summaryrefslogtreecommitdiff
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig18
-rw-r--r--arch/arm64/include/asm/atomic_ll_sc.h2
-rw-r--r--arch/arm64/include/asm/atomic_lse.h2
-rw-r--r--arch/arm64/include/asm/cache.h9
-rw-r--r--arch/arm64/include/asm/cpufeature.h6
-rw-r--r--arch/arm64/include/asm/cputype.h4
-rw-r--r--arch/arm64/include/asm/el2_setup.h7
-rw-r--r--arch/arm64/include/asm/esr.h10
-rw-r--r--arch/arm64/include/asm/fpsimd.h30
-rw-r--r--arch/arm64/include/asm/fpsimdmacros.h22
-rw-r--r--arch/arm64/include/asm/hugetlb.h9
-rw-r--r--arch/arm64/include/asm/hwcap.h6
-rw-r--r--arch/arm64/include/asm/kvm_arm.h18
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h46
-rw-r--r--arch/arm64/include/asm/kvm_host.h21
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h4
-rw-r--r--arch/arm64/include/asm/kvm_pgtable.h8
-rw-r--r--arch/arm64/include/asm/pgtable.h16
-rw-r--r--arch/arm64/include/asm/processor.h2
-rw-r--r--arch/arm64/include/asm/sysreg.h1
-rw-r--r--arch/arm64/include/asm/uprobes.h2
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h6
-rw-r--r--arch/arm64/include/uapi/asm/sigcontext.h19
-rw-r--r--arch/arm64/kernel/cacheinfo.c5
-rw-r--r--arch/arm64/kernel/cpu_errata.c7
-rw-r--r--arch/arm64/kernel/cpufeature.c28
-rw-r--r--arch/arm64/kernel/cpuinfo.c6
-rw-r--r--arch/arm64/kernel/efi-rt-wrapper.S1
-rw-r--r--arch/arm64/kernel/elfcore.c61
-rw-r--r--arch/arm64/kernel/entry-fpsimd.S30
-rw-r--r--arch/arm64/kernel/fpsimd.c49
-rw-r--r--arch/arm64/kernel/idreg-override.c1
-rw-r--r--arch/arm64/kernel/process.c21
-rw-r--r--arch/arm64/kernel/ptrace.c62
-rw-r--r--arch/arm64/kernel/signal.c122
-rw-r--r--arch/arm64/kvm/Kconfig1
-rw-r--r--arch/arm64/kvm/arch_timer.c106
-rw-r--r--arch/arm64/kvm/arm.c95
-rw-r--r--arch/arm64/kvm/fpsimd.c2
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/fault.h2
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h2
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h2
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c43
-rw-r--r--arch/arm64/kvm/mmu.c51
-rw-r--r--arch/arm64/kvm/reset.c9
-rw-r--r--arch/arm64/kvm/sys_regs.c285
-rw-r--r--arch/arm64/kvm/vgic/vgic-init.c19
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3.c2
-rw-r--r--arch/arm64/kvm/vmid.c6
-rw-r--r--arch/arm64/mm/hugetlbpage.c21
-rw-r--r--arch/arm64/mm/mmu.c21
-rw-r--r--arch/arm64/tools/cpucaps2
-rwxr-xr-xarch/arm64/tools/gen-sysreg.awk20
-rw-r--r--arch/arm64/tools/sysreg44
54 files changed, 993 insertions, 401 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 03934808b2ed..c5ccca26a408 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -184,8 +184,6 @@ config ARM64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
- if $(cc-option,-fpatchable-function-entry=2)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -972,6 +970,22 @@ config ARM64_ERRATUM_2457168
If unsure, say Y.
+config ARM64_ERRATUM_2645198
+ bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
+ default y
+ help
+ This option adds the workaround for ARM Cortex-A715 erratum 2645198.
+
+ If a Cortex-A715 cpu sees a page mapping permissions change from executable
+ to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
+ next instruction abort caused by permission fault.
+
+ Only user-space does executable to non-executable permission transition via
+ mprotect() system call. Workaround the problem by doing a break-before-make
+ TLB invalidation, for all changes to executable user space mappings.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index 0890e4f568fb..cbb3d961123b 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \
" cbnz %w0, 1b\n" \
" " #mb "\n" \
"2:" \
- : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \
+ : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \
: "r" (old1), "r" (old2), "r" (new1), "r" (new2) \
: cl); \
\
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 52075e93de6c..a94d6dacc029 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]" \
: [old1] "+&r" (x0), [old2] "+&r" (x1), \
- [v] "+Q" (*(unsigned long *)ptr) \
+ [v] "+Q" (*(__uint128_t *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
: cl); \
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index c0b178d1bb4f..a51e6e8f3171 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -16,6 +16,15 @@
#define CLIDR_LOC(clidr) (((clidr) >> CLIDR_LOC_SHIFT) & 0x7)
#define CLIDR_LOUIS(clidr) (((clidr) >> CLIDR_LOUIS_SHIFT) & 0x7)
+/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */
+#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1))
+#define CLIDR_CTYPE_MASK(level) (7 << CLIDR_CTYPE_SHIFT(level))
+#define CLIDR_CTYPE(clidr, level) \
+ (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
+
+/* Ttypen, bits [2(n - 1) + 34 : 2(n - 1) + 33], for n = 1 to 7 */
+#define CLIDR_TTYPE_SHIFT(level) (2 * ((level) - 1) + CLIDR_EL1_Ttypen_SHIFT)
+
/*
* Memory returned by kmalloc() may be used for DMA, so we must make
* sure that all such allocations are cache aligned. Otherwise,
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 03d1c9d7af82..fc2c739f48f1 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -769,6 +769,12 @@ static __always_inline bool system_supports_sme(void)
cpus_have_const_cap(ARM64_SME);
}
+static __always_inline bool system_supports_sme2(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_SME) &&
+ cpus_have_const_cap(ARM64_SME2);
+}
+
static __always_inline bool system_supports_fa64(void)
{
return IS_ENABLED(CONFIG_ARM64_SME) &&
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 4e8b66c74ea2..683ca3af4084 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -124,6 +124,8 @@
#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define APPLE_CPU_PART_M2_BLIZZARD 0x032
+#define APPLE_CPU_PART_M2_AVALANCHE 0x033
#define AMPERE_CPU_PART_AMPERE1 0xAC3
@@ -177,6 +179,8 @@
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 1cc29960fcdb..ea78c095a9c7 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -269,6 +269,13 @@
orr x0, x0, SMCR_ELx_FA64_MASK
.Lskip_sme_fa64_\@:
+ // ZT0 available?
+ mrs_s x1, SYS_ID_AA64SMFR0_EL1
+ __check_override id_aa64smfr0, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, .Linit_sme_zt0_\@, .Lskip_sme_zt0_\@, x1, x2
+.Linit_sme_zt0_\@:
+ orr x0, x0, SMCR_ELx_EZT0_MASK
+.Lskip_sme_zt0_\@:
+
orr x0, x0, #SMCR_ELx_LEN_MASK // Enable full SME vector
msr_s SYS_SMCR_EL2, x0 // length for EL1.
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 15b34fbfca66..c9f15b9e3c71 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -114,6 +114,15 @@
#define ESR_ELx_FSC_ACCESS (0x08)
#define ESR_ELx_FSC_FAULT (0x04)
#define ESR_ELx_FSC_PERM (0x0C)
+#define ESR_ELx_FSC_SEA_TTW0 (0x14)
+#define ESR_ELx_FSC_SEA_TTW1 (0x15)
+#define ESR_ELx_FSC_SEA_TTW2 (0x16)
+#define ESR_ELx_FSC_SEA_TTW3 (0x17)
+#define ESR_ELx_FSC_SECC (0x18)
+#define ESR_ELx_FSC_SECC_TTW0 (0x1c)
+#define ESR_ELx_FSC_SECC_TTW1 (0x1d)
+#define ESR_ELx_FSC_SECC_TTW2 (0x1e)
+#define ESR_ELx_FSC_SECC_TTW3 (0x1f)
/* ISS field definitions for Data Aborts */
#define ESR_ELx_ISV_SHIFT (24)
@@ -341,6 +350,7 @@
#define ESR_ELx_SME_ISS_ILL 1
#define ESR_ELx_SME_ISS_SM_DISABLED 2
#define ESR_ELx_SME_ISS_ZA_DISABLED 3
+#define ESR_ELx_SME_ISS_ZT_DISABLED 4
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index e6fa1e2982c8..67f2fb781f59 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -61,7 +61,7 @@ extern void fpsimd_kvm_prepare(void);
struct cpu_fp_state {
struct user_fpsimd_state *st;
void *sve_state;
- void *za_state;
+ void *sme_state;
u64 *svcr;
unsigned int sve_vl;
unsigned int sme_vl;
@@ -105,6 +105,13 @@ static inline void *sve_pffr(struct thread_struct *thread)
return (char *)thread->sve_state + sve_ffr_offset(vl);
}
+static inline void *thread_zt_state(struct thread_struct *thread)
+{
+ /* The ZT register state is stored immediately after the ZA state */
+ unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread));
+ return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq);
+}
+
extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
extern void sve_load_state(void const *state, u32 const *pfpsr,
int restore_ffr);
@@ -112,12 +119,13 @@ extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
extern unsigned int sve_get_vl(void);
extern void sve_set_vq(unsigned long vq_minus_1);
extern void sme_set_vq(unsigned long vq_minus_1);
-extern void za_save_state(void *state);
-extern void za_load_state(void const *state);
+extern void sme_save_state(void *state, int zt);
+extern void sme_load_state(void const *state, int zt);
struct arm64_cpu_capabilities;
extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern u64 read_zcr_features(void);
@@ -355,14 +363,20 @@ extern int sme_get_current_vl(void);
/*
* Return how many bytes of memory are required to store the full SME
- * specific state (currently just ZA) for task, given task's currently
- * configured vector length.
+ * specific state for task, given task's currently configured vector
+ * length.
*/
-static inline size_t za_state_size(struct task_struct const *task)
+static inline size_t sme_state_size(struct task_struct const *task)
{
unsigned int vl = task_get_sme_vl(task);
+ size_t size;
+
+ size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+
+ if (system_supports_sme2())
+ size += ZT_SIG_REG_SIZE;
- return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+ return size;
}
#else
@@ -382,7 +396,7 @@ static inline int sme_max_virtualisable_vl(void) { return 0; }
static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
static inline int sme_get_current_vl(void) { return -EINVAL; }
-static inline size_t za_state_size(struct task_struct const *task)
+static inline size_t sme_state_size(struct task_struct const *task)
{
return 0;
}
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 5e0910cf4832..cd03819a3b68 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -221,6 +221,28 @@
.endm
/*
+ * LDR (ZT0)
+ *
+ * LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+ _check_general_reg \nx
+ .inst 0xe11f8000 \
+ | (\nx << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ * STR ZT0, nx
+ */
+.macro _str_zt nx
+ _check_general_reg \nx
+ .inst 0xe13f8000 \
+ | (\nx << 5)
+.endm
+
+/*
* Zero the entire ZA array
* ZERO ZA
*/
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index d20f5da2d76f..6a4a1ab8eb23 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep);
void __init arm64_hugetlb_cma_reserve(void);
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
+
#include <asm-generic/hugetlb.h>
#endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 06dd12c514e6..475c803ecf42 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -123,6 +123,12 @@
#define KERNEL_HWCAP_CSSC __khwcap2_feature(CSSC)
#define KERNEL_HWCAP_RPRFM __khwcap2_feature(RPRFM)
#define KERNEL_HWCAP_SVE2P1 __khwcap2_feature(SVE2P1)
+#define KERNEL_HWCAP_SME2 __khwcap2_feature(SME2)
+#define KERNEL_HWCAP_SME2P1 __khwcap2_feature(SME2P1)
+#define KERNEL_HWCAP_SME_I16I32 __khwcap2_feature(SME_I16I32)
+#define KERNEL_HWCAP_SME_BI32I32 __khwcap2_feature(SME_BI32I32)
+#define KERNEL_HWCAP_SME_B16B16 __khwcap2_feature(SME_B16B16)
+#define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16)
/*
* This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0df3fc3a0173..350466baa2e0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -81,11 +81,12 @@
* SWIO: Turn set/way invalidates into set/way clean+invalidate
* PTW: Take a stage2 fault if a stage1 walk steps in device memory
* TID3: Trap EL1 reads of group 3 ID registers
+ * TID2: Trap CTR_EL0, CCSIDR2_EL1, CLIDR_EL1, and CSSELR_EL1
*/
#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
HCR_BSU_IS | HCR_FB | HCR_TACR | \
HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
- HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 )
+ HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID2)
#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
@@ -319,21 +320,6 @@
BIT(18) | \
GENMASK(16, 15))
-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT ESR_ELx_FSC_FAULT
-#define FSC_ACCESS ESR_ELx_FSC_ACCESS
-#define FSC_PERM ESR_ELx_FSC_PERM
-#define FSC_SEA ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0 (0x14)
-#define FSC_SEA_TTW1 (0x15)
-#define FSC_SEA_TTW2 (0x16)
-#define FSC_SEA_TTW3 (0x17)
-#define FSC_SECC (0x18)
-#define FSC_SECC_TTW0 (0x1c)
-#define FSC_SECC_TTW1 (0x1d)
-#define FSC_SECC_TTW2 (0x1e)
-#define FSC_SECC_TTW3 (0x1f)
-
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
/*
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 9bdba47f7e14..b1134af843bd 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -88,10 +88,6 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
if (vcpu_el1_is_32bit(vcpu))
vcpu->arch.hcr_el2 &= ~HCR_RW;
- if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
- vcpu_el1_is_32bit(vcpu))
- vcpu->arch.hcr_el2 |= HCR_TID2;
-
if (kvm_has_mte(vcpu->kvm))
vcpu->arch.hcr_el2 |= HCR_ATA;
}
@@ -349,16 +345,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *v
static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
{
switch (kvm_vcpu_trap_get_fault(vcpu)) {
- case FSC_SEA:
- case FSC_SEA_TTW0:
- case FSC_SEA_TTW1:
- case FSC_SEA_TTW2:
- case FSC_SEA_TTW3:
- case FSC_SECC:
- case FSC_SECC_TTW0:
- case FSC_SECC_TTW1:
- case FSC_SECC_TTW2:
- case FSC_SECC_TTW3:
+ case ESR_ELx_FSC_EXTABT:
+ case ESR_ELx_FSC_SEA_TTW0:
+ case ESR_ELx_FSC_SEA_TTW1:
+ case ESR_ELx_FSC_SEA_TTW2:
+ case ESR_ELx_FSC_SEA_TTW3:
+ case ESR_ELx_FSC_SECC:
+ case ESR_ELx_FSC_SECC_TTW0:
+ case ESR_ELx_FSC_SECC_TTW1:
+ case ESR_ELx_FSC_SECC_TTW2:
+ case ESR_ELx_FSC_SECC_TTW3:
return true;
default:
return false;
@@ -373,8 +369,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_abt_iss1tw(vcpu))
- return true;
+ if (kvm_vcpu_abt_iss1tw(vcpu)) {
+ /*
+ * Only a permission fault on a S1PTW should be
+ * considered as a write. Otherwise, page tables baked
+ * in a read-only memslot will result in an exception
+ * being delivered in the guest.
+ *
+ * The drawback is that we end-up faulting twice if the
+ * guest is using any of HW AF/DB: a translation fault
+ * to map the page containing the PT (read only at
+ * first), then a permission fault to allow the flags
+ * to be set.
+ */
+ switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+ case ESR_ELx_FSC_PERM:
+ return true;
+ default:
+ return false;
+ }
+ }
if (kvm_vcpu_trap_is_iabt(vcpu))
return false;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 35a159d131b5..82fdd26b6597 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -66,8 +66,8 @@ enum kvm_mode kvm_get_mode(void);
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
-extern unsigned int kvm_sve_max_vl;
-int kvm_arm_init_sve(void);
+extern unsigned int __ro_after_init kvm_sve_max_vl;
+int __init kvm_arm_init_sve(void);
u32 __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -252,6 +252,7 @@ struct kvm_vcpu_fault_info {
enum vcpu_sysreg {
__INVALID_SYSREG__, /* 0 is reserved as an invalid value */
MPIDR_EL1, /* MultiProcessor Affinity Register */
+ CLIDR_EL1, /* Cache Level ID Register */
CSSELR_EL1, /* Cache Size Selection Register */
SCTLR_EL1, /* System Control Register */
ACTLR_EL1, /* Auxiliary Control Register */
@@ -501,6 +502,9 @@ struct kvm_vcpu_arch {
u64 last_steal;
gpa_t base;
} steal;
+
+ /* Per-vcpu CCSIDR override or NULL */
+ u32 *ccsidr;
};
/*
@@ -705,7 +709,6 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
return false;
switch (reg) {
- case CSSELR_EL1: *val = read_sysreg_s(SYS_CSSELR_EL1); break;
case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break;
case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break;
case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break;
@@ -750,7 +753,6 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
return false;
switch (reg) {
- case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); break;
case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break;
case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break;
case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break;
@@ -877,7 +879,7 @@ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
-int kvm_sys_reg_table_init(void);
+int __init kvm_sys_reg_table_init(void);
/* MMIO helpers */
void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
@@ -908,9 +910,9 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
-extern unsigned int kvm_arm_vmid_bits;
-int kvm_arm_vmid_alloc_init(void);
-void kvm_arm_vmid_alloc_free(void);
+extern unsigned int __ro_after_init kvm_arm_vmid_bits;
+int __init kvm_arm_vmid_alloc_init(void);
+void __init kvm_arm_vmid_alloc_free(void);
void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
void kvm_arm_vmid_clear_active(void);
@@ -943,7 +945,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
-static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
@@ -994,7 +995,7 @@ static inline void kvm_clr_pmu_events(u32 clr) {}
void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
-int kvm_set_ipa_limit(void);
+int __init kvm_set_ipa_limit(void);
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e4a7e6369499..7f7c1231679e 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -163,7 +163,7 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
void __iomem **haddr);
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
void **haddr);
-void free_hyp_pgds(void);
+void __init free_hyp_pgds(void);
void stage2_unmap_vm(struct kvm *kvm);
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
@@ -175,7 +175,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
phys_addr_t kvm_mmu_get_httbr(void);
phys_addr_t kvm_get_idmap_vector(void);
-int kvm_mmu_init(u32 *hyp_va_bits);
+int __init kvm_mmu_init(u32 *hyp_va_bits);
static inline void *__kvm_vector_slot2addr(void *base,
enum arm64_hyp_spectre_vector slot)
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 63f81b27a4e3..4cd6762bda80 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -71,6 +71,11 @@ static inline kvm_pte_t kvm_phys_to_pte(u64 pa)
return pte;
}
+static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte)
+{
+ return __phys_to_pfn(kvm_pte_to_phys(pte));
+}
+
static inline u64 kvm_granule_shift(u32 level)
{
/* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
@@ -188,12 +193,15 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
* children.
* @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared
* with other software walkers.
+ * @KVM_PGTABLE_WALK_HANDLE_FAULT: Indicates the page-table walk was
+ * invoked from a fault handler.
*/
enum kvm_pgtable_walk_flags {
KVM_PGTABLE_WALK_LEAF = BIT(0),
KVM_PGTABLE_WALK_TABLE_PRE = BIT(1),
KVM_PGTABLE_WALK_TABLE_POST = BIT(2),
KVM_PGTABLE_WALK_SHARED = BIT(3),
+ KVM_PGTABLE_WALK_HANDLE_FAULT = BIT(4),
};
struct kvm_pgtable_visit_ctx {
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b4bbeed80fb6..65e78999c75d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud))
#define pud_valid(pud) pte_valid(pud_pte(pud))
#define pud_user(pud) pte_user(pud_pte(pud))
-
+#define pud_user_exec(pud) pte_user_exec(pud_pte(pud))
static inline void set_pud(pud_t *pudp, pud_t pud)
{
@@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud)
#else
#define pud_page_paddr(pud) ({ BUILD_BUG(); 0; })
+#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */
/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
#define pmd_set_fixmap(addr) NULL
@@ -862,12 +863,12 @@ static inline bool pte_user_accessible_page(pte_t pte)
static inline bool pmd_user_accessible_page(pmd_t pmd)
{
- return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+ return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
}
static inline bool pud_user_accessible_page(pud_t pud)
{
- return pud_leaf(pud) && pud_user(pud);
+ return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
}
#endif
@@ -1093,6 +1094,15 @@ static inline bool pud_sect_supported(void)
}
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index d51b32a69309..3918f2a67970 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -161,7 +161,7 @@ struct thread_struct {
enum fp_type fp_type; /* registers FPSIMD or SVE? */
unsigned int fpsimd_cpu;
void *sve_state; /* SVE registers, if any */
- void *za_state; /* ZA register, if any */
+ void *sme_state; /* ZA and ZT state, if any */
unsigned int vl[ARM64_VEC_MAX]; /* vector length */
unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
unsigned long fault_address; /* fault info */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 1312fb48f18b..a2a93b3fc557 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -404,7 +404,6 @@
#define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0)
-#define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0)
#define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7)
#define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0)
diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
index ba4bff5ca674..2b09495499c6 100644
--- a/arch/arm64/include/asm/uprobes.h
+++ b/arch/arm64/include/asm/uprobes.h
@@ -16,7 +16,7 @@
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES
-typedef u32 uprobe_opcode_t;
+typedef __le32 uprobe_opcode_t;
struct arch_uprobe_task {
};
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index b713d30544f1..69a4fb749c65 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -96,5 +96,11 @@
#define HWCAP2_CSSC (1UL << 34)
#define HWCAP2_RPRFM (1UL << 35)
#define HWCAP2_SVE2P1 (1UL << 36)
+#define HWCAP2_SME2 (1UL << 37)
+#define HWCAP2_SME2P1 (1UL << 38)
+#define HWCAP2_SME_I16I32 (1UL << 39)
+#define HWCAP2_SME_BI32I32 (1UL << 40)
+#define HWCAP2_SME_B16B16 (1UL << 41)
+#define HWCAP2_SME_F16F16 (1UL << 42)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index 9525041e4a14..46e9072985a5 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -152,6 +152,14 @@ struct za_context {
__u16 __reserved[3];
};
+#define ZT_MAGIC 0x5a544e01
+
+struct zt_context {
+ struct _aarch64_ctx head;
+ __u16 nregs;
+ __u16 __reserved[3];
+};
+
#endif /* !__ASSEMBLY__ */
#include <asm/sve_context.h>
@@ -304,4 +312,15 @@ struct za_context {
#define ZA_SIG_CONTEXT_SIZE(vq) \
(ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
+#define ZT_SIG_REG_SIZE 512
+
+#define ZT_SIG_REG_BYTES (ZT_SIG_REG_SIZE / 8)
+
+#define ZT_SIG_REGS_OFFSET sizeof(struct zt_context)
+
+#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n)
+
+#define ZT_SIG_CONTEXT_SIZE(n) \
+ (sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n))
+
#endif /* _UAPI__ASM_SIGCONTEXT_H */
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 97c42be71338..daa7b3f55997 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -11,11 +11,6 @@
#include <linux/of.h>
#define MAX_CACHE_LEVEL 7 /* Max 7 level supported */
-/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */
-#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1))
-#define CLIDR_CTYPE_MASK(level) (7 << CLIDR_CTYPE_SHIFT(level))
-#define CLIDR_CTYPE(clidr, level) \
- (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
int cache_line_size(void)
{
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 89ac00084f38..307faa2b4395 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+ {
+ .desc = "ARM erratum 2645198",
+ .capability = ARM64_WORKAROUND_2645198,
+ ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+ },
+#endif
#ifdef CONFIG_ARM64_ERRATUM_2077057
{
.desc = "ARM erratum 2077057",
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index a77315b338e6..5bd959bd9a1f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -283,16 +283,26 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I32_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+ FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0),
ARM64_FTR_END,
};
@@ -2649,6 +2659,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
.cpu_enable = fa64_kernel_enable,
},
+ {
+ .desc = "SME2",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_SME2,
+ .sys_reg = SYS_ID_AA64PFR1_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64PFR1_EL1_SME_SHIFT,
+ .field_width = ID_AA64PFR1_EL1_SME_WIDTH,
+ .min_field_value = ID_AA64PFR1_EL1_SME_SME2,
+ .matches = has_cpuid_feature,
+ .cpu_enable = sme2_kernel_enable,
+ },
#endif /* CONFIG_ARM64_SME */
{
.desc = "WFx with timeout",
@@ -2827,11 +2849,17 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
#ifdef CONFIG_ARM64_SME
HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SME_IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_FA64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_SMEver_SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_SMEver_SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F64F64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16B16_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F16_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I8I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+ HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_BI32I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F32F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
#endif /* CONFIG_ARM64_SME */
{},
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 379695262b77..85e54417d141 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -119,6 +119,12 @@ static const char *const hwcap_str[] = {
[KERNEL_HWCAP_CSSC] = "cssc",
[KERNEL_HWCAP_RPRFM] = "rprfm",
[KERNEL_HWCAP_SVE2P1] = "sve2p1",
+ [KERNEL_HWCAP_SME2] = "sme2",
+ [KERNEL_HWCAP_SME2P1] = "sme2p1",
+ [KERNEL_HWCAP_SME_I16I32] = "smei16i32",
+ [KERNEL_HWCAP_SME_BI32I32] = "smebi32i32",
+ [KERNEL_HWCAP_SME_B16B16] = "smeb16b16",
+ [KERNEL_HWCAP_SME_F16F16] = "smef16f16",
};
#ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index a00886410537..d872d18101d8 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -4,6 +4,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
SYM_FUNC_START(__efi_rt_asm_wrapper)
stp x29, x30, [sp, #-112]!
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 353009d7f307..2e94d20c4ac7 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -8,28 +8,27 @@
#include <asm/cpufeature.h>
#include <asm/mte.h>
-#define for_each_mte_vma(vmi, vma) \
+#define for_each_mte_vma(cprm, i, m) \
if (system_supports_mte()) \
- for_each_vma(vmi, vma) \
- if (vma->vm_flags & VM_MTE)
+ for (i = 0, m = cprm->vma_meta; \
+ i < cprm->vma_count; \
+ i++, m = cprm->vma_meta + i) \
+ if (m->flags & VM_MTE)
-static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m)
{
- if (vma->vm_flags & VM_DONTDUMP)
- return 0;
-
- return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+ return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE;
}
/* Derived from dump_user_range(); start/end must be page-aligned */
static int mte_dump_tag_range(struct coredump_params *cprm,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long len)
{
int ret = 1;
unsigned long addr;
void *tags = NULL;
- for (addr = start; addr < end; addr += PAGE_SIZE) {
+ for (addr = start; addr < start + len; addr += PAGE_SIZE) {
struct page *page = get_dump_page(addr);
/*
@@ -65,7 +64,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
mte_save_page_tags(page_address(page), tags);
put_page(page);
if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
- mte_free_tag_storage(tags);
ret = 0;
break;
}
@@ -77,13 +75,13 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
return ret;
}
-Elf_Half elf_core_extra_phdrs(void)
+Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
int vma_count = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
+ for_each_mte_vma(cprm, i, m)
vma_count++;
return vma_count;
@@ -91,18 +89,18 @@ Elf_Half elf_core_extra_phdrs(void)
int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
+ int i;
+ struct core_vma_metadata *m;
- for_each_mte_vma(vmi, vma) {
+ for_each_mte_vma(cprm, i, m) {
struct elf_phdr phdr;
phdr.p_type = PT_AARCH64_MEMTAG_MTE;
phdr.p_offset = offset;
- phdr.p_vaddr = vma->vm_start;
+ phdr.p_vaddr = m->start;
phdr.p_paddr = 0;
- phdr.p_filesz = mte_vma_tag_dump_size(vma);
- phdr.p_memsz = vma->vm_end - vma->vm_start;
+ phdr.p_filesz = mte_vma_tag_dump_size(m);
+ phdr.p_memsz = m->end - m->start;
offset += phdr.p_filesz;
phdr.p_flags = 0;
phdr.p_align = 0;
@@ -114,28 +112,25 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
size_t data_size = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
- data_size += mte_vma_tag_dump_size(vma);
+ for_each_mte_vma(cprm, i, m)
+ data_size += mte_vma_tag_dump_size(m);
return data_size;
}
int elf_core_write_extra_data(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
-
- for_each_mte_vma(vmi, vma) {
- if (vma->vm_flags & VM_DONTDUMP)
- continue;
+ int i;
+ struct core_vma_metadata *m;
- if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+ for_each_mte_vma(cprm, i, m) {
+ if (!mte_dump_tag_range(cprm, m->start, m->dump_size))
return 0;
}
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 229436f33df5..6325db1a2179 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -100,25 +100,35 @@ SYM_FUNC_START(sme_set_vq)
SYM_FUNC_END(sme_set_vq)
/*
- * Save the SME state
+ * Save the ZA and ZT state
*
* x0 - pointer to buffer for state
+ * x1 - number of ZT registers to save
*/
-SYM_FUNC_START(za_save_state)
- _sme_rdsvl 1, 1 // x1 = VL/8
- sme_save_za 0, x1, 12
+SYM_FUNC_START(sme_save_state)
+ _sme_rdsvl 2, 1 // x2 = VL/8
+ sme_save_za 0, x2, 12 // Leaves x0 pointing to the end of ZA
+
+ cbz x1, 1f
+ _str_zt 0
+1:
ret
-SYM_FUNC_END(za_save_state)
+SYM_FUNC_END(sme_save_state)
/*
- * Load the SME state
+ * Load the ZA and ZT state
*
* x0 - pointer to buffer for state
+ * x1 - number of ZT registers to save
*/
-SYM_FUNC_START(za_load_state)
- _sme_rdsvl 1, 1 // x1 = VL/8
- sme_load_za 0, x1, 12
+SYM_FUNC_START(sme_load_state)
+ _sme_rdsvl 2, 1 // x2 = VL/8
+ sme_load_za 0, x2, 12 // Leaves x0 pointing to the end of ZA
+
+ cbz x1, 1f
+ _ldr_zt 0
+1:
ret
-SYM_FUNC_END(za_load_state)
+SYM_FUNC_END(sme_load_state)
#endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index dcc81e7200d4..7c67190c44e4 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
/*
* TIF_SME controls whether a task can use SME without trapping while
* in userspace, when TIF_SME is set then we must have storage
- * alocated in sve_state and za_state to store the contents of both ZA
+ * alocated in sve_state and sme_state to store the contents of both ZA
* and the SVE registers for both streaming and non-streaming modes.
*
* If both SVCR.ZA and SVCR.SM are disabled then at any point we
@@ -385,7 +385,7 @@ static void task_fpsimd_load(void)
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
@@ -429,7 +429,8 @@ static void task_fpsimd_load(void)
write_sysreg_s(current->thread.svcr, SYS_SVCR);
if (thread_za_enabled(&current->thread))
- za_load_state(current->thread.za_state);
+ sme_load_state(current->thread.sme_state,
+ system_supports_sme2());
if (thread_sm_enabled(&current->thread))
restore_ffr = system_supports_fa64();
@@ -490,7 +491,8 @@ static void fpsimd_save(void)
*svcr = read_sysreg_s(SYS_SVCR);
if (*svcr & SVCR_ZA_MASK)
- za_save_state(last->za_state);
+ sme_save_state(last->sme_state,
+ system_supports_sme2());
/* If we are in streaming mode override regular SVE. */
if (*svcr & SVCR_SM_MASK) {
@@ -1257,30 +1259,30 @@ void fpsimd_release_task(struct task_struct *dead_task)
#ifdef CONFIG_ARM64_SME
/*
- * Ensure that task->thread.za_state is allocated and sufficiently large.
+ * Ensure that task->thread.sme_state is allocated and sufficiently large.
*
* This function should be used only in preparation for replacing
- * task->thread.za_state with new data. The memory is always zeroed
+ * task->thread.sme_state with new data. The memory is always zeroed
* here to prevent stale data from showing through: this is done in
* the interest of testability and predictability, the architecture
* guarantees that when ZA is enabled it will be zeroed.
*/
void sme_alloc(struct task_struct *task)
{
- if (task->thread.za_state) {
- memset(task->thread.za_state, 0, za_state_size(task));
+ if (task->thread.sme_state) {
+ memset(task->thread.sme_state, 0, sme_state_size(task));
return;
}
/* This could potentially be up to 64K. */
- task->thread.za_state =
- kzalloc(za_state_size(task), GFP_KERNEL);
+ task->thread.sme_state =
+ kzalloc(sme_state_size(task), GFP_KERNEL);
}
static void sme_free(struct task_struct *task)
{
- kfree(task->thread.za_state);
- task->thread.za_state = NULL;
+ kfree(task->thread.sme_state);
+ task->thread.sme_state = NULL;
}
void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
@@ -1302,6 +1304,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
* This must be called after sme_kernel_enable(), we rely on the
* feature table being sorted to ensure this.
*/
+void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+ /* Allow use of ZT0 */
+ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
+ SYS_SMCR_EL1);
+}
+
+/*
+ * This must be called after sme_kernel_enable(), we rely on the
+ * feature table being sorted to ensure this.
+ */
void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
{
/* Allow use of FA64 */
@@ -1488,7 +1501,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
sve_alloc(current, false);
sme_alloc(current);
- if (!current->thread.sve_state || !current->thread.za_state) {
+ if (!current->thread.sve_state || !current->thread.sme_state) {
force_sig(SIGKILL);
return;
}
@@ -1609,7 +1622,7 @@ static void fpsimd_flush_thread_vl(enum vec_type type)
void fpsimd_flush_thread(void)
{
void *sve_state = NULL;
- void *za_state = NULL;
+ void *sme_state = NULL;
if (!system_supports_fpsimd())
return;
@@ -1634,8 +1647,8 @@ void fpsimd_flush_thread(void)
clear_thread_flag(TIF_SME);
/* Defer kfree() while in atomic context */
- za_state = current->thread.za_state;
- current->thread.za_state = NULL;
+ sme_state = current->thread.sme_state;
+ current->thread.sme_state = NULL;
fpsimd_flush_thread_vl(ARM64_VEC_SME);
current->thread.svcr = 0;
@@ -1645,7 +1658,7 @@ void fpsimd_flush_thread(void)
put_cpu_fpsimd_context();
kfree(sve_state);
- kfree(za_state);
+ kfree(sme_state);
}
/*
@@ -1711,7 +1724,7 @@ static void fpsimd_bind_task_to_cpu(void)
WARN_ON(!system_supports_fpsimd());
last->st = &current->thread.uw.fpsimd_state;
last->sve_state = current->thread.sve_state;
- last->za_state = current->thread.za_state;
+ last->sme_state = current->thread.sme_state;
last->sve_vl = task_get_sve_vl(current);
last->sme_vl = task_get_sme_vl(current);
last->svcr = &current->thread.svcr;
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index 95133765ed29..d833d78a7f31 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -131,6 +131,7 @@ static const struct ftr_set_desc smfr0 __initconst = {
.name = "id_aa64smfr0",
.override = &id_aa64smfr0_override,
.fields = {
+ FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL),
/* FA64 is a one bit field... :-/ */
{ "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, },
{}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 269ac1c25ae2..71d59b5abede 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -307,27 +307,28 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
/*
* In the unlikely event that we create a new thread with ZA
- * enabled we should retain the ZA state so duplicate it here.
- * This may be shortly freed if we exec() or if CLONE_SETTLS
- * but it's simpler to do it here. To avoid confusing the rest
- * of the code ensure that we have a sve_state allocated
- * whenever za_state is allocated.
+ * enabled we should retain the ZA and ZT state so duplicate
+ * it here. This may be shortly freed if we exec() or if
+ * CLONE_SETTLS but it's simpler to do it here. To avoid
+ * confusing the rest of the code ensure that we have a
+ * sve_state allocated whenever sme_state is allocated.
*/
if (thread_za_enabled(&src->thread)) {
dst->thread.sve_state = kzalloc(sve_state_size(src),
GFP_KERNEL);
if (!dst->thread.sve_state)
return -ENOMEM;
- dst->thread.za_state = kmemdup(src->thread.za_state,
- za_state_size(src),
- GFP_KERNEL);
- if (!dst->thread.za_state) {
+
+ dst->thread.sme_state = kmemdup(src->thread.sme_state,
+ sme_state_size(src),
+ GFP_KERNEL);
+ if (!dst->thread.sme_state) {
kfree(dst->thread.sve_state);
dst->thread.sve_state = NULL;
return -ENOMEM;
}
} else {
- dst->thread.za_state = NULL;
+ dst->thread.sme_state = NULL;
clear_tsk_thread_flag(dst, TIF_SME);
}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 2686ab157601..89b87f1021ed 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1045,7 +1045,7 @@ static int za_get(struct task_struct *target,
if (thread_za_enabled(&target->thread)) {
start = end;
end = ZA_PT_SIZE(vq);
- membuf_write(&to, target->thread.za_state, end - start);
+ membuf_write(&to, target->thread.sme_state, end - start);
}
/* Zero any trailing padding */
@@ -1099,7 +1099,7 @@ static int za_set(struct task_struct *target,
/* Allocate/reinit ZA storage */
sme_alloc(target);
- if (!target->thread.za_state) {
+ if (!target->thread.sme_state) {
ret = -ENOMEM;
goto out;
}
@@ -1124,7 +1124,7 @@ static int za_set(struct task_struct *target,
start = ZA_PT_ZA_OFFSET;
end = ZA_PT_SIZE(vq);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- target->thread.za_state,
+ target->thread.sme_state,
start, end);
if (ret)
goto out;
@@ -1138,6 +1138,51 @@ out:
return ret;
}
+static int zt_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!system_supports_sme2())
+ return -EINVAL;
+
+ /*
+ * If PSTATE.ZA is not set then ZT will be zeroed when it is
+ * enabled so report the current register value as zero.
+ */
+ if (thread_za_enabled(&target->thread))
+ membuf_write(&to, thread_zt_state(&target->thread),
+ ZT_SIG_REG_BYTES);
+ else
+ membuf_zero(&to, ZT_SIG_REG_BYTES);
+
+ return 0;
+}
+
+static int zt_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!system_supports_sme2())
+ return -EINVAL;
+
+ if (!thread_za_enabled(&target->thread)) {
+ sme_alloc(target);
+ if (!target->thread.sme_state)
+ return -ENOMEM;
+ }
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ thread_zt_state(&target->thread),
+ 0, ZT_SIG_REG_BYTES);
+ if (ret == 0)
+ target->thread.svcr |= SVCR_ZA_MASK;
+
+ return ret;
+}
+
#endif /* CONFIG_ARM64_SME */
#ifdef CONFIG_ARM64_PTR_AUTH
@@ -1357,9 +1402,10 @@ enum aarch64_regset {
#ifdef CONFIG_ARM64_SVE
REGSET_SVE,
#endif
-#ifdef CONFIG_ARM64_SVE
+#ifdef CONFIG_ARM64_SME
REGSET_SSVE,
REGSET_ZA,
+ REGSET_ZT,
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
REGSET_PAC_MASK,
@@ -1467,6 +1513,14 @@ static const struct user_regset aarch64_regsets[] = {
.regset_get = za_get,
.set = za_set,
},
+ [REGSET_ZT] = { /* SME ZT */
+ .core_note_type = NT_ARM_ZT,
+ .n = 1,
+ .size = ZT_SIG_REG_BYTES,
+ .align = sizeof(u64),
+ .regset_get = zt_get,
+ .set = zt_set,
+ },
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
[REGSET_PAC_MASK] = {
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e0d09bf5b01b..14779619375b 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -57,6 +57,7 @@ struct rt_sigframe_user_layout {
unsigned long esr_offset;
unsigned long sve_offset;
unsigned long za_offset;
+ unsigned long zt_offset;
unsigned long extra_offset;
unsigned long end_offset;
};
@@ -221,6 +222,7 @@ struct user_ctxs {
struct fpsimd_context __user *fpsimd;
struct sve_context __user *sve;
struct za_context __user *za;
+ struct zt_context __user *zt;
};
#ifdef CONFIG_ARM64_SVE
@@ -281,7 +283,12 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
vl = task_get_sme_vl(current);
} else {
- if (!system_supports_sve())
+ /*
+ * A SME only system use SVE for streaming mode so can
+ * have a SVE formatted context with a zero VL and no
+ * payload data.
+ */
+ if (!system_supports_sve() && !system_supports_sme())
return -EINVAL;
vl = task_get_sve_vl(current);
@@ -389,7 +396,7 @@ static int preserve_za_context(struct za_context __user *ctx)
* fpsimd_signal_preserve_current_state().
*/
err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
- current->thread.za_state,
+ current->thread.sme_state,
ZA_SIG_REGS_SIZE(vq));
}
@@ -420,7 +427,7 @@ static int restore_za_context(struct user_ctxs *user)
/*
* Careful: we are about __copy_from_user() directly into
- * thread.za_state with preemption enabled, so protection is
+ * thread.sme_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
@@ -429,13 +436,13 @@ static int restore_za_context(struct user_ctxs *user)
/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
sme_alloc(current);
- if (!current->thread.za_state) {
+ if (!current->thread.sme_state) {
current->thread.svcr &= ~SVCR_ZA_MASK;
clear_thread_flag(TIF_SME);
return -ENOMEM;
}
- err = __copy_from_user(current->thread.za_state,
+ err = __copy_from_user(current->thread.sme_state,
(char __user const *)user->za +
ZA_SIG_REGS_OFFSET,
ZA_SIG_REGS_SIZE(vq));
@@ -447,11 +454,81 @@ static int restore_za_context(struct user_ctxs *user)
return 0;
}
+
+static int preserve_zt_context(struct zt_context __user *ctx)
+{
+ int err = 0;
+ u16 reserved[ARRAY_SIZE(ctx->__reserved)];
+
+ if (WARN_ON(!thread_za_enabled(&current->thread)))
+ return -EINVAL;
+
+ memset(reserved, 0, sizeof(reserved));
+
+ __put_user_error(ZT_MAGIC, &ctx->head.magic, err);
+ __put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16),
+ &ctx->head.size, err);
+ __put_user_error(1, &ctx->nregs, err);
+ BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
+ err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
+
+ /*
+ * This assumes that the ZT state has already been saved to
+ * the task struct by calling the function
+ * fpsimd_signal_preserve_current_state().
+ */
+ err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
+ thread_zt_state(&current->thread),
+ ZT_SIG_REGS_SIZE(1));
+
+ return err ? -EFAULT : 0;
+}
+
+static int restore_zt_context(struct user_ctxs *user)
+{
+ int err;
+ struct zt_context zt;
+
+ /* ZA must be restored first for this check to be valid */
+ if (!thread_za_enabled(&current->thread))
+ return -EINVAL;
+
+ if (__copy_from_user(&zt, user->zt, sizeof(zt)))
+ return -EFAULT;
+
+ if (zt.nregs != 1)
+ return -EINVAL;
+
+ if (zt.head.size != ZT_SIG_CONTEXT_SIZE(zt.nregs))
+ return -EINVAL;
+
+ /*
+ * Careful: we are about __copy_from_user() directly into
+ * thread.zt_state with preemption enabled, so protection is
+ * needed to prevent a racing context switch from writing stale
+ * registers back over the new data.
+ */
+
+ fpsimd_flush_task_state(current);
+ /* From now, fpsimd_thread_switch() won't touch ZT in thread state */
+
+ err = __copy_from_user(thread_zt_state(&current->thread),
+ (char __user const *)user->zt +
+ ZT_SIG_REGS_OFFSET,
+ ZT_SIG_REGS_SIZE(1));
+ if (err)
+ return -EFAULT;
+
+ return 0;
+}
+
#else /* ! CONFIG_ARM64_SME */
/* Turn any non-optimised out attempts to use these into a link error: */
extern int preserve_za_context(void __user *ctx);
extern int restore_za_context(struct user_ctxs *user);
+extern int preserve_zt_context(void __user *ctx);
+extern int restore_zt_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_SME */
@@ -469,6 +546,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->fpsimd = NULL;
user->sve = NULL;
user->za = NULL;
+ user->zt = NULL;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
@@ -547,6 +625,19 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->za = (struct za_context __user *)head;
break;
+ case ZT_MAGIC:
+ if (!system_supports_sme2())
+ goto invalid;
+
+ if (user->zt)
+ goto invalid;
+
+ if (size < sizeof(*user->zt))
+ goto invalid;
+
+ user->zt = (struct zt_context __user *)head;
+ break;
+
case EXTRA_MAGIC:
if (have_extra_context)
goto invalid;
@@ -669,6 +760,9 @@ static int restore_sigframe(struct pt_regs *regs,
if (err == 0 && system_supports_sme() && user.za)
err = restore_za_context(&user);
+ if (err == 0 && system_supports_sme2() && user.zt)
+ err = restore_zt_context(&user);
+
return err;
}
@@ -732,7 +826,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
return err;
}
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
if (add_all || test_thread_flag(TIF_SVE) ||
@@ -769,6 +863,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
return err;
}
+ if (system_supports_sme2()) {
+ if (add_all || thread_za_enabled(&current->thread)) {
+ err = sigframe_alloc(user, &user->zt_offset,
+ ZT_SIG_CONTEXT_SIZE(1));
+ if (err)
+ return err;
+ }
+ }
+
return sigframe_alloc_end(user);
}
@@ -824,6 +927,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
err |= preserve_za_context(za_ctx);
}
+ /* ZT state if present */
+ if (system_supports_sme2() && err == 0 && user->zt_offset) {
+ struct zt_context __user *zt_ctx =
+ apply_user_offset(user, user->zt_offset);
+ err |= preserve_zt_context(zt_ctx);
+ }
+
if (err == 0 && user->extra_offset) {
char __user *sfp = (char __user *)user->sigframe;
char __user *userp =
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 05da3c8f7e88..ca6eadeb7d1a 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,7 @@ if VIRTUALIZATION
menuconfig KVM
bool "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM
+ select KVM_GENERIC_HARDWARE_ENABLING
select MMU_NOTIFIER
select PREEMPT_NOTIFIERS
select HAVE_KVM_CPU_RELAX_INTERCEPT
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index bb24a76b4224..00610477ec7b 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -428,14 +428,17 @@ static void timer_emulate(struct arch_timer_context *ctx)
* scheduled for the future. If the timer cannot fire at all,
* then we also don't need a soft timer.
*/
- if (!kvm_timer_irq_can_fire(ctx)) {
- soft_timer_cancel(&ctx->hrtimer);
+ if (should_fire || !kvm_timer_irq_can_fire(ctx))
return;
- }
soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx));
}
+static void set_cntvoff(u64 cntvoff)
+{
+ kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff);
+}
+
static void timer_save_state(struct arch_timer_context *ctx)
{
struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu);
@@ -459,6 +462,22 @@ static void timer_save_state(struct arch_timer_context *ctx)
write_sysreg_el0(0, SYS_CNTV_CTL);
isb();
+ /*
+ * The kernel may decide to run userspace after
+ * calling vcpu_put, so we reset cntvoff to 0 to
+ * ensure a consistent read between user accesses to
+ * the virtual counter and kernel access to the
+ * physical counter of non-VHE case.
+ *
+ * For VHE, the virtual counter uses a fixed virtual
+ * offset of zero, so no need to zero CNTVOFF_EL2
+ * register, but this is actually useful when switching
+ * between EL1/vEL2 with NV.
+ *
+ * Do it unconditionally, as this is either unavoidable
+ * or dirt cheap.
+ */
+ set_cntvoff(0);
break;
case TIMER_PTIMER:
timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
@@ -532,6 +551,7 @@ static void timer_restore_state(struct arch_timer_context *ctx)
switch (index) {
case TIMER_VTIMER:
+ set_cntvoff(timer_get_offset(ctx));
write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL);
isb();
write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
@@ -552,11 +572,6 @@ out:
local_irq_restore(flags);
}
-static void set_cntvoff(u64 cntvoff)
-{
- kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff);
-}
-
static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active)
{
int r;
@@ -631,8 +646,6 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
kvm_timer_vcpu_load_nogic(vcpu);
}
- set_cntvoff(timer_get_offset(map.direct_vtimer));
-
kvm_timer_unblocking(vcpu);
timer_restore_state(map.direct_vtimer);
@@ -688,15 +701,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
if (kvm_vcpu_is_blocking(vcpu))
kvm_timer_blocking(vcpu);
-
- /*
- * The kernel may decide to run userspace after calling vcpu_put, so
- * we reset cntvoff to 0 to ensure a consistent read between user
- * accesses to the virtual counter and kernel access to the physical
- * counter of non-VHE case. For VHE, the virtual counter uses a fixed
- * virtual offset of zero, so no need to zero CNTVOFF_EL2 register.
- */
- set_cntvoff(0);
}
/*
@@ -811,10 +815,18 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
ptimer->host_timer_irq_flags = host_ptimer_irq_flags;
}
-static void kvm_timer_init_interrupt(void *info)
+void kvm_timer_cpu_up(void)
{
enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
- enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags);
+ if (host_ptimer_irq)
+ enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags);
+}
+
+void kvm_timer_cpu_down(void)
+{
+ disable_percpu_irq(host_vtimer_irq);
+ if (host_ptimer_irq)
+ disable_percpu_irq(host_ptimer_irq);
}
int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
@@ -926,14 +938,22 @@ u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu,
enum kvm_arch_timers tmr,
enum kvm_arch_timer_regs treg)
{
+ struct arch_timer_context *timer;
+ struct timer_map map;
u64 val;
+ get_timer_map(vcpu, &map);
+ timer = vcpu_get_timer(vcpu, tmr);
+
+ if (timer == map.emul_ptimer)
+ return kvm_arm_timer_read(vcpu, timer, treg);
+
preempt_disable();
- kvm_timer_vcpu_put(vcpu);
+ timer_save_state(timer);
- val = kvm_arm_timer_read(vcpu, vcpu_get_timer(vcpu, tmr), treg);
+ val = kvm_arm_timer_read(vcpu, timer, treg);
- kvm_timer_vcpu_load(vcpu);
+ timer_restore_state(timer);
preempt_enable();
return val;
@@ -967,25 +987,22 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
enum kvm_arch_timer_regs treg,
u64 val)
{
- preempt_disable();
- kvm_timer_vcpu_put(vcpu);
-
- kvm_arm_timer_write(vcpu, vcpu_get_timer(vcpu, tmr), treg, val);
-
- kvm_timer_vcpu_load(vcpu);
- preempt_enable();
-}
-
-static int kvm_timer_starting_cpu(unsigned int cpu)
-{
- kvm_timer_init_interrupt(NULL);
- return 0;
-}
+ struct arch_timer_context *timer;
+ struct timer_map map;
-static int kvm_timer_dying_cpu(unsigned int cpu)
-{
- disable_percpu_irq(host_vtimer_irq);
- return 0;
+ get_timer_map(vcpu, &map);
+ timer = vcpu_get_timer(vcpu, tmr);
+ if (timer == map.emul_ptimer) {
+ soft_timer_cancel(&timer->hrtimer);
+ kvm_arm_timer_write(vcpu, timer, treg, val);
+ timer_emulate(timer);
+ } else {
+ preempt_disable();
+ timer_save_state(timer);
+ kvm_arm_timer_write(vcpu, timer, treg, val);
+ timer_restore_state(timer);
+ preempt_enable();
+ }
}
static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
@@ -1117,7 +1134,7 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info)
return 0;
}
-int kvm_timer_hyp_init(bool has_gic)
+int __init kvm_timer_hyp_init(bool has_gic)
{
struct arch_timer_kvm_info *info;
int err;
@@ -1185,9 +1202,6 @@ int kvm_timer_hyp_init(bool has_gic)
goto out_free_irq;
}
- cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
- "kvm/arm/timer:starting", kvm_timer_starting_cpu,
- kvm_timer_dying_cpu);
return 0;
out_free_irq:
free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus());
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index d9c6ec650b42..69d99951768b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -63,16 +63,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}
-int kvm_arch_hardware_setup(void *opaque)
-{
- return 0;
-}
-
-int kvm_arch_check_processor_compat(void *opaque)
-{
- return 0;
-}
-
int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap)
{
@@ -146,7 +136,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (ret)
goto err_unshare_kvm;
- if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) {
+ if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL_ACCOUNT)) {
ret = -ENOMEM;
goto err_unshare_kvm;
}
@@ -1539,7 +1529,7 @@ static int kvm_init_vector_slots(void)
return 0;
}
-static void cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
+static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
{
struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
unsigned long tcr;
@@ -1682,7 +1672,15 @@ static void _kvm_arch_hardware_enable(void *discard)
int kvm_arch_hardware_enable(void)
{
+ int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled);
+
_kvm_arch_hardware_enable(NULL);
+
+ if (!was_enabled) {
+ kvm_vgic_cpu_up();
+ kvm_timer_cpu_up();
+ }
+
return 0;
}
@@ -1696,6 +1694,11 @@ static void _kvm_arch_hardware_disable(void *discard)
void kvm_arch_hardware_disable(void)
{
+ if (__this_cpu_read(kvm_arm_hardware_enabled)) {
+ kvm_timer_cpu_down();
+ kvm_vgic_cpu_down();
+ }
+
if (!is_protected_kvm_enabled())
_kvm_arch_hardware_disable(NULL);
}
@@ -1738,26 +1741,26 @@ static struct notifier_block hyp_init_cpu_pm_nb = {
.notifier_call = hyp_init_cpu_pm_notifier,
};
-static void hyp_cpu_pm_init(void)
+static void __init hyp_cpu_pm_init(void)
{
if (!is_protected_kvm_enabled())
cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
}
-static void hyp_cpu_pm_exit(void)
+static void __init hyp_cpu_pm_exit(void)
{
if (!is_protected_kvm_enabled())
cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
}
#else
-static inline void hyp_cpu_pm_init(void)
+static inline void __init hyp_cpu_pm_init(void)
{
}
-static inline void hyp_cpu_pm_exit(void)
+static inline void __init hyp_cpu_pm_exit(void)
{
}
#endif
-static void init_cpu_logical_map(void)
+static void __init init_cpu_logical_map(void)
{
unsigned int cpu;
@@ -1774,7 +1777,7 @@ static void init_cpu_logical_map(void)
#define init_psci_0_1_impl_state(config, what) \
config.psci_0_1_ ## what ## _implemented = psci_ops.what
-static bool init_psci_relay(void)
+static bool __init init_psci_relay(void)
{
/*
* If PSCI has not been initialized, protected KVM cannot install
@@ -1797,7 +1800,7 @@ static bool init_psci_relay(void)
return true;
}
-static int init_subsystems(void)
+static int __init init_subsystems(void)
{
int err = 0;
@@ -1838,13 +1841,22 @@ static int init_subsystems(void)
kvm_register_perf_callbacks(NULL);
out:
+ if (err)
+ hyp_cpu_pm_exit();
+
if (err || !is_protected_kvm_enabled())
on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);
return err;
}
-static void teardown_hyp_mode(void)
+static void __init teardown_subsystems(void)
+{
+ kvm_unregister_perf_callbacks();
+ hyp_cpu_pm_exit();
+}
+
+static void __init teardown_hyp_mode(void)
{
int cpu;
@@ -1855,7 +1867,7 @@ static void teardown_hyp_mode(void)
}
}
-static int do_pkvm_init(u32 hyp_va_bits)
+static int __init do_pkvm_init(u32 hyp_va_bits)
{
void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base));
int ret;
@@ -1892,7 +1904,7 @@ static void kvm_hyp_init_symbols(void)
kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
}
-static int kvm_hyp_init_protection(u32 hyp_va_bits)
+static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
{
void *addr = phys_to_virt(hyp_mem_base);
int ret;
@@ -1913,7 +1925,7 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits)
/**
* Inits Hyp-mode on all online CPUs
*/
-static int init_hyp_mode(void)
+static int __init init_hyp_mode(void)
{
u32 hyp_va_bits;
int cpu;
@@ -2095,7 +2107,7 @@ out_err:
return err;
}
-static void _kvm_host_prot_finalize(void *arg)
+static void __init _kvm_host_prot_finalize(void *arg)
{
int *err = arg;
@@ -2103,7 +2115,7 @@ static void _kvm_host_prot_finalize(void *arg)
WRITE_ONCE(*err, -EINVAL);
}
-static int pkvm_drop_host_privileges(void)
+static int __init pkvm_drop_host_privileges(void)
{
int ret = 0;
@@ -2116,7 +2128,7 @@ static int pkvm_drop_host_privileges(void)
return ret;
}
-static int finalize_hyp_mode(void)
+static int __init finalize_hyp_mode(void)
{
if (!is_protected_kvm_enabled())
return 0;
@@ -2191,7 +2203,7 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons)
/**
* Initialize Hyp-mode and memory mappings on all CPUs.
*/
-int kvm_arch_init(void *opaque)
+static __init int kvm_arm_init(void)
{
int err;
bool in_hyp_mode;
@@ -2242,7 +2254,7 @@ int kvm_arch_init(void *opaque)
err = kvm_init_vector_slots();
if (err) {
kvm_err("Cannot initialise vector slots\n");
- goto out_err;
+ goto out_hyp;
}
err = init_subsystems();
@@ -2253,7 +2265,7 @@ int kvm_arch_init(void *opaque)
err = finalize_hyp_mode();
if (err) {
kvm_err("Failed to finalize Hyp protection\n");
- goto out_hyp;
+ goto out_subs;
}
}
@@ -2265,10 +2277,19 @@ int kvm_arch_init(void *opaque)
kvm_info("Hyp mode initialized successfully\n");
}
+ /*
+ * FIXME: Do something reasonable if kvm_init() fails after pKVM
+ * hypervisor protection is finalized.
+ */
+ err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+ if (err)
+ goto out_subs;
+
return 0;
+out_subs:
+ teardown_subsystems();
out_hyp:
- hyp_cpu_pm_exit();
if (!in_hyp_mode)
teardown_hyp_mode();
out_err:
@@ -2276,12 +2297,6 @@ out_err:
return err;
}
-/* NOP: Compiling as a module not supported */
-void kvm_arch_exit(void)
-{
- kvm_unregister_perf_callbacks();
-}
-
static int __init early_kvm_mode_cfg(char *arg)
{
if (!arg)
@@ -2320,10 +2335,4 @@ enum kvm_mode kvm_get_mode(void)
return kvm_mode;
}
-static int arm_init(void)
-{
- int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
- return rc;
-}
-
-module_init(arm_init);
+module_init(kvm_arm_init);
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 02dd7e9ebd39..235775d0c825 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -143,7 +143,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
fp_state.st = &vcpu->arch.ctxt.fp_regs;
fp_state.sve_state = vcpu->arch.sve_state;
fp_state.sve_vl = vcpu->arch.sve_max_vl;
- fp_state.za_state = NULL;
+ fp_state.sme_state = NULL;
fp_state.svcr = &vcpu->arch.svcr;
fp_state.fp_type = &vcpu->arch.fp_type;
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 1b8a2dcd712f..9ddcfe2c3e57 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
*/
if (!(esr & ESR_ELx_S1PTW) &&
(cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 3330d1b76bdd..07d37ff88a3f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -367,7 +367,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
- valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
kvm_vcpu_dabt_isvalid(vcpu) &&
!kvm_vcpu_abt_issea(vcpu) &&
!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index baa5b9b3dde5..147cb4c846c6 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -39,7 +39,6 @@ static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt)
static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
{
- ctxt_sys_reg(ctxt, CSSELR_EL1) = read_sysreg(csselr_el1);
ctxt_sys_reg(ctxt, SCTLR_EL1) = read_sysreg_el1(SYS_SCTLR);
ctxt_sys_reg(ctxt, CPACR_EL1) = read_sysreg_el1(SYS_CPACR);
ctxt_sys_reg(ctxt, TTBR0_EL1) = read_sysreg_el1(SYS_TTBR0);
@@ -95,7 +94,6 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
{
write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1), vmpidr_el2);
- write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1), csselr_el1);
if (has_vhe() ||
!cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index b11cf2c618a6..3d61bd3e591d 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -168,6 +168,25 @@ static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data,
return walker->cb(ctx, visit);
}
+static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
+ int r)
+{
+ /*
+ * Visitor callbacks return EAGAIN when the conditions that led to a
+ * fault are no longer reflected in the page tables due to a race to
+ * update a PTE. In the context of a fault handler this is interpreted
+ * as a signal to retry guest execution.
+ *
+ * Ignore the return code altogether for walkers outside a fault handler
+ * (e.g. write protecting a range of memory) and chug along with the
+ * page table walk.
+ */
+ if (r == -EAGAIN)
+ return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT);
+
+ return !r;
+}
+
static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level);
@@ -200,7 +219,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
table = kvm_pte_table(ctx.old, level);
}
- if (ret)
+ if (!kvm_pgtable_walk_continue(data->walker, ret))
goto out;
if (!table) {
@@ -211,13 +230,16 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops);
ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1);
- if (ret)
+ if (!kvm_pgtable_walk_continue(data->walker, ret))
goto out;
if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST)
ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST);
out:
+ if (kvm_pgtable_walk_continue(data->walker, ret))
+ return 0;
+
return ret;
}
@@ -584,12 +606,14 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
lvls = 2;
vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
+#ifdef CONFIG_ARM64_HW_AFDBM
/*
* Enable the Hardware Access Flag management, unconditionally
* on all CPUs. The features is RES0 on CPUs without the support
* and must be ignored by the CPUs.
*/
vtcr |= VTCR_EL2_HA;
+#endif /* CONFIG_ARM64_HW_AFDBM */
/* Set the vmid bits */
vtcr |= (get_vmid_bits(mmfr1) == 16) ?
@@ -1026,7 +1050,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
if (!kvm_pte_valid(ctx->old))
- return 0;
+ return -EAGAIN;
data->level = ctx->level;
data->pte = pte;
@@ -1094,9 +1118,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
{
kvm_pte_t pte = 0;
- stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
- &pte, NULL, 0);
- dsb(ishst);
+ int ret;
+
+ ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
+ &pte, NULL,
+ KVM_PGTABLE_WALK_HANDLE_FAULT |
+ KVM_PGTABLE_WALK_SHARED);
+ if (!ret)
+ dsb(ishst);
+
return pte;
}
@@ -1141,6 +1171,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
+ KVM_PGTABLE_WALK_HANDLE_FAULT |
KVM_PGTABLE_WALK_SHARED);
if (!ret)
kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 31d7fa4c7c14..cfc7777fa490 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -25,11 +25,11 @@
static struct kvm_pgtable *hyp_pgtable;
static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
-static unsigned long hyp_idmap_start;
-static unsigned long hyp_idmap_end;
-static phys_addr_t hyp_idmap_vector;
+static unsigned long __ro_after_init hyp_idmap_start;
+static unsigned long __ro_after_init hyp_idmap_end;
+static phys_addr_t __ro_after_init hyp_idmap_vector;
-static unsigned long io_map_base;
+static unsigned long __ro_after_init io_map_base;
static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
{
@@ -280,7 +280,7 @@ static void stage2_flush_vm(struct kvm *kvm)
/**
* free_hyp_pgds - free Hyp-mode page tables
*/
-void free_hyp_pgds(void)
+void __init free_hyp_pgds(void)
{
mutex_lock(&kvm_hyp_pgd_mutex);
if (hyp_pgtable) {
@@ -1212,7 +1212,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
VM_BUG_ON(write_fault && exec_fault);
- if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+ if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
@@ -1277,7 +1277,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* only exception to this is when dirty logging is enabled at runtime
* and a write fault needs to collapse a block entry into a table.
*/
- if (fault_status != FSC_PERM || (logging_active && write_fault)) {
+ if (fault_status != ESR_ELx_FSC_PERM ||
+ (logging_active && write_fault)) {
ret = kvm_mmu_topup_memory_cache(memcache,
kvm_mmu_cache_min_pages(kvm));
if (ret)
@@ -1342,7 +1343,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
- if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+ if (fault_status == ESR_ELx_FSC_PERM &&
+ fault_granule > PAGE_SIZE)
vma_pagesize = fault_granule;
else
vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1350,7 +1352,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
&fault_ipa);
}
- if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+ if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new disallowed VMA */
if (kvm_vma_mte_allowed(vma)) {
sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1376,12 +1378,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* permissions only if vma_pagesize equals fault_granule. Otherwise,
* kvm_pgtable_stage2_map() should be called to change block size.
*/
- if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
+ if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
else
ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
__pfn_to_phys(pfn), prot,
- memcache, KVM_PGTABLE_WALK_SHARED);
+ memcache,
+ KVM_PGTABLE_WALK_HANDLE_FAULT |
+ KVM_PGTABLE_WALK_SHARED);
/* Mark the page dirty only if the fault is handled successfully */
if (writable && !ret) {
@@ -1399,20 +1403,18 @@ out_unlock:
/* Resolve the access fault by making the page young again. */
static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
- pte_t pte;
- kvm_pte_t kpte;
+ kvm_pte_t pte;
struct kvm_s2_mmu *mmu;
trace_kvm_access_fault(fault_ipa);
- write_lock(&vcpu->kvm->mmu_lock);
+ read_lock(&vcpu->kvm->mmu_lock);
mmu = vcpu->arch.hw_mmu;
- kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
- write_unlock(&vcpu->kvm->mmu_lock);
+ pte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
+ read_unlock(&vcpu->kvm->mmu_lock);
- pte = __pte(kpte);
- if (pte_valid(pte))
- kvm_set_pfn_accessed(pte_pfn(pte));
+ if (kvm_pte_valid(pte))
+ kvm_set_pfn_accessed(kvm_pte_to_pfn(pte));
}
/**
@@ -1441,7 +1443,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (fault_status == FSC_FAULT) {
+ if (fault_status == ESR_ELx_FSC_FAULT) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
@@ -1476,8 +1478,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
kvm_vcpu_get_hfar(vcpu), fault_ipa);
/* Check the stage-2 fault is trans. fault or write fault */
- if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
- fault_status != FSC_ACCESS) {
+ if (fault_status != ESR_ELx_FSC_FAULT &&
+ fault_status != ESR_ELx_FSC_PERM &&
+ fault_status != ESR_ELx_FSC_ACCESS) {
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1539,7 +1542,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
- if (fault_status == FSC_ACCESS) {
+ if (fault_status == ESR_ELx_FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
ret = 1;
goto out_unlock;
@@ -1665,7 +1668,7 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
.virt_to_phys = kvm_host_pa,
};
-int kvm_mmu_init(u32 *hyp_va_bits)
+int __init kvm_mmu_init(u32 *hyp_va_bits)
{
int err;
u32 idmap_bits;
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index e0267f672b8a..4a39da302b88 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -30,7 +30,7 @@
#include <asm/virt.h>
/* Maximum phys_shift supported for any VM on this host */
-static u32 kvm_ipa_limit;
+static u32 __ro_after_init kvm_ipa_limit;
/*
* ARMv8 Reset Values
@@ -41,9 +41,9 @@ static u32 kvm_ipa_limit;
#define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
PSR_AA32_I_BIT | PSR_AA32_F_BIT)
-unsigned int kvm_sve_max_vl;
+unsigned int __ro_after_init kvm_sve_max_vl;
-int kvm_arm_init_sve(void)
+int __init kvm_arm_init_sve(void)
{
if (system_supports_sve()) {
kvm_sve_max_vl = sve_max_virtualisable_vl();
@@ -157,6 +157,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
if (sve_state)
kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu));
kfree(sve_state);
+ kfree(vcpu->arch.ccsidr);
}
static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu)
@@ -352,7 +353,7 @@ u32 get_kvm_ipa_limit(void)
return kvm_ipa_limit;
}
-int kvm_set_ipa_limit(void)
+int __init kvm_set_ipa_limit(void)
{
unsigned int parange;
u64 mmfr0;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d5ee52d6bf73..6d2e6e47d009 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -11,6 +11,7 @@
#include <linux/bitfield.h>
#include <linux/bsearch.h>
+#include <linux/cacheinfo.h>
#include <linux/kvm_host.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -81,25 +82,97 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
__vcpu_sys_reg(vcpu, reg) = val;
}
-/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
-static u32 cache_levels;
-
/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
#define CSSELR_MAX 14
+/*
+ * Returns the minimum line size for the selected cache, expressed as
+ * Log2(bytes).
+ */
+static u8 get_min_cache_line_size(bool icache)
+{
+ u64 ctr = read_sanitised_ftr_reg(SYS_CTR_EL0);
+ u8 field;
+
+ if (icache)
+ field = SYS_FIELD_GET(CTR_EL0, IminLine, ctr);
+ else
+ field = SYS_FIELD_GET(CTR_EL0, DminLine, ctr);
+
+ /*
+ * Cache line size is represented as Log2(words) in CTR_EL0.
+ * Log2(bytes) can be derived with the following:
+ *
+ * Log2(words) + 2 = Log2(bytes / 4) + 2
+ * = Log2(bytes) - 2 + 2
+ * = Log2(bytes)
+ */
+ return field + 2;
+}
+
/* Which cache CCSIDR represents depends on CSSELR value. */
-static u32 get_ccsidr(u32 csselr)
+static u32 get_ccsidr(struct kvm_vcpu *vcpu, u32 csselr)
+{
+ u8 line_size;
+
+ if (vcpu->arch.ccsidr)
+ return vcpu->arch.ccsidr[csselr];
+
+ line_size = get_min_cache_line_size(csselr & CSSELR_EL1_InD);
+
+ /*
+ * Fabricate a CCSIDR value as the overriding value does not exist.
+ * The real CCSIDR value will not be used as it can vary by the
+ * physical CPU which the vcpu currently resides in.
+ *
+ * The line size is determined with get_min_cache_line_size(), which
+ * should be valid for all CPUs even if they have different cache
+ * configuration.
+ *
+ * The associativity bits are cleared, meaning the geometry of all data
+ * and unified caches (which are guaranteed to be PIPT and thus
+ * non-aliasing) are 1 set and 1 way.
+ * Guests should not be doing cache operations by set/way at all, and
+ * for this reason, we trap them and attempt to infer the intent, so
+ * that we can flush the entire guest's address space at the appropriate
+ * time. The exposed geometry minimizes the number of the traps.
+ * [If guests should attempt to infer aliasing properties from the
+ * geometry (which is not permitted by the architecture), they would
+ * only do so for virtually indexed caches.]
+ *
+ * We don't check if the cache level exists as it is allowed to return
+ * an UNKNOWN value if not.
+ */
+ return SYS_FIELD_PREP(CCSIDR_EL1, LineSize, line_size - 4);
+}
+
+static int set_ccsidr(struct kvm_vcpu *vcpu, u32 csselr, u32 val)
{
- u32 ccsidr;
+ u8 line_size = FIELD_GET(CCSIDR_EL1_LineSize, val) + 4;
+ u32 *ccsidr = vcpu->arch.ccsidr;
+ u32 i;
+
+ if ((val & CCSIDR_EL1_RES0) ||
+ line_size < get_min_cache_line_size(csselr & CSSELR_EL1_InD))
+ return -EINVAL;
+
+ if (!ccsidr) {
+ if (val == get_ccsidr(vcpu, csselr))
+ return 0;
+
+ ccsidr = kmalloc_array(CSSELR_MAX, sizeof(u32), GFP_KERNEL_ACCOUNT);
+ if (!ccsidr)
+ return -ENOMEM;
- /* Make sure noone else changes CSSELR during this! */
- local_irq_disable();
- write_sysreg(csselr, csselr_el1);
- isb();
- ccsidr = read_sysreg(ccsidr_el1);
- local_irq_enable();
+ for (i = 0; i < CSSELR_MAX; i++)
+ ccsidr[i] = get_ccsidr(vcpu, i);
- return ccsidr;
+ vcpu->arch.ccsidr = ccsidr;
+ }
+
+ ccsidr[csselr] = val;
+
+ return 0;
}
/*
@@ -646,7 +719,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
return;
/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
- pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
+ pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
if (!kvm_supports_32bit_el0())
pmcr |= ARMV8_PMU_PMCR_LC;
@@ -1049,7 +1122,9 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
treg = TIMER_REG_CVAL;
break;
default:
- BUG();
+ print_sys_reg_msg(p, "%s", "Unhandled trapped timer register");
+ kvm_inject_undefined(vcpu);
+ return false;
}
if (p->is_write)
@@ -1155,6 +1230,12 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r
val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon),
pmuver_to_perfmon(vcpu_pmuver(vcpu)));
break;
+ case SYS_ID_AA64MMFR2_EL1:
+ val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
+ break;
+ case SYS_ID_MMFR4_EL1:
+ val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
+ break;
}
return val;
@@ -1385,10 +1466,78 @@ static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (p->is_write)
return write_to_read_only(vcpu, p, r);
- p->regval = read_sysreg(clidr_el1);
+ p->regval = __vcpu_sys_reg(vcpu, r->reg);
return true;
}
+/*
+ * Fabricate a CLIDR_EL1 value instead of using the real value, which can vary
+ * by the physical CPU which the vcpu currently resides in.
+ */
+static void reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
+ u64 clidr;
+ u8 loc;
+
+ if ((ctr_el0 & CTR_EL0_IDC)) {
+ /*
+ * Data cache clean to the PoU is not required so LoUU and LoUIS
+ * will not be set and a unified cache, which will be marked as
+ * LoC, will be added.
+ *
+ * If not DIC, let the unified cache L2 so that an instruction
+ * cache can be added as L1 later.
+ */
+ loc = (ctr_el0 & CTR_EL0_DIC) ? 1 : 2;
+ clidr = CACHE_TYPE_UNIFIED << CLIDR_CTYPE_SHIFT(loc);
+ } else {
+ /*
+ * Data cache clean to the PoU is required so let L1 have a data
+ * cache and mark it as LoUU and LoUIS. As L1 has a data cache,
+ * it can be marked as LoC too.
+ */
+ loc = 1;
+ clidr = 1 << CLIDR_LOUU_SHIFT;
+ clidr |= 1 << CLIDR_LOUIS_SHIFT;
+ clidr |= CACHE_TYPE_DATA << CLIDR_CTYPE_SHIFT(1);
+ }
+
+ /*
+ * Instruction cache invalidation to the PoU is required so let L1 have
+ * an instruction cache. If L1 already has a data cache, it will be
+ * CACHE_TYPE_SEPARATE.
+ */
+ if (!(ctr_el0 & CTR_EL0_DIC))
+ clidr |= CACHE_TYPE_INST << CLIDR_CTYPE_SHIFT(1);
+
+ clidr |= loc << CLIDR_LOC_SHIFT;
+
+ /*
+ * Add tag cache unified to data cache. Allocation tags and data are
+ * unified in a cache line so that it looks valid even if there is only
+ * one cache line.
+ */
+ if (kvm_has_mte(vcpu->kvm))
+ clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
+
+ __vcpu_sys_reg(vcpu, r->reg) = clidr;
+}
+
+static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+ u64 val)
+{
+ u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0);
+ u64 idc = !CLIDR_LOC(val) || (!CLIDR_LOUIS(val) && !CLIDR_LOUU(val));
+
+ if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc))
+ return -EINVAL;
+
+ __vcpu_sys_reg(vcpu, rd->reg) = val;
+
+ return 0;
+}
+
static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
@@ -1410,22 +1559,10 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
return write_to_read_only(vcpu, p, r);
csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1);
- p->regval = get_ccsidr(csselr);
+ csselr &= CSSELR_EL1_Level | CSSELR_EL1_InD;
+ if (csselr < CSSELR_MAX)
+ p->regval = get_ccsidr(vcpu, csselr);
- /*
- * Guests should not be doing cache operations by set/way at all, and
- * for this reason, we trap them and attempt to infer the intent, so
- * that we can flush the entire guest's address space at the appropriate
- * time.
- * To prevent this trapping from causing performance problems, let's
- * expose the geometry of all data and unified caches (which are
- * guaranteed to be PIPT and thus non-aliasing) as 1 set and 1 way.
- * [If guests should attempt to infer aliasing properties from the
- * geometry (which is not permitted by the architecture), they would
- * only do so for virtually indexed caches.]
- */
- if (!(csselr & 1)) // data or unified cache
- p->regval &= ~GENMASK(27, 3);
return true;
}
@@ -1717,7 +1854,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
- { SYS_DESC(SYS_CLIDR_EL1), access_clidr },
+ { SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1,
+ .set_user = set_clidr },
+ { SYS_DESC(SYS_CCSIDR2_EL1), undef_access },
{ SYS_DESC(SYS_SMIDR_EL1), undef_access },
{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
{ SYS_DESC(SYS_CTR_EL0), access_ctr },
@@ -2219,6 +2358,10 @@ static const struct sys_reg_desc cp15_regs[] = {
{ Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr },
{ Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr },
+
+ /* CCSIDR2 */
+ { Op1(1), CRn( 0), CRm( 0), Op2(2), undef_access },
+
{ Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, CSSELR_EL1 },
};
@@ -2724,7 +2867,6 @@ id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id,
FUNCTION_INVARIANT(midr_el1)
FUNCTION_INVARIANT(revidr_el1)
-FUNCTION_INVARIANT(clidr_el1)
FUNCTION_INVARIANT(aidr_el1)
static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r)
@@ -2733,10 +2875,9 @@ static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r)
}
/* ->val is filled in by kvm_sys_reg_table_init() */
-static struct sys_reg_desc invariant_sys_regs[] = {
+static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = {
{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },
{ SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 },
- { SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 },
{ SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 },
{ SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 },
};
@@ -2773,33 +2914,7 @@ static int set_invariant_sys_reg(u64 id, u64 __user *uaddr)
return 0;
}
-static bool is_valid_cache(u32 val)
-{
- u32 level, ctype;
-
- if (val >= CSSELR_MAX)
- return false;
-
- /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */
- level = (val >> 1);
- ctype = (cache_levels >> (level * 3)) & 7;
-
- switch (ctype) {
- case 0: /* No cache */
- return false;
- case 1: /* Instruction cache only */
- return (val & 1);
- case 2: /* Data cache only */
- case 4: /* Unified cache */
- return !(val & 1);
- case 3: /* Separate instruction and data caches */
- return true;
- default: /* Reserved: we can't know instruction or data. */
- return false;
- }
-}
-
-static int demux_c15_get(u64 id, void __user *uaddr)
+static int demux_c15_get(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
{
u32 val;
u32 __user *uval = uaddr;
@@ -2815,16 +2930,16 @@ static int demux_c15_get(u64 id, void __user *uaddr)
return -ENOENT;
val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
>> KVM_REG_ARM_DEMUX_VAL_SHIFT;
- if (!is_valid_cache(val))
+ if (val >= CSSELR_MAX)
return -ENOENT;
- return put_user(get_ccsidr(val), uval);
+ return put_user(get_ccsidr(vcpu, val), uval);
default:
return -ENOENT;
}
}
-static int demux_c15_set(u64 id, void __user *uaddr)
+static int demux_c15_set(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
{
u32 val, newval;
u32 __user *uval = uaddr;
@@ -2840,16 +2955,13 @@ static int demux_c15_set(u64 id, void __user *uaddr)
return -ENOENT;
val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
>> KVM_REG_ARM_DEMUX_VAL_SHIFT;
- if (!is_valid_cache(val))
+ if (val >= CSSELR_MAX)
return -ENOENT;
if (get_user(newval, uval))
return -EFAULT;
- /* This is also invariant: you can't change it. */
- if (newval != get_ccsidr(val))
- return -EINVAL;
- return 0;
+ return set_ccsidr(vcpu, val, newval);
default:
return -ENOENT;
}
@@ -2886,7 +2998,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
int err;
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
- return demux_c15_get(reg->id, uaddr);
+ return demux_c15_get(vcpu, reg->id, uaddr);
err = get_invariant_sys_reg(reg->id, uaddr);
if (err != -ENOENT)
@@ -2930,7 +3042,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
int err;
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
- return demux_c15_set(reg->id, uaddr);
+ return demux_c15_set(vcpu, reg->id, uaddr);
err = set_invariant_sys_reg(reg->id, uaddr);
if (err != -ENOENT)
@@ -2942,13 +3054,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
static unsigned int num_demux_regs(void)
{
- unsigned int i, count = 0;
-
- for (i = 0; i < CSSELR_MAX; i++)
- if (is_valid_cache(i))
- count++;
-
- return count;
+ return CSSELR_MAX;
}
static int write_demux_regids(u64 __user *uindices)
@@ -2958,8 +3064,6 @@ static int write_demux_regids(u64 __user *uindices)
val |= KVM_REG_ARM_DEMUX_ID_CCSIDR;
for (i = 0; i < CSSELR_MAX; i++) {
- if (!is_valid_cache(i))
- continue;
if (put_user(val | i, uindices))
return -EFAULT;
uindices++;
@@ -3057,11 +3161,10 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
return write_demux_regids(uindices);
}
-int kvm_sys_reg_table_init(void)
+int __init kvm_sys_reg_table_init(void)
{
bool valid = true;
unsigned int i;
- struct sys_reg_desc clidr;
/* Make sure tables are unique and in order. */
valid &= check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false);
@@ -3078,23 +3181,5 @@ int kvm_sys_reg_table_init(void)
for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]);
- /*
- * CLIDR format is awkward, so clean it up. See ARM B4.1.20:
- *
- * If software reads the Cache Type fields from Ctype1
- * upwards, once it has seen a value of 0b000, no caches
- * exist at further-out levels of the hierarchy. So, for
- * example, if Ctype3 is the first Cache Type field with a
- * value of 0b000, the values of Ctype4 to Ctype7 must be
- * ignored.
- */
- get_clidr_el1(NULL, &clidr); /* Ugly... */
- cache_levels = clidr.val;
- for (i = 0; i < 7; i++)
- if (((cache_levels >> (i*3)) & 7) == 0)
- break;
- /* Clear all higher bits. */
- cache_levels &= (1 << (i*3))-1;
-
return 0;
}
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index f6d4f4052555..6c7f6ae21ec0 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -465,17 +465,15 @@ out:
/* GENERIC PROBE */
-static int vgic_init_cpu_starting(unsigned int cpu)
+void kvm_vgic_cpu_up(void)
{
enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
- return 0;
}
-static int vgic_init_cpu_dying(unsigned int cpu)
+void kvm_vgic_cpu_down(void)
{
disable_percpu_irq(kvm_vgic_global_state.maint_irq);
- return 0;
}
static irqreturn_t vgic_maintenance_handler(int irq, void *data)
@@ -584,19 +582,6 @@ int kvm_vgic_hyp_init(void)
return ret;
}
- ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
- "kvm/arm/vgic:starting",
- vgic_init_cpu_starting, vgic_init_cpu_dying);
- if (ret) {
- kvm_err("Cannot register vgic CPU notifier\n");
- goto out_free_irq;
- }
-
kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
return 0;
-
-out_free_irq:
- free_percpu_irq(kvm_vgic_global_state.maint_irq,
- kvm_get_running_vcpus());
- return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 826ff6f2a4e7..2074521d4a8c 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -616,6 +616,8 @@ static const struct midr_range broken_seis[] = {
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
{},
};
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index d78ae63d7c15..08978d0672e7 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -16,7 +16,7 @@
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
-unsigned int kvm_arm_vmid_bits;
+unsigned int __ro_after_init kvm_arm_vmid_bits;
static DEFINE_RAW_SPINLOCK(cpu_vmid_lock);
static atomic64_t vmid_generation;
@@ -172,7 +172,7 @@ void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
/*
* Initialize the VMID allocator
*/
-int kvm_arm_vmid_alloc_init(void)
+int __init kvm_arm_vmid_alloc_init(void)
{
kvm_arm_vmid_bits = kvm_get_vmid_bits();
@@ -190,7 +190,7 @@ int kvm_arm_vmid_alloc_init(void)
return 0;
}
-void kvm_arm_vmid_alloc_free(void)
+void __init kvm_arm_vmid_alloc_free(void)
{
kfree(vmid_map);
}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 35e9a468d13e..95364e8bdc19 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
{
return __hugetlb_valid_size(size);
}
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return huge_ptep_clear_flush(vma, addr, ptep);
+ }
+ return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 14c87e8d69d8..d77c9f56b7b4 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1630,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void)
}
early_initcall(prevent_bootmem_remove_init);
#endif
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return ptep_clear_flush(vma, addr, ptep);
+ }
+ return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index a86ee376920a..37b6a1d8d8b0 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -50,6 +50,7 @@ MTE
MTE_ASYMM
SME
SME_FA64
+SME2
SPECTRE_V2
SPECTRE_V3A
SPECTRE_V4
@@ -71,6 +72,7 @@ WORKAROUND_2038923
WORKAROUND_2064142
WORKAROUND_2077057
WORKAROUND_2457168
+WORKAROUND_2645198
WORKAROUND_2658417
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk
index c350164a3955..e1df4b956596 100755
--- a/arch/arm64/tools/gen-sysreg.awk
+++ b/arch/arm64/tools/gen-sysreg.awk
@@ -98,6 +98,7 @@ END {
res0 = "UL(0)"
res1 = "UL(0)"
+ unkn = "UL(0)"
next_bit = 63
@@ -112,11 +113,13 @@ END {
define(reg "_RES0", "(" res0 ")")
define(reg "_RES1", "(" res1 ")")
+ define(reg "_UNKN", "(" unkn ")")
print ""
reg = null
res0 = null
res1 = null
+ unkn = null
next
}
@@ -134,6 +137,7 @@ END {
res0 = "UL(0)"
res1 = "UL(0)"
+ unkn = "UL(0)"
define("REG_" reg, "S" op0 "_" op1 "_C" crn "_C" crm "_" op2)
define("SYS_" reg, "sys_reg(" op0 ", " op1 ", " crn ", " crm ", " op2 ")")
@@ -161,7 +165,9 @@ END {
define(reg "_RES0", "(" res0 ")")
if (res1 != null)
define(reg "_RES1", "(" res1 ")")
- if (res0 != null || res1 != null)
+ if (unkn != null)
+ define(reg "_UNKN", "(" unkn ")")
+ if (res0 != null || res1 != null || unkn != null)
print ""
reg = null
@@ -172,6 +178,7 @@ END {
op2 = null
res0 = null
res1 = null
+ unkn = null
next
}
@@ -190,6 +197,7 @@ END {
next_bit = 0
res0 = null
res1 = null
+ unkn = null
next
}
@@ -215,6 +223,16 @@ END {
next
}
+/^Unkn/ && (block == "Sysreg" || block == "SysregFields") {
+ expect_fields(2)
+ parse_bitdef(reg, "UNKN", $2)
+ field = "UNKN_" msb "_" lsb
+
+ unkn = unkn " | GENMASK_ULL(" msb ", " lsb ")"
+
+ next
+}
+
/^Field/ && (block == "Sysreg" || block == "SysregFields") {
expect_fields(3)
field = $3
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 184e58fd5631..330569fb2336 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -15,6 +15,8 @@
# Res1 <msb>[:<lsb>]
+# Unkn <msb>[:<lsb>]
+
# Field <msb>[:<lsb>] <name>
# Enum <msb>[:<lsb>] <name>
@@ -894,6 +896,7 @@ EndEnum
Enum 27:24 SME
0b0000 NI
0b0001 IMP
+ 0b0010 SME2
EndEnum
Res0 23:20
Enum 19:16 MPAM_frac
@@ -975,7 +978,9 @@ Enum 63 FA64
EndEnum
Res0 62:60
Enum 59:56 SMEver
- 0b0000 IMP
+ 0b0000 SME
+ 0b0001 SME2
+ 0b0010 SME2p1
EndEnum
Enum 55:52 I16I64
0b0000 NI
@@ -986,7 +991,19 @@ Enum 48 F64F64
0b0 NI
0b1 IMP
EndEnum
-Res0 47:40
+Enum 47:44 I16I32
+ 0b0000 NI
+ 0b0101 IMP
+EndEnum
+Enum 43 B16B16
+ 0b0 NI
+ 0b1 IMP
+EndEnum
+Enum 42 F16F16
+ 0b0 NI
+ 0b1 IMP
+EndEnum
+Res0 41:40
Enum 39:36 I8I32
0b0000 NI
0b1111 IMP
@@ -999,7 +1016,10 @@ Enum 34 B16F32
0b0 NI
0b1 IMP
EndEnum
-Res0 33
+Enum 33 BI32I32
+ 0b0 NI
+ 0b1 IMP
+EndEnum
Enum 32 F32F32
0b0 NI
0b1 IMP
@@ -1599,7 +1619,8 @@ EndSysreg
SysregFields SMCR_ELx
Res0 63:32
Field 31 FA64
-Res0 30:9
+Field 30 EZT0
+Res0 29:9
Raz 8:4
Field 3:0 LEN
EndSysregFields
@@ -1635,6 +1656,16 @@ Sysreg SCXTNUM_EL1 3 0 13 0 7
Field 63:0 SoftwareContextNumber
EndSysreg
+# The bit layout for CCSIDR_EL1 depends on whether FEAT_CCIDX is implemented.
+# The following is for case when FEAT_CCIDX is not implemented.
+Sysreg CCSIDR_EL1 3 1 0 0 0
+Res0 63:32
+Unkn 31:28
+Field 27:13 NumSets
+Field 12:3 Associativity
+Field 2:0 LineSize
+EndSysreg
+
Sysreg CLIDR_EL1 3 1 0 0 1
Res0 63:47
Field 46:33 Ttypen
@@ -1651,6 +1682,11 @@ Field 5:3 Ctype2
Field 2:0 Ctype1
EndSysreg
+Sysreg CCSIDR2_EL1 3 1 0 0 2
+Res0 63:24
+Field 23:0 NumSets
+EndSysreg
+
Sysreg GMID_EL1 3 1 0 0 4
Res0 63:4
Field 3:0 BS