From: Marc Zyngier maz@kernel.org

Add a bit of documentation for KVM_EXIT_ARM_LDST64B so that userspace knows what to expect.

Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Yicong Yang yangyicong@hisilicon.com --- Documentation/virt/kvm/api.rst | 43 ++++++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 7 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 43ed57e048a8..dae6a31025e1 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1300,12 +1300,13 @@ userspace, for example because of missing instruction syndrome decode information or because there is no device mapped at the accessed IPA, then userspace can ask the kernel to inject an external abort using the address from the exiting fault on the VCPU. It is a programming error to set -ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or -KVM_EXIT_ARM_NISV. This feature is only available if the system supports -KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in -how userspace reports accesses for the above cases to guests, across different -userspace implementations. Nevertheless, userspace can still emulate all Arm -exceptions by manipulating individual registers using the KVM_SET_ONE_REG API. +ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO, +KVM_EXIT_ARM_NISV, or KVM_EXIT_ARM_LDST64B. This feature is only available if +the system supports KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which +provides commonality in how userspace reports accesses for the above cases to +guests, across different userspace implementations. Nevertheless, userspace +can still emulate all Arm exceptions by manipulating individual registers +using the KVM_SET_ONE_REG API.

See KVM_GET_VCPU_EVENTS for the data structure.

@@ -7002,12 +7003,14 @@ in send_page or recv a buffer to recv_page).

::

- /* KVM_EXIT_ARM_NISV */ + /* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */ struct { __u64 esr_iss; __u64 fault_ipa; } arm_nisv;

+- KVM_EXIT_ARM_NISV: + Used on arm64 systems. If a guest accesses memory not in a memslot, KVM will typically return to userspace and ask it to do MMIO emulation on its behalf. However, for certain classes of instructions, no instruction decode @@ -7041,6 +7044,32 @@ Note that although KVM_CAP_ARM_NISV_TO_USER will be reported if queried outside of a protected VM context, the feature will not be exposed if queried on a protected VM file descriptor.

+- KVM_EXIT_ARM_LDST64B: + +Used on arm64 systems. When a guest using a LD64B, ST64B, ST64BV, ST64BV0, +outside of a memslot, KVM will return to userspace with KVM_EXIT_ARM_LDST64B, +exposing the relevant ESR_EL2 information and faulting IPA, similarly to +KVM_EXIT_ARM_NISV. + +Userspace is supposed to fully emulate the instructions, which includes: + + - fetch of the operands for a store, including ACCDATA_EL1 in the case + of a ST64BV0 instruction + - deal with the endianness if the guest is big-endian + - emulate the access, including the delivery of an exception if the + access didn't succeed + - provide a return value in the case of ST64BV/ST64BV0 + - return the data in the case of a load + - increment PC if the instruction was successfully executed + +Note that there is no expectation of performance for this emulation, as it +involves a large number of interaction with the guest state. It is, however, +expected that the instruction's semantics are preserved, specially the +single-copy atomicity property of the 64 byte access. + +This exit reason must be handled if userspace sets ID_AA64ISAR1_EL1.LS64 to a +non-zero value, indicating that FEAT_LS64* is enabled. + ::

/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */

From: Yicong Yang yangyicong@hisilicon.com

Instructions introduced by FEAT_{LS64, LS64_V} is controlled by HCRX_EL2.{EnALS, EnASR}. Configure all of these to allow usage at EL0/1.

This doesn't mean these instructions are always available in EL0/1 if provided. The hypervisor still have the control at runtime.

Signed-off-by: Yicong Yang yangyicong@hisilicon.com --- arch/arm64/include/asm/el2_setup.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 9f38340d24c2..46e085af7c98 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -57,9 +57,19 @@ /* Enable GCS if supported */ mrs_s x1, SYS_ID_AA64PFR1_EL1 ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4 - cbz x1, .Lset_hcrx_@ + cbz x1, .Lskip_gcs_hcrx_@ orr x0, x0, #HCRX_EL2_GCSEn

+.Lskip_gcs_hcrx_@: + /* Enable LS64, LS64_V if supported */ + mrs_s x1, SYS_ID_AA64ISAR1_EL1 + ubfx x1, x1, #ID_AA64ISAR1_EL1_LS64_SHIFT, #4 + cbz x1, .Lset_hcrx_@ + orr x0, x0, #HCRX_EL2_EnALS + cmp x1, #ID_AA64ISAR1_EL1_LS64_LS64_V + b.lt .Lset_hcrx_@ + orr x0, x0, #HCRX_EL2_EnASR + .Lset_hcrx_@: msr_s SYS_HCRX_EL2, x0 .Lskip_hcrx_@:

From: Yicong Yang yangyicong@hisilicon.com

Armv8.7 introduces single-copy atomic 64-byte loads and stores instructions and its variants named under FEAT_{LS64, LS64_V}. These features are identified by ID_AA64ISAR1_EL1.LS64 and the use of such instructions in userspace (EL0) can be trapped. In order to support the use of corresponding instructions in userspace: - Make ID_AA64ISAR1_EL1.LS64 visbile to userspace - Add identifying and enabling in the cpufeature list - Expose these support of these features to userspace through HWCAP3 and cpuinfo

Signed-off-by: Yicong Yang yangyicong@hisilicon.com --- Documentation/arch/arm64/booting.rst | 12 ++++++ Documentation/arch/arm64/elf_hwcaps.rst | 6 +++ arch/arm64/include/asm/hwcap.h | 2 + arch/arm64/include/uapi/asm/hwcap.h | 2 + arch/arm64/kernel/cpufeature.c | 51 +++++++++++++++++++++++++ arch/arm64/kernel/cpuinfo.c | 2 + arch/arm64/tools/cpucaps | 2 + 7 files changed, 77 insertions(+)

diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst index ee9b790c0d72..837823d49212 100644 --- a/Documentation/arch/arm64/booting.rst +++ b/Documentation/arch/arm64/booting.rst @@ -483,6 +483,18 @@ Before jumping into the kernel, the following conditions must be met:

- MDCR_EL3.TPM (bit 6) must be initialized to 0b0

+ For CPUs support for 64-byte loads and stores without status (FEAT_LS64): + + - If the kernel is entered at EL1 and EL2 is present: + + - HCRX_EL2.EnALS (bit 1) must be initialised to 0b1. + + For CPUs support for 64-byte loads and stores with status (FEAT_LS64_V): + + - If the kernel is entered at EL1 and EL2 is present: + + - HCRX_EL2.EnASR (bit 2) must be initialised to 0b1. + The requirements described above for CPU mode, caches, MMUs, architected timers, coherency and system registers apply to all CPUs. All CPUs must enter the kernel in the same exception level. Where the values documented diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 69d7afe56853..9e6db258ff48 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -435,6 +435,12 @@ HWCAP2_SME_SF8DP4 HWCAP2_POE Functionality implied by ID_AA64MMFR3_EL1.S1POE == 0b0001.

+HWCAP3_LS64 + Functionality implied by ID_AA64ISAR1_EL1.LS64 == 0b0001. + +HWCAP3_LS64_V + Functionality implied by ID_AA64ISAR1_EL1.LS64 == 0b0010. + 4. Unused AT_HWCAP bits -----------------------

diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 1c3f9617d54f..f45ab66d3466 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -176,6 +176,8 @@ #define KERNEL_HWCAP_POE __khwcap2_feature(POE)

#define __khwcap3_feature(x) (const_ilog2(HWCAP3_ ## x) + 128) +#define KERNEL_HWCAP_LS64 __khwcap3_feature(LS64) +#define KERNEL_HWCAP_LS64_V __khwcap3_feature(LS64_V)

/* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 705a7afa8e58..88579dad778d 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -143,5 +143,7 @@ /* * HWCAP3 flags - for AT_HWCAP3 */ +#define HWCAP3_LS64 (1UL << 0) +#define HWCAP3_LS64_V (1UL << 1)

#endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e151585c6cca..095f78d95507 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -238,6 +238,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { };

static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_LS64_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_XS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, 0), @@ -2291,6 +2292,38 @@ static void cpu_enable_e0pd(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_E0PD */

+static bool has_ls64(const struct arm64_cpu_capabilities *entry, int __unused) +{ + u64 ls64; + + ls64 = cpuid_feature_extract_field(__read_sysreg_by_encoding(entry->sys_reg), + entry->field_pos, entry->sign); + + if (ls64 == ID_AA64ISAR1_EL1_LS64_NI || + ls64 > ID_AA64ISAR1_EL1_LS64_LS64_ACCDATA) + return false; + + if (entry->capability == ARM64_HAS_LS64 && + ls64 >= ID_AA64ISAR1_EL1_LS64_LS64) + return true; + + if (entry->capability == ARM64_HAS_LS64_V && + ls64 >= ID_AA64ISAR1_EL1_LS64_LS64_V) + return true; + + return false; +} + +static void cpu_enable_ls64(struct arm64_cpu_capabilities const *cap) +{ + sysreg_clear_set(sctlr_el1, SCTLR_EL1_EnALS, SCTLR_EL1_EnALS); +} + +static void cpu_enable_ls64_v(struct arm64_cpu_capabilities const *cap) +{ + sysreg_clear_set(sctlr_el1, SCTLR_EL1_EnASR, SCTLR_EL1_EnASR); +} + #ifdef CONFIG_ARM64_PSEUDO_NMI static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry, int scope) @@ -3061,6 +3094,22 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_pmuv3, }, #endif + { + .desc = "LS64", + .capability = ARM64_HAS_LS64, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_ls64, + .cpu_enable = cpu_enable_ls64, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, LS64, LS64) + }, + { + .desc = "LS64_V", + .capability = ARM64_HAS_LS64_V, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_ls64, + .cpu_enable = cpu_enable_ls64_v, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, LS64, LS64_V) + }, {}, };

@@ -3180,6 +3229,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16), HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH), HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM), + HWCAP_CAP(ID_AA64ISAR1_EL1, LS64, LS64, CAP_HWCAP, KERNEL_HWCAP_LS64), + HWCAP_CAP(ID_AA64ISAR1_EL1, LS64, LS64_V, CAP_HWCAP, KERNEL_HWCAP_LS64_V), HWCAP_CAP(ID_AA64ISAR2_EL1, LUT, IMP, CAP_HWCAP, KERNEL_HWCAP_LUT), HWCAP_CAP(ID_AA64ISAR3_EL1, FAMINMAX, IMP, CAP_HWCAP, KERNEL_HWCAP_FAMINMAX), HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index c1f2b6b04b41..3cca8d0a36f1 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -81,6 +81,8 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_PACA] = "paca", [KERNEL_HWCAP_PACG] = "pacg", [KERNEL_HWCAP_GCS] = "gcs", + [KERNEL_HWCAP_LS64] = "ls64", + [KERNEL_HWCAP_LS64_V] = "ls64_v", [KERNEL_HWCAP_DCPODP] = "dcpodp", [KERNEL_HWCAP_SVE2] = "sve2", [KERNEL_HWCAP_SVEAES] = "sveaes", diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 10effd4cff6b..8930208a1b07 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -43,6 +43,8 @@ HAS_HCX HAS_LDAPR HAS_LPA2 HAS_LSE_ATOMICS +HAS_LS64 +HAS_LS64_V HAS_MOPS HAS_NESTED_VIRT HAS_PAN

From: Yicong Yang yangyicong@hisilicon.com

Add tests for FEAT_{LS64, LS64_V}. Issue related instructions if feature presents, no SIGILL should be received. When such instructions operate on Device memory or non-cacheable memory, we may received a SIGBUS during the test (w/o FEAT_LS64WB). Just ignore it since we only tested whether the instruction itself can be issued as expected on platforms declaring the support of such features.

Signed-off-by: Yicong Yang yangyicong@hisilicon.com --- tools/testing/selftests/arm64/abi/hwcap.c | 90 +++++++++++++++++++++++ 1 file changed, 90 insertions(+)

diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 35f521e5f41c..e1724f038cc1 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -11,6 +11,8 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include <linux/auxvec.h> +#include <linux/compiler.h> #include <sys/auxv.h> #include <sys/prctl.h> #include <asm/hwcap.h> @@ -578,6 +580,78 @@ static void lrcpc3_sigill(void) : "=r" (data0), "=r" (data1) : "r" (src) :); }

+static void ignore_signal(int sig, siginfo_t *info, void *context) +{ + ucontext_t *uc = context; + + uc->uc_mcontext.pc += 4; +} + +static void ls64_sigill(void) +{ + struct sigaction ign, old; + char src[64] __aligned(64) = { 1 }; + + /* + * LS64, LS64_V require target memory to be Device/Non-cacheable (if + * FEAT_LS64WB not supported) and the completer supports these + * instructions, otherwise we'll receive a SIGBUS. Since we are only + * testing the ABI here, so just ignore the SIGBUS and see if we can + * execute the instructions without receiving a SIGILL. Restore the + * handler of SIGBUS after this test. + */ + ign.sa_sigaction = ignore_signal; + ign.sa_flags = SA_SIGINFO | SA_RESTART; + sigemptyset(&ign.sa_mask); + sigaction(SIGBUS, &ign, &old); + + register void *xn asm ("x8") = src; + register u64 xt_1 asm ("x0"); + register u64 __maybe_unused xt_2 asm ("x1"); + register u64 __maybe_unused xt_3 asm ("x2"); + register u64 __maybe_unused xt_4 asm ("x3"); + register u64 __maybe_unused xt_5 asm ("x4"); + register u64 __maybe_unused xt_6 asm ("x5"); + register u64 __maybe_unused xt_7 asm ("x6"); + register u64 __maybe_unused xt_8 asm ("x7"); + + /* LD64B x0, [x8] */ + asm volatile(".inst 0xf83fd100" : "=r" (xt_1) : "r" (xn)); + + /* ST64B x0, [x8] */ + asm volatile(".inst 0xf83f9100" : : "r" (xt_1), "r" (xn)); + + sigaction(SIGBUS, &old, NULL); +} + +static void ls64_v_sigill(void) +{ + struct sigaction ign, old; + char dst[64] __aligned(64); + + /* See comment in ls64_sigill() */ + ign.sa_sigaction = ignore_signal; + ign.sa_flags = SA_SIGINFO | SA_RESTART; + sigemptyset(&ign.sa_mask); + sigaction(SIGBUS, &ign, &old); + + register void *xn asm ("x8") = dst; + register u64 xt_1 asm ("x0") = 1; + register u64 __maybe_unused xt_2 asm ("x1") = 2; + register u64 __maybe_unused xt_3 asm ("x2") = 3; + register u64 __maybe_unused xt_4 asm ("x3") = 4; + register u64 __maybe_unused xt_5 asm ("x4") = 5; + register u64 __maybe_unused xt_6 asm ("x5") = 6; + register u64 __maybe_unused xt_7 asm ("x6") = 7; + register u64 __maybe_unused xt_8 asm ("x7") = 8; + register u64 st asm ("x9"); + + /* ST64BV x9, x0, [x8] */ + asm volatile(".inst 0xf829b100" : "=r" (st) : "r" (xt_1), "r" (xn)); + + sigaction(SIGBUS, &old, NULL); +} + static const struct hwcap_data { const char *name; unsigned long at_hwcap; @@ -1098,6 +1172,22 @@ static const struct hwcap_data { .sigill_fn = hbc_sigill, .sigill_reliable = true, }, + { + .name = "LS64", + .at_hwcap = AT_HWCAP3, + .hwcap_bit = HWCAP3_LS64, + .cpuinfo = "ls64", + .sigill_fn = ls64_sigill, + .sigill_reliable = true, + }, + { + .name = "LS64_V", + .at_hwcap = AT_HWCAP3, + .hwcap_bit = HWCAP3_LS64_V, + .cpuinfo = "ls64_v", + .sigill_fn = ls64_v_sigill, + .sigill_reliable = true, + }, };

typedef void (*sighandler_fn)(int, siginfo_t *, void *);