diff options
Diffstat (limited to 'arch/arm64')
-rw-r--r-- | arch/arm64/Kconfig | 4 | ||||
-rw-r--r-- | arch/arm64/crypto/aes-ce-ccm-core.S | 150 | ||||
-rw-r--r-- | arch/arm64/crypto/ghash-ce-core.S | 76 | ||||
-rw-r--r-- | arch/arm64/crypto/ghash-ce-glue.c | 8 | ||||
-rw-r--r-- | arch/arm64/include/asm/efi.h | 3 | ||||
-rw-r--r-- | arch/arm64/include/asm/irq.h | 2 | ||||
-rw-r--r-- | arch/arm64/include/asm/tlb.h | 2 | ||||
-rw-r--r-- | arch/arm64/kernel/cpufeature.c | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/irq.c | 10 | ||||
-rw-r--r-- | arch/arm64/mm/hugetlbpage.c | 7 | ||||
-rw-r--r-- | arch/arm64/mm/init.c | 4 |
11 files changed, 100 insertions, 170 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 42c090cf0292..3d1011957823 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -74,6 +74,7 @@ config ARM64 select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP select GENERIC_IDLE_POLL_SETUP + select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -264,9 +265,6 @@ config ARCH_SUPPORTS_UPROBES config ARCH_PROC_KCORE_TEXT def_bool y -config MULTI_IRQ_HANDLER - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S index 88f5aef7934c..e3a375c4cb83 100644 --- a/arch/arm64/crypto/aes-ce-ccm-core.S +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -19,33 +19,24 @@ * u32 *macp, u8 const rk[], u32 rounds); */ ENTRY(ce_aes_ccm_auth_data) - frame_push 7 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - - ldr w25, [x22] /* leftover from prev round? */ + ldr w8, [x3] /* leftover from prev round? */ ld1 {v0.16b}, [x0] /* load mac */ - cbz w25, 1f - sub w25, w25, #16 + cbz w8, 1f + sub w8, w8, #16 eor v1.16b, v1.16b, v1.16b -0: ldrb w7, [x20], #1 /* get 1 byte of input */ - subs w21, w21, #1 - add w25, w25, #1 +0: ldrb w7, [x1], #1 /* get 1 byte of input */ + subs w2, w2, #1 + add w8, w8, #1 ins v1.b[0], w7 ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */ beq 8f /* out of input? */ - cbnz w25, 0b + cbnz w8, 0b eor v0.16b, v0.16b, v1.16b -1: ld1 {v3.4s}, [x23] /* load first round key */ - prfm pldl1strm, [x20] - cmp w24, #12 /* which key size? */ - add x6, x23, #16 - sub w7, w24, #2 /* modified # of rounds */ +1: ld1 {v3.4s}, [x4] /* load first round key */ + prfm pldl1strm, [x1] + cmp w5, #12 /* which key size? */ + add x6, x4, #16 + sub w7, w5, #2 /* modified # of rounds */ bmi 2f bne 5f mov v5.16b, v3.16b @@ -64,43 +55,33 @@ ENTRY(ce_aes_ccm_auth_data) ld1 {v5.4s}, [x6], #16 /* load next round key */ bpl 3b aese v0.16b, v4.16b - subs w21, w21, #16 /* last data? */ + subs w2, w2, #16 /* last data? */ eor v0.16b, v0.16b, v5.16b /* final round */ bmi 6f - ld1 {v1.16b}, [x20], #16 /* load next input block */ + ld1 {v1.16b}, [x1], #16 /* load next input block */ eor v0.16b, v0.16b, v1.16b /* xor with mac */ - beq 6f - - if_will_cond_yield_neon - st1 {v0.16b}, [x19] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x19] /* reload mac */ - endif_yield_neon - - b 1b -6: st1 {v0.16b}, [x19] /* store mac */ + bne 1b +6: st1 {v0.16b}, [x0] /* store mac */ beq 10f - adds w21, w21, #16 + adds w2, w2, #16 beq 10f - mov w25, w21 -7: ldrb w7, [x20], #1 + mov w8, w2 +7: ldrb w7, [x1], #1 umov w6, v0.b[0] eor w6, w6, w7 - strb w6, [x19], #1 - subs w21, w21, #1 + strb w6, [x0], #1 + subs w2, w2, #1 beq 10f ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ b 7b -8: mov w7, w25 - add w25, w25, #16 +8: mov w7, w8 + add w8, w8, #16 9: ext v1.16b, v1.16b, v1.16b, #1 adds w7, w7, #1 bne 9b eor v0.16b, v0.16b, v1.16b - st1 {v0.16b}, [x19] -10: str w25, [x22] - - frame_pop + st1 {v0.16b}, [x0] +10: str w8, [x3] ret ENDPROC(ce_aes_ccm_auth_data) @@ -145,29 +126,19 @@ ENTRY(ce_aes_ccm_final) ENDPROC(ce_aes_ccm_final) .macro aes_ccm_do_crypt,enc - frame_push 8 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - - ldr x26, [x25, #8] /* load lower ctr */ - ld1 {v0.16b}, [x24] /* load mac */ -CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ + ldr x8, [x6, #8] /* load lower ctr */ + ld1 {v0.16b}, [x5] /* load mac */ +CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */ 0: /* outer loop */ - ld1 {v1.8b}, [x25] /* load upper ctr */ - prfm pldl1strm, [x20] - add x26, x26, #1 - rev x9, x26 - cmp w23, #12 /* which key size? */ - sub w7, w23, #2 /* get modified # of rounds */ + ld1 {v1.8b}, [x6] /* load upper ctr */ + prfm pldl1strm, [x1] + add x8, x8, #1 + rev x9, x8 + cmp w4, #12 /* which key size? */ + sub w7, w4, #2 /* get modified # of rounds */ ins v1.d[1], x9 /* no carry in lower ctr */ - ld1 {v3.4s}, [x22] /* load first round key */ - add x10, x22, #16 + ld1 {v3.4s}, [x3] /* load first round key */ + add x10, x3, #16 bmi 1f bne 4f mov v5.16b, v3.16b @@ -194,9 +165,9 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ bpl 2b aese v0.16b, v4.16b aese v1.16b, v4.16b - subs w21, w21, #16 - bmi 7f /* partial block? */ - ld1 {v2.16b}, [x20], #16 /* load next input block */ + subs w2, w2, #16 + bmi 6f /* partial block? */ + ld1 {v2.16b}, [x1], #16 /* load next input block */ .if \enc == 1 eor v2.16b, v2.16b, v5.16b /* final round enc+mac */ eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */ @@ -205,29 +176,18 @@ CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */ eor v1.16b, v2.16b, v5.16b /* final round enc */ .endif eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */ - st1 {v1.16b}, [x19], #16 /* write output block */ - beq 5f - - if_will_cond_yield_neon - st1 {v0.16b}, [x24] /* store mac */ - do_cond_yield_neon - ld1 {v0.16b}, [x24] /* reload mac */ - endif_yield_neon - - b 0b -5: -CPU_LE( rev x26, x26 ) - st1 {v0.16b}, [x24] /* store mac */ - str x26, [x25, #8] /* store lsb end of ctr (BE) */ - -6: frame_pop - ret - -7: eor v0.16b, v0.16b, v5.16b /* final round mac */ + st1 {v1.16b}, [x0], #16 /* write output block */ + bne 0b +CPU_LE( rev x8, x8 ) + st1 {v0.16b}, [x5] /* store mac */ + str x8, [x6, #8] /* store lsb end of ctr (BE) */ +5: ret + +6: eor v0.16b, v0.16b, v5.16b /* final round mac */ eor v1.16b, v1.16b, v5.16b /* final round enc */ - st1 {v0.16b}, [x24] /* store mac */ - add w21, w21, #16 /* process partial tail block */ -8: ldrb w9, [x20], #1 /* get 1 byte of input */ + st1 {v0.16b}, [x5] /* store mac */ + add w2, w2, #16 /* process partial tail block */ +7: ldrb w9, [x1], #1 /* get 1 byte of input */ umov w6, v1.b[0] /* get top crypted ctr byte */ umov w7, v0.b[0] /* get top mac byte */ .if \enc == 1 @@ -237,13 +197,13 @@ CPU_LE( rev x26, x26 ) eor w9, w9, w6 eor w7, w7, w9 .endif - strb w9, [x19], #1 /* store out byte */ - strb w7, [x24], #1 /* store mac byte */ - subs w21, w21, #1 - beq 6b + strb w9, [x0], #1 /* store out byte */ + strb w7, [x5], #1 /* store mac byte */ + subs w2, w2, #1 + beq 5b ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */ ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */ - b 8b + b 7b .endm /* diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index dcffb9e77589..c723647b37db 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -322,55 +322,41 @@ ENDPROC(pmull_ghash_update_p8) .endm .macro pmull_gcm_do_crypt, enc - frame_push 10 + ld1 {SHASH.2d}, [x4] + ld1 {XL.2d}, [x1] + ldr x8, [x5, #8] // load lower counter - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 - mov x26, x7 - .if \enc == 1 - ldr x27, [sp, #96] // first stacked arg - .endif - - ldr x28, [x24, #8] // load lower counter -CPU_LE( rev x28, x28 ) - -0: mov x0, x25 - load_round_keys w26, x0 - ld1 {SHASH.2d}, [x23] - ld1 {XL.2d}, [x20] + load_round_keys w7, x6 movi MASK.16b, #0xe1 ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 +CPU_LE( rev x8, x8 ) shl MASK.2d, MASK.2d, #57 eor SHASH2.16b, SHASH2.16b, SHASH.16b .if \enc == 1 - ld1 {KS.16b}, [x27] + ldr x10, [sp] + ld1 {KS.16b}, [x10] .endif -1: ld1 {CTR.8b}, [x24] // load upper counter - ld1 {INP.16b}, [x22], #16 - rev x9, x28 - add x28, x28, #1 - sub w19, w19, #1 +0: ld1 {CTR.8b}, [x5] // load upper counter + ld1 {INP.16b}, [x3], #16 + rev x9, x8 + add x8, x8, #1 + sub w0, w0, #1 ins CTR.d[1], x9 // set lower counter .if \enc == 1 eor INP.16b, INP.16b, KS.16b // encrypt input - st1 {INP.16b}, [x21], #16 + st1 {INP.16b}, [x2], #16 .endif rev64 T1.16b, INP.16b - cmp w26, #12 - b.ge 4f // AES-192/256? + cmp w7, #12 + b.ge 2f // AES-192/256? -2: enc_round CTR, v21 +1: enc_round CTR, v21 ext T2.16b, XL.16b, XL.16b, #8 ext IN1.16b, T1.16b, T1.16b, #8 @@ -425,39 +411,27 @@ CPU_LE( rev x28, x28 ) .if \enc == 0 eor INP.16b, INP.16b, KS.16b - st1 {INP.16b}, [x21], #16 + st1 {INP.16b}, [x2], #16 .endif - cbz w19, 3f + cbnz w0, 0b - if_will_cond_yield_neon - st1 {XL.2d}, [x20] - .if \enc == 1 - st1 {KS.16b}, [x27] - .endif - do_cond_yield_neon - b 0b - endif_yield_neon +CPU_LE( rev x8, x8 ) + st1 {XL.2d}, [x1] + str x8, [x5, #8] // store lower counter - b 1b - -3: st1 {XL.2d}, [x20] .if \enc == 1 - st1 {KS.16b}, [x27] + st1 {KS.16b}, [x10] .endif -CPU_LE( rev x28, x28 ) - str x28, [x24, #8] // store lower counter - - frame_pop ret -4: b.eq 5f // AES-192? +2: b.eq 3f // AES-192? enc_round CTR, v17 enc_round CTR, v18 -5: enc_round CTR, v19 +3: enc_round CTR, v19 enc_round CTR, v20 - b 2b + b 1b .endm /* diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 7cf0b1aa6ea8..8a10f1d7199a 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req) err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } - if (walk.nbytes) - pmull_gcm_encrypt_block(iv, iv, NULL, + if (walk.nbytes) { + kernel_neon_begin(); + pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc, num_rounds(&ctx->aes_key)); + kernel_neon_end(); + } + } else { __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, num_rounds(&ctx->aes_key)); diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 192d791f1103..7ed320895d1f 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, #define efi_call_runtime(f, ...) sys_table_arg->runtime->f(__VA_ARGS__) #define efi_is_64bit() (true) +#define efi_table_attr(table, attr, instance) \ + ((table##_t *)instance)->attr + #define efi_call_proto(protocol, f, instance, ...) \ ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index a0fee6985e6a..b2b0c6405eb0 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -8,8 +8,6 @@ struct pt_regs; -extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); - static inline int nr_legacy_irqs(void) { return 0; diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index ffdaea7954bb..0ad1cf233470 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); /* * The ASID allocator will either invalidate the ASID or mark diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f24892a40d2c..c6d80743f4ed 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void update_cpu_capabilities(u16 scope_mask) { - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); __update_cpu_capabilities(arm64_errata, scope_mask, "enabling workaround for"); + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); } static int __enable_cpu_capability(void *arg) @@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void __init enable_cpu_capabilities(u16 scope_mask) { - __enable_cpu_capabilities(arm64_features, scope_mask); __enable_cpu_capabilities(arm64_errata, scope_mask); + __enable_cpu_capabilities(arm64_features, scope_mask); } /* diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 60e5fc661f74..780a12f59a8f 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -void (*handle_arch_irq)(struct pt_regs *) = NULL; - -void __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) -{ - if (handle_arch_irq) - return; - - handle_arch_irq = handle_irq; -} - #ifdef CONFIG_VMAP_STACK static void init_irq_stacks(void) { diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ecc6818191df..192b3ba07075 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; pte_t orig_pte = huge_ptep_get(ptep); bool valid = pte_valid(orig_pte); unsigned long i, saddr = addr; @@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm, orig_pte = pte_mkdirty(orig_pte); } - if (valid) + if (valid) { + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, saddr, addr); + } return orig_pte; } @@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325cfb3b858a..9abf8a1e7b25 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -611,11 +611,13 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Make sure we chose the upper bound of sizeof(struct page) - * correctly. + * correctly when sizing the VMEMMAP array. */ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); +#endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; |