/cpu.h +0
-2@@ -1111,8 +1111,6 @@ struct ArchCPU {bool prop_pauth_qarma5;bool prop_lpa2; -/* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ -uint8_t dcz_blocksize;/* GM blocksize, in log_2(words), ie low 4 bits of GMID_EL0 */ uint8_t gm_blocksize;@@ -1178,6 +1176,18 @@ struct ARMCPUClass {ResettablePhases parent_phases; };
Quoted 15 lines
target/arm/cpu.h struct ARMCPUClass { · line 1189
Quoted 11 lines
target/arm/cpu.h +11
-0+static inline uint8_t get_dczid_bs (ARMCPU *cpu) +{ +return extract64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 ); +} + +static inline void set_dczid_bs (ARMCPU *cpu,uint8_t bs) +{ +/* keep dzp unchanged */ + cpu->isar.idregs[DCZID_EL0_IDX ] = +deposit64 (cpu->isar.idregs[DCZID_EL0_IDX ],0 ,4 , bs); +}Given that dzp is always computed, I don't see the point of this. Or... is the point that KVM *will* eventually support
DCZID_EL0, and we won't be computing DZP along the KVM trap-and-read path?
The idea was to move all of the ID registers into the idregs array eventually, to be prepared for switching to an automatically generated cpu-sysregs.h.inc. (Still remaining after this patch are CCSIDR* and friends.) I'm not sure if KVM will support DCZID_EL0 anytime soon, but if that happens, it will be easier to integrate.
Quoted 3 lines
You could usefully split this patch, introducing the get/set helpers before changing the representation.
Can do that.