diff options
Diffstat (limited to 'arch')
61 files changed, 3831 insertions, 1192 deletions
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 7b285dd4fe05..c6133a045352 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -109,4 +109,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 61a0cb15067e..f1b3f1d575d4 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -50,7 +50,7 @@ config ARM select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) select HAVE_ARCH_TRACEHOOK select HAVE_ARM_SMCCC if CPU_V7 - select HAVE_CBPF_JIT + select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 select HAVE_CC_STACKPROTECTOR select HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts index 58834330a5ba..1be9daacc4f9 100644 --- a/arch/arm/boot/dts/rk3228-evb.dts +++ b/arch/arm/boot/dts/rk3228-evb.dts @@ -50,6 +50,16 @@ device_type = "memory"; reg = <0x60000000 0x40000000>; }; + + vcc_phy: vcc-phy-regulator { + compatible = "regulator-fixed"; + enable-active-high; + regulator-name = "vcc_phy"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; }; &emmc { @@ -60,6 +70,30 @@ status = "okay"; }; +&gmac { + assigned-clocks = <&cru SCLK_MAC_SRC>; + assigned-clock-rates = <50000000>; + clock_in_out = "output"; + phy-supply = <&vcc_phy>; + phy-mode = "rmii"; + phy-handle = <&phy>; + status = "okay"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + phy: phy@0 { + compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22"; + reg = <0>; + clocks = <&cru SCLK_MAC_PHY>; + resets = <&cru SRST_MACPHY>; + phy-is-integrated; + }; + }; +}; + &tsadc { status = "okay"; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 4d19c1b4b8e7..94d7e71c69c4 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -270,6 +270,7 @@ CONFIG_ICPLUS_PHY=y CONFIG_REALTEK_PHY=y CONFIG_MICREL_PHY=y CONFIG_FIXED_PHY=y +CONFIG_ROCKCHIP_PHY=y CONFIG_USB_PEGASUS=y CONFIG_USB_RTL8152=m CONFIG_USB_USBNET=y diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index b9adedcc5b2e..ec72752d5668 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -94,14 +94,15 @@ config CRYPTO_AES_ARM_CE ARMv8 Crypto Extensions config CRYPTO_GHASH_ARM_CE - tristate "PMULL-accelerated GHASH using ARMv8 Crypto Extensions" + tristate "PMULL-accelerated GHASH using NEON/ARMv8 Crypto Extensions" depends on KERNEL_MODE_NEON select CRYPTO_HASH select CRYPTO_CRYPTD help Use an implementation of GHASH (used by the GCM AEAD chaining mode) that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64) - that is part of the ARMv8 Crypto Extensions + that is part of the ARMv8 Crypto Extensions, or a slower variant that + uses the vmull.p8 instruction that is part of the basic NEON ISA. config CRYPTO_CRCT10DIF_ARM_CE tristate "CRCT10DIF digest algorithm using PMULL instructions" diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index 0f966a8ca1ce..d0a9cec73707 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -285,9 +285,7 @@ static int ctr_encrypt(struct skcipher_request *req) ce_aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, num_rounds(ctx), blocks, walk.iv); - if (tdst != tsrc) - memcpy(tdst, tsrc, nbytes); - crypto_xor(tdst, tail, nbytes); + crypto_xor_cpy(tdst, tsrc, tail, nbytes); err = skcipher_walk_done(&walk, 0); } kernel_neon_end(); diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S index c817a86c4ca8..54b384084637 100644 --- a/arch/arm/crypto/aes-cipher-core.S +++ b/arch/arm/crypto/aes-cipher-core.S @@ -10,6 +10,7 @@ */ #include <linux/linkage.h> +#include <asm/cache.h> .text .align 5 @@ -32,19 +33,19 @@ .endif .endm - .macro __load, out, in, idx + .macro __load, out, in, idx, sz, op .if __LINUX_ARM_ARCH__ < 7 && \idx > 0 - ldr \out, [ttab, \in, lsr #(8 * \idx) - 2] + ldr\op \out, [ttab, \in, lsr #(8 * \idx) - \sz] .else - ldr \out, [ttab, \in, lsl #2] + ldr\op \out, [ttab, \in, lsl #\sz] .endif .endm - .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc + .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op __select \out0, \in0, 0 __select t0, \in1, 1 - __load \out0, \out0, 0 - __load t0, t0, 1 + __load \out0, \out0, 0, \sz, \op + __load t0, t0, 1, \sz, \op .if \enc __select \out1, \in1, 0 @@ -53,10 +54,10 @@ __select \out1, \in3, 0 __select t1, \in0, 1 .endif - __load \out1, \out1, 0 + __load \out1, \out1, 0, \sz, \op __select t2, \in2, 2 - __load t1, t1, 1 - __load t2, t2, 2 + __load t1, t1, 1, \sz, \op + __load t2, t2, 2, \sz, \op eor \out0, \out0, t0, ror #24 @@ -68,9 +69,9 @@ __select \t3, \in1, 2 __select \t4, \in2, 3 .endif - __load \t3, \t3, 2 - __load t0, t0, 3 - __load \t4, \t4, 3 + __load \t3, \t3, 2, \sz, \op + __load t0, t0, 3, \sz, \op + __load \t4, \t4, 3, \sz, \op eor \out1, \out1, t1, ror #24 eor \out0, \out0, t2, ror #16 @@ -82,14 +83,14 @@ eor \out1, \out1, t2 .endm - .macro fround, out0, out1, out2, out3, in0, in1, in2, in3 - __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1 - __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1 + .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op + __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op + __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op .endm - .macro iround, out0, out1, out2, out3, in0, in1, in2, in3 - __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0 - __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0 + .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op + __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op + __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op .endm .macro __rev, out, in @@ -114,7 +115,7 @@ .endif .endm - .macro do_crypt, round, ttab, ltab + .macro do_crypt, round, ttab, ltab, bsz push {r3-r11, lr} ldr r4, [in] @@ -146,9 +147,12 @@ 1: subs rounds, rounds, #4 \round r8, r9, r10, r11, r4, r5, r6, r7 - __adrl ttab, \ltab, ls + bls 2f \round r4, r5, r6, r7, r8, r9, r10, r11 - bhi 0b + b 0b + +2: __adrl ttab, \ltab + \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b #ifdef CONFIG_CPU_BIG_ENDIAN __rev r4, r4 @@ -170,10 +174,48 @@ .ltorg .endm + .align L1_CACHE_SHIFT + .type __aes_arm_inverse_sbox, %object +__aes_arm_inverse_sbox: + .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38 + .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb + .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87 + .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb + .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d + .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e + .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2 + .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25 + .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16 + .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92 + .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda + .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84 + .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a + .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06 + .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02 + .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b + .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea + .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73 + .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85 + .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e + .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89 + .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b + .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20 + .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4 + .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31 + .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f + .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d + .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef + .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0 + .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61 + .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26 + .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d + .size __aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox + ENTRY(__aes_arm_encrypt) - do_crypt fround, crypto_ft_tab, crypto_fl_tab + do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2 ENDPROC(__aes_arm_encrypt) + .align 5 ENTRY(__aes_arm_decrypt) - do_crypt iround, crypto_it_tab, crypto_il_tab + do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0 ENDPROC(__aes_arm_decrypt) diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c index c76377961444..18768f330449 100644 --- a/arch/arm/crypto/aes-neonbs-glue.c +++ b/arch/arm/crypto/aes-neonbs-glue.c @@ -221,9 +221,8 @@ static int ctr_encrypt(struct skcipher_request *req) u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; - if (dst != src) - memcpy(dst, src, walk.total % AES_BLOCK_SIZE); - crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE); + crypto_xor_cpy(dst, src, final, + walk.total % AES_BLOCK_SIZE); err = skcipher_walk_done(&walk, 0); break; diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S index f6ab8bcc9efe..2f78c10b1881 100644 --- a/arch/arm/crypto/ghash-ce-core.S +++ b/arch/arm/crypto/ghash-ce-core.S @@ -1,7 +1,7 @@ /* - * Accelerated GHASH implementation with ARMv8 vmull.p64 instructions. + * Accelerated GHASH implementation with NEON/ARMv8 vmull.p8/64 instructions. * - * Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2015 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -12,40 +12,162 @@ #include <asm/assembler.h> SHASH .req q0 - SHASH2 .req q1 - T1 .req q2 - T2 .req q3 - MASK .req q4 - XL .req q5 - XM .req q6 - XH .req q7 - IN1 .req q7 + T1 .req q1 + XL .req q2 + XM .req q3 + XH .req q4 + IN1 .req q4 SHASH_L .req d0 SHASH_H .req d1 - SHASH2_L .req d2 - T1_L .req d4 - MASK_L .req d8 - XL_L .req d10 - XL_H .req d11 - XM_L .req d12 - XM_H .req d13 - XH_L .req d14 + T1_L .req d2 + T1_H .req d3 + XL_L .req d4 + XL_H .req d5 + XM_L .req d6 + XM_H .req d7 + XH_L .req d8 + + t0l .req d10 + t0h .req d11 + t1l .req d12 + t1h .req d13 + t2l .req d14 + t2h .req d15 + t3l .req d16 + t3h .req d17 + t4l .req d18 + t4h .req d19 + + t0q .req q5 + t1q .req q6 + t2q .req q7 + t3q .req q8 + t4q .req q9 + T2 .req q9 + + s1l .req d20 + s1h .req d21 + s2l .req d22 + s2h .req d23 + s3l .req d24 + s3h .req d25 + s4l .req d26 + s4h .req d27 + + MASK .req d28 + SHASH2_p8 .req d28 + + k16 .req d29 + k32 .req d30 + k48 .req d31 + SHASH2_p64 .req d31 .text .fpu crypto-neon-fp-armv8 + .macro __pmull_p64, rd, rn, rm, b1, b2, b3, b4 + vmull.p64 \rd, \rn, \rm + .endm + /* - * void pmull_ghash_update(int blocks, u64 dg[], const char *src, - * struct ghash_key const *k, const char *head) + * This implementation of 64x64 -> 128 bit polynomial multiplication + * using vmull.p8 instructions (8x8 -> 16) is taken from the paper + * "Fast Software Polynomial Multiplication on ARM Processors Using + * the NEON Engine" by Danilo Camara, Conrado Gouvea, Julio Lopez and + * Ricardo Dahab (https://hal.inria.fr/hal-01506572) + * + * It has been slightly tweaked for in-order performance, and to allow + * 'rq' to overlap with 'ad' or 'bd'. */ -ENTRY(pmull_ghash_update) - vld1.64 {SHASH}, [r3] + .macro __pmull_p8, rq, ad, bd, b1=t4l, b2=t3l, b3=t4l, b4=t3l + vext.8 t0l, \ad, \ad, #1 @ A1 + .ifc \b1, t4l + vext.8 t4l, \bd, \bd, #1 @ B1 + .endif + vmull.p8 t0q, t0l, \bd @ F = A1*B + vext.8 t1l, \ad, \ad, #2 @ A2 + vmull.p8 t4q, \ad, \b1 @ E = A*B1 + .ifc \b2, t3l + vext.8 t3l, \bd, \bd, #2 @ B2 + .endif + vmull.p8 t1q, t1l, \bd @ H = A2*B + vext.8 t2l, \ad, \ad, #3 @ A3 + vmull.p8 t3q, \ad, \b2 @ G = A*B2 + veor t0q, t0q, t4q @ L = E + F + .ifc \b3, t4l + vext.8 t4l, \bd, \bd, #3 @ B3 + .endif + vmull.p8 t2q, t2l, \bd @ J = A3*B + veor t0l, t0l, t0h @ t0 = (L) (P0 + P1) << 8 + veor t1q, t1q, t3q @ M = G + H + .ifc \b4, t3l + vext.8 t3l, \bd, \bd, #4 @ B4 + .endif + vmull.p8 t4q, \ad, \b3 @ I = A*B3 + veor t1l, t1l, t1h @ t1 = (M) (P2 + P3) << 16 + vmull.p8 t3q, \ad, \b4 @ K = A*B4 + vand t0h, t0h, k48 + vand t1h, t1h, k32 + veor t2q, t2q, t4q @ N = I + J + veor t0l, t0l, t0h + veor t1l, t1l, t1h + veor t2l, t2l, t2h @ t2 = (N) (P4 + P5) << 24 + vand t2h, t2h, k16 + veor t3l, t3l, t3h @ t3 = (K) (P6 + P7) << 32 + vmov.i64 t3h, #0 + vext.8 t0q, t0q, t0q, #15 + veor t2l, t2l, t2h + vext.8 t1q, t1q, t1q, #14 + vmull.p8 \rq, \ad, \bd @ D = A*B + vext.8 t2q, t2q, t2q, #13 + vext.8 t3q, t3q, t3q, #12 + veor t0q, t0q, t1q + veor t2q, t2q, t3q + veor \rq, \rq, t0q + veor \rq, \rq, t2q + .endm + + // + // PMULL (64x64->128) based reduction for CPUs that can do + // it in a single instruction. + // + .macro __pmull_reduce_p64 + vmull.p64 T1, XL_L, MASK + + veor XH_L, XH_L, XM_H + vext.8 T1, T1, T1, #8 + veor XL_H, XL_H, XM_L + veor T1, T1, XL + + vmull.p64 XL, T1_H, MASK + .endm + + // + // Alternative reduction for CPUs that lack support for the + // 64x64->128 PMULL instruction + // + .macro __pmull_reduce_p8 + veor XL_H, XL_H, XM_L + veor XH_L, XH_L, XM_H + + vshl.i64 T1, XL, #57 + vshl.i64 T2, XL, #62 + veor T1, T1, T2 + vshl.i64 T2, XL, #63 + veor T1, T1, T2 + veor XL_H, XL_H, T1_L + veor XH_L, XH_L, T1_H + + vshr.u64 T1, XL, #1 + veor XH, XH, XL + veor XL, XL, T1 + vshr.u64 T1, T1, #6 + vshr.u64 XL, XL, #1 + .endm + + .macro ghash_update, pn vld1.64 {XL}, [r1] - vmov.i8 MASK, #0xe1 - vext.8 SHASH2, SHASH, SHASH, #8 - vshl.u64 MASK, MASK, #57 - veor SHASH2, SHASH2, SHASH /* do the head block first, if supplied */ ldr ip, [sp] @@ -62,33 +184,59 @@ ENTRY(pmull_ghash_update) #ifndef CONFIG_CPU_BIG_ENDIAN vrev64.8 T1, T1 #endif - vext.8 T2, XL, XL, #8 vext.8 IN1, T1, T1, #8 - veor T1, T1, T2 + veor T1_L, T1_L, XL_H veor XL, XL, IN1 - vmull.p64 XH, SHASH_H, XL_H @ a1 * b1 + __pmull_\pn XH, XL_H, SHASH_H, s1h, s2h, s3h, s4h @ a1 * b1 veor T1, T1, XL - vmull.p64 XL, SHASH_L, XL_L @ a0 * b0 - vmull.p64 XM, SHASH2_L, T1_L @ (a1 + a0)(b1 + b0) + __pmull_\pn XL, XL_L, SHASH_L, s1l, s2l, s3l, s4l @ a0 * b0 + __pmull_\pn XM, T1_L, SHASH2_\pn @ (a1+a0)(b1+b0) - vext.8 T1, XL, XH, #8 - veor T2, XL, XH + veor T1, XL, XH veor XM, XM, T1 - veor XM, XM, T2 - vmull.p64 T2, XL_L, MASK_L - vmov XH_L, XM_H - vmov XM_H, XL_L + __pmull_reduce_\pn - veor XL, XM, T2 - vext.8 T2, XL, XL, #8 - vmull.p64 XL, XL_L, MASK_L - veor T2, T2, XH - veor XL, XL, T2 + veor T1, T1, XH + veor XL, XL, T1 bne 0b vst1.64 {XL}, [r1] bx lr -ENDPROC(pmull_ghash_update) + .endm + + /* + * void pmull_ghash_update(int blocks, u64 dg[], const char *src, + * struct ghash_key const *k, const char *head) + */ +ENTRY(pmull_ghash_update_p64) + vld1.64 {SHASH}, [r3] + veor SHASH2_p64, SHASH_L, SHASH_H + + vmov.i8 MASK, #0xe1 + vshl.u64 MASK, MASK, #57 + + ghash_update p64 +ENDPROC(pmull_ghash_update_p64) + +ENTRY(pmull_ghash_update_p8) + vld1.64 {SHASH}, [r3] + veor SHASH2_p8, SHASH_L, SHASH_H + + vext.8 s1l, SHASH_L, SHASH_L, #1 + vext.8 s2l, SHASH_L, SHASH_L, #2 + vext.8 s3l, SHASH_L, SHASH_L, #3 + vext.8 s4l, SHASH_L, SHASH_L, #4 + vext.8 s1h, SHASH_H, SHASH_H, #1 + vext.8 s2h, SHASH_H, SHASH_H, #2 + vext.8 s3h, SHASH_H, SHASH_H, #3 + vext.8 s4h, SHASH_H, SHASH_H, #4 + + vmov.i64 k16, #0xffff + vmov.i64 k32, #0xffffffff + vmov.i64 k48, #0xffffffffffff + + ghash_update p8 +ENDPROC(pmull_ghash_update_p8) diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c index 6bac8bea9f1e..d9bb52cae2ac 100644 --- a/arch/arm/crypto/ghash-ce-glue.c +++ b/arch/arm/crypto/ghash-ce-glue.c @@ -22,6 +22,7 @@ MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("ghash"); #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 @@ -41,8 +42,17 @@ struct ghash_async_ctx { struct cryptd_ahash *cryptd_tfm; }; -asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src, - struct ghash_key const *k, const char *head); +asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, + const char *head); + +asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, + const char *head); + +static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, + const char *head); static int ghash_init(struct shash_desc *desc) { @@ -312,6 +322,14 @@ static int __init ghash_ce_mod_init(void) { int err; + if (!(elf_hwcap & HWCAP_NEON)) + return -ENODEV; + + if (elf_hwcap2 & HWCAP2_PMULL) + pmull_ghash_update = pmull_ghash_update_p64; + else + pmull_ghash_update = pmull_ghash_update_p8; + err = crypto_register_shash(&ghash_alg); if (err) return err; @@ -332,5 +350,5 @@ static void __exit ghash_ce_mod_exit(void) crypto_unregister_shash(&ghash_alg); } -module_cpu_feature_match(PMULL, ghash_ce_mod_init); +module_init(ghash_ce_mod_init); module_exit(ghash_ce_mod_exit); diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index d5b9fa19b684..c199990e12b6 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1,6 +1,7 @@ /* - * Just-In-Time compiler for BPF filters on 32bit ARM + * Just-In-Time compiler for eBPF filters on 32bit ARM * + * Copyright (c) 2017 Shubham Bansal <illusionist.neo@gmail.com> * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com> * * This program is free software; you can redistribute it and/or modify it @@ -8,6 +9,7 @@ * Free Software Foundation; version 2 of the License. */ +#include <linux/bpf.h> #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/errno.h> @@ -18,54 +20,101 @@ #include <linux/if_vlan.h> #include <asm/cacheflush.h> -#include <asm/set_memory.h> #include <asm/hwcap.h> #include <asm/opcodes.h> #include "bpf_jit_32.h" +int bpf_jit_enable __read_mostly; + +#define STACK_OFFSET(k) (k) +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */ +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */ +#define TCALL_CNT (MAX_BPF_JIT_REG + 2) /* Tail Call Count */ + +/* Flags used for JIT optimization */ +#define SEEN_CALL (1 << 0) + +#define FLAG_IMM_OVERFLOW (1 << 0) + /* - * ABI: + * Map eBPF registers to ARM 32bit registers or stack scratch space. + * + * 1. First argument is passed using the arm 32bit registers and rest of the + * arguments are passed on stack scratch space. + * 2. First callee-saved arugument is mapped to arm 32 bit registers and rest + * arguments are mapped to scratch space on stack. + * 3. We need two 64 bit temp registers to do complex operations on eBPF + * registers. + * + * As the eBPF registers are all 64 bit registers and arm has only 32 bit + * registers, we have to map each eBPF registers with two arm 32 bit regs or + * scratch memory space and we have to build eBPF 64 bit register from those. * - * r0 scratch register - * r4 BPF register A - * r5 BPF register X - * r6 pointer to the skb - * r7 skb->data - * r8 skb_headlen(skb) */ +static const u8 bpf2a32[][2] = { + /* return value from in-kernel function, and exit value from eBPF */ + [BPF_REG_0] = {ARM_R1, ARM_R0}, + /* arguments from eBPF program to in-kernel function */ + [BPF_REG_1] = {ARM_R3, ARM_R2}, + /* Stored on stack scratch space */ + [BPF_REG_2] = {STACK_OFFSET(0), STACK_OFFSET(4)}, + [BPF_REG_3] = {STACK_OFFSET(8), STACK_OFFSET(12)}, + [BPF_REG_4] = {STACK_OFFSET(16), STACK_OFFSET(20)}, + [BPF_REG_5] = {STACK_OFFSET(24), STACK_OFFSET(28)}, + /* callee saved registers that in-kernel function will preserve */ + [BPF_REG_6] = {ARM_R5, ARM_R4}, + /* Stored on stack scratch space */ + [BPF_REG_7] = {STACK_OFFSET(32), STACK_OFFSET(36)}, + [BPF_REG_8] = {STACK_OFFSET(40), STACK_OFFSET(44)}, + [BPF_REG_9] = {STACK_OFFSET(48), STACK_OFFSET(52)}, + /* Read only Frame Pointer to access Stack */ + [BPF_REG_FP] = {STACK_OFFSET(56), STACK_OFFSET(60)}, + /* Temporary Register for internal BPF JIT, can be used + * for constant blindings and others. + */ + [TMP_REG_1] = {ARM_R7, ARM_R6}, + [TMP_REG_2] = {ARM_R10, ARM_R8}, + /* Tail call count. Stored on stack scratch space. */ + [TCALL_CNT] = {STACK_OFFSET(64), STACK_OFFSET(68)}, + /* temporary register for blinding constants. + * Stored on stack scratch space. + */ + [BPF_REG_AX] = {STACK_OFFSET(72), STACK_OFFSET(76)}, +}; -#define r_scratch ARM_R0 -/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */ -#define r_off ARM_R1 -#define r_A ARM_R4 -#define r_X ARM_R5 -#define r_skb ARM_R6 -#define r_skb_data ARM_R7 -#define r_skb_hl ARM_R8 - -#define SCRATCH_SP_OFFSET 0 -#define SCRATCH_OFF(k) (SCRATCH_SP_OFFSET + 4 * (k)) - -#define SEEN_MEM ((1 << BPF_MEMWORDS) - 1) -#define SEEN_MEM_WORD(k) (1 << (k)) -#define SEEN_X (1 << BPF_MEMWORDS) -#define SEEN_CALL (1 << (BPF_MEMWORDS + 1)) -#define SEEN_SKB (1 << (BPF_MEMWORDS + 2)) -#define SEEN_DATA (1 << (BPF_MEMWORDS + 3)) +#define dst_lo dst[1] +#define dst_hi dst[0] +#define src_lo src[1] +#define src_hi src[0] -#define FLAG_NEED_X_RESET (1 << 0) -#define FLAG_IMM_OVERFLOW (1 << 1) +/* + * JIT Context: + * + * prog : bpf_prog + * idx : index of current last JITed instruction. + * prologue_bytes : bytes used in prologue. + * epilogue_offset : offset of epilogue starting. + * seen : bit mask used for JIT optimization. + * offsets : array of eBPF instruction offsets in + * JITed code. + * target : final JITed code. + * epilogue_bytes : no of bytes used in epilogue. + * imm_count : no of immediate counts used for global + * variables. + * imms : array of global variable addresses. + */ struct jit_ctx { - const struct bpf_prog *skf; - unsigned idx; - unsigned prologue_bytes; - int ret0_fp_idx; + const struct bpf_prog *prog; + unsigned int idx; + unsigned int prologue_bytes; + unsigned int epilogue_offset; u32 seen; u32 flags; u32 *offsets; u32 *target; + u32 stack_size; #if __LINUX_ARM_ARCH__ < 7 u16 epilogue_bytes; u16 imm_count; @@ -73,68 +122,16 @@ struct jit_ctx { #endif }; -int bpf_jit_enable __read_mostly; - -static inline int call_neg_helper(struct sk_buff *skb, int offset, void *ret, - unsigned int size) -{ - void *ptr = bpf_internal_load_pointer_neg_helper(skb, offset, size); - - if (!ptr) - return -EFAULT; - memcpy(ret, ptr, size); - return 0; -} - -static u64 jit_get_skb_b(struct sk_buff *skb, int offset) -{ - u8 ret; - int err; - - if (offset < 0) - err = call_neg_helper(skb, offset, &ret, 1); - else - err = skb_copy_bits(skb, offset, &ret, 1); - - return (u64)err << 32 | ret; -} - -static u64 jit_get_skb_h(struct sk_buff *skb, int offset) -{ - u16 ret; - int err; - - if (offset < 0) - err = call_neg_helper(skb, offset, &ret, 2); - else - err = skb_copy_bits(skb, offset, &ret, 2); - - return (u64)err << 32 | ntohs(ret); -} - -static u64 jit_get_skb_w(struct sk_buff *skb, int offset) -{ - u32 ret; - int err; - - if (offset < 0) - err = call_neg_helper(skb, offset, &ret, 4); - else - err = skb_copy_bits(skb, offset, &ret, 4); - - return (u64)err << 32 | ntohl(ret); -} - /* * Wrappers which handle both OABI and EABI and assures Thumb2 interworking * (where the assembly routines like __aeabi_uidiv could cause problems). */ -static u32 jit_udiv(u32 dividend, u32 divisor) +static u32 jit_udiv32(u32 dividend, u32 divisor) { return dividend / divisor; } -static u32 jit_mod(u32 dividend, u32 divisor) +static u32 jit_mod32(u32 dividend, u32 divisor) { return dividend % divisor; } @@ -158,36 +155,22 @@ static inline void emit(u32 inst, struct jit_ctx *ctx) _emit(ARM_COND_AL, inst, ctx); } -static u16 saved_regs(struct jit_ctx *ctx) +/* + * Checks if immediate value can be converted to imm12(12 bits) value. + */ +static int16_t imm8m(u32 x) { - u16 ret = 0; - - if ((ctx->skf->len > 1) || - (ctx->skf->insns[0].code == (BPF_RET | BPF_A))) - ret |= 1 << r_A; - -#ifdef CONFIG_FRAME_POINTER - ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC); -#else - if (ctx->seen & SEEN_CALL) - ret |= 1 << ARM_LR; -#endif - if (ctx->seen & (SEEN_DATA | SEEN_SKB)) - ret |= 1 << r_skb; - if (ctx->seen & SEEN_DATA) - ret |= (1 << r_skb_data) | (1 << r_skb_hl); - if (ctx->seen & SEEN_X) - ret |= 1 << r_X; - - return ret; -} + u32 rot; -static inline int mem_words_used(struct jit_ctx *ctx) -{ - /* yes, we do waste some stack space IF there are "holes" in the set" */ - return fls(ctx->seen & SEEN_MEM); + for (rot = 0; rot < 16; rot++) + if ((x & ~ror32(0xff, 2 * rot)) == 0) + return rol32(x, 2 * rot) | (rot << 8); + return -1; } +/* + * Initializes the JIT space with undefined instructions. + */ static void jit_fill_hole(void *area, unsigned int size) { u32 *ptr; @@ -196,88 +179,34 @@ static void jit_fill_hole(void *area, unsigned int size) *ptr++ = __opcode_to_mem_arm(ARM_INST_UDF); } -static void build_prologue(struct jit_ctx *ctx) -{ - u16 reg_set = saved_regs(ctx); - u16 off; - -#ifdef CONFIG_FRAME_POINTER - emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx); - emit(ARM_PUSH(reg_set), ctx); - emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx); -#else - if (reg_set) - emit(ARM_PUSH(reg_set), ctx); -#endif - - if (ctx->seen & (SEEN_DATA | SEEN_SKB)) - emit(ARM_MOV_R(r_skb, ARM_R0), ctx); - - if (ctx->seen & SEEN_DATA) { - off = offsetof(struct sk_buff, data); - emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx); - /* headlen = len - data_len */ - off = offsetof(struct sk_buff, len); - emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx); - off = offsetof(struct sk_buff, data_len); - emit(ARM_LDR_I(r_scratch, r_skb, off), ctx); - emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx); - } - - if (ctx->flags & FLAG_NEED_X_RESET) - emit(ARM_MOV_I(r_X, 0), ctx); - - /* do not leak kernel data to userspace */ - if (bpf_needs_clear_a(&ctx->skf->insns[0])) - emit(ARM_MOV_I(r_A, 0), ctx); - - /* stack space for the BPF_MEM words */ - if (ctx->seen & SEEN_MEM) - emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx); -} - -static void build_epilogue(struct jit_ctx *ctx) -{ - u16 reg_set = saved_regs(ctx); - - if (ctx->seen & SEEN_MEM) - emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx); - - reg_set &= ~(1 << ARM_LR); +/* Stack must be multiples of 16 Bytes */ +#define STACK_ALIGN(sz) (((sz) + 3) & ~3) -#ifdef CONFIG_FRAME_POINTER - /* the first instruction of the prologue was: mov ip, sp */ - reg_set &= ~(1 << ARM_IP); - reg_set |= (1 << ARM_SP); - emit(ARM_LDM(ARM_SP, reg_set), ctx); -#else - if (reg_set) { - if (ctx->seen & SEEN_CALL) - reg_set |= 1 << ARM_PC; - emit(ARM_POP(reg_set), ctx); - } +/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4, + * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9, + * BPF_REG_FP and Tail call counts. + */ +#define SCRATCH_SIZE 80 - if (!(ctx->seen & SEEN_CALL)) - emit(ARM_BX(ARM_LR), ctx); -#endif -} +/* total stack size used in JITed code */ +#define _STACK_SIZE \ + (ctx->prog->aux->stack_depth + \ + + SCRATCH_SIZE + \ + + 4 /* extra for skb_copy_bits buffer */) -static int16_t imm8m(u32 x) -{ - u32 rot; +#define STACK_SIZE STACK_ALIGN(_STACK_SIZE) - for (rot = 0; rot < 16; rot++) - if ((x & ~ror32(0xff, 2 * rot)) == 0) - return rol32(x, 2 * rot) | (rot << 8); +/* Get the offset of eBPF REGISTERs stored on scratch space. */ +#define STACK_VAR(off) (STACK_SIZE-off-4) - return -1; -} +/* Offset of skb_copy_bits buffer */ +#define SKB_BUFFER STACK_VAR(SCRATCH_SIZE) #if __LINUX_ARM_ARCH__ < 7 static u16 imm_offset(u32 k, struct jit_ctx *ctx) { - unsigned i = 0, offset; + unsigned int i = 0, offset; u16 imm; /* on the "fake" run we just count them (duplicates included) */ @@ -296,7 +225,7 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx) ctx->imms[i] = k; /* constants go just after the epilogue */ - offset = ctx->offsets[ctx->skf->len]; + offset = ctx->offsets[ctx->prog->len - 1] * 4; offset += ctx->prologue_bytes; offset += ctx->epilogue_bytes; offset += i * 4; @@ -320,10 +249,22 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx) #endif /* __LINUX_ARM_ARCH__ */ +static inline int bpf2a32_offset(int bpf_to, int bpf_from, + const struct jit_ctx *ctx) { + int to, from; + + if (ctx->target == NULL) + return 0; + to = ctx->offsets[bpf_to]; + from = ctx->offsets[bpf_from]; + + return to - from - 1; +} + /* * Move an immediate that's not an imm8m to a core register. */ -static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx) +static inline void emit_mov_i_no8m(const u8 rd, u32 val, struct jit_ctx *ctx) { #if __LINUX_ARM_ARCH__ < 7 emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx); @@ -334,7 +275,7 @@ static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx) #endif } -static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx) +static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx) { int imm12 = imm8m(val); @@ -344,676 +285,1594 @@ static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx) emit_mov_i_no8m(rd, val, ctx); } -#if __LINUX_ARM_ARCH__ < 6 - -static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx) { - _emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx); - _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx); - _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx); - _emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx); - _emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx); - _emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx); - _emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx); - _emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx); + ctx->seen |= SEEN_CALL; +#if __LINUX_ARM_ARCH__ < 5 + emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx); + + if (elf_hwcap & HWCAP_THUMB) + emit(ARM_BX(tgt_reg), ctx); + else + emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx); +#else + emit(ARM_BLX_R(tgt_reg), ctx); +#endif } -static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +static inline int epilogue_offset(const struct jit_ctx *ctx) { - _emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx); - _emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx); - _emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx); + int to, from; + /* No need for 1st dummy run */ + if (ctx->target == NULL) + return 0; + to = ctx->epilogue_offset; + from = ctx->idx; + + return to - from - 2; } -static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx) +static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op) { - /* r_dst = (r_src << 8) | (r_src >> 8) */ - emit(ARM_LSL_I(ARM_R1, r_src, 8), ctx); - emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSR, 8), ctx); + const u8 *tmp = bpf2a32[TMP_REG_1]; + s32 jmp_offset; + + /* checks if divisor is zero or not. If it is, then + * exit directly. + */ + emit(ARM_CMP_I(rn, 0), ctx); + _emit(ARM_COND_EQ, ARM_MOV_I(ARM_R0, 0), ctx); + jmp_offset = epilogue_offset(ctx); + _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx); +#if __LINUX_ARM_ARCH__ == 7 + if (elf_hwcap & HWCAP_IDIVA) { + if (op == BPF_DIV) + emit(ARM_UDIV(rd, rm, rn), ctx); + else { + emit(ARM_UDIV(ARM_IP, rm, rn), ctx); + emit(ARM_MLS(rd, rn, ARM_IP, rm), ctx); + } + return; + } +#endif /* - * we need to mask out the bits set in r_dst[23:16] due to - * the first shift instruction. - * - * note that 0x8ff is the encoded immediate 0x00ff0000. + * For BPF_ALU | BPF_DIV | BPF_K instructions + * As ARM_R1 and ARM_R0 contains 1st argument of bpf + * function, we need to save it on caller side to save + * it from getting destroyed within callee. + * After the return from the callee, we restore ARM_R0 + * ARM_R1. */ - emit(ARM_BIC_I(r_dst, r_dst, 0x8ff), ctx); -} + if (rn != ARM_R1) { + emit(ARM_MOV_R(tmp[0], ARM_R1), ctx); + emit(ARM_MOV_R(ARM_R1, rn), ctx); + } + if (rm != ARM_R0) { + emit(ARM_MOV_R(tmp[1], ARM_R0), ctx); + emit(ARM_MOV_R(ARM_R0, rm), ctx); + } -#else /* ARMv6+ */ + /* Call appropriate function */ + ctx->seen |= SEEN_CALL; + emit_mov_i(ARM_IP, op == BPF_DIV ? + (u32)jit_udiv32 : (u32)jit_mod32, ctx); + emit_blx_r(ARM_IP, ctx); -static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) -{ - _emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx); -#ifdef __LITTLE_ENDIAN - _emit(cond, ARM_REV(r_res, r_res), ctx); -#endif + /* Save return value */ + if (rd != ARM_R0) + emit(ARM_MOV_R(rd, ARM_R0), ctx); + + /* Restore ARM_R0 and ARM_R1 */ + if (rn != ARM_R1) + emit(ARM_MOV_R(ARM_R1, tmp[0]), ctx); + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx); } -static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx) +/* Checks whether BPF register is on scratch stack space or not. */ +static inline bool is_on_stack(u8 bpf_reg) { - _emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx); -#ifdef __LITTLE_ENDIAN - _emit(cond, ARM_REV16(r_res, r_res), ctx); -#endif + static u8 stack_regs[] = {BPF_REG_AX, BPF_REG_3, BPF_REG_4, BPF_REG_5, + BPF_REG_7, BPF_REG_8, BPF_REG_9, TCALL_CNT, + BPF_REG_2, BPF_REG_FP}; + int i, reg_len = sizeof(stack_regs); + + for (i = 0 ; i < reg_len ; i++) { + if (bpf_reg == stack_regs[i]) + return true; + } + return false; } -static inline void emit_swap16(u8 r_dst __maybe_unused, - u8 r_src __maybe_unused, - struct jit_ctx *ctx __maybe_unused) +static inline void emit_a32_mov_i(const u8 dst, const u32 val, + bool dstk, struct jit_ctx *ctx) { -#ifdef __LITTLE_ENDIAN - emit(ARM_REV16(r_dst, r_src), ctx); -#endif + const u8 *tmp = bpf2a32[TMP_REG_1]; + + if (dstk) { + emit_mov_i(tmp[1], val, ctx); + emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx); + } else { + emit_mov_i(dst, val, ctx); + } } -#endif /* __LINUX_ARM_ARCH__ < 6 */ +/* Sign extended move */ +static inline void emit_a32_mov_i64(const bool is64, const u8 dst[], + const u32 val, bool dstk, + struct jit_ctx *ctx) { + u32 hi = 0; + if (is64 && (val & (1<<31))) + hi = (u32)~0; + emit_a32_mov_i(dst_lo, val, dstk, ctx); + emit_a32_mov_i(dst_hi, hi, dstk, ctx); +} -/* Compute the immediate value for a PC-relative branch. */ -static inline u32 b_imm(unsigned tgt, struct jit_ctx *ctx) -{ - u32 imm; +static inline void emit_a32_add_r(const u8 dst, const u8 src, + const bool is64, const bool hi, + struct jit_ctx *ctx) { + /* 64 bit : + * adds dst_lo, dst_lo, src_lo + * adc dst_hi, dst_hi, src_hi + * 32 bit : + * add dst_lo, dst_lo, src_lo + */ + if (!hi && is64) + emit(ARM_ADDS_R(dst, dst, src), ctx); + else if (hi && is64) + emit(ARM_ADC_R(dst, dst, src), ctx); + else + emit(ARM_ADD_R(dst, dst, src), ctx); +} - if (ctx->target == NULL) - return 0; - /* - * BPF allows only forward jumps and the offset of the target is - * still the one computed during the first pass. +static inline void emit_a32_sub_r(const u8 dst, const u8 src, + const bool is64, const bool hi, + struct jit_ctx *ctx) { + /* 64 bit : + * subs dst_lo, dst_lo, src_lo + * sbc dst_hi, dst_hi, src_hi + * 32 bit : + * sub dst_lo, dst_lo, src_lo */ - imm = ctx->offsets[tgt] + ctx->prologue_bytes - (ctx->idx * 4 + 8); + if (!hi && is64) + emit(ARM_SUBS_R(dst, dst, src), ctx); + else if (hi && is64) + emit(ARM_SBC_R(dst, dst, src), ctx); + else + emit(ARM_SUB_R(dst, dst, src), ctx); +} - return imm >> 2; +static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64, + const bool hi, const u8 op, struct jit_ctx *ctx){ + switch (BPF_OP(op)) { + /* dst = dst + src */ + case BPF_ADD: + emit_a32_add_r(dst, src, is64, hi, ctx); + break; + /* dst = dst - src */ + case BPF_SUB: + emit_a32_sub_r(dst, src, is64, hi, ctx); + break; + /* dst = dst | src */ + case BPF_OR: + emit(ARM_ORR_R(dst, dst, src), ctx); + break; + /* dst = dst & src */ + case BPF_AND: + emit(ARM_AND_R(dst, dst, src), ctx); + break; + /* dst = dst ^ src */ + case BPF_XOR: + emit(ARM_EOR_R(dst, dst, src), ctx); + break; + /* dst = dst * src */ + case BPF_MUL: + emit(ARM_MUL(dst, dst, src), ctx); + break; + /* dst = dst << src */ + case BPF_LSH: + emit(ARM_LSL_R(dst, dst, src), ctx); + break; + /* dst = dst >> src */ + case BPF_RSH: + emit(ARM_LSR_R(dst, dst, src), ctx); + break; + /* dst = dst >> src (signed)*/ + case BPF_ARSH: + emit(ARM_MOV_SR(dst, dst, SRTYPE_ASR, src), ctx); + break; + } } -#define OP_IMM3(op, r1, r2, imm_val, ctx) \ - do { \ - imm12 = imm8m(imm_val); \ - if (imm12 < 0) { \ - emit_mov_i_no8m(r_scratch, imm_val, ctx); \ - emit(op ## _R((r1), (r2), r_scratch), ctx); \ - } else { \ - emit(op ## _I((r1), (r2), imm12), ctx); \ - } \ - } while (0) - -static inline void emit_err_ret(u8 cond, struct jit_ctx *ctx) -{ - if (ctx->ret0_fp_idx >= 0) { - _emit(cond, ARM_B(b_imm(ctx->ret0_fp_idx, ctx)), ctx); - /* NOP to keep the size constant between passes */ - emit(ARM_MOV_R(ARM_R0, ARM_R0), ctx); +/* ALU operation (32 bit) + * dst = dst (op) src + */ +static inline void emit_a32_alu_r(const u8 dst, const u8 src, + bool dstk, bool sstk, + struct jit_ctx *ctx, const bool is64, + const bool hi, const u8 op) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + u8 rn = sstk ? tmp[1] : src; + + if (sstk) + emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx); + + /* ALU operation */ + if (dstk) { + emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx); + emit_alu_r(tmp[0], rn, is64, hi, op, ctx); + emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx); } else { - _emit(cond, ARM_MOV_I(ARM_R0, 0), ctx); - _emit(cond, ARM_B(b_imm(ctx->skf->len, ctx)), ctx); + emit_alu_r(dst, rn, is64, hi, op, ctx); } } -static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx) -{ -#if __LINUX_ARM_ARCH__ < 5 - emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx); +/* ALU operation (64 bit) */ +static inline void emit_a32_alu_r64(const bool is64, const u8 dst[], + const u8 src[], bool dstk, + bool sstk, struct jit_ctx *ctx, + const u8 op) { + emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op); + if (is64) + emit_a32_alu_r(dst_hi, src_hi, dstk, sstk, ctx, is64, true, op); + else + emit_a32_mov_i(dst_hi, 0, dstk, ctx); +} - if (elf_hwcap & HWCAP_THUMB) - emit(ARM_BX(tgt_reg), ctx); +/* dst = imm (4 bytes)*/ +static inline void emit_a32_mov_r(const u8 dst, const u8 src, + bool dstk, bool sstk, + struct jit_ctx *ctx) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + u8 rt = sstk ? tmp[0] : src; + + if (sstk) + emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx); + if (dstk) + emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx); else - emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx); -#else - emit(ARM_BLX_R(tgt_reg), ctx); -#endif + emit(ARM_MOV_R(dst, rt), ctx); } -static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, - int bpf_op) -{ -#if __LINUX_ARM_ARCH__ == 7 - if (elf_hwcap & HWCAP_IDIVA) { - if (bpf_op == BPF_DIV) - emit(ARM_UDIV(rd, rm, rn), ctx); - else { - emit(ARM_UDIV(ARM_R3, rm, rn), ctx); - emit(ARM_MLS(rd, rn, ARM_R3, rm), ctx); - } - return; +/* dst = src */ +static inline void emit_a32_mov_r64(const bool is64, const u8 dst[], + const u8 src[], bool dstk, + bool sstk, struct jit_ctx *ctx) { + emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx); + if (is64) { + /* complete 8 byte move */ + emit_a32_mov_r(dst_hi, src_hi, dstk, sstk, ctx); + } else { + /* Zero out high 4 bytes */ + emit_a32_mov_i(dst_hi, 0, dstk, ctx); } -#endif +} - /* - * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 - * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into - * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm - * before using it as a source for ARM_R1. - * - * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is - * ARM_R5 (r_X) so there is no particular register overlap - * issues. - */ - if (rn != ARM_R1) - emit(ARM_MOV_R(ARM_R1, rn), ctx); - if (rm != ARM_R0) - emit(ARM_MOV_R(ARM_R0, rm), ctx); +/* Shift operations */ +static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk, + struct jit_ctx *ctx, const u8 op) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + u8 rd = dstk ? tmp[0] : dst; + + if (dstk) + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); + + /* Do shift operation */ + switch (op) { + case BPF_LSH: + emit(ARM_LSL_I(rd, rd, val), ctx); + break; + case BPF_RSH: + emit(ARM_LSR_I(rd, rd, val), ctx); + break; + case BPF_NEG: + emit(ARM_RSB_I(rd, rd, val), ctx); + break; + } + if (dstk) + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); +} + +/* dst = ~dst (64 bit) */ +static inline void emit_a32_neg64(const u8 dst[], bool dstk, + struct jit_ctx *ctx){ + const u8 *tmp = bpf2a32[TMP_REG_1]; + u8 rd = dstk ? tmp[1] : dst[1]; + u8 rm = dstk ? tmp[0] : dst[0]; + + /* Setup Operand */ + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do Negate Operation */ + emit(ARM_RSBS_I(rd, rd, 0), ctx); + emit(ARM_RSC_I(rm, rm, 0), ctx); + + if (dstk) { + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } +} + +/* dst = dst << src */ +static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk, + bool sstk, struct jit_ctx *ctx) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + + /* Setup Operands */ + u8 rt = sstk ? tmp2[1] : src_lo; + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + + if (sstk) + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do LSH operation */ + emit(ARM_SUB_I(ARM_IP, rt, 32), ctx); + emit(ARM_RSB_I(tmp2[0], rt, 32), ctx); + /* As we are using ARM_LR */ ctx->seen |= SEEN_CALL; - emit_mov_i(ARM_R3, bpf_op == BPF_DIV ? (u32)jit_udiv : (u32)jit_mod, - ctx); - emit_blx_r(ARM_R3, ctx); + emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx); + emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx); + emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx); + + if (dstk) { + emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx); + } else { + emit(ARM_MOV_R(rd, ARM_LR), ctx); + emit(ARM_MOV_R(rm, ARM_IP), ctx); + } +} - if (rd != ARM_R0) - emit(ARM_MOV_R(rd, ARM_R0), ctx); +/* dst = dst >> src (signed)*/ +static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk, + bool sstk, struct jit_ctx *ctx) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + /* Setup Operands */ + u8 rt = sstk ? tmp2[1] : src_lo; + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + + if (sstk) + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do the ARSH operation */ + emit(ARM_RSB_I(ARM_IP, rt, 32), ctx); + emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx); + /* As we are using ARM_LR */ + ctx->seen |= SEEN_CALL; + emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx); + _emit(ARM_COND_MI, ARM_B(0), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx); + emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx); + if (dstk) { + emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx); + } else { + emit(ARM_MOV_R(rd, ARM_LR), ctx); + emit(ARM_MOV_R(rm, ARM_IP), ctx); + } +} + +/* dst = dst >> src */ +static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk, + bool sstk, struct jit_ctx *ctx) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + /* Setup Operands */ + u8 rt = sstk ? tmp2[1] : src_lo; + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + + if (sstk) + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do LSH operation */ + emit(ARM_RSB_I(ARM_IP, rt, 32), ctx); + emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx); + /* As we are using ARM_LR */ + ctx->seen |= SEEN_CALL; + emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx); + emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx); + emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx); + if (dstk) { + emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx); + } else { + emit(ARM_MOV_R(rd, ARM_LR), ctx); + emit(ARM_MOV_R(rm, ARM_IP), ctx); + } } -static inline void update_on_xread(struct jit_ctx *ctx) +/* dst = dst << val */ +static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk, + const u32 val, struct jit_ctx *ctx){ + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + /* Setup operands */ + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do LSH operation */ + if (val < 32) { + emit(ARM_MOV_SI(tmp2[0], rm, SRTYPE_ASL, val), ctx); + emit(ARM_ORR_SI(rm, tmp2[0], rd, SRTYPE_LSR, 32 - val), ctx); + emit(ARM_MOV_SI(rd, rd, SRTYPE_ASL, val), ctx); + } else { + if (val == 32) + emit(ARM_MOV_R(rm, rd), ctx); + else + emit(ARM_MOV_SI(rm, rd, SRTYPE_ASL, val - 32), ctx); + emit(ARM_EOR_R(rd, rd, rd), ctx); + } + + if (dstk) { + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } +} + +/* dst = dst >> val */ +static inline void emit_a32_lsr_i64(const u8 dst[], bool dstk, + const u32 val, struct jit_ctx *ctx) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + /* Setup operands */ + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do LSR operation */ + if (val < 32) { + emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx); + emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx); + emit(ARM_MOV_SI(rm, rm, SRTYPE_LSR, val), ctx); + } else if (val == 32) { + emit(ARM_MOV_R(rd, rm), ctx); + emit(ARM_MOV_I(rm, 0), ctx); + } else { + emit(ARM_MOV_SI(rd, rm, SRTYPE_LSR, val - 32), ctx); + emit(ARM_MOV_I(rm, 0), ctx); + } + + if (dstk) { + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } +} + +/* dst = dst >> val (signed) */ +static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk, + const u32 val, struct jit_ctx *ctx){ + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + /* Setup operands */ + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Do ARSH operation */ + if (val < 32) { + emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx); + emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx); + emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, val), ctx); + } else if (val == 32) { + emit(ARM_MOV_R(rd, rm), ctx); + emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx); + } else { + emit(ARM_MOV_SI(rd, rm, SRTYPE_ASR, val - 32), ctx); + emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx); + } + + if (dstk) { + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } +} + +static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk, + bool sstk, struct jit_ctx *ctx) { + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + /* Setup operands for multiplication */ + u8 rd = dstk ? tmp[1] : dst_lo; + u8 rm = dstk ? tmp[0] : dst_hi; + u8 rt = sstk ? tmp2[1] : src_lo; + u8 rn = sstk ? tmp2[0] : src_hi; + + if (dstk) { + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + if (sstk) { + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx); + emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx); + } + + /* Do Multiplication */ + emit(ARM_MUL(ARM_IP, rd, rn), ctx); + emit(ARM_MUL(ARM_LR, rm, rt), ctx); + /* As we are using ARM_LR */ + ctx->seen |= SEEN_CALL; + emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx); + + emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx); + emit(ARM_ADD_R(rm, ARM_LR, rm), ctx); + if (dstk) { + emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx); + } else { + emit(ARM_MOV_R(rd, ARM_IP), ctx); + } +} + +/* *(size *)(dst + off) = src */ +static inline void emit_str_r(const u8 dst, const u8 src, bool dstk, + const s32 off, struct jit_ctx *ctx, const u8 sz){ + const u8 *tmp = bpf2a32[TMP_REG_1]; + u8 rd = dstk ? tmp[1] : dst; + + if (dstk) + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); + if (off) { + emit_a32_mov_i(tmp[0], off, false, ctx); + emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx); + rd = tmp[0]; + } + switch (sz) { + case BPF_W: + /* Store a Word */ + emit(ARM_STR_I(src, rd, 0), ctx); + break; + case BPF_H: + /* Store a HalfWord */ + emit(ARM_STRH_I(src, rd, 0), ctx); + break; + case BPF_B: + /* Store a Byte */ + emit(ARM_STRB_I(src, rd, 0), ctx); + break; + } +} + +/* dst = *(size*)(src + off) */ +static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk, + const s32 off, struct jit_ctx *ctx, const u8 sz){ + const u8 *tmp = bpf2a32[TMP_REG_1]; + u8 rd = dstk ? tmp[1] : dst; + u8 rm = src; + + if (off) { + emit_a32_mov_i(tmp[0], off, false, ctx); + emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx); + rm = tmp[0]; + } + switch (sz) { + case BPF_W: + /* Load a Word */ + emit(ARM_LDR_I(rd, rm, 0), ctx); + break; + case BPF_H: + /* Load a HalfWord */ + emit(ARM_LDRH_I(rd, rm, 0), ctx); + break; + case BPF_B: + /* Load a Byte */ + emit(ARM_LDRB_I(rd, rm, 0), ctx); + break; + } + if (dstk) + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx); +} + +/* Arithmatic Operation */ +static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm, + const u8 rn, struct jit_ctx *ctx, u8 op) { + switch (op) { + case BPF_JSET: + ctx->seen |= SEEN_CALL; + emit(ARM_AND_R(ARM_IP, rt, rn), ctx); + emit(ARM_AND_R(ARM_LR, rd, rm), ctx); + emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx); + break; + case BPF_JEQ: + case BPF_JNE: + case BPF_JGT: + case BPF_JGE: + case BPF_JLE: + case BPF_JLT: + emit(ARM_CMP_R(rd, rm), ctx); + _emit(ARM_COND_EQ, ARM_CMP_R(rt, rn), ctx); + break; + case BPF_JSLE: + case BPF_JSGT: + emit(ARM_CMP_R(rn, rt), ctx); + emit(ARM_SBCS_R(ARM_IP, rm, rd), ctx); + break; + case BPF_JSLT: + case BPF_JSGE: + emit(ARM_CMP_R(rt, rn), ctx); + emit(ARM_SBCS_R(ARM_IP, rd, rm), ctx); + break; + } +} + +static int out_offset = -1; /* initialized on the first pass of build_body() */ +static int emit_bpf_tail_call(struct jit_ctx *ctx) { - if (!(ctx->seen & SEEN_X)) - ctx->flags |= FLAG_NEED_X_RESET; - ctx->seen |= SEEN_X; + /* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */ + const u8 *r2 = bpf2a32[BPF_REG_2]; + const u8 *r3 = bpf2a32[BPF_REG_3]; + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + const u8 *tcc = bpf2a32[TCALL_CNT]; + const int idx0 = ctx->idx; +#define cur_offset (ctx->idx - idx0) +#define jmp_offset (out_offset - (cur_offset)) + u32 off, lo, hi; + + /* if (index >= array->map.max_entries) + * goto out; + */ + off = offsetof(struct bpf_array, map.max_entries); + /* array->map.max_entries */ + emit_a32_mov_i(tmp[1], off, false, ctx); + emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx); + emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx); + /* index (64 bit) */ + emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx); + /* index >= array->map.max_entries */ + emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx); + _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx); + + /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + * tail_call_cnt++; + */ + lo = (u32)MAX_TAIL_CALL_CNT; + hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32); + emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx); + emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx); + emit(ARM_CMP_I(tmp[0], hi), ctx); + _emit(ARM_COND_EQ, ARM_CMP_I(tmp[1], lo), ctx); + _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx); + emit(ARM_ADDS_I(tmp[1], tmp[1], 1), ctx); + emit(ARM_ADC_I(tmp[0], tmp[0], 0), ctx); + emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx); + emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx); + + /* prog = array->ptrs[index] + * if (prog == NULL) + * goto out; + */ + off = offsetof(struct bpf_array, ptrs); + emit_a32_mov_i(tmp[1], off, false, ctx); + emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx); + emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx); + emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx); + emit(ARM_MOV_SI(tmp[0], tmp2[1], SRTYPE_ASL, 2), ctx); + emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx); + emit(ARM_CMP_I(tmp[1], 0), ctx); + _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx); + + /* goto *(prog->bpf_func + prologue_size); */ + off = offsetof(struct bpf_prog, bpf_func); + emit_a32_mov_i(tmp2[1], off, false, ctx); + emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx); + emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx); + emit(ARM_BX(tmp[1]), ctx); + + /* out: */ + if (out_offset == -1) + out_offset = cur_offset; + if (cur_offset != out_offset) { + pr_err_once("tail_call out_offset = %d, expected %d!\n", + cur_offset, out_offset); + return -1; + } + return 0; +#undef cur_offset +#undef jmp_offset } -static int build_body(struct jit_ctx *ctx) +/* 0xabcd => 0xcdab */ +static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx) { - void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w}; - const struct bpf_prog *prog = ctx->skf; - const struct sock_filter *inst; - unsigned i, load_order, off, condt; - int imm12; - u32 k; +#if __LINUX_ARM_ARCH__ < 6 + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + + emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx); + emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 8), ctx); + emit(ARM_AND_I(tmp2[0], tmp2[0], 0xff), ctx); + emit(ARM_ORR_SI(rd, tmp2[0], tmp2[1], SRTYPE_LSL, 8), ctx); +#else /* ARMv6+ */ + emit(ARM_REV16(rd, rn), ctx); +#endif +} - for (i = 0; i < prog->len; i++) { - u16 code; +/* 0xabcdefgh => 0xghefcdab */ +static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx) +{ +#if __LINUX_ARM_ARCH__ < 6 + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + + emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx); + emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 24), ctx); + emit(ARM_ORR_SI(ARM_IP, tmp2[0], tmp2[1], SRTYPE_LSL, 24), ctx); + + emit(ARM_MOV_SI(tmp2[1], rn, SRTYPE_LSR, 8), ctx); + emit(ARM_AND_I(tmp2[1], tmp2[1], 0xff), ctx); + emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 16), ctx); + emit(ARM_AND_I(tmp2[0], tmp2[0], 0xff), ctx); + emit(ARM_MOV_SI(tmp2[0], tmp2[0], SRTYPE_LSL, 8), ctx); + emit(ARM_ORR_SI(tmp2[0], tmp2[0], tmp2[1], SRTYPE_LSL, 16), ctx); + emit(ARM_ORR_R(rd, ARM_IP, tmp2[0]), ctx); + +#else /* ARMv6+ */ + emit(ARM_REV(rd, rn), ctx); +#endif +} - inst = &(prog->insns[i]); - /* K as an immediate value operand */ - k = inst->k; - code = bpf_anc_helper(inst); +// push the scratch stack register on top of the stack +static inline void emit_push_r64(const u8 src[], const u8 shift, + struct jit_ctx *ctx) +{ + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + u16 reg_set = 0; - /* compute offsets only in the fake pass */ - if (ctx->target == NULL) - ctx->offsets[i] = ctx->idx * 4; + emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx); + emit(ARM_LDR_I(tmp2[0], ARM_SP, STACK_VAR(src[0]+shift)), ctx); + + reg_set = (1 << tmp2[1]) | (1 << tmp2[0]); + emit(ARM_PUSH(reg_set), ctx); +} + +static void build_prologue(struct jit_ctx *ctx) +{ + const u8 r0 = bpf2a32[BPF_REG_0][1]; + const u8 r2 = bpf2a32[BPF_REG_1][1]; + const u8 r3 = bpf2a32[BPF_REG_1][0]; + const u8 r4 = bpf2a32[BPF_REG_6][1]; + const u8 r5 = bpf2a32[BPF_REG_6][0]; + const u8 r6 = bpf2a32[TMP_REG_1][1]; + const u8 r7 = bpf2a32[TMP_REG_1][0]; + const u8 r8 = bpf2a32[TMP_REG_2][1]; + const u8 r10 = bpf2a32[TMP_REG_2][0]; + const u8 fplo = bpf2a32[BPF_REG_FP][1]; + const u8 fphi = bpf2a32[BPF_REG_FP][0]; + const u8 sp = ARM_SP; + const u8 *tcc = bpf2a32[TCALL_CNT]; + + u16 reg_set = 0; + + /* + * eBPF prog stack layout + * + * high + * original ARM_SP => +-----+ eBPF prologue + * |FP/LR| + * current ARM_FP => +-----+ + * | ... | callee saved registers + * eBPF fp register => +-----+ <= (BPF_FP) + * | ... | eBPF JIT scratch space + * | | eBPF prog stack + * +-----+ + * |RSVD | JIT scratchpad + * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE) + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + */ + + /* Save callee saved registers. */ + reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10); +#ifdef CONFIG_FRAME_POINTER + reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC); + emit(ARM_MOV_R(ARM_IP, sp), ctx); + emit(ARM_PUSH(reg_set), ctx); + emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx); +#else + /* Check if call instruction exists in BPF body */ + if (ctx->seen & SEEN_CALL) + reg_set |= (1<<ARM_LR); + emit(ARM_PUSH(reg_set), ctx); +#endif + /* Save frame pointer for later */ + emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx); + + ctx->stack_size = imm8m(STACK_SIZE); + + /* Set up function call stack */ + emit(ARM_SUB_I(ARM_SP, ARM_SP, ctx->stack_size), ctx); - switch (code) { - case BPF_LD | BPF_IMM: - emit_mov_i(r_A, k, ctx); + /* Set up BPF prog stack base register */ + emit_a32_mov_r(fplo, ARM_IP, true, false, ctx); + emit_a32_mov_i(fphi, 0, true, ctx); + + /* mov r4, 0 */ + emit(ARM_MOV_I(r4, 0), ctx); + + /* Move BPF_CTX to BPF_R1 */ + emit(ARM_MOV_R(r3, r4), ctx); + emit(ARM_MOV_R(r2, r0), ctx); + /* Initialize Tail Count */ + emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[0])), ctx); + emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[1])), ctx); + /* end of prologue */ +} + +static void build_epilogue(struct jit_ctx *ctx) +{ + const u8 r4 = bpf2a32[BPF_REG_6][1]; + const u8 r5 = bpf2a32[BPF_REG_6][0]; + const u8 r6 = bpf2a32[TMP_REG_1][1]; + const u8 r7 = bpf2a32[TMP_REG_1][0]; + const u8 r8 = bpf2a32[TMP_REG_2][1]; + const u8 r10 = bpf2a32[TMP_REG_2][0]; + u16 reg_set = 0; + + /* unwind function call stack */ + emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx); + + /* restore callee saved registers. */ + reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10); +#ifdef CONFIG_FRAME_POINTER + /* the first instruction of the prologue was: mov ip, sp */ + reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC); + emit(ARM_LDM(ARM_SP, reg_set), ctx); +#else + if (ctx->seen & SEEN_CALL) + reg_set |= (1<<ARM_PC); + /* Restore callee saved registers. */ + emit(ARM_POP(reg_set), ctx); + /* Return back to the callee function */ + if (!(ctx->seen & SEEN_CALL)) + emit(ARM_BX(ARM_LR), ctx); +#endif +} + +/* + * Convert an eBPF instruction to native instruction, i.e + * JITs an eBPF instruction. + * Returns : + * 0 - Successfully JITed an 8-byte eBPF instruction + * >0 - Successfully JITed a 16-byte eBPF instruction + * <0 - Failed to JIT. + */ +static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) +{ + const u8 code = insn->code; + const u8 *dst = bpf2a32[insn->dst_reg]; + const u8 *src = bpf2a32[insn->src_reg]; + const u8 *tmp = bpf2a32[TMP_REG_1]; + const u8 *tmp2 = bpf2a32[TMP_REG_2]; + const s16 off = insn->off; + const s32 imm = insn->imm; + const int i = insn - ctx->prog->insnsi; + const bool is64 = BPF_CLASS(code) == BPF_ALU64; + const bool dstk = is_on_stack(insn->dst_reg); + const bool sstk = is_on_stack(insn->src_reg); + u8 rd, rt, rm, rn; + s32 jmp_offset; + +#define check_imm(bits, imm) do { \ + if ((((imm) > 0) && ((imm) >> (bits))) || \ + (((imm) < 0) && (~(imm) >> (bits)))) { \ + pr_info("[%2d] imm=%d(0x%x) out of range\n", \ + i, imm, imm); \ + return -EINVAL; \ + } \ +} while (0) +#define check_imm24(imm) check_imm(24, imm) + + switch (code) { + /* ALU operations */ + + /* dst = src */ + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU | BPF_MOV | BPF_X: + case BPF_ALU64 | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_MOV | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_a32_mov_r64(is64, dst, src, dstk, sstk, ctx); break; - case BPF_LD | BPF_W | BPF_LEN: - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); - emit(ARM_LDR_I(r_A, r_skb, - offsetof(struct sk_buff, len)), ctx); + case BPF_K: + /* Sign-extend immediate value to destination reg */ + emit_a32_mov_i64(is64, dst, imm, dstk, ctx); break; - case BPF_LD | BPF_MEM: - /* A = scratch[k] */ - ctx->seen |= SEEN_MEM_WORD(k); - emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); + } + break; + /* dst = dst + src/imm */ + /* dst = dst - src/imm */ + /* dst = dst | src/imm */ + /* dst = dst & src/imm */ + /* dst = dst ^ src/imm */ + /* dst = dst * src/imm */ + /* dst = dst << src */ + /* dst = dst >> src */ + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_a32_alu_r64(is64, dst, src, dstk, sstk, + ctx, BPF_OP(code)); break; - case BPF_LD | BPF_W | BPF_ABS: - load_order = 2; - goto load; - case BPF_LD | BPF_H | BPF_ABS: - load_order = 1; - goto load; - case BPF_LD | BPF_B | BPF_ABS: - load_order = 0; -load: - emit_mov_i(r_off, k, ctx); -load_common: - ctx->seen |= SEEN_DATA | SEEN_CALL; - - if (load_order > 0) { - emit(ARM_SUB_I(r_scratch, r_skb_hl, - 1 << load_order), ctx); - emit(ARM_CMP_R(r_scratch, r_off), ctx); - condt = ARM_COND_GE; - } else { - emit(ARM_CMP_R(r_skb_hl, r_off), ctx); - condt = ARM_COND_HI; - } - - /* - * test for negative offset, only if we are - * currently scheduled to take the fast - * path. this will update the flags so that - * the slowpath instruction are ignored if the - * offset is negative. - * - * for loard_order == 0 the HI condition will - * make loads at offset 0 take the slow path too. + case BPF_K: + /* Move immediate value to the temporary register + * and then do the ALU operation on the temporary + * register as this will sign-extend the immediate + * value into temporary reg and then it would be + * safe to do the operation on it. */ - _emit(condt, ARM_CMP_I(r_off, 0), ctx); - - _emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data), - ctx); - - if (load_order == 0) - _emit(condt, ARM_LDRB_I(r_A, r_scratch, 0), - ctx); - else if (load_order == 1) - emit_load_be16(condt, r_A, r_scratch, ctx); - else if (load_order == 2) - emit_load_be32(condt, r_A, r_scratch, ctx); - - _emit(condt, ARM_B(b_imm(i + 1, ctx)), ctx); - - /* the slowpath */ - emit_mov_i(ARM_R3, (u32)load_func[load_order], ctx); - emit(ARM_MOV_R(ARM_R0, r_skb), ctx); - /* the offset is already in R1 */ - emit_blx_r(ARM_R3, ctx); - /* check the result of skb_copy_bits */ - emit(ARM_CMP_I(ARM_R1, 0), ctx); - emit_err_ret(ARM_COND_NE, ctx); - emit(ARM_MOV_R(r_A, ARM_R0), ctx); + emit_a32_mov_i64(is64, tmp2, imm, false, ctx); + emit_a32_alu_r64(is64, dst, tmp2, dstk, false, + ctx, BPF_OP(code)); break; - case BPF_LD | BPF_W | BPF_IND: - load_order = 2; - goto load_ind; - case BPF_LD | BPF_H | BPF_IND: - load_order = 1; - goto load_ind; - case BPF_LD | BPF_B | BPF_IND: - load_order = 0; -load_ind: - update_on_xread(ctx); - OP_IMM3(ARM_ADD, r_off, r_X, k, ctx); - goto load_common; - case BPF_LDX | BPF_IMM: - ctx->seen |= SEEN_X; - emit_mov_i(r_X, k, ctx); + } + break; + /* dst = dst / src(imm) */ + /* dst = dst % src(imm) */ + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_MOD | BPF_X: + rt = src_lo; + rd = dstk ? tmp2[1] : dst_lo; + if (dstk) + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + switch (BPF_SRC(code)) { + case BPF_X: + rt = sstk ? tmp2[0] : rt; + if (sstk) + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), + ctx); break; - case BPF_LDX | BPF_W | BPF_LEN: - ctx->seen |= SEEN_X | SEEN_SKB; - emit(ARM_LDR_I(r_X, r_skb, - offsetof(struct sk_buff, len)), ctx); + case BPF_K: + rt = tmp2[0]; + emit_a32_mov_i(rt, imm, false, ctx); break; - case BPF_LDX | BPF_MEM: - ctx->seen |= SEEN_X | SEEN_MEM_WORD(k); - emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); + } + emit_udivmod(rd, rd, rt, ctx, BPF_OP(code)); + if (dstk) + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit_a32_mov_i(dst_hi, 0, dstk, ctx); + break; + case BPF_ALU64 | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + goto notyet; + /* dst = dst >> imm */ + /* dst = dst << imm */ + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_LSH | BPF_K: + if (unlikely(imm > 31)) + return -EINVAL; + if (imm) + emit_a32_alu_i(dst_lo, imm, dstk, ctx, BPF_OP(code)); + emit_a32_mov_i(dst_hi, 0, dstk, ctx); + break; + /* dst = dst << imm */ + case BPF_ALU64 | BPF_LSH | BPF_K: + if (unlikely(imm > 63)) + return -EINVAL; + emit_a32_lsh_i64(dst, dstk, imm, ctx); + break; + /* dst = dst >> imm */ + case BPF_ALU64 | BPF_RSH | BPF_K: + if (unlikely(imm > 63)) + return -EINVAL; + emit_a32_lsr_i64(dst, dstk, imm, ctx); + break; + /* dst = dst << src */ + case BPF_ALU64 | BPF_LSH | BPF_X: + emit_a32_lsh_r64(dst, src, dstk, sstk, ctx); + break; + /* dst = dst >> src */ + case BPF_ALU64 | BPF_RSH | BPF_X: + emit_a32_lsr_r64(dst, src, dstk, sstk, ctx); + break; + /* dst = dst >> src (signed) */ + case BPF_ALU64 | BPF_ARSH | BPF_X: + emit_a32_arsh_r64(dst, src, dstk, sstk, ctx); + break; + /* dst = dst >> imm (signed) */ + case BPF_ALU64 | BPF_ARSH | BPF_K: + if (unlikely(imm > 63)) + return -EINVAL; + emit_a32_arsh_i64(dst, dstk, imm, ctx); + break; + /* dst = ~dst */ + case BPF_ALU | BPF_NEG: + emit_a32_alu_i(dst_lo, 0, dstk, ctx, BPF_OP(code)); + emit_a32_mov_i(dst_hi, 0, dstk, ctx); + break; + /* dst = ~dst (64 bit) */ + case BPF_ALU64 | BPF_NEG: + emit_a32_neg64(dst, dstk, ctx); + break; + /* dst = dst * src/imm */ + case BPF_ALU64 | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + switch (BPF_SRC(code)) { + case BPF_X: + emit_a32_mul_r64(dst, src, dstk, sstk, ctx); break; - case BPF_LDX | BPF_B | BPF_MSH: - /* x = ((*(frame + k)) & 0xf) << 2; */ - ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL; - /* the interpreter should deal with the negative K */ - if ((int)k < 0) - return -1; - /* offset in r1: we might have to take the slow path */ - emit_mov_i(r_off, k, ctx); - emit(ARM_CMP_R(r_skb_hl, r_off), ctx); - - /* load in r0: common with the slowpath */ - _emit(ARM_COND_HI, ARM_LDRB_R(ARM_R0, r_skb_data, - ARM_R1), ctx); - /* - * emit_mov_i() might generate one or two instructions, - * the same holds for emit_blx_r() + case BPF_K: + /* Move immediate value to the temporary register + * and then do the multiplication on it as this + * will sign-extend the immediate value into temp + * reg then it would be safe to do the operation + * on it. */ - _emit(ARM_COND_HI, ARM_B(b_imm(i + 1, ctx) - 2), ctx); - - emit(ARM_MOV_R(ARM_R0, r_skb), ctx); - /* r_off is r1 */ - emit_mov_i(ARM_R3, (u32)jit_get_skb_b, ctx); - emit_blx_r(ARM_R3, ctx); - /* check the return value of skb_copy_bits */ - emit(ARM_CMP_I(ARM_R1, 0), ctx); - emit_err_ret(ARM_COND_NE, ctx); - - emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx); - emit(ARM_LSL_I(r_X, r_X, 2), ctx); - break; - case BPF_ST: - ctx->seen |= SEEN_MEM_WORD(k); - emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx); - break; - case BPF_STX: - update_on_xread(ctx); - ctx->seen |= SEEN_MEM_WORD(k); - emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx); - break; - case BPF_ALU | BPF_ADD | BPF_K: - /* A += K */ - OP_IMM3(ARM_ADD, r_A, r_A, k, ctx); - break; - case BPF_ALU | BPF_ADD | BPF_X: - update_on_xread(ctx); - emit(ARM_ADD_R(r_A, r_A, r_X), ctx); - break; - case BPF_ALU | BPF_SUB | BPF_K: - /* A -= K */ - OP_IMM3(ARM_SUB, r_A, r_A, k, ctx); - break; - case BPF_ALU | BPF_SUB | BPF_X: - update_on_xread(ctx); - emit(ARM_SUB_R(r_A, r_A, r_X), ctx); - break; - case BPF_ALU | BPF_MUL | BPF_K: - /* A *= K */ - emit_mov_i(r_scratch, k, ctx); - emit(ARM_MUL(r_A, r_A, r_scratch), ctx); - break; - case BPF_ALU | BPF_MUL | BPF_X: - update_on_xread(ctx); - emit(ARM_MUL(r_A, r_A, r_X), ctx); + emit_a32_mov_i64(is64, tmp2, imm, false, ctx); + emit_a32_mul_r64(dst, tmp2, dstk, false, ctx); break; - case BPF_ALU | BPF_DIV | BPF_K: - if (k == 1) - break; - emit_mov_i(r_scratch, k, ctx); - emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_DIV); - break; - case BPF_ALU | BPF_DIV | BPF_X: - update_on_xread(ctx); - emit(ARM_CMP_I(r_X, 0), ctx); - emit_err_ret(ARM_COND_EQ, ctx); - emit_udivmod(r_A, r_A, r_X, ctx, BPF_DIV); + } + break; + /* dst = htole(dst) */ + /* dst = htobe(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: + case BPF_ALU | BPF_END | BPF_FROM_BE: + rd = dstk ? tmp[0] : dst_hi; + rt = dstk ? tmp[1] : dst_lo; + if (dstk) { + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + if (BPF_SRC(code) == BPF_FROM_LE) + goto emit_bswap_uxt; + switch (imm) { + case 16: + emit_rev16(rt, rt, ctx); + goto emit_bswap_uxt; + case 32: + emit_rev32(rt, rt, ctx); + goto emit_bswap_uxt; + case 64: + /* Because of the usage of ARM_LR */ + ctx->seen |= SEEN_CALL; + emit_rev32(ARM_LR, rt, ctx); + emit_rev32(rt, rd, ctx); + emit(ARM_MOV_R(rd, ARM_LR), ctx); break; - case BPF_ALU | BPF_MOD | BPF_K: - if (k == 1) { - emit_mov_i(r_A, 0, ctx); - break; - } - emit_mov_i(r_scratch, k, ctx); - emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_MOD); + } + goto exit; +emit_bswap_uxt: + switch (imm) { + case 16: + /* zero-extend 16 bits into 64 bits */ +#if __LINUX_ARM_ARCH__ < 6 + emit_a32_mov_i(tmp2[1], 0xffff, false, ctx); + emit(ARM_AND_R(rt, rt, tmp2[1]), ctx); +#else /* ARMv6+ */ + emit(ARM_UXTH(rt, rt), ctx); +#endif + emit(ARM_EOR_R(rd, rd, rd), ctx); break; - case BPF_ALU | BPF_MOD | BPF_X: - update_on_xread(ctx); - emit(ARM_CMP_I(r_X, 0), ctx); - emit_err_ret(ARM_COND_EQ, ctx); - emit_udivmod(r_A, r_A, r_X, ctx, BPF_MOD); + case 32: + /* zero-extend 32 bits into 64 bits */ + emit(ARM_EOR_R(rd, rd, rd), ctx); break; - case BPF_ALU | BPF_OR | BPF_K: - /* A |= K */ - OP_IMM3(ARM_ORR, r_A, r_A, k, ctx); + case 64: + /* nop */ break; - case BPF_ALU | BPF_OR | BPF_X: - update_on_xread(ctx); - emit(ARM_ORR_R(r_A, r_A, r_X), ctx); + } +exit: + if (dstk) { + emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + break; + /* dst = imm64 */ + case BPF_LD | BPF_IMM | BPF_DW: + { + const struct bpf_insn insn1 = insn[1]; + u32 hi, lo = imm; + + hi = insn1.imm; + emit_a32_mov_i(dst_lo, lo, dstk, ctx); + emit_a32_mov_i(dst_hi, hi, dstk, ctx); + + return 1; + } + /* LDX: dst = *(size *)(src + off) */ + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_DW: + rn = sstk ? tmp2[1] : src_lo; + if (sstk) + emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); + switch (BPF_SIZE(code)) { + case BPF_W: + /* Load a Word */ + case BPF_H: + /* Load a Half-Word */ + case BPF_B: + /* Load a Byte */ + emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code)); + emit_a32_mov_i(dst_hi, 0, dstk, ctx); break; - case BPF_ALU | BPF_XOR | BPF_K: - /* A ^= K; */ - OP_IMM3(ARM_EOR, r_A, r_A, k, ctx); + case BPF_DW: + /* Load a double word */ + emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W); + emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W); break; - case BPF_ANC | SKF_AD_ALU_XOR_X: - case BPF_ALU | BPF_XOR | BPF_X: - /* A ^= X */ - update_on_xread(ctx); - emit(ARM_EOR_R(r_A, r_A, r_X), ctx); + } + break; + /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ + case BPF_LD | BPF_ABS | BPF_W: + case BPF_LD | BPF_ABS | BPF_H: + case BPF_LD | BPF_ABS | BPF_B: + /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */ + case BPF_LD | BPF_IND | BPF_W: + case BPF_LD | BPF_IND | BPF_H: + case BPF_LD | BPF_IND | BPF_B: + { + const u8 r4 = bpf2a32[BPF_REG_6][1]; /* r4 = ptr to sk_buff */ + const u8 r0 = bpf2a32[BPF_REG_0][1]; /*r0: struct sk_buff *skb*/ + /* rtn value */ + const u8 r1 = bpf2a32[BPF_REG_0][0]; /* r1: int k */ + const u8 r2 = bpf2a32[BPF_REG_1][1]; /* r2: unsigned int size */ + const u8 r3 = bpf2a32[BPF_REG_1][0]; /* r3: void *buffer */ + const u8 r6 = bpf2a32[TMP_REG_1][1]; /* r6: void *(*func)(..) */ + int size; + + /* Setting up first argument */ + emit(ARM_MOV_R(r0, r4), ctx); + + /* Setting up second argument */ + emit_a32_mov_i(r1, imm, false, ctx); + if (BPF_MODE(code) == BPF_IND) + emit_a32_alu_r(r1, src_lo, false, sstk, ctx, + false, false, BPF_ADD); + + /* Setting up third argument */ + switch (BPF_SIZE(code)) { + case BPF_W: + size = 4; break; - case BPF_ALU | BPF_AND | BPF_K: - /* A &= K */ - OP_IMM3(ARM_AND, r_A, r_A, k, ctx); + case BPF_H: + size = 2; break; - case BPF_ALU | BPF_AND | BPF_X: - update_on_xread(ctx); - emit(ARM_AND_R(r_A, r_A, r_X), ctx); + case BPF_B: + size = 1; break; - case BPF_ALU | BPF_LSH | BPF_K: - if (unlikely(k > 31)) - return -1; - emit(ARM_LSL_I(r_A, r_A, k), ctx); + default: + return -EINVAL; + } + emit_a32_mov_i(r2, size, false, ctx); + + /* Setting up fourth argument */ + emit(ARM_ADD_I(r3, ARM_SP, imm8m(SKB_BUFFER)), ctx); + + /* Setting up function pointer to call */ + emit_a32_mov_i(r6, (unsigned int)bpf_load_pointer, false, ctx); + emit_blx_r(r6, ctx); + + emit(ARM_EOR_R(r1, r1, r1), ctx); + /* Check if return address is NULL or not. + * if NULL then jump to epilogue + * else continue to load the value from retn address + */ + emit(ARM_CMP_I(r0, 0), ctx); + jmp_offset = epilogue_offset(ctx); + check_imm24(jmp_offset); + _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx); + + /* Load value from the address */ + switch (BPF_SIZE(code)) { + case BPF_W: + emit(ARM_LDR_I(r0, r0, 0), ctx); + emit_rev32(r0, r0, ctx); break; - case BPF_ALU | BPF_LSH | BPF_X: - update_on_xread(ctx); - emit(ARM_LSL_R(r_A, r_A, r_X), ctx); + case BPF_H: + emit(ARM_LDRH_I(r0, r0, 0), ctx); + emit_rev16(r0, r0, ctx); break; - case BPF_ALU | BPF_RSH | BPF_K: - if (unlikely(k > 31)) - return -1; - if (k) - emit(ARM_LSR_I(r_A, r_A, k), ctx); + case BPF_B: + emit(ARM_LDRB_I(r0, r0, 0), ctx); + /* No need to reverse */ break; - case BPF_ALU | BPF_RSH | BPF_X: - update_on_xread(ctx); - emit(ARM_LSR_R(r_A, r_A, r_X), ctx); + } + break; + } + /* ST: *(size *)(dst + off) = imm */ + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_DW: + switch (BPF_SIZE(code)) { + case BPF_DW: + /* Sign-extend immediate value into temp reg */ + emit_a32_mov_i64(true, tmp2, imm, false, ctx); + emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, BPF_W); + emit_str_r(dst_lo, tmp2[0], dstk, off+4, ctx, BPF_W); break; - case BPF_ALU | BPF_NEG: - /* A = -A */ - emit(ARM_RSB_I(r_A, r_A, 0), ctx); + case BPF_W: + case BPF_H: + case BPF_B: + emit_a32_mov_i(tmp2[1], imm, false, ctx); + emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, + BPF_SIZE(code)); break; - case BPF_JMP | BPF_JA: - /* pc += K */ - emit(ARM_B(b_imm(i + k + 1, ctx)), ctx); + } + break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_W: + /* STX XADD: lock *(u64 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_DW: + goto notyet; + /* STX: *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_DW: + { + u8 sz = BPF_SIZE(code); + + rn = sstk ? tmp2[1] : src_lo; + rm = sstk ? tmp2[0] : src_hi; + if (sstk) { + emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx); + } + + /* Store the value */ + if (BPF_SIZE(code) == BPF_DW) { + emit_str_r(dst_lo, rn, dstk, off, ctx, BPF_W); + emit_str_r(dst_lo, rm, dstk, off+4, ctx, BPF_W); + } else { + emit_str_r(dst_lo, rn, dstk, off, ctx, sz); + } + break; + } + /* PC += off if dst == src */ + /* PC += off if dst > src */ + /* PC += off if dst >= src */ + /* PC += off if dst < src */ + /* PC += off if dst <= src */ + /* PC += off if dst != src */ + /* PC += off if dst > src (signed) */ + /* PC += off if dst >= src (signed) */ + /* PC += off if dst < src (signed) */ + /* PC += off if dst <= src (signed) */ + /* PC += off if dst & src */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: + /* Setup source registers */ + rm = sstk ? tmp2[0] : src_hi; + rn = sstk ? tmp2[1] : src_lo; + if (sstk) { + emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); + emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx); + } + goto go_jmp; + /* PC += off if dst == imm */ + /* PC += off if dst > imm */ + /* PC += off if dst >= imm */ + /* PC += off if dst < imm */ + /* PC += off if dst <= imm */ + /* PC += off if dst != imm */ + /* PC += off if dst > imm (signed) */ + /* PC += off if dst >= imm (signed) */ + /* PC += off if dst < imm (signed) */ + /* PC += off if dst <= imm (signed) */ + /* PC += off if dst & imm */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: + if (off == 0) break; - case BPF_JMP | BPF_JEQ | BPF_K: - /* pc += (A == K) ? pc->jt : pc->jf */ - condt = ARM_COND_EQ; - goto cmp_imm; - case BPF_JMP | BPF_JGT | BPF_K: - /* pc += (A > K) ? pc->jt : pc->jf */ - condt = ARM_COND_HI; - goto cmp_imm; - case BPF_JMP | BPF_JGE | BPF_K: - /* pc += (A >= K) ? pc->jt : pc->jf */ - condt = ARM_COND_HS; -cmp_imm: - imm12 = imm8m(k); - if (imm12 < 0) { - emit_mov_i_no8m(r_scratch, k, ctx); - emit(ARM_CMP_R(r_A, r_scratch), ctx); - } else { - emit(ARM_CMP_I(r_A, imm12), ctx); - } -cond_jump: - if (inst->jt) - _emit(condt, ARM_B(b_imm(i + inst->jt + 1, - ctx)), ctx); - if (inst->jf) - _emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1, - ctx)), ctx); + rm = tmp2[0]; + rn = tmp2[1]; + /* Sign-extend immediate value */ + emit_a32_mov_i64(true, tmp2, imm, false, ctx); +go_jmp: + /* Setup destination register */ + rd = dstk ? tmp[0] : dst_hi; + rt = dstk ? tmp[1] : dst_lo; + if (dstk) { + emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx); + emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx); + } + + /* Check for the condition */ + emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code)); + + /* Setup JUMP instruction */ + jmp_offset = bpf2a32_offset(i+off, i, ctx); + switch (BPF_OP(code)) { + case BPF_JNE: + case BPF_JSET: + _emit(ARM_COND_NE, ARM_B(jmp_offset), ctx); break; - case BPF_JMP | BPF_JEQ | BPF_X: - /* pc += (A == X) ? pc->jt : pc->jf */ - condt = ARM_COND_EQ; - goto cmp_x; - case BPF_JMP | BPF_JGT | BPF_X: - /* pc += (A > X) ? pc->jt : pc->jf */ - condt = ARM_COND_HI; - goto cmp_x; - case BPF_JMP | BPF_JGE | BPF_X: - /* pc += (A >= X) ? pc->jt : pc->jf */ - condt = ARM_COND_CS; -cmp_x: - update_on_xread(ctx); - emit(ARM_CMP_R(r_A, r_X), ctx); - goto cond_jump; - case BPF_JMP | BPF_JSET | BPF_K: - /* pc += (A & K) ? pc->jt : pc->jf */ - condt = ARM_COND_NE; - /* not set iff all zeroes iff Z==1 iff EQ */ - - imm12 = imm8m(k); - if (imm12 < 0) { - emit_mov_i_no8m(r_scratch, k, ctx); - emit(ARM_TST_R(r_A, r_scratch), ctx); - } else { - emit(ARM_TST_I(r_A, imm12), ctx); - } - goto cond_jump; - case BPF_JMP | BPF_JSET | BPF_X: - /* pc += (A & X) ? pc->jt : pc->jf */ - update_on_xread(ctx); - condt = ARM_COND_NE; - emit(ARM_TST_R(r_A, r_X), ctx); - goto cond_jump; - case BPF_RET | BPF_A: - emit(ARM_MOV_R(ARM_R0, r_A), ctx); - goto b_epilogue; - case BPF_RET | BPF_K: - if ((k == 0) && (ctx->ret0_fp_idx < 0)) - ctx->ret0_fp_idx = i; - emit_mov_i(ARM_R0, k, ctx); -b_epilogue: - if (i != ctx->skf->len - 1) - emit(ARM_B(b_imm(prog->len, ctx)), ctx); + case BPF_JEQ: + _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx); break; - case BPF_MISC | BPF_TAX: - /* X = A */ - ctx->seen |= SEEN_X; - emit(ARM_MOV_R(r_X, r_A), ctx); + case BPF_JGT: + _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx); break; - case BPF_MISC | BPF_TXA: - /* A = X */ - update_on_xread(ctx); - emit(ARM_MOV_R(r_A, r_X), ctx); + case BPF_JGE: + _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_PROTOCOL: - /* A = ntohs(skb->protocol) */ - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, - protocol) != 2); - off = offsetof(struct sk_buff, protocol); - emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx); - emit_swap16(r_A, r_scratch, ctx); + case BPF_JSGT: + _emit(ARM_COND_LT, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_CPU: - /* r_scratch = current_thread_info() */ - OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx); - /* A = current_thread_info()->cpu */ - BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4); - off = offsetof(struct thread_info, cpu); - emit(ARM_LDR_I(r_A, r_scratch, off), ctx); + case BPF_JSGE: + _emit(ARM_COND_GE, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_IFINDEX: - case BPF_ANC | SKF_AD_HATYPE: - /* A = skb->dev->ifindex */ - /* A = skb->dev->type */ - ctx->seen |= SEEN_SKB; - off = offsetof(struct sk_buff, dev); - emit(ARM_LDR_I(r_scratch, r_skb, off), ctx); - - emit(ARM_CMP_I(r_scratch, 0), ctx); - emit_err_ret(ARM_COND_EQ, ctx); - - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, - ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, - type) != 2); - - if (code == (BPF_ANC | SKF_AD_IFINDEX)) { - off = offsetof(struct net_device, ifindex); - emit(ARM_LDR_I(r_A, r_scratch, off), ctx); - } else { - /* - * offset of field "type" in "struct - * net_device" is above what can be - * used in the ldrh rd, [rn, #imm] - * instruction, so load the offset in - * a register and use ldrh rd, [rn, rm] - */ - off = offsetof(struct net_device, type); - emit_mov_i(ARM_R3, off, ctx); - emit(ARM_LDRH_R(r_A, r_scratch, ARM_R3), ctx); - } + case BPF_JLE: + _emit(ARM_COND_LS, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_MARK: - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - off = offsetof(struct sk_buff, mark); - emit(ARM_LDR_I(r_A, r_skb, off), ctx); + case BPF_JLT: + _emit(ARM_COND_CC, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_RXHASH: - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - off = offsetof(struct sk_buff, hash); - emit(ARM_LDR_I(r_A, r_skb, off), ctx); + case BPF_JSLT: + _emit(ARM_COND_LT, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_VLAN_TAG: - case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - off = offsetof(struct sk_buff, vlan_tci); - emit(ARM_LDRH_I(r_A, r_skb, off), ctx); - if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) - OP_IMM3(ARM_AND, r_A, r_A, ~VLAN_TAG_PRESENT, ctx); - else { - OP_IMM3(ARM_LSR, r_A, r_A, 12, ctx); - OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx); - } + case BPF_JSLE: + _emit(ARM_COND_GE, ARM_B(jmp_offset), ctx); break; - case BPF_ANC | SKF_AD_PKTTYPE: - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, - __pkt_type_offset[0]) != 1); - off = PKT_TYPE_OFFSET(); - emit(ARM_LDRB_I(r_A, r_skb, off), ctx); - emit(ARM_AND_I(r_A, r_A, PKT_TYPE_MAX), ctx); -#ifdef __BIG_ENDIAN_BITFIELD - emit(ARM_LSR_I(r_A, r_A, 5), ctx); -#endif + } + break; + /* JMP OFF */ + case BPF_JMP | BPF_JA: + { + if (off == 0) break; - case BPF_ANC | SKF_AD_QUEUE: - ctx->seen |= SEEN_SKB; - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, - queue_mapping) != 2); - BUILD_BUG_ON(offsetof(struct sk_buff, - queue_mapping) > 0xff); - off = offsetof(struct sk_buff, queue_mapping); - emit(ARM_LDRH_I(r_A, r_skb, off), ctx); + jmp_offset = bpf2a32_offset(i+off, i, ctx); + check_imm24(jmp_offset); + emit(ARM_B(jmp_offset), ctx); + break; + } + /* tail call */ + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(ctx)) + return -EFAULT; + break; + /* function call */ + case BPF_JMP | BPF_CALL: + { + const u8 *r0 = bpf2a32[BPF_REG_0]; + const u8 *r1 = bpf2a32[BPF_REG_1]; + const u8 *r2 = bpf2a32[BPF_REG_2]; + const u8 *r3 = bpf2a32[BPF_REG_3]; + const u8 *r4 = bpf2a32[BPF_REG_4]; + const u8 *r5 = bpf2a32[BPF_REG_5]; + const u32 func = (u32)__bpf_call_base + (u32)imm; + + emit_a32_mov_r64(true, r0, r1, false, false, ctx); + emit_a32_mov_r64(true, r1, r2, false, true, ctx); + emit_push_r64(r5, 0, ctx); + emit_push_r64(r4, 8, ctx); + emit_push_r64(r3, 16, ctx); + + emit_a32_mov_i(tmp[1], func, false, ctx); + emit_blx_r(tmp[1], ctx); + + emit(ARM_ADD_I(ARM_SP, ARM_SP, imm8m(24)), ctx); // callee clean + break; + } + /* function return */ + case BPF_JMP | BPF_EXIT: + /* Optimization: when last instruction is EXIT + * simply fallthrough to epilogue. + */ + if (i == ctx->prog->len - 1) break; - case BPF_ANC | SKF_AD_PAY_OFFSET: - ctx->seen |= SEEN_SKB | SEEN_CALL; + jmp_offset = epilogue_offset(ctx); + check_imm24(jmp_offset); + emit(ARM_B(jmp_offset), ctx); + break; +notyet: + pr_info_once("*** NOT YET: opcode %02x ***\n", code); + return -EFAULT; + default: + pr_err_once("unknown opcode %02x\n", code); + return -EINVAL; + } - emit(ARM_MOV_R(ARM_R0, r_skb), ctx); - emit_mov_i(ARM_R3, (unsigned int)skb_get_poff, ctx); - emit_blx_r(ARM_R3, ctx); - emit(ARM_MOV_R(r_A, ARM_R0), ctx); - break; - case BPF_LDX | BPF_W | BPF_ABS: - /* - * load a 32bit word from struct seccomp_data. - * seccomp_check_filter() will already have checked - * that k is 32bit aligned and lies within the - * struct seccomp_data. - */ - ctx->seen |= SEEN_SKB; - emit(ARM_LDR_I(r_A, r_skb, k), ctx); - break; - default: - return -1; + if (ctx->flags & FLAG_IMM_OVERFLOW) + /* + * this instruction generated an overflow when + * trying to access the literal pool, so + * delegate this filter to the kernel interpreter. + */ + return -1; + return 0; +} + +static int build_body(struct jit_ctx *ctx) +{ + const struct bpf_prog *prog = ctx->prog; + unsigned int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &(prog->insnsi[i]); + int ret; + + ret = build_insn(insn, ctx); + + /* It's used with loading the 64 bit immediate value. */ + if (ret > 0) { + i++; + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx; + continue; } - if (ctx->flags & FLAG_IMM_OVERFLOW) - /* - * this instruction generated an overflow when - * trying to access the literal pool, so - * delegate this filter to the kernel interpreter. - */ - return -1; + if (ctx->target == NULL) + ctx->offsets[i] = ctx->idx; + + /* If unsuccesfull, return with error code */ + if (ret) + return ret; } + return 0; +} - /* compute offsets only during the first pass */ - if (ctx->target == NULL) - ctx->offsets[i] = ctx->idx * 4; +static int validate_code(struct jit_ctx *ctx) +{ + int i; + + for (i = 0; i < ctx->idx; i++) { + if (ctx->target[i] == __opcode_to_mem_arm(ARM_INST_UDF)) + return -1; + } return 0; } +void bpf_jit_compile(struct bpf_prog *prog) +{ + /* Nothing to do here. We support Internal BPF. */ +} -void bpf_jit_compile(struct bpf_prog *fp) +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { + struct bpf_prog *tmp, *orig_prog = prog; struct bpf_binary_header *header; + bool tmp_blinded = false; struct jit_ctx ctx; - unsigned tmp_idx; - unsigned alloc_size; - u8 *target_ptr; + unsigned int tmp_idx; + unsigned int image_size; + u8 *image_ptr; + /* If BPF JIT was not enabled then we must fall back to + * the interpreter. + */ if (!bpf_jit_enable) - return; + return orig_prog; - memset(&ctx, 0, sizeof(ctx)); - ctx.skf = fp; - ctx.ret0_fp_idx = -1; + /* If constant blinding was enabled and we failed during blinding + * then we must fall back to the interpreter. Otherwise, we save + * the new JITed code. + */ + tmp = bpf_jit_blind_constants(prog); - ctx.offsets = kzalloc(4 * (ctx.skf->len + 1), GFP_KERNEL); - if (ctx.offsets == NULL) - return; + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } - /* fake pass to fill in the ctx->seen */ - if (unlikely(build_body(&ctx))) + memset(&ctx, 0, sizeof(ctx)); + ctx.prog = prog; + + /* Not able to allocate memory for offsets[] , then + * we must fall back to the interpreter + */ + ctx.offsets = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + if (ctx.offsets == NULL) { + prog = orig_prog; goto out; + } + + /* 1) fake pass to find in the length of the JITed code, + * to compute ctx->offsets and other context variables + * needed to compute final JITed code. + * Also, calculate random starting pointer/start of JITed code + * which is prefixed by random number of fault instructions. + * + * If the first pass fails then there is no chance of it + * being successful in the second pass, so just fall back + * to the interpreter. + */ + if (build_body(&ctx)) { + prog = orig_prog; + goto out_off; + } tmp_idx = ctx.idx; build_prologue(&ctx); ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4; + ctx.epilogue_offset = ctx.idx; + #if __LINUX_ARM_ARCH__ < 7 tmp_idx = ctx.idx; build_epilogue(&ctx); @@ -1021,64 +1880,83 @@ void bpf_jit_compile(struct bpf_prog *fp) ctx.idx += ctx.imm_count; if (ctx.imm_count) { - ctx.imms = kzalloc(4 * ctx.imm_count, GFP_KERNEL); - if (ctx.imms == NULL) - goto out; + ctx.imms = kcalloc(ctx.imm_count, sizeof(u32), GFP_KERNEL); + if (ctx.imms == NULL) { + prog = orig_prog; + goto out_off; + } } #else - /* there's nothing after the epilogue on ARMv7 */ + /* there's nothing about the epilogue on ARMv7 */ build_epilogue(&ctx); #endif - alloc_size = 4 * ctx.idx; - header = bpf_jit_binary_alloc(alloc_size, &target_ptr, - 4, jit_fill_hole); - if (header == NULL) - goto out; + /* Now we can get the actual image size of the JITed arm code. + * Currently, we are not considering the THUMB-2 instructions + * for jit, although it can decrease the size of the image. + * + * As each arm instruction is of length 32bit, we are translating + * number of JITed intructions into the size required to store these + * JITed code. + */ + image_size = sizeof(u32) * ctx.idx; - ctx.target = (u32 *) target_ptr; + /* Now we know the size of the structure to make */ + header = bpf_jit_binary_alloc(image_size, &image_ptr, + sizeof(u32), jit_fill_hole); + /* Not able to allocate memory for the structure then + * we must fall back to the interpretation + */ + if (header == NULL) { + prog = orig_prog; + goto out_imms; + } + + /* 2.) Actual pass to generate final JIT code */ + ctx.target = (u32 *) image_ptr; ctx.idx = 0; build_prologue(&ctx); + + /* If building the body of the JITed code fails somehow, + * we fall back to the interpretation. + */ if (build_body(&ctx) < 0) { -#if __LINUX_ARM_ARCH__ < 7 - if (ctx.imm_count) - kfree(ctx.imms); -#endif + image_ptr = NULL; bpf_jit_binary_free(header); - goto out; + prog = orig_prog; + goto out_imms; } build_epilogue(&ctx); + /* 3.) Extra pass to validate JITed Code */ + if (validate_code(&ctx)) { + image_ptr = NULL; + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_imms; + } flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); -#if __LINUX_ARM_ARCH__ < 7 - if (ctx.imm_count) - kfree(ctx.imms); -#endif - if (bpf_jit_enable > 1) /* there are 2 passes here */ - bpf_jit_dump(fp->len, alloc_size, 2, ctx.target); + bpf_jit_dump(prog->len, image_size, 2, ctx.target); set_memory_ro((unsigned long)header, header->pages); - fp->bpf_func = (void *)ctx.target; - fp->jited = 1; -out: + prog->bpf_func = (void *)ctx.target; + prog->jited = 1; + prog->jited_len = image_size; + +out_imms: +#if __LINUX_ARM_ARCH__ < 7 + if (ctx.imm_count) + kfree(ctx.imms); +#endif +out_off: kfree(ctx.offsets); - return; +out: + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + return prog; } -void bpf_jit_free(struct bpf_prog *fp) -{ - unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; - struct bpf_binary_header *header = (void *)addr; - - if (!fp->jited) - goto free_filter; - - set_memory_rw(addr, header->pages); - bpf_jit_binary_free(header); - -free_filter: - bpf_prog_unlock_free(fp); -} diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h index c46fca2972f7..d5cf5f6208aa 100644 --- a/arch/arm/net/bpf_jit_32.h +++ b/arch/arm/net/bpf_jit_32.h @@ -11,6 +11,7 @@ #ifndef PFILTER_OPCODES_ARM_H #define PFILTER_OPCODES_ARM_H +/* ARM 32bit Registers */ #define ARM_R0 0 #define ARM_R1 1 #define ARM_R2 2 @@ -22,38 +23,43 @@ #define ARM_R8 8 #define ARM_R9 9 #define ARM_R10 10 -#define ARM_FP 11 -#define ARM_IP 12 -#define ARM_SP 13 -#define ARM_LR 14 -#define ARM_PC 15 - -#define ARM_COND_EQ 0x0 -#define ARM_COND_NE 0x1 -#define ARM_COND_CS 0x2 +#define ARM_FP 11 /* Frame Pointer */ +#define ARM_IP 12 /* Intra-procedure scratch register */ +#define ARM_SP 13 /* Stack pointer: as load/store base reg */ +#define ARM_LR 14 /* Link Register */ +#define ARM_PC 15 /* Program counter */ + +#define ARM_COND_EQ 0x0 /* == */ +#define ARM_COND_NE 0x1 /* != */ +#define ARM_COND_CS 0x2 /* unsigned >= */ #define ARM_COND_HS ARM_COND_CS -#define ARM_COND_CC 0x3 +#define ARM_COND_CC 0x3 /* unsigned < */ #define ARM_COND_LO ARM_COND_CC -#define ARM_COND_MI 0x4 -#define ARM_COND_PL 0x5 -#define ARM_COND_VS 0x6 -#define ARM_COND_VC 0x7 -#define ARM_COND_HI 0x8 -#define ARM_COND_LS 0x9 -#define ARM_COND_GE 0xa -#define ARM_COND_LT 0xb -#define ARM_COND_GT 0xc -#define ARM_COND_LE 0xd -#define ARM_COND_AL 0xe +#define ARM_COND_MI 0x4 /* < 0 */ +#define ARM_COND_PL 0x5 /* >= 0 */ +#define ARM_COND_VS 0x6 /* Signed Overflow */ +#define ARM_COND_VC 0x7 /* No Signed Overflow */ +#define ARM_COND_HI 0x8 /* unsigned > */ +#define ARM_COND_LS 0x9 /* unsigned <= */ +#define ARM_COND_GE 0xa /* Signed >= */ +#define ARM_COND_LT 0xb /* Signed < */ +#define ARM_COND_GT 0xc /* Signed > */ +#define ARM_COND_LE 0xd /* Signed <= */ +#define ARM_COND_AL 0xe /* None */ /* register shift types */ #define SRTYPE_LSL 0 #define SRTYPE_LSR 1 #define SRTYPE_ASR 2 #define SRTYPE_ROR 3 +#define SRTYPE_ASL (SRTYPE_LSL) #define ARM_INST_ADD_R 0x00800000 +#define ARM_INST_ADDS_R 0x00900000 +#define ARM_INST_ADC_R 0x00a00000 +#define ARM_INST_ADC_I 0x02a00000 #define ARM_INST_ADD_I 0x02800000 +#define ARM_INST_ADDS_I 0x02900000 #define ARM_INST_AND_R 0x00000000 #define ARM_INST_AND_I 0x02000000 @@ -76,8 +82,10 @@ #define ARM_INST_LDRH_I 0x01d000b0 #define ARM_INST_LDRH_R 0x019000b0 #define ARM_INST_LDR_I 0x05900000 +#define ARM_INST_LDR_R 0x07900000 #define ARM_INST_LDM 0x08900000 +#define ARM_INST_LDM_IA 0x08b00000 #define ARM_INST_LSL_I 0x01a00000 #define ARM_INST_LSL_R 0x01a00010 @@ -86,6 +94,7 @@ #define ARM_INST_LSR_R 0x01a00030 #define ARM_INST_MOV_R 0x01a00000 +#define ARM_INST_MOVS_R 0x01b00000 #define ARM_INST_MOV_I 0x03a00000 #define ARM_INST_MOVW 0x03000000 #define ARM_INST_MOVT 0x03400000 @@ -96,17 +105,28 @@ #define ARM_INST_PUSH 0x092d0000 #define ARM_INST_ORR_R 0x01800000 +#define ARM_INST_ORRS_R 0x01900000 #define ARM_INST_ORR_I 0x03800000 #define ARM_INST_REV 0x06bf0f30 #define ARM_INST_REV16 0x06bf0fb0 #define ARM_INST_RSB_I 0x02600000 +#define ARM_INST_RSBS_I 0x02700000 +#define ARM_INST_RSC_I 0x02e00000 #define ARM_INST_SUB_R 0x00400000 +#define ARM_INST_SUBS_R 0x00500000 +#define ARM_INST_RSB_R 0x00600000 #define ARM_INST_SUB_I 0x02400000 +#define ARM_INST_SUBS_I 0x02500000 +#define ARM_INST_SBC_I 0x02c00000 +#define ARM_INST_SBC_R 0x00c00000 +#define ARM_INST_SBCS_R 0x00d00000 #define ARM_INST_STR_I 0x05800000 +#define ARM_INST_STRB_I 0x05c00000 +#define ARM_INST_STRH_I 0x01c000b0 #define ARM_INST_TST_R 0x01100000 #define ARM_INST_TST_I 0x03100000 @@ -117,6 +137,8 @@ #define ARM_INST_MLS 0x00600090 +#define ARM_INST_UXTH 0x06ff0070 + /* * Use a suitable undefined instruction to use for ARM/Thumb2 faulting. * We need to be careful not to conflict with those used by other modules @@ -135,9 +157,15 @@ #define _AL3_R(op, rd, rn, rm) ((op ## _R) | (rd) << 12 | (rn) << 16 | (rm)) /* immediate */ #define _AL3_I(op, rd, rn, imm) ((op ## _I) | (rd) << 12 | (rn) << 16 | (imm)) +/* register with register-shift */ +#define _AL3_SR(inst) (inst | (1 << 4)) #define ARM_ADD_R(rd, rn, rm) _AL3_R(ARM_INST_ADD, rd, rn, rm) +#define ARM_ADDS_R(rd, rn, rm) _AL3_R(ARM_INST_ADDS, rd, rn, rm) #define ARM_ADD_I(rd, rn, imm) _AL3_I(ARM_INST_ADD, rd, rn, imm) +#define ARM_ADDS_I(rd, rn, imm) _AL3_I(ARM_INST_ADDS, rd, rn, imm) +#define ARM_ADC_R(rd, rn, rm) _AL3_R(ARM_INST_ADC, rd, rn, rm) +#define ARM_ADC_I(rd, rn, imm) _AL3_I(ARM_INST_ADC, rd, rn, imm) #define ARM_AND_R(rd, rn, rm) _AL3_R(ARM_INST_AND, rd, rn, rm) #define ARM_AND_I(rd, rn, imm) _AL3_I(ARM_INST_AND, rd, rn, imm) @@ -156,7 +184,9 @@ #define ARM_EOR_I(rd, rn, imm) _AL3_I(ARM_INST_EOR, rd, rn, imm) #define ARM_LDR_I(rt, rn, off) (ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \ - | (off)) + | ((off) & 0xfff)) +#define ARM_LDR_R(rt, rn, rm) (ARM_INST_LDR_R | (rt) << 12 | (rn) << 16 \ + | (rm)) #define ARM_LDRB_I(rt, rn, off) (ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \ | (off)) #define ARM_LDRB_R(rt, rn, rm) (ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \ @@ -167,15 +197,23 @@ | (rm)) #define ARM_LDM(rn, regs) (ARM_INST_LDM | (rn) << 16 | (regs)) +#define ARM_LDM_IA(rn, regs) (ARM_INST_LDM_IA | (rn) << 16 | (regs)) #define ARM_LSL_R(rd, rn, rm) (_AL3_R(ARM_INST_LSL, rd, 0, rn) | (rm) << 8) #define ARM_LSL_I(rd, rn, imm) (_AL3_I(ARM_INST_LSL, rd, 0, rn) | (imm) << 7) #define ARM_LSR_R(rd, rn, rm) (_AL3_R(ARM_INST_LSR, rd, 0, rn) | (rm) << 8) #define ARM_LSR_I(rd, rn, imm) (_AL3_I(ARM_INST_LSR, rd, 0, rn) | (imm) << 7) +#define ARM_ASR_R(rd, rn, rm) (_AL3_R(ARM_INST_ASR, rd, 0, rn) | (rm) << 8) +#define ARM_ASR_I(rd, rn, imm) (_AL3_I(ARM_INST_ASR, rd, 0, rn) | (imm) << 7) #define ARM_MOV_R(rd, rm) _AL3_R(ARM_INST_MOV, rd, 0, rm) +#define ARM_MOVS_R(rd, rm) _AL3_R(ARM_INST_MOVS, rd, 0, rm) #define ARM_MOV_I(rd, imm) _AL3_I(ARM_INST_MOV, rd, 0, imm) +#define ARM_MOV_SR(rd, rm, type, rs) \ + (_AL3_SR(ARM_MOV_R(rd, rm)) | (type) << 5 | (rs) << 8) +#define ARM_MOV_SI(rd, rm, type, imm6) \ + (ARM_MOV_R(rd, rm) | (type) << 5 | (imm6) << 7) #define ARM_MOVW(rd, imm) \ (ARM_INST_MOVW | ((imm) >> 12) << 16 | (rd) << 12 | ((imm) & 0x0fff)) @@ -190,19 +228,38 @@ #define ARM_ORR_R(rd, rn, rm) _AL3_R(ARM_INST_ORR, rd, rn, rm) #define ARM_ORR_I(rd, rn, imm) _AL3_I(ARM_INST_ORR, rd, rn, imm) -#define ARM_ORR_S(rd, rn, rm, type, rs) \ - (ARM_ORR_R(rd, rn, rm) | (type) << 5 | (rs) << 7) +#define ARM_ORR_SR(rd, rn, rm, type, rs) \ + (_AL3_SR(ARM_ORR_R(rd, rn, rm)) | (type) << 5 | (rs) << 8) +#define ARM_ORRS_R(rd, rn, rm) _AL3_R(ARM_INST_ORRS, rd, rn, rm) +#define ARM_ORRS_SR(rd, rn, rm, type, rs) \ + (_AL3_SR(ARM_ORRS_R(rd, rn, rm)) | (type) << 5 | (rs) << 8) +#define ARM_ORR_SI(rd, rn, rm, type, imm6) \ + (ARM_ORR_R(rd, rn, rm) | (type) << 5 | (imm6) << 7) +#define ARM_ORRS_SI(rd, rn, rm, type, imm6) \ + (ARM_ORRS_R(rd, rn, rm) | (type) << 5 | (imm6) << 7) #define ARM_REV(rd, rm) (ARM_INST_REV | (rd) << 12 | (rm)) #define ARM_REV16(rd, rm) (ARM_INST_REV16 | (rd) << 12 | (rm)) #define ARM_RSB_I(rd, rn, imm) _AL3_I(ARM_INST_RSB, rd, rn, imm) +#define ARM_RSBS_I(rd, rn, imm) _AL3_I(ARM_INST_RSBS, rd, rn, imm) +#define ARM_RSC_I(rd, rn, imm) _AL3_I(ARM_INST_RSC, rd, rn, imm) #define ARM_SUB_R(rd, rn, rm) _AL3_R(ARM_INST_SUB, rd, rn, rm) +#define ARM_SUBS_R(rd, rn, rm) _AL3_R(ARM_INST_SUBS, rd, rn, rm) +#define ARM_RSB_R(rd, rn, rm) _AL3_R(ARM_INST_RSB, rd, rn, rm) +#define ARM_SBC_R(rd, rn, rm) _AL3_R(ARM_INST_SBC, rd, rn, rm) +#define ARM_SBCS_R(rd, rn, rm) _AL3_R(ARM_INST_SBCS, rd, rn, rm) #define ARM_SUB_I(rd, rn, imm) _AL3_I(ARM_INST_SUB, rd, rn, imm) +#define ARM_SUBS_I(rd, rn, imm) _AL3_I(ARM_INST_SUBS, rd, rn, imm) +#define ARM_SBC_I(rd, rn, imm) _AL3_I(ARM_INST_SBC, rd, rn, imm) #define ARM_STR_I(rt, rn, off) (ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \ - | (off)) + | ((off) & 0xfff)) +#define ARM_STRH_I(rt, rn, off) (ARM_INST_STRH_I | (rt) << 12 | (rn) << 16 \ + | (((off) & 0xf0) << 4) | ((off) & 0xf)) +#define ARM_STRB_I(rt, rn, off) (ARM_INST_STRB_I | (rt) << 12 | (rn) << 16 \ + | (((off) & 0xf0) << 4) | ((off) & 0xf)) #define ARM_TST_R(rn, rm) _AL3_R(ARM_INST_TST, 0, rn, rm) #define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm) @@ -214,5 +271,6 @@ #define ARM_MLS(rd, rn, rm, ra) (ARM_INST_MLS | (rd) << 16 | (rn) | (rm) << 8 \ | (ra) << 12) +#define ARM_UXTH(rd, rm) (ARM_INST_UXTH | (rd) << 12 | (rm)) #endif /* PFILTER_OPCODES_ARM_H */ diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts index cf272392cebf..b9f36dad17e6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts @@ -50,6 +50,23 @@ chosen { stdout-path = "serial2:1500000n8"; }; + + vcc_phy: vcc-phy-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_phy"; + regulator-always-on; + regulator-boot-on; + }; +}; + +&gmac2phy { + phy-supply = <&vcc_phy>; + clock_in_out = "output"; + assigned-clocks = <&cru SCLK_MAC2PHY_SRC>; + assigned-clock-rate = <50000000>; + assigned-clocks = <&cru SCLK_MAC2PHY>; + assigned-clock-parents = <&cru SCLK_MAC2PHY_SRC>; + status = "okay"; }; &uart2 { diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 0be96cee27bd..d48bf5d9f8bd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -63,6 +63,8 @@ i2c1 = &i2c1; i2c2 = &i2c2; i2c3 = &i2c3; + ethernet0 = &gmac2io; + ethernet1 = &gmac2phy; }; cpus { @@ -424,6 +426,43 @@ status = "disabled"; }; + gmac2phy: ethernet@ff550000 { + compatible = "rockchip,rk3328-gmac"; + reg = <0x0 0xff550000 0x0 0x10000>; + rockchip,grf = <&grf>; + interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + clocks = <&cru SCLK_MAC2PHY_SRC>, <&cru SCLK_MAC2PHY_RXTX>, + <&cru SCLK_MAC2PHY_RXTX>, <&cru SCLK_MAC2PHY_REF>, + <&cru ACLK_MAC2PHY>, <&cru PCLK_MAC2PHY>, + <&cru SCLK_MAC2PHY_OUT>; + clock-names = "stmmaceth", "mac_clk_rx", + "mac_clk_tx", "clk_mac_ref", + "aclk_mac", "pclk_mac", + "clk_macphy"; + resets = <&cru SRST_GMAC2PHY_A>, <&cru SRST_MACPHY>; + reset-names = "stmmaceth", "mac-phy"; + phy-mode = "rmii"; + phy-handle = <&phy>; + status = "disabled"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + phy: phy@0 { + compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22"; + reg = <0>; + clocks = <&cru SCLK_MAC2PHY_OUT>; + resets = <&cru SRST_MACPHY>; + pinctrl-names = "default"; + pinctrl-0 = <&fephyled_rxm1 &fephyled_linkm1>; + phy-is-integrated; + }; + }; + }; + gic: interrupt-controller@ff811000 { compatible = "arm,gic-400"; #interrupt-cells = <3>; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index b4ca115b3be1..cdde4f56a281 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -203,6 +203,7 @@ CONFIG_MARVELL_PHY=m CONFIG_MESON_GXL_PHY=m CONFIG_MICREL_PHY=y CONFIG_REALTEK_PHY=m +CONFIG_ROCKCHIP_PHY=y CONFIG_USB_PEGASUS=m CONFIG_USB_RTL8150=m CONFIG_USB_RTL8152=m diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index d92293747d63..7ca54a76f6b9 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -18,18 +18,23 @@ config CRYPTO_SHA512_ARM64 config CRYPTO_SHA1_ARM64_CE tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" - depends on ARM64 && KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON select CRYPTO_HASH + select CRYPTO_SHA1 config CRYPTO_SHA2_ARM64_CE tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)" - depends on ARM64 && KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON select CRYPTO_HASH + select CRYPTO_SHA256_ARM64 config CRYPTO_GHASH_ARM64_CE - tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions" - depends on ARM64 && KERNEL_MODE_NEON + tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions" + depends on KERNEL_MODE_NEON select CRYPTO_HASH + select CRYPTO_GF128MUL + select CRYPTO_AES + select CRYPTO_AES_ARM64 config CRYPTO_CRCT10DIF_ARM64_CE tristate "CRCT10DIF digest algorithm using PMULL instructions" @@ -49,25 +54,29 @@ config CRYPTO_AES_ARM64_CE tristate "AES core cipher using ARMv8 Crypto Extensions" depends on ARM64 && KERNEL_MODE_NEON select CRYPTO_ALGAPI + select CRYPTO_AES_ARM64 config CRYPTO_AES_ARM64_CE_CCM tristate "AES in CCM mode using ARMv8 Crypto Extensions" depends on ARM64 && KERNEL_MODE_NEON select CRYPTO_ALGAPI select CRYPTO_AES_ARM64_CE + select CRYPTO_AES_ARM64 select CRYPTO_AEAD config CRYPTO_AES_ARM64_CE_BLK tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions" - depends on ARM64 && KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER select CRYPTO_AES_ARM64_CE + select CRYPTO_AES_ARM64 select CRYPTO_SIMD config CRYPTO_AES_ARM64_NEON_BLK tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions" - depends on ARM64 && KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64 select CRYPTO_AES select CRYPTO_SIMD @@ -82,6 +91,7 @@ config CRYPTO_AES_ARM64_BS depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER select CRYPTO_AES_ARM64_NEON_BLK + select CRYPTO_AES_ARM64 select CRYPTO_SIMD endif diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S index 3363560c79b7..e3a375c4cb83 100644 --- a/arch/arm64/crypto/aes-ce-ccm-core.S +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -1,7 +1,7 @@ /* * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions * - * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -32,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data) beq 8f /* out of input? */ cbnz w8, 0b eor v0.16b, v0.16b, v1.16b -1: ld1 {v3.16b}, [x4] /* load first round key */ +1: ld1 {v3.4s}, [x4] /* load first round key */ prfm pldl1strm, [x1] cmp w5, #12 /* which key size? */ add x6, x4, #16 @@ -42,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data) mov v5.16b, v3.16b b 4f 2: mov v4.16b, v3.16b - ld1 {v5.16b}, [x6], #16 /* load 2nd round key */ + ld1 {v5.4s}, [x6], #16 /* load 2nd round key */ 3: aese v0.16b, v4.16b aesmc v0.16b, v0.16b -4: ld1 {v3.16b}, [x6], #16 /* load next round key */ +4: ld1 {v3.4s}, [x6], #16 /* load next round key */ aese v0.16b, v5.16b aesmc v0.16b, v0.16b -5: ld1 {v4.16b}, [x6], #16 /* load next round key */ +5: ld1 {v4.4s}, [x6], #16 /* load next round key */ subs w7, w7, #3 aese v0.16b, v3.16b aesmc v0.16b, v0.16b - ld1 {v5.16b}, [x6], #16 /* load next round key */ + ld1 {v5.4s}, [x6], #16 /* load next round key */ bpl 3b aese v0.16b, v4.16b subs w2, w2, #16 /* last data? */ @@ -90,7 +90,7 @@ ENDPROC(ce_aes_ccm_auth_data) * u32 rounds); */ ENTRY(ce_aes_ccm_final) - ld1 {v3.16b}, [x2], #16 /* load first round key */ + ld1 {v3.4s}, [x2], #16 /* load first round key */ ld1 {v0.16b}, [x0] /* load mac */ cmp w3, #12 /* which key size? */ sub w3, w3, #2 /* modified # of rounds */ @@ -100,17 +100,17 @@ ENTRY(ce_aes_ccm_final) mov v5.16b, v3.16b b 2f 0: mov v4.16b, v3.16b -1: ld1 {v5.16b}, [x2], #16 /* load next round key */ +1: ld1 {v5.4s}, [x2], #16 /* load next round key */ aese v0.16b, v4.16b aesmc v0.16b, v0.16b aese v1.16b, v4.16b aesmc v1.16b, v1.16b -2: ld1 {v3.16b}, [x2], #16 /* load next round key */ +2: ld1 {v3.4s}, [x2], #16 /* load next round key */ aese v0.16b, v5.16b aesmc v0.16b, v0.16b aese v1.16b, v5.16b aesmc v1.16b, v1.16b -3: ld1 {v4.16b}, [x2], #16 /* load next round key */ +3: ld1 {v4.4s}, [x2], #16 /* load next round key */ subs w3, w3, #3 aese v0.16b, v3.16b aesmc v0.16b, v0.16b @@ -137,31 +137,31 @@ CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */ 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 {v3.16b}, [x3] /* load first round key */ + ld1 {v3.4s}, [x3] /* load first round key */ add x10, x3, #16 bmi 1f bne 4f mov v5.16b, v3.16b b 3f 1: mov v4.16b, v3.16b - ld1 {v5.16b}, [x10], #16 /* load 2nd round key */ + ld1 {v5.4s}, [x10], #16 /* load 2nd round key */ 2: /* inner loop: 3 rounds, 2x interleaved */ aese v0.16b, v4.16b aesmc v0.16b, v0.16b aese v1.16b, v4.16b aesmc v1.16b, v1.16b -3: ld1 {v3.16b}, [x10], #16 /* load next round key */ +3: ld1 {v3.4s}, [x10], #16 /* load next round key */ aese v0.16b, v5.16b aesmc v0.16b, v0.16b aese v1.16b, v5.16b aesmc v1.16b, v1.16b -4: ld1 {v4.16b}, [x10], #16 /* load next round key */ +4: ld1 {v4.4s}, [x10], #16 /* load next round key */ subs w7, w7, #3 aese v0.16b, v3.16b aesmc v0.16b, v0.16b aese v1.16b, v3.16b aesmc v1.16b, v1.16b - ld1 {v5.16b}, [x10], #16 /* load next round key */ + ld1 {v5.4s}, [x10], #16 /* load next round key */ bpl 2b aese v0.16b, v4.16b aese v1.16b, v4.16b diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c index 6a7dbc7c83a6..a1254036f2b1 100644 --- a/arch/arm64/crypto/aes-ce-ccm-glue.c +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -1,7 +1,7 @@ /* * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions * - * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -9,6 +9,7 @@ */ #include <asm/neon.h> +#include <asm/simd.h> #include <asm/unaligned.h> #include <crypto/aes.h> #include <crypto/scatterwalk.h> @@ -44,6 +45,8 @@ asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes, asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[], u32 rounds); +asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds); + static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key, unsigned int key_len) { @@ -103,7 +106,45 @@ static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen) return 0; } -static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[]) +static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[], + u32 abytes, u32 *macp, bool use_neon) +{ + if (likely(use_neon)) { + ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc, + num_rounds(key)); + } else { + if (*macp > 0 && *macp < AES_BLOCK_SIZE) { + int added = min(abytes, AES_BLOCK_SIZE - *macp); + + crypto_xor(&mac[*macp], in, added); + + *macp += added; + in += added; + abytes -= added; + } + + while (abytes > AES_BLOCK_SIZE) { + __aes_arm64_encrypt(key->key_enc, mac, mac, + num_rounds(key)); + crypto_xor(mac, in, AES_BLOCK_SIZE); + + in += AES_BLOCK_SIZE; + abytes -= AES_BLOCK_SIZE; + } + + if (abytes > 0) { + __aes_arm64_encrypt(key->key_enc, mac, mac, + num_rounds(key)); + crypto_xor(mac, in, abytes); + *macp = abytes; + } else { + *macp = 0; + } + } +} + +static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[], + bool use_neon) { struct crypto_aead *aead = crypto_aead_reqtfm(req); struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead); @@ -122,8 +163,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[]) ltag.len = 6; } - ce_aes_ccm_auth_data(mac, (u8 *)<ag, ltag.len, &macp, ctx->key_enc, - num_rounds(ctx)); + ccm_update_mac(ctx, mac, (u8 *)<ag, ltag.len, &macp, use_neon); scatterwalk_start(&walk, req->src); do { @@ -135,8 +175,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[]) n = scatterwalk_clamp(&walk, len); } p = scatterwalk_map(&walk); - ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc, - num_rounds(ctx)); + ccm_update_mac(ctx, mac, p, n, &macp, use_neon); len -= n; scatterwalk_unmap(p); @@ -145,6 +184,56 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[]) } while (len); } +static int ccm_crypt_fallback(struct skcipher_walk *walk, u8 mac[], u8 iv0[], + struct crypto_aes_ctx *ctx, bool enc) +{ + u8 buf[AES_BLOCK_SIZE]; + int err = 0; + + while (walk->nbytes) { + int blocks = walk->nbytes / AES_BLOCK_SIZE; + u32 tail = walk->nbytes % AES_BLOCK_SIZE; + u8 *dst = walk->dst.virt.addr; + u8 *src = walk->src.virt.addr; + u32 nbytes = walk->nbytes; + + if (nbytes == walk->total && tail > 0) { + blocks++; + tail = 0; + } + + do { + u32 bsize = AES_BLOCK_SIZE; + + if (nbytes < AES_BLOCK_SIZE) + bsize = nbytes; + + crypto_inc(walk->iv, AES_BLOCK_SIZE); + __aes_arm64_encrypt(ctx->key_enc, buf, walk->iv, + num_rounds(ctx)); + __aes_arm64_encrypt(ctx->key_enc, mac, mac, + num_rounds(ctx)); + if (enc) + crypto_xor(mac, src, bsize); + crypto_xor_cpy(dst, src, buf, bsize); + if (!enc) + crypto_xor(mac, dst, bsize); + dst += bsize; + src += bsize; + nbytes -= bsize; + } while (--blocks); + + err = skcipher_walk_done(walk, tail); + } + + if (!err) { + __aes_arm64_encrypt(ctx->key_enc, buf, iv0, num_rounds(ctx)); + __aes_arm64_encrypt(ctx->key_enc, mac, mac, num_rounds(ctx)); + crypto_xor(mac, buf, AES_BLOCK_SIZE); + } + return err; +} + static int ccm_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); @@ -153,39 +242,46 @@ static int ccm_encrypt(struct aead_request *req) u8 __aligned(8) mac[AES_BLOCK_SIZE]; u8 buf[AES_BLOCK_SIZE]; u32 len = req->cryptlen; + bool use_neon = may_use_simd(); int err; err = ccm_init_mac(req, mac, len); if (err) return err; - kernel_neon_begin_partial(6); + if (likely(use_neon)) + kernel_neon_begin(); if (req->assoclen) - ccm_calculate_auth_mac(req, mac); + ccm_calculate_auth_mac(req, mac, use_neon); /* preserve the original iv for the final round */ memcpy(buf, req->iv, AES_BLOCK_SIZE); err = skcipher_walk_aead_encrypt(&walk, req, true); - while (walk.nbytes) { - u32 tail = walk.nbytes % AES_BLOCK_SIZE; - - if (walk.nbytes == walk.total) - tail = 0; + if (likely(use_neon)) { + while (walk.nbytes) { + u32 tail = walk.nbytes % AES_BLOCK_SIZE; - ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr, - walk.nbytes - tail, ctx->key_enc, - num_rounds(ctx), mac, walk.iv); + if (walk.nbytes == walk.total) + tail = 0; - err = skcipher_walk_done(&walk, tail); - } - if (!err) - ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx)); + ce_aes_ccm_encrypt(walk.dst.virt.addr, + walk.src.virt.addr, + walk.nbytes - tail, ctx->key_enc, + num_rounds(ctx), mac, walk.iv); - kernel_neon_end(); + err = skcipher_walk_done(&walk, tail); + } + if (!err) + ce_aes_ccm_final(mac, buf, ctx->key_enc, + num_rounds(ctx)); + kernel_neon_end(); + } else { + err = ccm_crypt_fallback(&walk, mac, buf, ctx, true); + } if (err) return err; @@ -205,38 +301,46 @@ static int ccm_decrypt(struct aead_request *req) u8 __aligned(8) mac[AES_BLOCK_SIZE]; u8 buf[AES_BLOCK_SIZE]; u32 len = req->cryptlen - authsize; + bool use_neon = may_use_simd(); int err; err = ccm_init_mac(req, mac, len); if (err) return err; - kernel_neon_begin_partial(6); + if (likely(use_neon)) + kernel_neon_begin(); if (req->assoclen) - ccm_calculate_auth_mac(req, mac); + ccm_calculate_auth_mac(req, mac, use_neon); /* preserve the original iv for the final round */ memcpy(buf, req->iv, AES_BLOCK_SIZE); err = skcipher_walk_aead_decrypt(&walk, req, true); - while (walk.nbytes) { - u32 tail = walk.nbytes % AES_BLOCK_SIZE; + if (likely(use_neon)) { + while (walk.nbytes) { + u32 tail = walk.nbytes % AES_BLOCK_SIZE; - if (walk.nbytes == walk.total) - tail = 0; + if (walk.nbytes == walk.total) + tail = 0; - ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr, - walk.nbytes - tail, ctx->key_enc, - num_rounds(ctx), mac, walk.iv); + ce_aes_ccm_decrypt(walk.dst.virt.addr, + walk.src.virt.addr, + walk.nbytes - tail, ctx->key_enc, + num_rounds(ctx), mac, walk.iv); - err = skcipher_walk_done(&walk, tail); - } - if (!err) - ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx)); + err = skcipher_walk_done(&walk, tail); + } + if (!err) + ce_aes_ccm_final(mac, buf, ctx->key_enc, + num_rounds(ctx)); - kernel_neon_end(); + kernel_neon_end(); + } else { + err = ccm_crypt_fallback(&walk, mac, buf, ctx, false); + } if (err) return err; diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c index 50d9fe11d0c8..6a75cd75ed11 100644 --- a/arch/arm64/crypto/aes-ce-cipher.c +++ b/arch/arm64/crypto/aes-ce-cipher.c @@ -1,7 +1,7 @@ /* * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions * - * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -9,6 +9,8 @@ */ #include <asm/neon.h> +#include <asm/simd.h> +#include <asm/unaligned.h> #include <crypto/aes.h> #include <linux/cpufeature.h> #include <linux/crypto.h> @@ -20,6 +22,9 @@ MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds); +asmlinkage void __aes_arm64_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds); + struct aes_block { u8 b[AES_BLOCK_SIZE]; }; @@ -44,27 +49,32 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[]) void *dummy0; int dummy1; - kernel_neon_begin_partial(4); + if (!may_use_simd()) { + __aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx)); + return; + } + + kernel_neon_begin(); __asm__(" ld1 {v0.16b}, %[in] ;" - " ld1 {v1.16b}, [%[key]], #16 ;" + " ld1 {v1.4s}, [%[key]], #16 ;" " cmp %w[rounds], #10 ;" " bmi 0f ;" " bne 3f ;" " mov v3.16b, v1.16b ;" " b 2f ;" "0: mov v2.16b, v1.16b ;" - " ld1 {v3.16b}, [%[key]], #16 ;" + " ld1 {v3.4s}, [%[key]], #16 ;" "1: aese v0.16b, v2.16b ;" " aesmc v0.16b, v0.16b ;" - "2: ld1 {v1.16b}, [%[key]], #16 ;" + "2: ld1 {v1.4s}, [%[key]], #16 ;" " aese v0.16b, v3.16b ;" " aesmc v0.16b, v0.16b ;" - "3: ld1 {v2.16b}, [%[key]], #16 ;" + "3: ld1 {v2.4s}, [%[key]], #16 ;" " subs %w[rounds], %w[rounds], #3 ;" " aese v0.16b, v1.16b ;" " aesmc v0.16b, v0.16b ;" - " ld1 {v3.16b}, [%[key]], #16 ;" + " ld1 {v3.4s}, [%[key]], #16 ;" " bpl 1b ;" " aese v0.16b, v2.16b ;" " eor v0.16b, v0.16b, v3.16b ;" @@ -89,27 +99,32 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[]) void *dummy0; int dummy1; - kernel_neon_begin_partial(4); + if (!may_use_simd()) { + __aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx)); + return; + } + + kernel_neon_begin(); __asm__(" ld1 {v0.16b}, %[in] ;" - " ld1 {v1.16b}, [%[key]], #16 ;" + " ld1 {v1.4s}, [%[key]], #16 ;" " cmp %w[rounds], #10 ;" " bmi 0f ;" " bne 3f ;" " mov v3.16b, v1.16b ;" " b 2f ;" "0: mov v2.16b, v1.16b ;" - " ld1 {v3.16b}, [%[key]], #16 ;" + " ld1 {v3.4s}, [%[key]], #16 ;" "1: aesd v0.16b, v2.16b ;" " aesimc v0.16b, v0.16b ;" - "2: ld1 {v1.16b}, [%[key]], #16 ;" + "2: ld1 {v1.4s}, [%[key]], #16 ;" " aesd v0.16b, v3.16b ;" " aesimc v0.16b, v0.16b ;" - "3: ld1 {v2.16b}, [%[key]], #16 ;" + "3: ld1 {v2.4s}, [%[key]], #16 ;" " subs %w[rounds], %w[rounds], #3 ;" " aesd v0.16b, v1.16b ;" " aesimc v0.16b, v0.16b ;" - " ld1 {v3.16b}, [%[key]], #16 ;" + " ld1 {v3.4s}, [%[key]], #16 ;" " bpl 1b ;" " aesd v0.16b, v2.16b ;" " eor v0.16b, v0.16b, v3.16b ;" @@ -165,20 +180,16 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key, key_len != AES_KEYSIZE_256) return -EINVAL; - memcpy(ctx->key_enc, in_key, key_len); ctx->key_length = key_len; + for (i = 0; i < kwords; i++) + ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32)); - kernel_neon_begin_partial(2); + kernel_neon_begin(); for (i = 0; i < sizeof(rcon); i++) { u32 *rki = ctx->key_enc + (i * kwords); u32 *rko = rki + kwords; -#ifndef CONFIG_CPU_BIG_ENDIAN rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0]; -#else - rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^ - rki[0]; -#endif rko[1] = rko[0] ^ rki[1]; rko[2] = rko[1] ^ rki[2]; rko[3] = rko[2] ^ rki[3]; @@ -210,9 +221,9 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key, key_dec[0] = key_enc[j]; for (i = 1, j--; j > 0; i++, j--) - __asm__("ld1 {v0.16b}, %[in] ;" + __asm__("ld1 {v0.4s}, %[in] ;" "aesimc v1.16b, v0.16b ;" - "st1 {v1.16b}, %[out] ;" + "st1 {v1.4s}, %[out] ;" : [out] "=Q"(key_dec[i]) : [in] "Q"(key_enc[j]) diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S index b46093d567e5..50330f5c3adc 100644 --- a/arch/arm64/crypto/aes-ce.S +++ b/arch/arm64/crypto/aes-ce.S @@ -2,7 +2,7 @@ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with * Crypto Extensions * - * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -22,11 +22,11 @@ cmp \rounds, #12 blo 2222f /* 128 bits */ beq 1111f /* 192 bits */ - ld1 {v17.16b-v18.16b}, [\rk], #32 -1111: ld1 {v19.16b-v20.16b}, [\rk], #32 -2222: ld1 {v21.16b-v24.16b}, [\rk], #64 - ld1 {v25.16b-v28.16b}, [\rk], #64 - ld1 {v29.16b-v31.16b}, [\rk] + ld1 {v17.4s-v18.4s}, [\rk], #32 +1111: ld1 {v19.4s-v20.4s}, [\rk], #32 +2222: ld1 {v21.4s-v24.4s}, [\rk], #64 + ld1 {v25.4s-v28.4s}, [\rk], #64 + ld1 {v29.4s-v31.4s}, [\rk] .endm /* prepare for encryption with key in rk[] */ diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S index f2f9cc519309..6d2445d603cc 100644 --- a/arch/arm64/crypto/aes-cipher-core.S +++ b/arch/arm64/crypto/aes-cipher-core.S @@ -10,6 +10,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/cache.h> .text @@ -17,94 +18,155 @@ out .req x1 in .req x2 rounds .req x3 - tt .req x4 - lt .req x2 + tt .req x2 - .macro __pair, enc, reg0, reg1, in0, in1e, in1d, shift + .macro __pair1, sz, op, reg0, reg1, in0, in1e, in1d, shift + .ifc \op\shift, b0 + ubfiz \reg0, \in0, #2, #8 + ubfiz \reg1, \in1e, #2, #8 + .else ubfx \reg0, \in0, #\shift, #8 - .if \enc ubfx \reg1, \in1e, #\shift, #8 - .else - ubfx \reg1, \in1d, #\shift, #8 .endif + + /* + * AArch64 cannot do byte size indexed loads from a table containing + * 32-bit quantities, i.e., 'ldrb w12, [tt, w12, uxtw #2]' is not a + * valid instruction. So perform the shift explicitly first for the + * high bytes (the low byte is shifted implicitly by using ubfiz rather + * than ubfx above) + */ + .ifnc \op, b ldr \reg0, [tt, \reg0, uxtw #2] ldr \reg1, [tt, \reg1, uxtw #2] + .else + .if \shift > 0 + lsl \reg0, \reg0, #2 + lsl \reg1, \reg1, #2 + .endif + ldrb \reg0, [tt, \reg0, uxtw] + ldrb \reg1, [tt, \reg1, uxtw] + .endif .endm - .macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc + .macro __pair0, sz, op, reg0, reg1, in0, in1e, in1d, shift + ubfx \reg0, \in0, #\shift, #8 + ubfx \reg1, \in1d, #\shift, #8 + ldr\op \reg0, [tt, \reg0, uxtw #\sz] + ldr\op \reg1, [tt, \reg1, uxtw #\sz] + .endm + + .macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc, sz, op ldp \out0, \out1, [rk], #8 - __pair \enc, w13, w14, \in0, \in1, \in3, 0 - __pair \enc, w15, w16, \in1, \in2, \in0, 8 - __pair \enc, w17, w18, \in2, \in3, \in1, 16 - __pair \enc, \t0, \t1, \in3, \in0, \in2, 24 - - eor \out0, \out0, w13 - eor \out1, \out1, w14 - eor \out0, \out0, w15, ror #24 - eor \out1, \out1, w16, ror #24 - eor \out0, \out0, w17, ror #16 - eor \out1, \out1, w18, ror #16 + __pair\enc \sz, \op, w12, w13, \in0, \in1, \in3, 0 + __pair\enc \sz, \op, w14, w15, \in1, \in2, \in0, 8 + __pair\enc \sz, \op, w16, w17, \in2, \in3, \in1, 16 + __pair\enc \sz, \op, \t0, \t1, \in3, \in0, \in2, 24 + + eor \out0, \out0, w12 + eor \out1, \out1, w13 + eor \out0, \out0, w14, ror #24 + eor \out1, \out1, w15, ror #24 + eor \out0, \out0, w16, ror #16 + eor \out1, \out1, w17, ror #16 eor \out0, \out0, \t0, ror #8 eor \out1, \out1, \t1, ror #8 .endm - .macro fround, out0, out1, out2, out3, in0, in1, in2, in3 - __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1 - __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1 + .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op + __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op + __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op .endm - .macro iround, out0, out1, out2, out3, in0, in1, in2, in3 - __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0 - __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0 + .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op + __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op + __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op .endm - .macro do_crypt, round, ttab, ltab - ldp w5, w6, [in] - ldp w7, w8, [in, #8] - ldp w9, w10, [rk], #16 - ldp w11, w12, [rk, #-8] + .macro do_crypt, round, ttab, ltab, bsz + ldp w4, w5, [in] + ldp w6, w7, [in, #8] + ldp w8, w9, [rk], #16 + ldp w10, w11, [rk, #-8] +CPU_BE( rev w4, w4 ) CPU_BE( rev w5, w5 ) CPU_BE( rev w6, w6 ) CPU_BE( rev w7, w7 ) -CPU_BE( rev w8, w8 ) + eor w4, w4, w8 eor w5, w5, w9 eor w6, w6, w10 eor w7, w7, w11 - eor w8, w8, w12 adr_l tt, \ttab - adr_l lt, \ltab tbnz rounds, #1, 1f -0: \round w9, w10, w11, w12, w5, w6, w7, w8 - \round w5, w6, w7, w8, w9, w10, w11, w12 +0: \round w8, w9, w10, w11, w4, w5, w6, w7 + \round w4, w5, w6, w7, w8, w9, w10, w11 1: subs rounds, rounds, #4 - \round w9, w10, w11, w12, w5, w6, w7, w8 - csel tt, tt, lt, hi - \round w5, w6, w7, w8, w9, w10, w11, w12 - b.hi 0b - + \round w8, w9, w10, w11, w4, w5, w6, w7 + b.ls 3f +2: \round w4, w5, w6, w7, w8, w9, w10, w11 + b 0b +3: adr_l tt, \ltab + \round w4, w5, w6, w7, w8, w9, w10, w11, \bsz, b + +CPU_BE( rev w4, w4 ) CPU_BE( rev w5, w5 ) CPU_BE( rev w6, w6 ) CPU_BE( rev w7, w7 ) -CPU_BE( rev w8, w8 ) - stp w5, w6, [out] - stp w7, w8, [out, #8] + stp w4, w5, [out] + stp w6, w7, [out, #8] ret .endm - .align 5 + .align L1_CACHE_SHIFT + .type __aes_arm64_inverse_sbox, %object +__aes_arm64_inverse_sbox: + .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38 + .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb + .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87 + .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb + .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d + .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e + .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2 + .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25 + .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16 + .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92 + .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda + .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84 + .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a + .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06 + .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02 + .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b + .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea + .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73 + .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85 + .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e + .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89 + .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b + .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20 + .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4 + .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31 + .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f + .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d + .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef + .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0 + .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61 + .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26 + .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d + .size __aes_arm64_inverse_sbox, . - __aes_arm64_inverse_sbox + ENTRY(__aes_arm64_encrypt) - do_crypt fround, crypto_ft_tab, crypto_fl_tab + do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2 ENDPROC(__aes_arm64_encrypt) .align 5 ENTRY(__aes_arm64_decrypt) - do_crypt iround, crypto_it_tab, crypto_il_tab + do_crypt iround, crypto_it_tab, __aes_arm64_inverse_sbox, 0 ENDPROC(__aes_arm64_decrypt) diff --git a/arch/arm64/crypto/aes-ctr-fallback.h b/arch/arm64/crypto/aes-ctr-fallback.h new file mode 100644 index 000000000000..c9285717b6b5 --- /dev/null +++ b/arch/arm64/crypto/aes-ctr-fallback.h @@ -0,0 +1,53 @@ +/* + * Fallback for sync aes(ctr) in contexts where kernel mode NEON + * is not allowed + * + * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <crypto/aes.h> +#include <crypto/internal/skcipher.h> + +asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds); + +static inline int aes_ctr_encrypt_fallback(struct crypto_aes_ctx *ctx, + struct skcipher_request *req) +{ + struct skcipher_walk walk; + u8 buf[AES_BLOCK_SIZE]; + int err; + + err = skcipher_walk_virt(&walk, req, true); + + while (walk.nbytes > 0) { + u8 *dst = walk.dst.virt.addr; + u8 *src = walk.src.virt.addr; + int nbytes = walk.nbytes; + int tail = 0; + + if (nbytes < walk.total) { + nbytes = round_down(nbytes, AES_BLOCK_SIZE); + tail = walk.nbytes % AES_BLOCK_SIZE; + } + + do { + int bsize = min(nbytes, AES_BLOCK_SIZE); + + __aes_arm64_encrypt(ctx->key_enc, buf, walk.iv, + 6 + ctx->key_length / 4); + crypto_xor_cpy(dst, src, buf, bsize); + crypto_inc(walk.iv, AES_BLOCK_SIZE); + + dst += AES_BLOCK_SIZE; + src += AES_BLOCK_SIZE; + nbytes -= AES_BLOCK_SIZE; + } while (nbytes > 0); + + err = skcipher_walk_done(&walk, tail); + } + return err; +} diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index bcf596b0197e..998ba519a026 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -10,6 +10,7 @@ #include <asm/neon.h> #include <asm/hwcap.h> +#include <asm/simd.h> #include <crypto/aes.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> @@ -19,6 +20,7 @@ #include <crypto/xts.h> #include "aes-ce-setkey.h" +#include "aes-ctr-fallback.h" #ifdef USE_V8_CRYPTO_EXTENSIONS #define MODE "ce" @@ -241,9 +243,7 @@ static int ctr_encrypt(struct skcipher_request *req) aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds, blocks, walk.iv, first); - if (tdst != tsrc) - memcpy(tdst, tsrc, nbytes); - crypto_xor(tdst, tail, nbytes); + crypto_xor_cpy(tdst, tsrc, tail, nbytes); err = skcipher_walk_done(&walk, 0); } kernel_neon_end(); @@ -251,6 +251,17 @@ static int ctr_encrypt(struct skcipher_request *req) return err; } +static int ctr_encrypt_sync(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + + if (!may_use_simd()) + return aes_ctr_encrypt_fallback(ctx, req); + + return ctr_encrypt(req); +} + static int xts_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); @@ -357,8 +368,8 @@ static struct skcipher_alg aes_algs[] = { { .ivsize = AES_BLOCK_SIZE, .chunksize = AES_BLOCK_SIZE, .setkey = skcipher_aes_setkey, - .encrypt = ctr_encrypt, - .decrypt = ctr_encrypt, + .encrypt = ctr_encrypt_sync, + .decrypt = ctr_encrypt_sync, }, { .base = { .cra_name = "__xts(aes)", @@ -460,11 +471,35 @@ static int mac_init(struct shash_desc *desc) return 0; } +static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks, + u8 dg[], int enc_before, int enc_after) +{ + int rounds = 6 + ctx->key_length / 4; + + if (may_use_simd()) { + kernel_neon_begin(); + aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before, + enc_after); + kernel_neon_end(); + } else { + if (enc_before) + __aes_arm64_encrypt(ctx->key_enc, dg, dg, rounds); + + while (blocks--) { + crypto_xor(dg, in, AES_BLOCK_SIZE); + in += AES_BLOCK_SIZE; + + if (blocks || enc_after) + __aes_arm64_encrypt(ctx->key_enc, dg, dg, + rounds); + } + } +} + static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len) { struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct mac_desc_ctx *ctx = shash_desc_ctx(desc); - int rounds = 6 + tctx->key.key_length / 4; while (len > 0) { unsigned int l; @@ -476,10 +511,8 @@ static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len) len %= AES_BLOCK_SIZE; - kernel_neon_begin(); - aes_mac_update(p, tctx->key.key_enc, rounds, blocks, - ctx->dg, (ctx->len != 0), (len != 0)); - kernel_neon_end(); + mac_do_update(&tctx->key, p, blocks, ctx->dg, + (ctx->len != 0), (len != 0)); p += blocks * AES_BLOCK_SIZE; @@ -507,11 +540,8 @@ static int cbcmac_final(struct shash_desc *desc, u8 *out) { struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct mac_desc_ctx *ctx = shash_desc_ctx(desc); - int rounds = 6 + tctx->key.key_length / 4; - kernel_neon_begin(); - aes_mac_update(NULL, tctx->key.key_enc, rounds, 0, ctx->dg, 1, 0); - kernel_neon_end(); + mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1, 0); memcpy(out, ctx->dg, AES_BLOCK_SIZE); @@ -522,7 +552,6 @@ static int cmac_final(struct shash_desc *desc, u8 *out) { struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct mac_desc_ctx *ctx = shash_desc_ctx(desc); - int rounds = 6 + tctx->key.key_length / 4; u8 *consts = tctx->consts; if (ctx->len != AES_BLOCK_SIZE) { @@ -530,9 +559,7 @@ static int cmac_final(struct shash_desc *desc, u8 *out) consts += AES_BLOCK_SIZE; } - kernel_neon_begin(); - aes_mac_update(consts, tctx->key.key_enc, rounds, 1, ctx->dg, 0, 1); - kernel_neon_end(); + mac_do_update(&tctx->key, consts, 1, ctx->dg, 0, 1); memcpy(out, ctx->dg, AES_BLOCK_SIZE); diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index db2501d93550..c55d68ccb89f 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -1,7 +1,7 @@ /* * Bit sliced AES using NEON instructions * - * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -9,12 +9,15 @@ */ #include <asm/neon.h> +#include <asm/simd.h> #include <crypto/aes.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> #include <crypto/xts.h> #include <linux/module.h> +#include "aes-ctr-fallback.h" + MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); @@ -58,6 +61,11 @@ struct aesbs_cbc_ctx { u32 enc[AES_MAX_KEYLENGTH_U32]; }; +struct aesbs_ctr_ctx { + struct aesbs_ctx key; /* must be first member */ + struct crypto_aes_ctx fallback; +}; + struct aesbs_xts_ctx { struct aesbs_ctx key; u32 twkey[AES_MAX_KEYLENGTH_U32]; @@ -196,6 +204,25 @@ static int cbc_decrypt(struct skcipher_request *req) return err; } +static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm); + int err; + + err = crypto_aes_expand_key(&ctx->fallback, in_key, key_len); + if (err) + return err; + + ctx->key.rounds = 6 + key_len / 4; + + kernel_neon_begin(); + aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds); + kernel_neon_end(); + + return 0; +} + static int ctr_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); @@ -224,9 +251,8 @@ static int ctr_encrypt(struct skcipher_request *req) u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; - if (dst != src) - memcpy(dst, src, walk.total % AES_BLOCK_SIZE); - crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE); + crypto_xor_cpy(dst, src, final, + walk.total % AES_BLOCK_SIZE); err = skcipher_walk_done(&walk, 0); break; @@ -260,6 +286,17 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key, return aesbs_setkey(tfm, in_key, key_len); } +static int ctr_encrypt_sync(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm); + + if (!may_use_simd()) + return aes_ctr_encrypt_fallback(&ctx->fallback, req); + + return ctr_encrypt(req); +} + static int __xts_crypt(struct skcipher_request *req, void (*fn)(u8 out[], u8 const in[], u8 const rk[], int rounds, int blocks, u8 iv[])) @@ -356,7 +393,7 @@ static struct skcipher_alg aes_algs[] = { { .base.cra_driver_name = "ctr-aes-neonbs", .base.cra_priority = 250 - 1, .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct aesbs_ctx), + .base.cra_ctxsize = sizeof(struct aesbs_ctr_ctx), .base.cra_module = THIS_MODULE, .min_keysize = AES_MIN_KEY_SIZE, @@ -364,9 +401,9 @@ static struct skcipher_alg aes_algs[] = { { .chunksize = AES_BLOCK_SIZE, .walksize = 8 * AES_BLOCK_SIZE, .ivsize = AES_BLOCK_SIZE, - .setkey = aesbs_setkey, - .encrypt = ctr_encrypt, - .decrypt = ctr_encrypt, + .setkey = aesbs_ctr_setkey_sync, + .encrypt = ctr_encrypt_sync, + .decrypt = ctr_encrypt_sync, }, { .base.cra_name = "__xts(aes)", .base.cra_driver_name = "__xts-aes-neonbs", diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c index a7cd575ea223..cbdb75d15cd0 100644 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ b/arch/arm64/crypto/chacha20-neon-glue.c @@ -1,7 +1,7 @@ /* * ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions * - * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -26,6 +26,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> +#include <asm/simd.h> asmlinkage void chacha20_block_xor_neon(u32 *state, u8 *dst, const u8 *src); asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src); @@ -64,7 +65,7 @@ static int chacha20_neon(struct skcipher_request *req) u32 state[16]; int err; - if (req->cryptlen <= CHACHA20_BLOCK_SIZE) + if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE) return crypto_chacha20_crypt(req); err = skcipher_walk_virt(&walk, req, true); diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c index eccb1ae90064..624f4137918c 100644 --- a/arch/arm64/crypto/crc32-ce-glue.c +++ b/arch/arm64/crypto/crc32-ce-glue.c @@ -1,7 +1,7 @@ /* * Accelerated CRC32(C) using arm64 NEON and Crypto Extensions instructions * - * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -19,6 +19,7 @@ #include <asm/hwcap.h> #include <asm/neon.h> +#include <asm/simd.h> #include <asm/unaligned.h> #define PMULL_MIN_LEN 64L /* minimum size of buffer @@ -105,10 +106,10 @@ static int crc32_pmull_update(struct shash_desc *desc, const u8 *data, length -= l; } - if (length >= PMULL_MIN_LEN) { + if (length >= PMULL_MIN_LEN && may_use_simd()) { l = round_down(length, SCALE_F); - kernel_neon_begin_partial(10); + kernel_neon_begin(); *crc = crc32_pmull_le(data, l, *crc); kernel_neon_end(); @@ -137,10 +138,10 @@ static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data, length -= l; } - if (length >= PMULL_MIN_LEN) { + if (length >= PMULL_MIN_LEN && may_use_simd()) { l = round_down(length, SCALE_F); - kernel_neon_begin_partial(10); + kernel_neon_begin(); *crc = crc32c_pmull_le(data, l, *crc); kernel_neon_end(); diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c index 60cb590c2590..96f0cae4a022 100644 --- a/arch/arm64/crypto/crct10dif-ce-glue.c +++ b/arch/arm64/crypto/crct10dif-ce-glue.c @@ -1,7 +1,7 @@ /* * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions * - * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -18,6 +18,7 @@ #include <crypto/internal/hash.h> #include <asm/neon.h> +#include <asm/simd.h> #define CRC_T10DIF_PMULL_CHUNK_SIZE 16U @@ -48,9 +49,13 @@ static int crct10dif_update(struct shash_desc *desc, const u8 *data, } if (length > 0) { - kernel_neon_begin_partial(14); - *crc = crc_t10dif_pmull(*crc, data, length); - kernel_neon_end(); + if (may_use_simd()) { + kernel_neon_begin(); + *crc = crc_t10dif_pmull(*crc, data, length); + kernel_neon_end(); + } else { + *crc = crc_t10dif_generic(*crc, data, length); + } } return 0; diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index f0bb9f0b524f..11ebf1ae248a 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -1,7 +1,7 @@ /* * Accelerated GHASH implementation with ARMv8 PMULL instructions. * - * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -11,31 +11,215 @@ #include <linux/linkage.h> #include <asm/assembler.h> - SHASH .req v0 - SHASH2 .req v1 - T1 .req v2 - T2 .req v3 - MASK .req v4 - XL .req v5 - XM .req v6 - XH .req v7 - IN1 .req v7 + SHASH .req v0 + SHASH2 .req v1 + T1 .req v2 + T2 .req v3 + MASK .req v4 + XL .req v5 + XM .req v6 + XH .req v7 + IN1 .req v7 + + k00_16 .req v8 + k32_48 .req v9 + + t3 .req v10 + t4 .req v11 + t5 .req v12 + t6 .req v13 + t7 .req v14 + t8 .req v15 + t9 .req v16 + + perm1 .req v17 + perm2 .req v18 + perm3 .req v19 + + sh1 .req v20 + sh2 .req v21 + sh3 .req v22 + sh4 .req v23 + + ss1 .req v24 + ss2 .req v25 + ss3 .req v26 + ss4 .req v27 .text .arch armv8-a+crypto - /* - * void pmull_ghash_update(int blocks, u64 dg[], const char *src, - * struct ghash_key const *k, const char *head) - */ -ENTRY(pmull_ghash_update) + .macro __pmull_p64, rd, rn, rm + pmull \rd\().1q, \rn\().1d, \rm\().1d + .endm + + .macro __pmull2_p64, rd, rn, rm + pmull2 \rd\().1q, \rn\().2d, \rm\().2d + .endm + + .macro __pmull_p8, rq, ad, bd + ext t3.8b, \ad\().8b, \ad\().8b, #1 // A1 + ext t5.8b, \ad\().8b, \ad\().8b, #2 // A2 + ext t7.8b, \ad\().8b, \ad\().8b, #3 // A3 + + __pmull_p8_\bd \rq, \ad + .endm + + .macro __pmull2_p8, rq, ad, bd + tbl t3.16b, {\ad\().16b}, perm1.16b // A1 + tbl t5.16b, {\ad\().16b}, perm2.16b // A2 + tbl t7.16b, {\ad\().16b}, perm3.16b // A3 + + __pmull2_p8_\bd \rq, \ad + .endm + + .macro __pmull_p8_SHASH, rq, ad + __pmull_p8_tail \rq, \ad\().8b, SHASH.8b, 8b,, sh1, sh2, sh3, sh4 + .endm + + .macro __pmull_p8_SHASH2, rq, ad + __pmull_p8_tail \rq, \ad\().8b, SHASH2.8b, 8b,, ss1, ss2, ss3, ss4 + .endm + + .macro __pmull2_p8_SHASH, rq, ad + __pmull_p8_tail \rq, \ad\().16b, SHASH.16b, 16b, 2, sh1, sh2, sh3, sh4 + .endm + + .macro __pmull_p8_tail, rq, ad, bd, nb, t, b1, b2, b3, b4 + pmull\t t3.8h, t3.\nb, \bd // F = A1*B + pmull\t t4.8h, \ad, \b1\().\nb // E = A*B1 + pmull\t t5.8h, t5.\nb, \bd // H = A2*B + pmull\t t6.8h, \ad, \b2\().\nb // G = A*B2 + pmull\t t7.8h, t7.\nb, \bd // J = A3*B + pmull\t t8.8h, \ad, \b3\().\nb // I = A*B3 + pmull\t t9.8h, \ad, \b4\().\nb // K = A*B4 + pmull\t \rq\().8h, \ad, \bd // D = A*B + + eor t3.16b, t3.16b, t4.16b // L = E + F + eor t5.16b, t5.16b, t6.16b // M = G + H + eor t7.16b, t7.16b, t8.16b // N = I + J + + uzp1 t4.2d, t3.2d, t5.2d + uzp2 t3.2d, t3.2d, t5.2d + uzp1 t6.2d, t7.2d, t9.2d + uzp2 t7.2d, t7.2d, t9.2d + + // t3 = (L) (P0 + P1) << 8 + // t5 = (M) (P2 + P3) << 16 + eor t4.16b, t4.16b, t3.16b + and t3.16b, t3.16b, k32_48.16b + + // t7 = (N) (P4 + P5) << 24 + // t9 = (K) (P6 + P7) << 32 + eor t6.16b, t6.16b, t7.16b + and t7.16b, t7.16b, k00_16.16b + + eor t4.16b, t4.16b, t3.16b + eor t6.16b, t6.16b, t7.16b + + zip2 t5.2d, t4.2d, t3.2d + zip1 t3.2d, t4.2d, t3.2d + zip2 t9.2d, t6.2d, t7.2d + zip1 t7.2d, t6.2d, t7.2d + + ext t3.16b, t3.16b, t3.16b, #15 + ext t5.16b, t5.16b, t5.16b, #14 + ext t7.16b, t7.16b, t7.16b, #13 + ext t9.16b, t9.16b, t9.16b, #12 + + eor t3.16b, t3.16b, t5.16b + eor t7.16b, t7.16b, t9.16b + eor \rq\().16b, \rq\().16b, t3.16b + eor \rq\().16b, \rq\().16b, t7.16b + .endm + + .macro __pmull_pre_p64 + movi MASK.16b, #0xe1 + shl MASK.2d, MASK.2d, #57 + .endm + + .macro __pmull_pre_p8 + // k00_16 := 0x0000000000000000_000000000000ffff + // k32_48 := 0x00000000ffffffff_0000ffffffffffff + movi k32_48.2d, #0xffffffff + mov k32_48.h[2], k32_48.h[0] + ushr k00_16.2d, k32_48.2d, #32 + + // prepare the permutation vectors + mov_q x5, 0x080f0e0d0c0b0a09 + movi T1.8b, #8 + dup perm1.2d, x5 + eor perm1.16b, perm1.16b, T1.16b + ushr perm2.2d, perm1.2d, #8 + ushr perm3.2d, perm1.2d, #16 + ushr T1.2d, perm1.2d, #24 + sli perm2.2d, perm1.2d, #56 + sli perm3.2d, perm1.2d, #48 + sli T1.2d, perm1.2d, #40 + + // precompute loop invariants + tbl sh1.16b, {SHASH.16b}, perm1.16b + tbl sh2.16b, {SHASH.16b}, perm2.16b + tbl sh3.16b, {SHASH.16b}, perm3.16b + tbl sh4.16b, {SHASH.16b}, T1.16b + ext ss1.8b, SHASH2.8b, SHASH2.8b, #1 + ext ss2.8b, SHASH2.8b, SHASH2.8b, #2 + ext ss3.8b, SHASH2.8b, SHASH2.8b, #3 + ext ss4.8b, SHASH2.8b, SHASH2.8b, #4 + .endm + + // + // PMULL (64x64->128) based reduction for CPUs that can do + // it in a single instruction. + // + .macro __pmull_reduce_p64 + pmull T2.1q, XL.1d, MASK.1d + eor XM.16b, XM.16b, T1.16b + + mov XH.d[0], XM.d[1] + mov XM.d[1], XL.d[0] + + eor XL.16b, XM.16b, T2.16b + ext T2.16b, XL.16b, XL.16b, #8 + pmull XL.1q, XL.1d, MASK.1d + .endm + + // + // Alternative reduction for CPUs that lack support for the + // 64x64->128 PMULL instruction + // + .macro __pmull_reduce_p8 + eor XM.16b, XM.16b, T1.16b + + mov XL.d[1], XM.d[0] + mov XH.d[0], XM.d[1] + + shl T1.2d, XL.2d, #57 + shl T2.2d, XL.2d, #62 + eor T2.16b, T2.16b, T1.16b + shl T1.2d, XL.2d, #63 + eor T2.16b, T2.16b, T1.16b + ext T1.16b, XL.16b, XH.16b, #8 + eor T2.16b, T2.16b, T1.16b + + mov XL.d[1], T2.d[0] + mov XH.d[0], T2.d[1] + + ushr T2.2d, XL.2d, #1 + eor XH.16b, XH.16b, XL.16b + eor XL.16b, XL.16b, T2.16b + ushr T2.2d, T2.2d, #6 + ushr XL.2d, XL.2d, #1 + .endm + + .macro __pmull_ghash, pn ld1 {SHASH.2d}, [x3] ld1 {XL.2d}, [x1] - movi MASK.16b, #0xe1 ext SHASH2.16b, SHASH.16b, SHASH.16b, #8 - shl MASK.2d, MASK.2d, #57 eor SHASH2.16b, SHASH2.16b, SHASH.16b + __pmull_pre_\pn + /* do the head block first, if supplied */ cbz x4, 0f ld1 {T1.2d}, [x4] @@ -52,28 +236,209 @@ CPU_LE( rev64 T1.16b, T1.16b ) eor T1.16b, T1.16b, T2.16b eor XL.16b, XL.16b, IN1.16b + __pmull2_\pn XH, XL, SHASH // a1 * b1 + eor T1.16b, T1.16b, XL.16b + __pmull_\pn XL, XL, SHASH // a0 * b0 + __pmull_\pn XM, T1, SHASH2 // (a1 + a0)(b1 + b0) + + eor T2.16b, XL.16b, XH.16b + ext T1.16b, XL.16b, XH.16b, #8 + eor XM.16b, XM.16b, T2.16b + + __pmull_reduce_\pn + + eor T2.16b, T2.16b, XH.16b + eor XL.16b, XL.16b, T2.16b + + cbnz w0, 0b + + st1 {XL.2d}, [x1] + ret + .endm + + /* + * void pmull_ghash_update(int blocks, u64 dg[], const char *src, + * struct ghash_key const *k, const char *head) + */ +ENTRY(pmull_ghash_update_p64) + __pmull_ghash p64 +ENDPROC(pmull_ghash_update_p64) + +ENTRY(pmull_ghash_update_p8) + __pmull_ghash p8 +ENDPROC(pmull_ghash_update_p8) + + KS .req v8 + CTR .req v9 + INP .req v10 + + .macro load_round_keys, rounds, rk + cmp \rounds, #12 + blo 2222f /* 128 bits */ + beq 1111f /* 192 bits */ + ld1 {v17.4s-v18.4s}, [\rk], #32 +1111: ld1 {v19.4s-v20.4s}, [\rk], #32 +2222: ld1 {v21.4s-v24.4s}, [\rk], #64 + ld1 {v25.4s-v28.4s}, [\rk], #64 + ld1 {v29.4s-v31.4s}, [\rk] + .endm + + .macro enc_round, state, key + aese \state\().16b, \key\().16b + aesmc \state\().16b, \state\().16b + .endm + + .macro enc_block, state, rounds + cmp \rounds, #12 + b.lo 2222f /* 128 bits */ + b.eq 1111f /* 192 bits */ + enc_round \state, v17 + enc_round \state, v18 +1111: enc_round \state, v19 + enc_round \state, v20 +2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29 + enc_round \state, \key + .endr + aese \state\().16b, v30.16b + eor \state\().16b, \state\().16b, v31.16b + .endm + + .macro pmull_gcm_do_crypt, enc + ld1 {SHASH.2d}, [x4] + ld1 {XL.2d}, [x1] + ldr x8, [x5, #8] // load lower counter + + 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}, [x7] + .endif + +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}, [x2], #16 + .endif + + rev64 T1.16b, INP.16b + + cmp w6, #12 + b.ge 2f // AES-192/256? + +1: enc_round CTR, v21 + + ext T2.16b, XL.16b, XL.16b, #8 + ext IN1.16b, T1.16b, T1.16b, #8 + + enc_round CTR, v22 + + eor T1.16b, T1.16b, T2.16b + eor XL.16b, XL.16b, IN1.16b + + enc_round CTR, v23 + pmull2 XH.1q, SHASH.2d, XL.2d // a1 * b1 eor T1.16b, T1.16b, XL.16b + + enc_round CTR, v24 + pmull XL.1q, SHASH.1d, XL.1d // a0 * b0 pmull XM.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0) + enc_round CTR, v25 + ext T1.16b, XL.16b, XH.16b, #8 eor T2.16b, XL.16b, XH.16b eor XM.16b, XM.16b, T1.16b + + enc_round CTR, v26 + eor XM.16b, XM.16b, T2.16b pmull T2.1q, XL.1d, MASK.1d + enc_round CTR, v27 + mov XH.d[0], XM.d[1] mov XM.d[1], XL.d[0] + enc_round CTR, v28 + eor XL.16b, XM.16b, T2.16b + + enc_round CTR, v29 + ext T2.16b, XL.16b, XL.16b, #8 + + aese CTR.16b, v30.16b + pmull XL.1q, XL.1d, MASK.1d eor T2.16b, T2.16b, XH.16b + + eor KS.16b, CTR.16b, v31.16b + eor XL.16b, XL.16b, T2.16b + .if \enc == 0 + eor INP.16b, INP.16b, KS.16b + st1 {INP.16b}, [x2], #16 + .endif + cbnz w0, 0b +CPU_LE( rev x8, x8 ) st1 {XL.2d}, [x1] + str x8, [x5, #8] // store lower counter + + .if \enc == 1 + st1 {KS.16b}, [x7] + .endif + + ret + +2: b.eq 3f // AES-192? + enc_round CTR, v17 + enc_round CTR, v18 +3: enc_round CTR, v19 + enc_round CTR, v20 + b 1b + .endm + + /* + * void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[], const u8 src[], + * struct ghash_key const *k, u8 ctr[], + * int rounds, u8 ks[]) + */ +ENTRY(pmull_gcm_encrypt) + pmull_gcm_do_crypt 1 +ENDPROC(pmull_gcm_encrypt) + + /* + * void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[], const u8 src[], + * struct ghash_key const *k, u8 ctr[], + * int rounds) + */ +ENTRY(pmull_gcm_decrypt) + pmull_gcm_do_crypt 0 +ENDPROC(pmull_gcm_decrypt) + + /* + * void pmull_gcm_encrypt_block(u8 dst[], u8 src[], u8 rk[], int rounds) + */ +ENTRY(pmull_gcm_encrypt_block) + cbz x2, 0f + load_round_keys w3, x2 +0: ld1 {v0.16b}, [x1] + enc_block v0, w3 + st1 {v0.16b}, [x0] ret -ENDPROC(pmull_ghash_update) +ENDPROC(pmull_gcm_encrypt_block) diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 833ec1e3f3e9..cfc9c92814fd 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -1,7 +1,7 @@ /* * Accelerated GHASH implementation with ARMv8 PMULL instructions. * - * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -9,22 +9,33 @@ */ #include <asm/neon.h> +#include <asm/simd.h> #include <asm/unaligned.h> +#include <crypto/aes.h> +#include <crypto/algapi.h> +#include <crypto/b128ops.h> +#include <crypto/gf128mul.h> +#include <crypto/internal/aead.h> #include <crypto/internal/hash.h> +#include <crypto/internal/skcipher.h> +#include <crypto/scatterwalk.h> #include <linux/cpufeature.h> #include <linux/crypto.h> #include <linux/module.h> -MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions"); +MODULE_DESCRIPTION("GHASH and AES-GCM using ARMv8 Crypto Extensions"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("ghash"); #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 +#define GCM_IV_SIZE 12 struct ghash_key { u64 a; u64 b; + be128 k; }; struct ghash_desc_ctx { @@ -33,8 +44,35 @@ struct ghash_desc_ctx { u32 count; }; -asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src, - struct ghash_key const *k, const char *head); +struct gcm_aes_ctx { + struct crypto_aes_ctx aes_key; + struct ghash_key ghash_key; +}; + +asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, + const char *head); + +asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, + const char *head); + +static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src, + struct ghash_key const *k, + const char *head); + +asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[], + const u8 src[], struct ghash_key const *k, + u8 ctr[], int rounds, u8 ks[]); + +asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[], + const u8 src[], struct ghash_key const *k, + u8 ctr[], int rounds); + +asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[], + u32 const rk[], int rounds); + +asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds); static int ghash_init(struct shash_desc *desc) { @@ -44,6 +82,36 @@ static int ghash_init(struct shash_desc *desc) return 0; } +static void ghash_do_update(int blocks, u64 dg[], const char *src, + struct ghash_key *key, const char *head) +{ + if (likely(may_use_simd())) { + kernel_neon_begin(); + pmull_ghash_update(blocks, dg, src, key, head); + kernel_neon_end(); + } else { + be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) }; + + do { + const u8 *in = src; + + if (head) { + in = head; + blocks++; + head = NULL; + } else { + src += GHASH_BLOCK_SIZE; + } + + crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE); + gf128mul_lle(&dst, &key->k); + } while (--blocks); + + dg[0] = be64_to_cpu(dst.b); + dg[1] = be64_to_cpu(dst.a); + } +} + static int ghash_update(struct shash_desc *desc, const u8 *src, unsigned int len) { @@ -67,10 +135,9 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, blocks = len / GHASH_BLOCK_SIZE; len %= GHASH_BLOCK_SIZE; - kernel_neon_begin_partial(8); - pmull_ghash_update(blocks, ctx->digest, src, key, - partial ? ctx->buf : NULL); - kernel_neon_end(); + ghash_do_update(blocks, ctx->digest, src, key, + partial ? ctx->buf : NULL); + src += blocks * GHASH_BLOCK_SIZE; partial = 0; } @@ -89,9 +156,7 @@ static int ghash_final(struct shash_desc *desc, u8 *dst) memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial); - kernel_neon_begin_partial(8); - pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL); - kernel_neon_end(); + ghash_do_update(1, ctx->digest, ctx->buf, key, NULL); } put_unaligned_be64(ctx->digest[1], dst); put_unaligned_be64(ctx->digest[0], dst + 8); @@ -100,16 +165,13 @@ static int ghash_final(struct shash_desc *desc, u8 *dst) return 0; } -static int ghash_setkey(struct crypto_shash *tfm, - const u8 *inkey, unsigned int keylen) +static int __ghash_setkey(struct ghash_key *key, + const u8 *inkey, unsigned int keylen) { - struct ghash_key *key = crypto_shash_ctx(tfm); u64 a, b; - if (keylen != GHASH_BLOCK_SIZE) { - crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } + /* needed for the fallback */ + memcpy(&key->k, inkey, GHASH_BLOCK_SIZE); /* perform multiplication by 'x' in GF(2^128) */ b = get_unaligned_be64(inkey); @@ -124,33 +186,418 @@ static int ghash_setkey(struct crypto_shash *tfm, return 0; } +static int ghash_setkey(struct crypto_shash *tfm, + const u8 *inkey, unsigned int keylen) +{ + struct ghash_key *key = crypto_shash_ctx(tfm); + + if (keylen != GHASH_BLOCK_SIZE) { + crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + + return __ghash_setkey(key, inkey, keylen); +} + static struct shash_alg ghash_alg = { - .digestsize = GHASH_DIGEST_SIZE, - .init = ghash_init, - .update = ghash_update, - .final = ghash_final, - .setkey = ghash_setkey, - .descsize = sizeof(struct ghash_desc_ctx), - .base = { - .cra_name = "ghash", - .cra_driver_name = "ghash-ce", - .cra_priority = 200, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, - .cra_blocksize = GHASH_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct ghash_key), - .cra_module = THIS_MODULE, - }, + .base.cra_name = "ghash", + .base.cra_driver_name = "ghash-ce", + .base.cra_priority = 200, + .base.cra_flags = CRYPTO_ALG_TYPE_SHASH, + .base.cra_blocksize = GHASH_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct ghash_key), + .base.cra_module = THIS_MODULE, + + .digestsize = GHASH_DIGEST_SIZE, + .init = ghash_init, + .update = ghash_update, + .final = ghash_final, + .setkey = ghash_setkey, + .descsize = sizeof(struct ghash_desc_ctx), +}; + +static int num_rounds(struct crypto_aes_ctx *ctx) +{ + /* + * # of rounds specified by AES: + * 128 bit key 10 rounds + * 192 bit key 12 rounds + * 256 bit key 14 rounds + * => n byte key => 6 + (n/4) rounds + */ + return 6 + ctx->key_length / 4; +} + +static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey, + unsigned int keylen) +{ + struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm); + u8 key[GHASH_BLOCK_SIZE]; + int ret; + + ret = crypto_aes_expand_key(&ctx->aes_key, inkey, keylen); + if (ret) { + tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + + __aes_arm64_encrypt(ctx->aes_key.key_enc, key, (u8[AES_BLOCK_SIZE]){}, + num_rounds(&ctx->aes_key)); + + return __ghash_setkey(&ctx->ghash_key, key, sizeof(key)); +} + +static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize) +{ + switch (authsize) { + case 4: + case 8: + case 12 ... 16: + break; + default: + return -EINVAL; + } + return 0; +} + +static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[], + int *buf_count, struct gcm_aes_ctx *ctx) +{ + if (*buf_count > 0) { + int buf_added = min(count, GHASH_BLOCK_SIZE - *buf_count); + + memcpy(&buf[*buf_count], src, buf_added); + + *buf_count += buf_added; + src += buf_added; + count -= buf_added; + } + + if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) { + int blocks = count / GHASH_BLOCK_SIZE; + + ghash_do_update(blocks, dg, src, &ctx->ghash_key, + *buf_count ? buf : NULL); + + src += blocks * GHASH_BLOCK_SIZE; + count %= GHASH_BLOCK_SIZE; + *buf_count = 0; + } + + if (count > 0) { + memcpy(buf, src, count); + *buf_count = count; + } +} + +static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[]) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead); + u8 buf[GHASH_BLOCK_SIZE]; + struct scatter_walk walk; + u32 len = req->assoclen; + int buf_count = 0; + + scatterwalk_start(&walk, req->src); + + do { + u32 n = scatterwalk_clamp(&walk, len); + u8 *p; + + if (!n) { + scatterwalk_start(&walk, sg_next(walk.sg)); + n = scatterwalk_clamp(&walk, len); + } + p = scatterwalk_map(&walk); + + gcm_update_mac(dg, p, n, buf, &buf_count, ctx); + len -= n; + + scatterwalk_unmap(p); + scatterwalk_advance(&walk, n); + scatterwalk_done(&walk, 0, len); + } while (len); + + if (buf_count) { + memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count); + ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL); + } +} + +static void gcm_final(struct aead_request *req, struct gcm_aes_ctx *ctx, + u64 dg[], u8 tag[], int cryptlen) +{ + u8 mac[AES_BLOCK_SIZE]; + u128 lengths; + + lengths.a = cpu_to_be64(req->assoclen * 8); + lengths.b = cpu_to_be64(cryptlen * 8); + + ghash_do_update(1, dg, (void *)&lengths, &ctx->ghash_key, NULL); + + put_unaligned_be64(dg[1], mac); + put_unaligned_be64(dg[0], mac + 8); + + crypto_xor(tag, mac, AES_BLOCK_SIZE); +} + +static int gcm_encrypt(struct aead_request *req) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead); + struct skcipher_walk walk; + u8 iv[AES_BLOCK_SIZE]; + u8 ks[AES_BLOCK_SIZE]; + u8 tag[AES_BLOCK_SIZE]; + u64 dg[2] = {}; + int err; + + if (req->assoclen) + gcm_calculate_auth_mac(req, dg); + + memcpy(iv, req->iv, GCM_IV_SIZE); + put_unaligned_be32(1, iv + GCM_IV_SIZE); + + if (likely(may_use_simd())) { + kernel_neon_begin(); + + pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, + num_rounds(&ctx->aes_key)); + put_unaligned_be32(2, iv + GCM_IV_SIZE); + pmull_gcm_encrypt_block(ks, iv, NULL, + num_rounds(&ctx->aes_key)); + put_unaligned_be32(3, iv + GCM_IV_SIZE); + + err = skcipher_walk_aead_encrypt(&walk, req, true); + + while (walk.nbytes >= AES_BLOCK_SIZE) { + int blocks = walk.nbytes / AES_BLOCK_SIZE; + + pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr, + walk.src.virt.addr, &ctx->ghash_key, + iv, num_rounds(&ctx->aes_key), ks); + + err = skcipher_walk_done(&walk, + walk.nbytes % AES_BLOCK_SIZE); + } + kernel_neon_end(); + } else { + __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, + num_rounds(&ctx->aes_key)); + put_unaligned_be32(2, iv + GCM_IV_SIZE); + + err = skcipher_walk_aead_encrypt(&walk, req, true); + + while (walk.nbytes >= AES_BLOCK_SIZE) { + int blocks = walk.nbytes / AES_BLOCK_SIZE; + u8 *dst = walk.dst.virt.addr; + u8 *src = walk.src.virt.addr; + + do { + __aes_arm64_encrypt(ctx->aes_key.key_enc, + ks, iv, + num_rounds(&ctx->aes_key)); + crypto_xor_cpy(dst, src, ks, AES_BLOCK_SIZE); + crypto_inc(iv, AES_BLOCK_SIZE); + + dst += AES_BLOCK_SIZE; + src += AES_BLOCK_SIZE; + } while (--blocks > 0); + + ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg, + walk.dst.virt.addr, &ctx->ghash_key, + NULL); + + err = skcipher_walk_done(&walk, + walk.nbytes % AES_BLOCK_SIZE); + } + if (walk.nbytes) + __aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv, + num_rounds(&ctx->aes_key)); + } + + /* handle the tail */ + if (walk.nbytes) { + u8 buf[GHASH_BLOCK_SIZE]; + + crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, ks, + walk.nbytes); + + memcpy(buf, walk.dst.virt.addr, walk.nbytes); + memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes); + ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL); + + err = skcipher_walk_done(&walk, 0); + } + + if (err) + return err; + + gcm_final(req, ctx, dg, tag, req->cryptlen); + + /* copy authtag to end of dst */ + scatterwalk_map_and_copy(tag, req->dst, req->assoclen + req->cryptlen, + crypto_aead_authsize(aead), 1); + + return 0; +} + +static int gcm_decrypt(struct aead_request *req) +{ + struct crypto_aead *aead = crypto_aead_reqtfm(req); + struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead); + unsigned int authsize = crypto_aead_authsize(aead); + struct skcipher_walk walk; + u8 iv[AES_BLOCK_SIZE]; + u8 tag[AES_BLOCK_SIZE]; + u8 buf[GHASH_BLOCK_SIZE]; + u64 dg[2] = {}; + int err; + + if (req->assoclen) + gcm_calculate_auth_mac(req, dg); + + memcpy(iv, req->iv, GCM_IV_SIZE); + put_unaligned_be32(1, iv + GCM_IV_SIZE); + + if (likely(may_use_simd())) { + kernel_neon_begin(); + + pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, + num_rounds(&ctx->aes_key)); + put_unaligned_be32(2, iv + GCM_IV_SIZE); + + err = skcipher_walk_aead_decrypt(&walk, req, true); + + while (walk.nbytes >= AES_BLOCK_SIZE) { + int blocks = walk.nbytes / AES_BLOCK_SIZE; + + pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr, + walk.src.virt.addr, &ctx->ghash_key, + iv, num_rounds(&ctx->aes_key)); + + err = skcipher_walk_done(&walk, + walk.nbytes % AES_BLOCK_SIZE); + } + if (walk.nbytes) + pmull_gcm_encrypt_block(iv, iv, NULL, + num_rounds(&ctx->aes_key)); + + kernel_neon_end(); + } else { + __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, + num_rounds(&ctx->aes_key)); + put_unaligned_be32(2, iv + GCM_IV_SIZE); + + err = skcipher_walk_aead_decrypt(&walk, req, true); + + while (walk.nbytes >= AES_BLOCK_SIZE) { + int blocks = walk.nbytes / AES_BLOCK_SIZE; + u8 *dst = walk.dst.virt.addr; + u8 *src = walk.src.virt.addr; + + ghash_do_update(blocks, dg, walk.src.virt.addr, + &ctx->ghash_key, NULL); + + do { + __aes_arm64_encrypt(ctx->aes_key.key_enc, + buf, iv, + num_rounds(&ctx->aes_key)); + crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE); + crypto_inc(iv, AES_BLOCK_SIZE); + + dst += AES_BLOCK_SIZE; + src += AES_BLOCK_SIZE; + } while (--blocks > 0); + + err = skcipher_walk_done(&walk, + walk.nbytes % AES_BLOCK_SIZE); + } + if (walk.nbytes) + __aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv, + num_rounds(&ctx->aes_key)); + } + + /* handle the tail */ + if (walk.nbytes) { + memcpy(buf, walk.src.virt.addr, walk.nbytes); + memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes); + ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL); + + crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv, + walk.nbytes); + + err = skcipher_walk_done(&walk, 0); + } + + if (err) + return err; + + gcm_final(req, ctx, dg, tag, req->cryptlen - authsize); + + /* compare calculated auth tag with the stored one */ + scatterwalk_map_and_copy(buf, req->src, + req->assoclen + req->cryptlen - authsize, + authsize, 0); + + if (crypto_memneq(tag, buf, authsize)) + return -EBADMSG; + return 0; +} + +static struct aead_alg gcm_aes_alg = { + .ivsize = GCM_IV_SIZE, + .chunksize = AES_BLOCK_SIZE, + .maxauthsize = AES_BLOCK_SIZE, + .setkey = gcm_setkey, + .setauthsize = gcm_setauthsize, + .encrypt = gcm_encrypt, + .decrypt = gcm_decrypt, + + .base.cra_name = "gcm(aes)", + .base.cra_driver_name = "gcm-aes-ce", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct gcm_aes_ctx), + .base.cra_module = THIS_MODULE, }; static int __init ghash_ce_mod_init(void) { - return crypto_register_shash(&ghash_alg); + int ret; + + if (!(elf_hwcap & HWCAP_ASIMD)) + return -ENODEV; + + if (elf_hwcap & HWCAP_PMULL) + pmull_ghash_update = pmull_ghash_update_p64; + + else + pmull_ghash_update = pmull_ghash_update_p8; + + ret = crypto_register_shash(&ghash_alg); + if (ret) + return ret; + + if (elf_hwcap & HWCAP_PMULL) { + ret = crypto_register_aead(&gcm_aes_alg); + if (ret) + crypto_unregister_shash(&ghash_alg); + } + return ret; } static void __exit ghash_ce_mod_exit(void) { crypto_unregister_shash(&ghash_alg); + crypto_unregister_aead(&gcm_aes_alg); } -module_cpu_feature_match(PMULL, ghash_ce_mod_init); +static const struct cpu_feature ghash_cpu_feature[] = { + { cpu_feature(PMULL) }, { } +}; +MODULE_DEVICE_TABLE(cpu, ghash_cpu_feature); + +module_init(ghash_ce_mod_init); module_exit(ghash_ce_mod_exit); diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index ea319c055f5d..efbeb3e0dcfb 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -1,7 +1,7 @@ /* * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions * - * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -9,6 +9,7 @@ */ #include <asm/neon.h> +#include <asm/simd.h> #include <asm/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/sha.h> @@ -37,8 +38,11 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data, { struct sha1_ce_state *sctx = shash_desc_ctx(desc); + if (!may_use_simd()) + return crypto_sha1_update(desc, data, len); + sctx->finalize = 0; - kernel_neon_begin_partial(16); + kernel_neon_begin(); sha1_base_do_update(desc, data, len, (sha1_block_fn *)sha1_ce_transform); kernel_neon_end(); @@ -52,13 +56,16 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data, struct sha1_ce_state *sctx = shash_desc_ctx(desc); bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE); + if (!may_use_simd()) + return crypto_sha1_finup(desc, data, len, out); + /* * Allow the asm code to perform the finalization if there is no * partial data and the input is a round multiple of the block size. */ sctx->finalize = finalize; - kernel_neon_begin_partial(16); + kernel_neon_begin(); sha1_base_do_update(desc, data, len, (sha1_block_fn *)sha1_ce_transform); if (!finalize) @@ -71,8 +78,11 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out) { struct sha1_ce_state *sctx = shash_desc_ctx(desc); + if (!may_use_simd()) + return crypto_sha1_finup(desc, NULL, 0, out); + sctx->finalize = 0; - kernel_neon_begin_partial(16); + kernel_neon_begin(); sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform); kernel_neon_end(); return sha1_base_finish(desc, out); diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index 0ed9486f75dd..fd1ff2b13dfa 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -1,7 +1,7 @@ /* * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions * - * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org> + * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -9,6 +9,7 @@ */ #include <asm/neon.h> +#include <asm/simd.h> #include <asm/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/sha.h> @@ -34,13 +35,19 @@ const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state, const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state, finalize); +asmlinkage void sha256_block_data_order(u32 *digest, u8 const *src, int blocks); + static int sha256_ce_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct sha256_ce_state *sctx = shash_desc_ctx(desc); + if (!may_use_simd()) + return sha256_base_do_update(desc, data, len, + (sha256_block_fn *)sha256_block_data_order); + sctx->finalize = 0; - kernel_neon_begin_partial(28); + kernel_neon_begin(); sha256_base_do_update(desc, data, len, (sha256_block_fn *)sha2_ce_transform); kernel_neon_end(); @@ -54,13 +61,22 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data, struct sha256_ce_state *sctx = shash_desc_ctx(desc); bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE); + if (!may_use_simd()) { + if (len) + sha256_base_do_update(desc, data, len, + (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_finalize(desc, + (sha256_block_fn *)sha256_block_data_order); + return sha256_base_finish(desc, out); + } + /* * Allow the asm code to perform the finalization if there is no * partial data and the input is a round multiple of the block size. */ sctx->finalize = finalize; - kernel_neon_begin_partial(28); + kernel_neon_begin(); sha256_base_do_update(desc, data, len, (sha256_block_fn *)sha2_ce_transform); if (!finalize) @@ -74,8 +90,14 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out) { struct sha256_ce_state *sctx = shash_desc_ctx(desc); + if (!may_use_simd()) { + sha256_base_do_finalize(desc, + (sha256_block_fn *)sha256_block_data_order); + return sha256_base_finish(desc, out); + } + sctx->finalize = 0; - kernel_neon_begin_partial(28); + kernel_neon_begin(); sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform); kernel_neon_end(); return sha256_base_finish(desc, out); diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c index a2226f841960..b064d925fe2a 100644 --- a/arch/arm64/crypto/sha256-glue.c +++ b/arch/arm64/crypto/sha256-glue.c @@ -29,6 +29,7 @@ MODULE_ALIAS_CRYPTO("sha256"); asmlinkage void sha256_block_data_order(u32 *digest, const void *data, unsigned int num_blks); +EXPORT_SYMBOL(sha256_block_data_order); asmlinkage void sha256_block_neon(u32 *digest, const void *data, unsigned int num_blks); diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index b02a9268dfbf..783de51a6c4e 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -44,8 +44,12 @@ #define A64_COND_NE AARCH64_INSN_COND_NE /* != */ #define A64_COND_CS AARCH64_INSN_COND_CS /* unsigned >= */ #define A64_COND_HI AARCH64_INSN_COND_HI /* unsigned > */ +#define A64_COND_LS AARCH64_INSN_COND_LS /* unsigned <= */ +#define A64_COND_CC AARCH64_INSN_COND_CC /* unsigned < */ #define A64_COND_GE AARCH64_INSN_COND_GE /* signed >= */ #define A64_COND_GT AARCH64_INSN_COND_GT /* signed > */ +#define A64_COND_LE AARCH64_INSN_COND_LE /* signed <= */ +#define A64_COND_LT AARCH64_INSN_COND_LT /* signed < */ #define A64_B_(cond, imm19) A64_COND_BRANCH(cond, (imm19) << 2) /* Unconditional branch (immediate) */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index f32144b2e07f..ba38d403abb2 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -527,10 +527,14 @@ emit_bswap_uxt: /* IF (dst COND src) JUMP off */ case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: emit(A64_CMP(1, dst, src), ctx); emit_cond_jmp: jmp_offset = bpf2a64_offset(i + off, i, ctx); @@ -542,9 +546,15 @@ emit_cond_jmp: case BPF_JGT: jmp_cond = A64_COND_HI; break; + case BPF_JLT: + jmp_cond = A64_COND_CC; + break; case BPF_JGE: jmp_cond = A64_COND_CS; break; + case BPF_JLE: + jmp_cond = A64_COND_LS; + break; case BPF_JSET: case BPF_JNE: jmp_cond = A64_COND_NE; @@ -552,9 +562,15 @@ emit_cond_jmp: case BPF_JSGT: jmp_cond = A64_COND_GT; break; + case BPF_JSLT: + jmp_cond = A64_COND_LT; + break; case BPF_JSGE: jmp_cond = A64_COND_GE; break; + case BPF_JSLE: + jmp_cond = A64_COND_LE; + break; default: return -EFAULT; } @@ -566,10 +582,14 @@ emit_cond_jmp: /* IF (dst COND imm) JUMP off */ case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: emit_a64_mov_i(1, tmp, imm, ctx); emit(A64_CMP(1, dst, tmp), ctx); goto emit_cond_jmp; diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index f1e3b20dce9f..9abf02d6855a 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -102,5 +102,7 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 5dd5c5d0d642..002eb85a6941 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -111,4 +111,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index f8f7b47e247f..e268e51a38d1 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -102,4 +102,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 882823bec153..6c755bc07975 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -120,4 +120,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 3f87b96da5c4..7646891c4e9b 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -113,6 +113,7 @@ struct jit_ctx { u64 *reg_val_types; unsigned int long_b_conversion:1; unsigned int gen_b_offsets:1; + unsigned int use_bbit_insns:1; }; static void set_reg_val_type(u64 *rvt, int reg, enum reg_val_type type) @@ -655,19 +656,6 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int this_idx) return build_int_epilogue(ctx, MIPS_R_T9); } -static bool use_bbit_insns(void) -{ - switch (current_cpu_type()) { - case CPU_CAVIUM_OCTEON: - case CPU_CAVIUM_OCTEON_PLUS: - case CPU_CAVIUM_OCTEON2: - case CPU_CAVIUM_OCTEON3: - return true; - default: - return false; - } -} - static bool is_bad_offset(int b_off) { return b_off > 0x1ffff || b_off < -0x20000; @@ -682,6 +670,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, unsigned int target; u64 t64; s64 t64s; + int bpf_op = BPF_OP(insn->code); switch (insn->code) { case BPF_ALU64 | BPF_ADD | BPF_K: /* ALU64_IMM */ @@ -770,13 +759,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, sll, dst, dst, 0); if (insn->imm == 1) { /* div by 1 is a nop, mod by 1 is zero */ - if (BPF_OP(insn->code) == BPF_MOD) + if (bpf_op == BPF_MOD) emit_instr(ctx, addu, dst, MIPS_R_ZERO, MIPS_R_ZERO); break; } gen_imm_to_reg(insn, MIPS_R_AT, ctx); emit_instr(ctx, divu, dst, MIPS_R_AT); - if (BPF_OP(insn->code) == BPF_DIV) + if (bpf_op == BPF_DIV) emit_instr(ctx, mflo, dst); else emit_instr(ctx, mfhi, dst); @@ -798,13 +787,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (insn->imm == 1) { /* div by 1 is a nop, mod by 1 is zero */ - if (BPF_OP(insn->code) == BPF_MOD) + if (bpf_op == BPF_MOD) emit_instr(ctx, addu, dst, MIPS_R_ZERO, MIPS_R_ZERO); break; } gen_imm_to_reg(insn, MIPS_R_AT, ctx); emit_instr(ctx, ddivu, dst, MIPS_R_AT); - if (BPF_OP(insn->code) == BPF_DIV) + if (bpf_op == BPF_DIV) emit_instr(ctx, mflo, dst); else emit_instr(ctx, mfhi, dst); @@ -829,7 +818,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); did_move = false; if (insn->src_reg == BPF_REG_10) { - if (BPF_OP(insn->code) == BPF_MOV) { + if (bpf_op == BPF_MOV) { emit_instr(ctx, daddiu, dst, MIPS_R_SP, MAX_BPF_STACK); did_move = true; } else { @@ -839,7 +828,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, } else if (get_reg_val_type(ctx, this_idx, insn->src_reg) == REG_32BIT) { int tmp_reg = MIPS_R_AT; - if (BPF_OP(insn->code) == BPF_MOV) { + if (bpf_op == BPF_MOV) { tmp_reg = dst; did_move = true; } @@ -847,7 +836,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, dinsu, tmp_reg, MIPS_R_ZERO, 32, 32); src = MIPS_R_AT; } - switch (BPF_OP(insn->code)) { + switch (bpf_op) { case BPF_MOV: if (!did_move) emit_instr(ctx, daddu, dst, src, MIPS_R_ZERO); @@ -879,7 +868,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off); emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src); emit_instr(ctx, ddivu, dst, src); - if (BPF_OP(insn->code) == BPF_DIV) + if (bpf_op == BPF_DIV) emit_instr(ctx, mflo, dst); else emit_instr(ctx, mfhi, dst); @@ -923,7 +912,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (ts == REG_64BIT || ts == REG_32BIT_ZERO_EX) { int tmp_reg = MIPS_R_AT; - if (BPF_OP(insn->code) == BPF_MOV) { + if (bpf_op == BPF_MOV) { tmp_reg = dst; did_move = true; } @@ -931,7 +920,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, sll, tmp_reg, src, 0); src = MIPS_R_AT; } - switch (BPF_OP(insn->code)) { + switch (bpf_op) { case BPF_MOV: if (!did_move) emit_instr(ctx, addu, dst, src, MIPS_R_ZERO); @@ -962,7 +951,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off); emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src); emit_instr(ctx, divu, dst, src); - if (BPF_OP(insn->code) == BPF_DIV) + if (bpf_op == BPF_DIV) emit_instr(ctx, mflo, dst); else emit_instr(ctx, mfhi, dst); @@ -989,7 +978,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, break; case BPF_JMP | BPF_JEQ | BPF_K: /* JMP_IMM */ case BPF_JMP | BPF_JNE | BPF_K: /* JMP_IMM */ - cmp_eq = (BPF_OP(insn->code) == BPF_JEQ); + cmp_eq = (bpf_op == BPF_JEQ); dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); if (dst < 0) return dst; @@ -1002,8 +991,12 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, goto jeq_common; case BPF_JMP | BPF_JEQ | BPF_X: /* JMP_REG */ case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: case BPF_JMP | BPF_JSGT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JSET | BPF_X: @@ -1020,33 +1013,39 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, sll, MIPS_R_AT, dst, 0); dst = MIPS_R_AT; } - if (BPF_OP(insn->code) == BPF_JSET) { + if (bpf_op == BPF_JSET) { emit_instr(ctx, and, MIPS_R_AT, dst, src); cmp_eq = false; dst = MIPS_R_AT; src = MIPS_R_ZERO; - } else if (BPF_OP(insn->code) == BPF_JSGT) { + } else if (bpf_op == BPF_JSGT || bpf_op == BPF_JSLE) { emit_instr(ctx, dsubu, MIPS_R_AT, dst, src); if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) { b_off = b_imm(exit_idx, ctx); if (is_bad_offset(b_off)) return -E2BIG; - emit_instr(ctx, blez, MIPS_R_AT, b_off); + if (bpf_op == BPF_JSGT) + emit_instr(ctx, blez, MIPS_R_AT, b_off); + else + emit_instr(ctx, bgtz, MIPS_R_AT, b_off); emit_instr(ctx, nop); return 2; /* We consumed the exit. */ } b_off = b_imm(this_idx + insn->off + 1, ctx); if (is_bad_offset(b_off)) return -E2BIG; - emit_instr(ctx, bgtz, MIPS_R_AT, b_off); + if (bpf_op == BPF_JSGT) + emit_instr(ctx, bgtz, MIPS_R_AT, b_off); + else + emit_instr(ctx, blez, MIPS_R_AT, b_off); emit_instr(ctx, nop); break; - } else if (BPF_OP(insn->code) == BPF_JSGE) { + } else if (bpf_op == BPF_JSGE || bpf_op == BPF_JSLT) { emit_instr(ctx, slt, MIPS_R_AT, dst, src); - cmp_eq = true; + cmp_eq = bpf_op == BPF_JSGE; dst = MIPS_R_AT; src = MIPS_R_ZERO; - } else if (BPF_OP(insn->code) == BPF_JGT) { + } else if (bpf_op == BPF_JGT || bpf_op == BPF_JLE) { /* dst or src could be AT */ emit_instr(ctx, dsubu, MIPS_R_T8, dst, src); emit_instr(ctx, sltu, MIPS_R_AT, dst, src); @@ -1054,16 +1053,16 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit_instr(ctx, movz, MIPS_R_T9, MIPS_R_SP, MIPS_R_T8); emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_ZERO, MIPS_R_T8); emit_instr(ctx, or, MIPS_R_AT, MIPS_R_T9, MIPS_R_AT); - cmp_eq = true; + cmp_eq = bpf_op == BPF_JGT; dst = MIPS_R_AT; src = MIPS_R_ZERO; - } else if (BPF_OP(insn->code) == BPF_JGE) { + } else if (bpf_op == BPF_JGE || bpf_op == BPF_JLT) { emit_instr(ctx, sltu, MIPS_R_AT, dst, src); - cmp_eq = true; + cmp_eq = bpf_op == BPF_JGE; dst = MIPS_R_AT; src = MIPS_R_ZERO; } else { /* JNE/JEQ case */ - cmp_eq = (BPF_OP(insn->code) == BPF_JEQ); + cmp_eq = (bpf_op == BPF_JEQ); } jeq_common: /* @@ -1122,7 +1121,9 @@ jeq_common: break; case BPF_JMP | BPF_JSGT | BPF_K: /* JMP_IMM */ case BPF_JMP | BPF_JSGE | BPF_K: /* JMP_IMM */ - cmp_eq = (BPF_OP(insn->code) == BPF_JSGE); + case BPF_JMP | BPF_JSLT | BPF_K: /* JMP_IMM */ + case BPF_JMP | BPF_JSLE | BPF_K: /* JMP_IMM */ + cmp_eq = (bpf_op == BPF_JSGE); dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); if (dst < 0) return dst; @@ -1132,65 +1133,92 @@ jeq_common: b_off = b_imm(exit_idx, ctx); if (is_bad_offset(b_off)) return -E2BIG; - if (cmp_eq) - emit_instr(ctx, bltz, dst, b_off); - else + switch (bpf_op) { + case BPF_JSGT: emit_instr(ctx, blez, dst, b_off); + break; + case BPF_JSGE: + emit_instr(ctx, bltz, dst, b_off); + break; + case BPF_JSLT: + emit_instr(ctx, bgez, dst, b_off); + break; + case BPF_JSLE: + emit_instr(ctx, bgtz, dst, b_off); + break; + } emit_instr(ctx, nop); return 2; /* We consumed the exit. */ } b_off = b_imm(this_idx + insn->off + 1, ctx); if (is_bad_offset(b_off)) return -E2BIG; - if (cmp_eq) - emit_instr(ctx, bgez, dst, b_off); - else + switch (bpf_op) { + case BPF_JSGT: emit_instr(ctx, bgtz, dst, b_off); + break; + case BPF_JSGE: + emit_instr(ctx, bgez, dst, b_off); + break; + case BPF_JSLT: + emit_instr(ctx, bltz, dst, b_off); + break; + case BPF_JSLE: + emit_instr(ctx, blez, dst, b_off); + break; + } emit_instr(ctx, nop); break; } /* * only "LT" compare available, so we must use imm + 1 - * to generate "GT" + * to generate "GT" and imm -1 to generate LE */ - t64s = insn->imm + (cmp_eq ? 0 : 1); + if (bpf_op == BPF_JSGT) + t64s = insn->imm + 1; + else if (bpf_op == BPF_JSLE) + t64s = insn->imm + 1; + else + t64s = insn->imm; + + cmp_eq = bpf_op == BPF_JSGT || bpf_op == BPF_JSGE; if (t64s >= S16_MIN && t64s <= S16_MAX) { emit_instr(ctx, slti, MIPS_R_AT, dst, (int)t64s); src = MIPS_R_AT; dst = MIPS_R_ZERO; - cmp_eq = true; goto jeq_common; } emit_const_to_reg(ctx, MIPS_R_AT, (u64)t64s); emit_instr(ctx, slt, MIPS_R_AT, dst, MIPS_R_AT); src = MIPS_R_AT; dst = MIPS_R_ZERO; - cmp_eq = true; goto jeq_common; case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: - cmp_eq = (BPF_OP(insn->code) == BPF_JGE); + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: + cmp_eq = (bpf_op == BPF_JGE); dst = ebpf_to_mips_reg(ctx, insn, dst_reg_fp_ok); if (dst < 0) return dst; /* * only "LT" compare available, so we must use imm + 1 - * to generate "GT" + * to generate "GT" and imm -1 to generate LE */ - t64s = (u64)(u32)(insn->imm) + (cmp_eq ? 0 : 1); - if (t64s >= 0 && t64s <= S16_MAX) { - emit_instr(ctx, sltiu, MIPS_R_AT, dst, (int)t64s); - src = MIPS_R_AT; - dst = MIPS_R_ZERO; - cmp_eq = true; - goto jeq_common; - } + if (bpf_op == BPF_JGT) + t64s = (u64)(u32)(insn->imm) + 1; + else if (bpf_op == BPF_JLE) + t64s = (u64)(u32)(insn->imm) + 1; + else + t64s = (u64)(u32)(insn->imm); + + cmp_eq = bpf_op == BPF_JGT || bpf_op == BPF_JGE; + emit_const_to_reg(ctx, MIPS_R_AT, (u64)t64s); emit_instr(ctx, sltu, MIPS_R_AT, dst, MIPS_R_AT); src = MIPS_R_AT; dst = MIPS_R_ZERO; - cmp_eq = true; goto jeq_common; case BPF_JMP | BPF_JSET | BPF_K: /* JMP_IMM */ @@ -1198,7 +1226,7 @@ jeq_common: if (dst < 0) return dst; - if (use_bbit_insns() && hweight32((u32)insn->imm) == 1) { + if (ctx->use_bbit_insns && hweight32((u32)insn->imm) == 1) { if ((insn + 1)->code == (BPF_JMP | BPF_EXIT) && insn->off == 1) { b_off = b_imm(exit_idx, ctx); if (is_bad_offset(b_off)) @@ -1724,10 +1752,14 @@ static int reg_val_propagate_range(struct jit_ctx *ctx, u64 initial_rvt, case BPF_JEQ: case BPF_JGT: case BPF_JGE: + case BPF_JLT: + case BPF_JLE: case BPF_JSET: case BPF_JNE: case BPF_JSGT: case BPF_JSGE: + case BPF_JSLT: + case BPF_JSLE: if (follow_taken) { rvt[idx] |= RVT_BRANCH_TAKEN; idx += insn->off; @@ -1853,6 +1885,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) memset(&ctx, 0, sizeof(ctx)); + preempt_disable(); + switch (current_cpu_type()) { + case CPU_CAVIUM_OCTEON: + case CPU_CAVIUM_OCTEON_PLUS: + case CPU_CAVIUM_OCTEON2: + case CPU_CAVIUM_OCTEON3: + ctx.use_bbit_insns = 1; + break; + default: + ctx.use_bbit_insns = 0; + } + preempt_enable(); + ctx.offsets = kcalloc(prog->len + 1, sizeof(*ctx.offsets), GFP_KERNEL); if (ctx.offsets == NULL) goto out_err; diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index c710db354ff2..ac82a3f26dbf 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -102,4 +102,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/configs/c3000_defconfig b/arch/parisc/configs/c3000_defconfig index 0764d3971cf6..8d41a73bd71b 100644 --- a/arch/parisc/configs/c3000_defconfig +++ b/arch/parisc/configs/c3000_defconfig @@ -31,7 +31,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_INET6_IPCOMP=m CONFIG_IPV6_TUNNEL=m CONFIG_NETFILTER=y -CONFIG_NETFILTER_DEBUG=y CONFIG_NET_PKTGEN=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index a0d4dc9f4eb2..3b2bf7ae703b 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -101,4 +101,6 @@ #define SO_PEERGROUPS 0x4034 +#define SO_ZEROCOPY 0x4035 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 30cf03f53428..47fc6660845d 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -263,6 +263,7 @@ static inline bool is_nearbranch(int offset) #define COND_EQ (CR0_EQ | COND_CMP_TRUE) #define COND_NE (CR0_EQ | COND_CMP_FALSE) #define COND_LT (CR0_LT | COND_CMP_TRUE) +#define COND_LE (CR0_GT | COND_CMP_FALSE) #endif diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 861c5af1c9c4..faf20163bd4c 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -795,12 +795,24 @@ emit_clear: case BPF_JMP | BPF_JSGT | BPF_X: true_cond = COND_GT; goto cond_branch; + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_X: + true_cond = COND_LT; + goto cond_branch; case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSGE | BPF_X: true_cond = COND_GE; goto cond_branch; + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_X: + true_cond = COND_LE; + goto cond_branch; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: true_cond = COND_EQ; @@ -817,14 +829,18 @@ emit_clear: cond_branch: switch (code) { case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: /* unsigned comparison */ PPC_CMPLD(dst_reg, src_reg); break; case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: /* signed comparison */ PPC_CMPD(dst_reg, src_reg); break; @@ -834,7 +850,9 @@ cond_branch: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: /* * Need sign-extended load, so only positive * values can be used as imm in cmpldi @@ -849,7 +867,9 @@ cond_branch: } break; case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: /* * signed comparison, so any 16-bit value * can be used in cmpdi diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index ae2f740a82f1..5ffcdeb1eb17 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1749,7 +1749,7 @@ out: static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file_inode(file); - int err = filemap_write_and_wait_range(inode->i_mapping, start, end); + int err = file_write_and_wait_range(file, start, end); if (!err) { inode_lock(inode); err = spufs_mfc_flush(file, NULL); diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 52a63f4175cb..a56916c83565 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -108,4 +108,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 1803797fc885..8ec88497a28d 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1093,15 +1093,27 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i case BPF_JMP | BPF_JSGT | BPF_K: /* ((s64) dst > (s64) imm) */ mask = 0x2000; /* jh */ goto branch_ks; + case BPF_JMP | BPF_JSLT | BPF_K: /* ((s64) dst < (s64) imm) */ + mask = 0x4000; /* jl */ + goto branch_ks; case BPF_JMP | BPF_JSGE | BPF_K: /* ((s64) dst >= (s64) imm) */ mask = 0xa000; /* jhe */ goto branch_ks; + case BPF_JMP | BPF_JSLE | BPF_K: /* ((s64) dst <= (s64) imm) */ + mask = 0xc000; /* jle */ + goto branch_ks; case BPF_JMP | BPF_JGT | BPF_K: /* (dst_reg > imm) */ mask = 0x2000; /* jh */ goto branch_ku; + case BPF_JMP | BPF_JLT | BPF_K: /* (dst_reg < imm) */ + mask = 0x4000; /* jl */ + goto branch_ku; case BPF_JMP | BPF_JGE | BPF_K: /* (dst_reg >= imm) */ mask = 0xa000; /* jhe */ goto branch_ku; + case BPF_JMP | BPF_JLE | BPF_K: /* (dst_reg <= imm) */ + mask = 0xc000; /* jle */ + goto branch_ku; case BPF_JMP | BPF_JNE | BPF_K: /* (dst_reg != imm) */ mask = 0x7000; /* jne */ goto branch_ku; @@ -1119,15 +1131,27 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i case BPF_JMP | BPF_JSGT | BPF_X: /* ((s64) dst > (s64) src) */ mask = 0x2000; /* jh */ goto branch_xs; + case BPF_JMP | BPF_JSLT | BPF_X: /* ((s64) dst < (s64) src) */ + mask = 0x4000; /* jl */ + goto branch_xs; case BPF_JMP | BPF_JSGE | BPF_X: /* ((s64) dst >= (s64) src) */ mask = 0xa000; /* jhe */ goto branch_xs; + case BPF_JMP | BPF_JSLE | BPF_X: /* ((s64) dst <= (s64) src) */ + mask = 0xc000; /* jle */ + goto branch_xs; case BPF_JMP | BPF_JGT | BPF_X: /* (dst > src) */ mask = 0x2000; /* jh */ goto branch_xu; + case BPF_JMP | BPF_JLT | BPF_X: /* (dst < src) */ + mask = 0x4000; /* jl */ + goto branch_xu; case BPF_JMP | BPF_JGE | BPF_X: /* (dst >= src) */ mask = 0xa000; /* jhe */ goto branch_xu; + case BPF_JMP | BPF_JLE | BPF_X: /* (dst <= src) */ + mask = 0xc000; /* jle */ + goto branch_xu; case BPF_JMP | BPF_JNE | BPF_X: /* (dst != src) */ mask = 0x7000; /* jne */ goto branch_xu; diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig index 75c92fc1876b..56b5e4ce8d4a 100644 --- a/arch/sh/configs/se7751_defconfig +++ b/arch/sh/configs/se7751_defconfig @@ -28,7 +28,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y -CONFIG_NETFILTER_DEBUG=y CONFIG_IP_NF_QUEUE=y CONFIG_MTD=y CONFIG_MTD_PARTITIONS=y diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c index c90930de76ba..3cd4f6b198b6 100644 --- a/arch/sparc/crypto/aes_glue.c +++ b/arch/sparc/crypto/aes_glue.c @@ -344,8 +344,7 @@ static void ctr_crypt_final(struct crypto_sparc64_aes_ctx *ctx, ctx->ops->ecb_encrypt(&ctx->key[0], (const u64 *)ctrblk, keystream, AES_BLOCK_SIZE); - crypto_xor((u8 *) keystream, src, nbytes); - memcpy(dst, keystream, nbytes); + crypto_xor_cpy(dst, (u8 *) keystream, src, nbytes); crypto_inc(ctrblk, AES_BLOCK_SIZE); } diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 186fd8199f54..b2f5c50d0947 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -98,6 +98,8 @@ #define SO_PEERGROUPS 0x003d +#define SO_ZEROCOPY 0x003e + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 8799ae9a8788..c340af7b1371 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -128,6 +128,8 @@ static u32 WDISP10(u32 off) #define BA (BRANCH | CONDA) #define BG (BRANCH | CONDG) +#define BL (BRANCH | CONDL) +#define BLE (BRANCH | CONDLE) #define BGU (BRANCH | CONDGU) #define BLEU (BRANCH | CONDLEU) #define BGE (BRANCH | CONDGE) @@ -715,9 +717,15 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src, case BPF_JGT: br_opcode = BGU; break; + case BPF_JLT: + br_opcode = BLU; + break; case BPF_JGE: br_opcode = BGEU; break; + case BPF_JLE: + br_opcode = BLEU; + break; case BPF_JSET: case BPF_JNE: br_opcode = BNE; @@ -725,9 +733,15 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src, case BPF_JSGT: br_opcode = BG; break; + case BPF_JSLT: + br_opcode = BL; + break; case BPF_JSGE: br_opcode = BGE; break; + case BPF_JSLE: + br_opcode = BLE; + break; default: /* Make sure we dont leak kernel information to the * user. @@ -746,18 +760,30 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src, case BPF_JGT: cbcond_opcode = CBCONDGU; break; + case BPF_JLT: + cbcond_opcode = CBCONDLU; + break; case BPF_JGE: cbcond_opcode = CBCONDGEU; break; + case BPF_JLE: + cbcond_opcode = CBCONDLEU; + break; case BPF_JNE: cbcond_opcode = CBCONDNE; break; case BPF_JSGT: cbcond_opcode = CBCONDG; break; + case BPF_JSLT: + cbcond_opcode = CBCONDL; + break; case BPF_JSGE: cbcond_opcode = CBCONDGE; break; + case BPF_JSLE: + cbcond_opcode = CBCONDLE; + break; default: /* Make sure we dont leak kernel information to the * user. @@ -1176,10 +1202,14 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) /* IF (dst COND src) JUMP off */ case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: case BPF_JMP | BPF_JSET | BPF_X: { int err; @@ -1191,10 +1221,14 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) /* IF (dst COND imm) JUMP off */ case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: { int err; diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 4a55cdcdc008..5c15d6b57329 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -475,8 +475,8 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx, unsigned int nbytes = walk->nbytes; aesni_enc(ctx, keystream, ctrblk); - crypto_xor(keystream, src, nbytes); - memcpy(dst, keystream, nbytes); + crypto_xor_cpy(dst, keystream, src, nbytes); + crypto_inc(ctrblk, AES_BLOCK_SIZE); } diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index 17c05531dfd1..f9eca34301e2 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -271,8 +271,7 @@ static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk) unsigned int nbytes = walk->nbytes; blowfish_enc_blk(ctx, keystream, ctrblk); - crypto_xor(keystream, src, nbytes); - memcpy(dst, keystream, nbytes); + crypto_xor_cpy(dst, keystream, src, nbytes); crypto_inc(ctrblk, BF_BLOCK_SIZE); } diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 8648158f3916..dbea6020ffe7 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -256,8 +256,7 @@ static void ctr_crypt_final(struct blkcipher_desc *desc, unsigned int nbytes = walk->nbytes; __cast5_encrypt(ctx, keystream, ctrblk); - crypto_xor(keystream, src, nbytes); - memcpy(dst, keystream, nbytes); + crypto_xor_cpy(dst, keystream, src, nbytes); crypto_inc(ctrblk, CAST5_BLOCK_SIZE); } diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c index d6fc59aaaadf..30c0a37f4882 100644 --- a/arch/x86/crypto/des3_ede_glue.c +++ b/arch/x86/crypto/des3_ede_glue.c @@ -277,8 +277,7 @@ static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx, unsigned int nbytes = walk->nbytes; des3_ede_enc_blk(ctx, keystream, ctrblk); - crypto_xor(keystream, src, nbytes); - memcpy(dst, keystream, nbytes); + crypto_xor_cpy(dst, keystream, src, nbytes); crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE); } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d23e61dc0640..4893abf7f74f 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -198,6 +198,8 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) cr4_set_bits(mask); } +extern void initialize_tlbstate_and_flush(void); + static inline void __native_flush_tlb(void) { /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index efba8e3da3e2..fb1d3358a4af 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -333,6 +333,19 @@ static void setup_pcid(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_PCID)) { if (cpu_has(c, X86_FEATURE_PGE)) { + /* + * We'd like to use cr4_set_bits_and_update_boot(), + * but we can't. CR4.PCIDE is special and can only + * be set in long mode, and the early CPU init code + * doesn't know this and would try to restore CR4.PCIDE + * prior to entering long mode. + * + * Instead, we rely on the fact that hotplug, resume, + * etc all fully restore CR4 before they write anything + * that could have nonzero PCID bits to CR3. CR4.PCIDE + * has no effect on the page tables themselves, so we + * don't need it to be restored early. + */ cr4_set_bits(X86_CR4_PCIDE); } else { /* @@ -1583,6 +1596,7 @@ void cpu_init(void) mmgrab(&init_mm); me->active_mm = &init_mm; BUG_ON(me->mm); + initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, me); load_sp0(t, ¤t->thread); @@ -1637,6 +1651,7 @@ void cpu_init(void) mmgrab(&init_mm); curr->active_mm = &init_mm; BUG_ON(curr->mm); + initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, curr); load_sp0(t, thread); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index ce104b962a17..dbbcfd59726a 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -214,6 +214,50 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* + * Call this when reinitializing a CPU. It fixes the following potential + * problems: + * + * - The ASID changed from what cpu_tlbstate thinks it is (most likely + * because the CPU was taken down and came back up with CR3's PCID + * bits clear. CPU hotplug can do this. + * + * - The TLB contains junk in slots corresponding to inactive ASIDs. + * + * - The CPU went so far out to lunch that it may have missed a TLB + * flush. + */ +void initialize_tlbstate_and_flush(void) +{ + int i; + struct mm_struct *mm = this_cpu_read(cpu_tlbstate.loaded_mm); + u64 tlb_gen = atomic64_read(&init_mm.context.tlb_gen); + unsigned long cr3 = __read_cr3(); + + /* Assert that CR3 already references the right mm. */ + WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd)); + + /* + * Assert that CR4.PCIDE is set if needed. (CR4.PCIDE initialization + * doesn't work like other CR4 bits because it can only be set from + * long mode.) + */ + WARN_ON(boot_cpu_has(X86_CR4_PCIDE) && + !(cr4_read_shadow() & X86_CR4_PCIDE)); + + /* Force ASID 0 and force a TLB flush. */ + write_cr3(cr3 & ~CR3_PCID_MASK); + + /* Reinitialize tlbstate. */ + this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); + this_cpu_write(cpu_tlbstate.next_asid, 1); + this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); + this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen); + + for (i = 1; i < TLB_NR_DYN_ASIDS; i++) + this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0); +} + +/* * flush_tlb_func_common()'s memory ordering requirement is that any * TLB fills that happen after we flush the TLB are ordered after we * read active_mm's tlb_gen. We don't need any explicit barriers diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e1324f280e06..8c9573660d51 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -94,7 +94,9 @@ static int bpf_size_to_x86_bytes(int bpf_size) #define X86_JNE 0x75 #define X86_JBE 0x76 #define X86_JA 0x77 +#define X86_JL 0x7C #define X86_JGE 0x7D +#define X86_JLE 0x7E #define X86_JG 0x7F static void bpf_flush_icache(void *start, void *end) @@ -285,7 +287,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ offsetof(struct bpf_array, map.max_entries)); EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ -#define OFFSET1 47 /* number of bytes to jump */ +#define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -294,21 +296,20 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 36 +#define OFFSET2 32 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, 36); /* mov dword ptr [rbp + 36], eax */ /* prog = array->ptrs[index]; */ - EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */ offsetof(struct bpf_array, ptrs)); - EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) * goto out; */ - EMIT4(0x48, 0x83, 0xF8, 0x00); /* cmp rax, 0 */ + EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ #define OFFSET3 10 EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; @@ -888,9 +889,13 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: /* cmp dst_reg, src_reg */ EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39, add_2reg(0xC0, dst_reg, src_reg)); @@ -911,9 +916,13 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: /* cmp dst_reg, imm8/32 */ EMIT1(add_1mod(0x48, dst_reg)); @@ -935,18 +944,34 @@ emit_cond_jmp: /* convert BPF opcode to x86 */ /* GT is unsigned '>', JA in x86 */ jmp_cond = X86_JA; break; + case BPF_JLT: + /* LT is unsigned '<', JB in x86 */ + jmp_cond = X86_JB; + break; case BPF_JGE: /* GE is unsigned '>=', JAE in x86 */ jmp_cond = X86_JAE; break; + case BPF_JLE: + /* LE is unsigned '<=', JBE in x86 */ + jmp_cond = X86_JBE; + break; case BPF_JSGT: /* signed '>', GT in x86 */ jmp_cond = X86_JG; break; + case BPF_JSLT: + /* signed '<', LT in x86 */ + jmp_cond = X86_JL; + break; case BPF_JSGE: /* signed '>=', GE in x86 */ jmp_cond = X86_JGE; break; + case BPF_JSLE: + /* signed '<=', LE in x86 */ + jmp_cond = X86_JLE; + break; default: /* to silence gcc warning */ return -EFAULT; } diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 78459a6d455a..4d68d59f457d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -181,6 +181,7 @@ static void fix_processor_context(void) #endif load_TR_desc(); /* This does ltr */ load_mm_ldt(current->active_mm); /* This does lldt */ + initialize_tlbstate_and_flush(); fpu__resume_cpu(); diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 3eed2761c149..220059999e74 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -113,4 +113,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* _XTENSA_SOCKET_H */ |