diff options
Diffstat (limited to 'arch/arm64')
-rw-r--r-- | arch/arm64/crypto/aes-glue.c | 2 | ||||
-rw-r--r-- | arch/arm64/crypto/aes-modes.S | 88 | ||||
-rw-r--r-- | arch/arm64/include/asm/kvm_emulate.h | 16 | ||||
-rw-r--r-- | arch/arm64/include/asm/percpu.h | 120 | ||||
-rw-r--r-- | arch/arm64/include/asm/spinlock.h | 10 | ||||
-rw-r--r-- | arch/arm64/include/uapi/asm/ptrace.h | 1 | ||||
-rw-r--r-- | arch/arm64/kernel/head.S | 3 | ||||
-rw-r--r-- | arch/arm64/kernel/ptrace.c | 11 |
8 files changed, 131 insertions, 120 deletions
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 05d9e16c0dfd..6a51dfccfe71 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -211,7 +211,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE); } - if (nbytes) { + if (walk.nbytes % AES_BLOCK_SIZE) { u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; u8 __aligned(8) tail[AES_BLOCK_SIZE]; diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index f6e372c528eb..94b5669ee4d3 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt) cbz w6, .Lcbcencloop ld1 {v0.16b}, [x5] /* get iv */ - enc_prepare w3, x2, x5 + enc_prepare w3, x2, x6 .Lcbcencloop: ld1 {v1.16b}, [x1], #16 /* get next pt block */ eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */ - encrypt_block v0, w3, x2, x5, w6 + encrypt_block v0, w3, x2, x6, w7 st1 {v0.16b}, [x0], #16 subs w4, w4, #1 bne .Lcbcencloop + st1 {v0.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_encrypt) @@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt) cbz w6, .LcbcdecloopNx ld1 {v7.16b}, [x5] /* get iv */ - dec_prepare w3, x2, x5 + dec_prepare w3, x2, x6 .LcbcdecloopNx: #if INTERLEAVE >= 2 @@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt) .Lcbcdecloop: ld1 {v1.16b}, [x1], #16 /* get next ct block */ mov v0.16b, v1.16b /* ...and copy to v0 */ - decrypt_block v0, w3, x2, x5, w6 + decrypt_block v0, w3, x2, x6, w7 eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */ mov v7.16b, v1.16b /* ct is next iv */ st1 {v0.16b}, [x0], #16 @@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt) bne .Lcbcdecloop .Lcbcdecout: FRAME_POP + st1 {v7.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_decrypt) @@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt) AES_ENTRY(aes_ctr_encrypt) FRAME_PUSH - cbnz w6, .Lctrfirst /* 1st time around? */ - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 -#if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ - bcs .Lctrinc - add x5, x5, #1 /* increment BE ctr */ - b .LctrincNx -#else - b .Lctrinc -#endif -.Lctrfirst: + cbz w6, .Lctrnotfirst /* 1st time around? */ enc_prepare w3, x2, x6 ld1 {v4.16b}, [x5] - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 + +.Lctrnotfirst: + umov x8, v4.d[1] /* keep swabbed ctr in reg */ + rev x8, x8 #if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ + cmn w8, w4 /* 32 bit overflow? */ bcs .Lctrloop .LctrloopNx: subs w4, w4, #INTERLEAVE @@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt) #if INTERLEAVE == 2 mov v0.8b, v4.8b mov v1.8b, v4.8b - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v0.d[1], x7 - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v1.d[1], x7 ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ do_encrypt_block2x @@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt) st1 {v0.16b-v1.16b}, [x0], #32 #else ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ - dup v7.4s, w5 + dup v7.4s, w8 mov v0.16b, v4.16b add v7.4s, v7.4s, v8.4s mov v1.16b, v4.16b @@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt) eor v2.16b, v7.16b, v2.16b eor v3.16b, v5.16b, v3.16b st1 {v0.16b-v3.16b}, [x0], #64 - add x5, x5, #INTERLEAVE + add x8, x8, #INTERLEAVE #endif - cbz w4, .LctroutNx -.LctrincNx: - rev x7, x5 + rev x7, x8 ins v4.d[1], x7 + cbz w4, .Lctrout b .LctrloopNx -.LctroutNx: - sub x5, x5, #1 - rev x7, x5 - ins v4.d[1], x7 - b .Lctrout .Lctr1x: adds w4, w4, #INTERLEAVE beq .Lctrout @@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt) .Lctrloop: mov v0.16b, v4.16b encrypt_block v0, w3, x2, x6, w7 + + adds x8, x8, #1 /* increment BE ctr */ + rev x7, x8 + ins v4.d[1], x7 + bcs .Lctrcarry /* overflow? */ + +.Lctrcarrydone: subs w4, w4, #1 bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */ ld1 {v3.16b}, [x1], #16 eor v3.16b, v0.16b, v3.16b st1 {v3.16b}, [x0], #16 - beq .Lctrout -.Lctrinc: - adds x5, x5, #1 /* increment BE ctr */ - rev x7, x5 - ins v4.d[1], x7 - bcc .Lctrloop /* no overflow? */ - umov x7, v4.d[0] /* load upper word of ctr */ - rev x7, x7 /* ... to handle the carry */ - add x7, x7, #1 - rev x7, x7 - ins v4.d[0], x7 - b .Lctrloop + bne .Lctrloop + +.Lctrout: + st1 {v4.16b}, [x5] /* return next CTR value */ + FRAME_POP + ret + .Lctrhalfblock: ld1 {v3.8b}, [x1] eor v3.8b, v0.8b, v3.8b st1 {v3.8b}, [x0] -.Lctrout: FRAME_POP ret + +.Lctrcarry: + umov x7, v4.d[0] /* load upper word of ctr */ + rev x7, x7 /* ... to handle the carry */ + add x7, x7, #1 + rev x7, x7 + ins v4.d[0], x7 + b .Lctrcarrydone AES_ENDPROC(aes_ctr_encrypt) .ltorg diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 3ca894ecf699..3e3c4c7a5082 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -153,11 +153,6 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); } -static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) -{ - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR); -} - static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE); @@ -178,6 +173,17 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } +static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) +{ + return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || + kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ +} + +static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) +{ + return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM); +} + static inline int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) { return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 4fde8c1df97f..9d096bc89287 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -52,48 +52,44 @@ static inline unsigned long __percpu_##op(void *ptr, \ \ switch (size) { \ case 1: \ - do { \ - asm ("//__per_cpu_" #op "_1\n" \ - "ldxrb %w[ret], %[ptr]\n" \ + asm ("//__per_cpu_" #op "_1\n" \ + "1: ldxrb %w[ret], %[ptr]\n" \ #asm_op " %w[ret], %w[ret], %w[val]\n" \ - "stxrb %w[loop], %w[ret], %[ptr]\n" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u8 *)ptr) \ - : [val] "Ir" (val)); \ - } while (loop); \ + " stxrb %w[loop], %w[ret], %[ptr]\n" \ + " cbnz %w[loop], 1b" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u8 *)ptr) \ + : [val] "Ir" (val)); \ break; \ case 2: \ - do { \ - asm ("//__per_cpu_" #op "_2\n" \ - "ldxrh %w[ret], %[ptr]\n" \ + asm ("//__per_cpu_" #op "_2\n" \ + "1: ldxrh %w[ret], %[ptr]\n" \ #asm_op " %w[ret], %w[ret], %w[val]\n" \ - "stxrh %w[loop], %w[ret], %[ptr]\n" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u16 *)ptr) \ - : [val] "Ir" (val)); \ - } while (loop); \ + " stxrh %w[loop], %w[ret], %[ptr]\n" \ + " cbnz %w[loop], 1b" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u16 *)ptr) \ + : [val] "Ir" (val)); \ break; \ case 4: \ - do { \ - asm ("//__per_cpu_" #op "_4\n" \ - "ldxr %w[ret], %[ptr]\n" \ + asm ("//__per_cpu_" #op "_4\n" \ + "1: ldxr %w[ret], %[ptr]\n" \ #asm_op " %w[ret], %w[ret], %w[val]\n" \ - "stxr %w[loop], %w[ret], %[ptr]\n" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u32 *)ptr) \ - : [val] "Ir" (val)); \ - } while (loop); \ + " stxr %w[loop], %w[ret], %[ptr]\n" \ + " cbnz %w[loop], 1b" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u32 *)ptr) \ + : [val] "Ir" (val)); \ break; \ case 8: \ - do { \ - asm ("//__per_cpu_" #op "_8\n" \ - "ldxr %[ret], %[ptr]\n" \ + asm ("//__per_cpu_" #op "_8\n" \ + "1: ldxr %[ret], %[ptr]\n" \ #asm_op " %[ret], %[ret], %[val]\n" \ - "stxr %w[loop], %[ret], %[ptr]\n" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u64 *)ptr) \ - : [val] "Ir" (val)); \ - } while (loop); \ + " stxr %w[loop], %[ret], %[ptr]\n" \ + " cbnz %w[loop], 1b" \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u64 *)ptr) \ + : [val] "Ir" (val)); \ break; \ default: \ BUILD_BUG(); \ @@ -158,44 +154,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, switch (size) { case 1: - do { - asm ("//__percpu_xchg_1\n" - "ldxrb %w[ret], %[ptr]\n" - "stxrb %w[loop], %w[val], %[ptr]\n" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u8 *)ptr) - : [val] "r" (val)); - } while (loop); + asm ("//__percpu_xchg_1\n" + "1: ldxrb %w[ret], %[ptr]\n" + " stxrb %w[loop], %w[val], %[ptr]\n" + " cbnz %w[loop], 1b" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u8 *)ptr) + : [val] "r" (val)); break; case 2: - do { - asm ("//__percpu_xchg_2\n" - "ldxrh %w[ret], %[ptr]\n" - "stxrh %w[loop], %w[val], %[ptr]\n" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u16 *)ptr) - : [val] "r" (val)); - } while (loop); + asm ("//__percpu_xchg_2\n" + "1: ldxrh %w[ret], %[ptr]\n" + " stxrh %w[loop], %w[val], %[ptr]\n" + " cbnz %w[loop], 1b" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u16 *)ptr) + : [val] "r" (val)); break; case 4: - do { - asm ("//__percpu_xchg_4\n" - "ldxr %w[ret], %[ptr]\n" - "stxr %w[loop], %w[val], %[ptr]\n" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u32 *)ptr) - : [val] "r" (val)); - } while (loop); + asm ("//__percpu_xchg_4\n" + "1: ldxr %w[ret], %[ptr]\n" + " stxr %w[loop], %w[val], %[ptr]\n" + " cbnz %w[loop], 1b" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u32 *)ptr) + : [val] "r" (val)); break; case 8: - do { - asm ("//__percpu_xchg_8\n" - "ldxr %[ret], %[ptr]\n" - "stxr %w[loop], %[val], %[ptr]\n" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u64 *)ptr) - : [val] "r" (val)); - } while (loop); + asm ("//__percpu_xchg_8\n" + "1: ldxr %[ret], %[ptr]\n" + " stxr %w[loop], %[val], %[ptr]\n" + " cbnz %w[loop], 1b" + : [loop] "=&r"(loop), [ret] "=&r"(ret), + [ptr] "+Q"(*(u64 *)ptr) + : [val] "r" (val)); break; default: BUILD_BUG(); diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index cee128732435..d155a9bbfab6 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -231,4 +231,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() +/* + * Accesses appearing in program order before a spin_lock() operation + * can be reordered with accesses inside the critical section, by virtue + * of arch_spin_lock being constructed using acquire semantics. + * + * In cases where this is problematic (e.g. try_to_wake_up), an + * smp_mb__before_spinlock() can restore the required ordering. + */ +#define smp_mb__before_spinlock() smp_mb() + #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 6913643bbe54..c136fd53c847 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -75,6 +75,7 @@ struct user_fpsimd_state { __uint128_t vregs[32]; __u32 fpsr; __u32 fpcr; + __u32 __reserved[2]; }; struct user_hwdebug_state { diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index cc7435c9676e..b346b35f827d 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -572,8 +572,9 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to - msr mdcr_el2, x0 // all PMU counters from EL1 4: + csel x0, xzr, x0, lt // all PMU counters from EL1 + msr mdcr_el2, x0 // (if they exist) /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 7038b9a3b42c..f7738bbc8c3f 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -450,6 +450,8 @@ static int hw_break_set(struct task_struct *target, /* (address, ctrl) registers */ limit = regset->n * regset->size; while (count && offset < limit) { + if (count < PTRACE_HBP_ADDR_SZ) + return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, offset, offset + PTRACE_HBP_ADDR_SZ); if (ret) @@ -459,6 +461,8 @@ static int hw_break_set(struct task_struct *target, return ret; offset += PTRACE_HBP_ADDR_SZ; + if (!count) + break; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, offset, offset + PTRACE_HBP_CTRL_SZ); if (ret) @@ -495,7 +499,7 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { int ret; - struct user_pt_regs newregs; + struct user_pt_regs newregs = task_pt_regs(target)->user_regs; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1); if (ret) @@ -525,7 +529,8 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { int ret; - struct user_fpsimd_state newstate; + struct user_fpsimd_state newstate = + target->thread.fpsimd_state.user_fpsimd; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1); if (ret) @@ -549,7 +554,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { int ret; - unsigned long tls; + unsigned long tls = target->thread.tp_value; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); if (ret) |