The AES block mode implementation using Crypto Extensions or plain NEON was written before real hardware existed, and so its interleave factor was made build time configurable (as well as an option to instantiate all interleaved sequences inline rather than as subroutines) We ended up using INTERLEAVE=4 with inlining disabled for both flavors of the core AES routines, so let's stick with that, and remove the option to configure this at build time. This makes the code easier to modify, which is nice now that we're adding yield support. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> --- arch/arm64/crypto/Makefile | 3 - arch/arm64/crypto/aes-modes.S | 237 ++++---------------- 2 files changed, 40 insertions(+), 200 deletions(-) diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index cee9b8d9830b..b6b624602582 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -59,9 +59,6 @@ aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o obj-$(CONFIG_CRYPTO_AES_ARM64_BS) += aes-neon-bs.o aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o -AFLAGS_aes-ce.o := -DINTERLEAVE=4 -AFLAGS_aes-neon.o := -DINTERLEAVE=4 - CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index 65b273667b34..27a235b2ddee 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -13,44 +13,6 @@ .text .align 4 -/* - * There are several ways to instantiate this code: - * - no interleave, all inline - * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2) - * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE) - * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4) - * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE) - * - * Macros imported by this code: - * - enc_prepare - setup NEON registers for encryption - * - dec_prepare - setup NEON registers for decryption - * - enc_switch_key - change to new key after having prepared for encryption - * - encrypt_block - encrypt a single block - * - decrypt block - decrypt a single block - * - encrypt_block2x - encrypt 2 blocks in parallel (if INTERLEAVE == 2) - * - decrypt_block2x - decrypt 2 blocks in parallel (if INTERLEAVE == 2) - * - encrypt_block4x - encrypt 4 blocks in parallel (if INTERLEAVE == 4) - * - decrypt_block4x - decrypt 4 blocks in parallel (if INTERLEAVE == 4) - */ - -#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE) -#define FRAME_PUSH stp x29, x30, [sp,#-16]! ; mov x29, sp -#define FRAME_POP ldp x29, x30, [sp],#16 - -#if INTERLEAVE == 2 - -aes_encrypt_block2x: - encrypt_block2x v0, v1, w3, x2, x8, w7 - ret -ENDPROC(aes_encrypt_block2x) - -aes_decrypt_block2x: - decrypt_block2x v0, v1, w3, x2, x8, w7 - ret -ENDPROC(aes_decrypt_block2x) - -#elif INTERLEAVE == 4 - aes_encrypt_block4x: encrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7 ret @@ -61,48 +23,6 @@ aes_decrypt_block4x: ret ENDPROC(aes_decrypt_block4x) -#else -#error INTERLEAVE should equal 2 or 4 -#endif - - .macro do_encrypt_block2x - bl aes_encrypt_block2x - .endm - - .macro do_decrypt_block2x - bl aes_decrypt_block2x - .endm - - .macro do_encrypt_block4x - bl aes_encrypt_block4x - .endm - - .macro do_decrypt_block4x - bl aes_decrypt_block4x - .endm - -#else -#define FRAME_PUSH -#define FRAME_POP - - .macro do_encrypt_block2x - encrypt_block2x v0, v1, w3, x2, x8, w7 - .endm - - .macro do_decrypt_block2x - decrypt_block2x v0, v1, w3, x2, x8, w7 - .endm - - .macro do_encrypt_block4x - encrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7 - .endm - - .macro do_decrypt_block4x - decrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7 - .endm - -#endif - /* * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, * int blocks) @@ -111,28 +31,21 @@ ENDPROC(aes_decrypt_block4x) */ AES_ENTRY(aes_ecb_encrypt) - FRAME_PUSH + stp x29, x30, [sp, #-16]! + mov x29, sp enc_prepare w3, x2, x5 .LecbencloopNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #4 bmi .Lecbenc1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */ - do_encrypt_block2x - st1 {v0.16b-v1.16b}, [x0], #32 -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ - do_encrypt_block4x + bl aes_encrypt_block4x st1 {v0.16b-v3.16b}, [x0], #64 -#endif b .LecbencloopNx .Lecbenc1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #4 beq .Lecbencout -#endif .Lecbencloop: ld1 {v0.16b}, [x1], #16 /* get next pt block */ encrypt_block v0, w3, x2, x5, w6 @@ -140,34 +53,27 @@ AES_ENTRY(aes_ecb_encrypt) subs w4, w4, #1 bne .Lecbencloop .Lecbencout: - FRAME_POP + ldp x29, x30, [sp], #16 ret AES_ENDPROC(aes_ecb_encrypt) AES_ENTRY(aes_ecb_decrypt) - FRAME_PUSH + stp x29, x30, [sp, #-16]! + mov x29, sp dec_prepare w3, x2, x5 .LecbdecloopNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #4 bmi .Lecbdec1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ - do_decrypt_block2x - st1 {v0.16b-v1.16b}, [x0], #32 -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ - do_decrypt_block4x + bl aes_decrypt_block4x st1 {v0.16b-v3.16b}, [x0], #64 -#endif b .LecbdecloopNx .Lecbdec1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #4 beq .Lecbdecout -#endif .Lecbdecloop: ld1 {v0.16b}, [x1], #16 /* get next ct block */ decrypt_block v0, w3, x2, x5, w6 @@ -175,7 +81,7 @@ AES_ENTRY(aes_ecb_decrypt) subs w4, w4, #1 bne .Lecbdecloop .Lecbdecout: - FRAME_POP + ldp x29, x30, [sp], #16 ret AES_ENDPROC(aes_ecb_decrypt) @@ -204,30 +110,20 @@ AES_ENDPROC(aes_cbc_encrypt) AES_ENTRY(aes_cbc_decrypt) - FRAME_PUSH + stp x29, x30, [sp, #-16]! + mov x29, sp ld1 {v7.16b}, [x5] /* get iv */ dec_prepare w3, x2, x6 .LcbcdecloopNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #4 bmi .Lcbcdec1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ - mov v2.16b, v0.16b - mov v3.16b, v1.16b - do_decrypt_block2x - eor v0.16b, v0.16b, v7.16b - eor v1.16b, v1.16b, v2.16b - mov v7.16b, v3.16b - st1 {v0.16b-v1.16b}, [x0], #32 -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ mov v4.16b, v0.16b mov v5.16b, v1.16b mov v6.16b, v2.16b - do_decrypt_block4x + bl aes_decrypt_block4x sub x1, x1, #16 eor v0.16b, v0.16b, v7.16b eor v1.16b, v1.16b, v4.16b @@ -235,12 +131,10 @@ AES_ENTRY(aes_cbc_decrypt) eor v2.16b, v2.16b, v5.16b eor v3.16b, v3.16b, v6.16b st1 {v0.16b-v3.16b}, [x0], #64 -#endif b .LcbcdecloopNx .Lcbcdec1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #4 beq .Lcbcdecout -#endif .Lcbcdecloop: ld1 {v1.16b}, [x1], #16 /* get next ct block */ mov v0.16b, v1.16b /* ...and copy to v0 */ @@ -251,8 +145,8 @@ AES_ENTRY(aes_cbc_decrypt) subs w4, w4, #1 bne .Lcbcdecloop .Lcbcdecout: - FRAME_POP st1 {v7.16b}, [x5] /* return iv */ + ldp x29, x30, [sp], #16 ret AES_ENDPROC(aes_cbc_decrypt) @@ -263,34 +157,19 @@ AES_ENDPROC(aes_cbc_decrypt) */ AES_ENTRY(aes_ctr_encrypt) - FRAME_PUSH + stp x29, x30, [sp, #-16]! + mov x29, sp enc_prepare w3, x2, x6 ld1 {v4.16b}, [x5] umov x6, v4.d[1] /* keep swabbed ctr in reg */ rev x6, x6 -#if INTERLEAVE >= 2 cmn w6, w4 /* 32 bit overflow? */ bcs .Lctrloop .LctrloopNx: - subs w4, w4, #INTERLEAVE + subs w4, w4, #4 bmi .Lctr1x -#if INTERLEAVE == 2 - mov v0.8b, v4.8b - mov v1.8b, v4.8b - rev x7, x6 - add x6, x6, #1 - ins v0.d[1], x7 - rev x7, x6 - add x6, x6, #1 - ins v1.d[1], x7 - ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ - do_encrypt_block2x - eor v0.16b, v0.16b, v2.16b - eor v1.16b, v1.16b, v3.16b - st1 {v0.16b-v1.16b}, [x0], #32 -#else ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ dup v7.4s, w6 mov v0.16b, v4.16b @@ -303,23 +182,21 @@ AES_ENTRY(aes_ctr_encrypt) mov v2.s[3], v8.s[1] mov v3.s[3], v8.s[2] ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */ - do_encrypt_block4x + bl aes_encrypt_block4x eor v0.16b, v5.16b, v0.16b ld1 {v5.16b}, [x1], #16 /* get 1 input block */ eor v1.16b, v6.16b, v1.16b eor v2.16b, v7.16b, v2.16b eor v3.16b, v5.16b, v3.16b st1 {v0.16b-v3.16b}, [x0], #64 - add x6, x6, #INTERLEAVE -#endif + add x6, x6, #4 rev x7, x6 ins v4.d[1], x7 cbz w4, .Lctrout b .LctrloopNx .Lctr1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #4 beq .Lctrout -#endif .Lctrloop: mov v0.16b, v4.16b encrypt_block v0, w3, x2, x8, w7 @@ -339,12 +216,12 @@ AES_ENTRY(aes_ctr_encrypt) .Lctrout: st1 {v4.16b}, [x5] /* return next CTR value */ - FRAME_POP + ldp x29, x30, [sp], #16 ret .Lctrtailblock: st1 {v0.16b}, [x0] - FRAME_POP + ldp x29, x30, [sp], #16 ret .Lctrcarry: @@ -378,7 +255,9 @@ CPU_LE( .quad 1, 0x87 ) CPU_BE( .quad 0x87, 1 ) AES_ENTRY(aes_xts_encrypt) - FRAME_PUSH + stp x29, x30, [sp, #-16]! + mov x29, sp + ld1 {v4.16b}, [x6] cbz w7, .Lxtsencnotfirst @@ -394,25 +273,8 @@ AES_ENTRY(aes_xts_encrypt) ldr q7, .Lxts_mul_x next_tweak v4, v4, v7, v8 .LxtsencNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #4 bmi .Lxtsenc1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */ - next_tweak v5, v4, v7, v8 - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - do_encrypt_block2x - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - st1 {v0.16b-v1.16b}, [x0], #32 - cbz w4, .LxtsencoutNx - next_tweak v4, v5, v7, v8 - b .LxtsencNx -.LxtsencoutNx: - mov v4.16b, v5.16b - b .Lxtsencout -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ next_tweak v5, v4, v7, v8 eor v0.16b, v0.16b, v4.16b @@ -421,7 +283,7 @@ AES_ENTRY(aes_xts_encrypt) eor v2.16b, v2.16b, v6.16b next_tweak v7, v6, v7, v8 eor v3.16b, v3.16b, v7.16b - do_encrypt_block4x + bl aes_encrypt_block4x eor v3.16b, v3.16b, v7.16b eor v0.16b, v0.16b, v4.16b eor v1.16b, v1.16b, v5.16b @@ -430,11 +292,9 @@ AES_ENTRY(aes_xts_encrypt) mov v4.16b, v7.16b cbz w4, .Lxtsencout b .LxtsencloopNx -#endif .Lxtsenc1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #4 beq .Lxtsencout -#endif .Lxtsencloop: ld1 {v1.16b}, [x1], #16 eor v0.16b, v1.16b, v4.16b @@ -447,13 +307,15 @@ AES_ENTRY(aes_xts_encrypt) b .Lxtsencloop .Lxtsencout: st1 {v4.16b}, [x6] - FRAME_POP + ldp x29, x30, [sp], #16 ret AES_ENDPROC(aes_xts_encrypt) AES_ENTRY(aes_xts_decrypt) - FRAME_PUSH + stp x29, x30, [sp, #-16]! + mov x29, sp + ld1 {v4.16b}, [x6] cbz w7, .Lxtsdecnotfirst @@ -469,25 +331,8 @@ AES_ENTRY(aes_xts_decrypt) ldr q7, .Lxts_mul_x next_tweak v4, v4, v7, v8 .LxtsdecNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #4 bmi .Lxtsdec1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ - next_tweak v5, v4, v7, v8 - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - do_decrypt_block2x - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - st1 {v0.16b-v1.16b}, [x0], #32 - cbz w4, .LxtsdecoutNx - next_tweak v4, v5, v7, v8 - b .LxtsdecNx -.LxtsdecoutNx: - mov v4.16b, v5.16b - b .Lxtsdecout -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ next_tweak v5, v4, v7, v8 eor v0.16b, v0.16b, v4.16b @@ -496,7 +341,7 @@ AES_ENTRY(aes_xts_decrypt) eor v2.16b, v2.16b, v6.16b next_tweak v7, v6, v7, v8 eor v3.16b, v3.16b, v7.16b - do_decrypt_block4x + bl aes_decrypt_block4x eor v3.16b, v3.16b, v7.16b eor v0.16b, v0.16b, v4.16b eor v1.16b, v1.16b, v5.16b @@ -505,11 +350,9 @@ AES_ENTRY(aes_xts_decrypt) mov v4.16b, v7.16b cbz w4, .Lxtsdecout b .LxtsdecloopNx -#endif .Lxtsdec1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #4 beq .Lxtsdecout -#endif .Lxtsdecloop: ld1 {v1.16b}, [x1], #16 eor v0.16b, v1.16b, v4.16b @@ -522,7 +365,7 @@ AES_ENTRY(aes_xts_decrypt) b .Lxtsdecloop .Lxtsdecout: st1 {v4.16b}, [x6] - FRAME_POP + ldp x29, x30, [sp], #16 ret AES_ENDPROC(aes_xts_decrypt) -- 2.15.1