diff options
Diffstat (limited to 'arch/arm64')
77 files changed, 4043 insertions, 1124 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3f047afb982c..fcc6635666b4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -67,7 +67,7 @@ config ARM64 select ARCH_USE_QUEUED_SPINLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_SUPPORTS_ATOMIC_RMW - select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG) select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT @@ -143,6 +143,8 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS \ + if $(cc-option,-fpatchable-function-entry=2) select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD @@ -266,6 +268,10 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y +config ZONE_DMA + bool "Support DMA zone" if EXPERT + default y + config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y @@ -538,6 +544,16 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. +config ARM64_ERRATUM_1319367 + bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" + default y + help + This option adds work arounds for ARM Cortex-A57 erratum 1319537 + and A72 erratum 1319367 + + Cortex-A57 and A72 cores could end-up with corrupted TLBs by + speculating an AT instruction during a guest context switch. + If unsure, say Y. config ARM64_ERRATUM_1463225 @@ -558,6 +574,22 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. +config ARM64_ERRATUM_1542419 + bool "Neoverse-N1: workaround mis-ordering of instruction fetches" + default y + help + This option adds a workaround for ARM Neoverse-N1 erratum + 1542419. + + Affected Neoverse-N1 cores could execute a stale instruction when + modified by another CPU. The workaround depends on a firmware + counterpart. + + Workaround the issue by hiding the DIC feature from EL0. This + forces user-space to perform cache maintenance. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -845,10 +877,26 @@ config ARM64_PA_BITS default 48 if ARM64_PA_BITS_48 default 52 if ARM64_PA_BITS_52 +choice + prompt "Endianness" + default CPU_LITTLE_ENDIAN + help + Select the endianness of data accesses performed by the CPU. Userspace + applications will need to be compiled and linked for the endianness + that is selected here. + config CPU_BIG_ENDIAN bool "Build big-endian kernel" help - Say Y if you plan on running a kernel in big-endian mode. + Say Y if you plan on running a kernel with a big-endian userspace. + +config CPU_LITTLE_ENDIAN + bool "Build little-endian kernel" + help + Say Y if you plan on running a kernel with a little-endian userspace. + This is usually the case for distributions targeting arm64. + +endchoice config SCHED_MC bool "Multi-core scheduler support" @@ -1597,6 +1645,7 @@ config CMDLINE config CMDLINE_FORCE bool "Always use the default kernel command string" + depends on CMDLINE != "" help Always use the default kernel command string, even if the boot loader passes other arguments to the kernel. diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2c0238ce0551..1fbe24d4fdb6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) KBUILD_LDS_MODULE += $(srctree)/arch/arm64/kernel/module.lds endif +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=2 +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index 4922c4451e7c..b8eb0453123d 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -86,7 +86,7 @@ config CRYPTO_AES_ARM64_CE_CCM config CRYPTO_AES_ARM64_CE_BLK tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions" depends on KERNEL_MODE_NEON - select CRYPTO_BLKCIPHER + select CRYPTO_SKCIPHER select CRYPTO_AES_ARM64_CE select CRYPTO_AES_ARM64 select CRYPTO_SIMD @@ -94,7 +94,7 @@ config CRYPTO_AES_ARM64_CE_BLK config CRYPTO_AES_ARM64_NEON_BLK tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions" depends on KERNEL_MODE_NEON - select CRYPTO_BLKCIPHER + select CRYPTO_SKCIPHER select CRYPTO_AES_ARM64 select CRYPTO_LIB_AES select CRYPTO_SIMD @@ -102,8 +102,15 @@ config CRYPTO_AES_ARM64_NEON_BLK config CRYPTO_CHACHA20_NEON tristate "ChaCha20, XChaCha20, and XChaCha12 stream ciphers using NEON instructions" depends on KERNEL_MODE_NEON - select CRYPTO_BLKCIPHER - select CRYPTO_CHACHA20 + select CRYPTO_SKCIPHER + select CRYPTO_LIB_CHACHA_GENERIC + select CRYPTO_ARCH_HAVE_LIB_CHACHA + +config CRYPTO_POLY1305_NEON + tristate "Poly1305 hash function using scalar or NEON instructions" + depends on KERNEL_MODE_NEON + select CRYPTO_HASH + select CRYPTO_ARCH_HAVE_LIB_POLY1305 config CRYPTO_NHPOLY1305_NEON tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)" @@ -113,7 +120,7 @@ config CRYPTO_NHPOLY1305_NEON config CRYPTO_AES_ARM64_BS tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm" depends on KERNEL_MODE_NEON - select CRYPTO_BLKCIPHER + select CRYPTO_SKCIPHER select CRYPTO_AES_ARM64_NEON_BLK select CRYPTO_AES_ARM64 select CRYPTO_LIB_AES diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index 0435f2a0610e..d0901e610df3 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -50,6 +50,10 @@ sha512-arm64-y := sha512-glue.o sha512-core.o obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o +obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o +poly1305-neon-y := poly1305-core.o poly1305-glue.o +AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64 + obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o @@ -68,11 +72,15 @@ ifdef REGENERATE_ARM64_CRYPTO quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $(<) void $(@) +$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv8.pl + $(call cmd,perlasm) + $(src)/sha256-core.S_shipped: $(src)/sha512-armv8.pl $(call cmd,perlasm) $(src)/sha512-core.S_shipped: $(src)/sha512-armv8.pl $(call cmd,perlasm) + endif -clean-files += sha256-core.S sha512-core.S +clean-files += poly1305-core.S sha256-core.S sha512-core.S diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index ea873b8904c4..e3e27349a9fe 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -384,7 +384,7 @@ static int __xts_crypt(struct skcipher_request *req, bool encrypt, goto xts_tail; kernel_neon_end(); - skcipher_walk_done(&walk, nbytes); + err = skcipher_walk_done(&walk, nbytes); } if (err || likely(!tail)) diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c index 1495d2b18518..b08029d7bde6 100644 --- a/arch/arm64/crypto/chacha-neon-glue.c +++ b/arch/arm64/crypto/chacha-neon-glue.c @@ -1,5 +1,5 @@ /* - * ARM NEON accelerated ChaCha and XChaCha stream ciphers, + * ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers, * including ChaCha20 (RFC7539) * * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org> @@ -20,9 +20,10 @@ */ #include <crypto/algapi.h> -#include <crypto/chacha.h> +#include <crypto/internal/chacha.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> +#include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> @@ -36,6 +37,8 @@ asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src, int nrounds, int bytes); asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds); +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); + static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, int bytes, int nrounds) { @@ -59,6 +62,37 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, } } +void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds) +{ + if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) { + hchacha_block_generic(state, stream, nrounds); + } else { + kernel_neon_begin(); + hchacha_block_neon(state, stream, nrounds); + kernel_neon_end(); + } +} +EXPORT_SYMBOL(hchacha_block_arch); + +void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv) +{ + chacha_init_generic(state, key, iv); +} +EXPORT_SYMBOL(chacha_init_arch); + +void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, + int nrounds) +{ + if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE || + !crypto_simd_usable()) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, bytes, nrounds); + kernel_neon_end(); +} +EXPORT_SYMBOL(chacha_crypt_arch); + static int chacha_neon_stream_xor(struct skcipher_request *req, const struct chacha_ctx *ctx, const u8 *iv) { @@ -68,7 +102,7 @@ static int chacha_neon_stream_xor(struct skcipher_request *req, err = skcipher_walk_virt(&walk, req, false); - crypto_chacha_init(state, ctx, iv); + chacha_init_generic(state, ctx->key, iv); while (walk.nbytes > 0) { unsigned int nbytes = walk.nbytes; @@ -76,10 +110,17 @@ static int chacha_neon_stream_xor(struct skcipher_request *req, if (nbytes < walk.total) nbytes = rounddown(nbytes, walk.stride); - kernel_neon_begin(); - chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr, - nbytes, ctx->nrounds); - kernel_neon_end(); + if (!static_branch_likely(&have_neon) || + !crypto_simd_usable()) { + chacha_crypt_generic(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, + ctx->nrounds); + } else { + kernel_neon_begin(); + chacha_doneon(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, ctx->nrounds); + kernel_neon_end(); + } err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } @@ -91,9 +132,6 @@ static int chacha_neon(struct skcipher_request *req) struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); - if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) - return crypto_chacha_crypt(req); - return chacha_neon_stream_xor(req, ctx, req->iv); } @@ -105,14 +143,8 @@ static int xchacha_neon(struct skcipher_request *req) u32 state[16]; u8 real_iv[16]; - if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) - return crypto_xchacha_crypt(req); - - crypto_chacha_init(state, ctx, req->iv); - - kernel_neon_begin(); - hchacha_block_neon(state, subctx.key, ctx->nrounds); - kernel_neon_end(); + chacha_init_generic(state, ctx->key, req->iv); + hchacha_block_arch(state, subctx.key, ctx->nrounds); subctx.nrounds = ctx->nrounds; memcpy(&real_iv[0], req->iv + 24, 8); @@ -134,7 +166,7 @@ static struct skcipher_alg algs[] = { .ivsize = CHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, .walksize = 5 * CHACHA_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, + .setkey = chacha20_setkey, .encrypt = chacha_neon, .decrypt = chacha_neon, }, { @@ -150,7 +182,7 @@ static struct skcipher_alg algs[] = { .ivsize = XCHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, .walksize = 5 * CHACHA_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, + .setkey = chacha20_setkey, .encrypt = xchacha_neon, .decrypt = xchacha_neon, }, { @@ -166,7 +198,7 @@ static struct skcipher_alg algs[] = { .ivsize = XCHACHA_IV_SIZE, .chunksize = CHACHA_BLOCK_SIZE, .walksize = 5 * CHACHA_BLOCK_SIZE, - .setkey = crypto_chacha12_setkey, + .setkey = chacha12_setkey, .encrypt = xchacha_neon, .decrypt = xchacha_neon, } @@ -175,14 +207,17 @@ static struct skcipher_alg algs[] = { static int __init chacha_simd_mod_init(void) { if (!cpu_have_named_feature(ASIMD)) - return -ENODEV; + return 0; + + static_branch_enable(&have_neon); return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); } static void __exit chacha_simd_mod_fini(void) { - crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + if (cpu_have_named_feature(ASIMD)) + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } module_init(chacha_simd_mod_init); diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S index 410e8afcf5a7..a791c4adf8e6 100644 --- a/arch/arm64/crypto/ghash-ce-core.S +++ b/arch/arm64/crypto/ghash-ce-core.S @@ -13,8 +13,8 @@ T1 .req v2 T2 .req v3 MASK .req v4 - XL .req v5 - XM .req v6 + XM .req v5 + XL .req v6 XH .req v7 IN1 .req v7 @@ -358,20 +358,37 @@ ENTRY(pmull_ghash_update_p8) __pmull_ghash p8 ENDPROC(pmull_ghash_update_p8) - KS0 .req v12 - KS1 .req v13 - INP0 .req v14 - INP1 .req v15 - - .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] + KS0 .req v8 + KS1 .req v9 + KS2 .req v10 + KS3 .req v11 + + INP0 .req v21 + INP1 .req v22 + INP2 .req v23 + INP3 .req v24 + + K0 .req v25 + K1 .req v26 + K2 .req v27 + K3 .req v28 + K4 .req v12 + K5 .req v13 + K6 .req v4 + K7 .req v5 + K8 .req v14 + K9 .req v15 + KK .req v29 + KL .req v30 + KM .req v31 + + .macro load_round_keys, rounds, rk, tmp + add \tmp, \rk, #64 + ld1 {K0.4s-K3.4s}, [\rk] + ld1 {K4.4s-K5.4s}, [\tmp] + add \tmp, \rk, \rounds, lsl #4 + sub \tmp, \tmp, #32 + ld1 {KK.4s-KM.4s}, [\tmp] .endm .macro enc_round, state, key @@ -379,197 +396,367 @@ ENDPROC(pmull_ghash_update_p8) 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 + .macro enc_qround, s0, s1, s2, s3, key + enc_round \s0, \key + enc_round \s1, \key + enc_round \s2, \key + enc_round \s3, \key + .endm + + .macro enc_block, state, rounds, rk, tmp + add \tmp, \rk, #96 + ld1 {K6.4s-K7.4s}, [\tmp], #32 + .irp key, K0, K1, K2, K3, K4 K5 enc_round \state, \key .endr - aese \state\().16b, v30.16b - eor \state\().16b, \state\().16b, v31.16b + + tbnz \rounds, #2, .Lnot128_\@ +.Lout256_\@: + enc_round \state, K6 + enc_round \state, K7 + +.Lout192_\@: + enc_round \state, KK + aese \state\().16b, KL.16b + eor \state\().16b, \state\().16b, KM.16b + + .subsection 1 +.Lnot128_\@: + ld1 {K8.4s-K9.4s}, [\tmp], #32 + enc_round \state, K6 + enc_round \state, K7 + ld1 {K6.4s-K7.4s}, [\tmp] + enc_round \state, K8 + enc_round \state, K9 + tbz \rounds, #1, .Lout192_\@ + b .Lout256_\@ + .previous .endm + .align 6 .macro pmull_gcm_do_crypt, enc - ld1 {SHASH.2d}, [x4], #16 - ld1 {HH.2d}, [x4] - ld1 {XL.2d}, [x1] - ldr x8, [x5, #8] // load lower counter + stp x29, x30, [sp, #-32]! + mov x29, sp + str x19, [sp, #24] + + load_round_keys x7, x6, x8 + + ld1 {SHASH.2d}, [x3], #16 + ld1 {HH.2d-HH4.2d}, [x3] - movi MASK.16b, #0xe1 trn1 SHASH2.2d, SHASH.2d, HH.2d trn2 T1.2d, SHASH.2d, HH.2d -CPU_LE( rev x8, x8 ) - shl MASK.2d, MASK.2d, #57 eor SHASH2.16b, SHASH2.16b, T1.16b - .if \enc == 1 - ldr x10, [sp] - ld1 {KS0.16b-KS1.16b}, [x10] - .endif + trn1 HH34.2d, HH3.2d, HH4.2d + trn2 T1.2d, HH3.2d, HH4.2d + eor HH34.16b, HH34.16b, T1.16b - cbnz x6, 4f + ld1 {XL.2d}, [x4] -0: ld1 {INP0.16b-INP1.16b}, [x3], #32 + cbz x0, 3f // tag only? - rev x9, x8 - add x11, x8, #1 - add x8, x8, #2 + ldr w8, [x5, #12] // load lower counter +CPU_LE( rev w8, w8 ) - .if \enc == 1 - eor INP0.16b, INP0.16b, KS0.16b // encrypt input - eor INP1.16b, INP1.16b, KS1.16b +0: mov w9, #4 // max blocks per round + add x10, x0, #0xf + lsr x10, x10, #4 // remaining blocks + + subs x0, x0, #64 + csel w9, w10, w9, mi + add w8, w8, w9 + + bmi 1f + ld1 {INP0.16b-INP3.16b}, [x2], #64 + .subsection 1 + /* + * Populate the four input registers right to left with up to 63 bytes + * of data, using overlapping loads to avoid branches. + * + * INP0 INP1 INP2 INP3 + * 1 byte | | | |x | + * 16 bytes | | | |xxxxxxxx| + * 17 bytes | | |xxxxxxxx|x | + * 47 bytes | |xxxxxxxx|xxxxxxxx|xxxxxxx | + * etc etc + * + * Note that this code may read up to 15 bytes before the start of + * the input. It is up to the calling code to ensure this is safe if + * this happens in the first iteration of the loop (i.e., when the + * input size is < 16 bytes) + */ +1: mov x15, #16 + ands x19, x0, #0xf + csel x19, x19, x15, ne + adr_l x17, .Lpermute_table + 16 + + sub x11, x15, x19 + add x12, x17, x11 + sub x17, x17, x11 + ld1 {T1.16b}, [x12] + sub x10, x1, x11 + sub x11, x2, x11 + + cmp x0, #-16 + csel x14, x15, xzr, gt + cmp x0, #-32 + csel x15, x15, xzr, gt + cmp x0, #-48 + csel x16, x19, xzr, gt + csel x1, x1, x10, gt + csel x2, x2, x11, gt + + ld1 {INP0.16b}, [x2], x14 + ld1 {INP1.16b}, [x2], x15 + ld1 {INP2.16b}, [x2], x16 + ld1 {INP3.16b}, [x2] + tbl INP3.16b, {INP3.16b}, T1.16b + b 2f + .previous + +2: .if \enc == 0 + bl pmull_gcm_ghash_4x .endif - ld1 {KS0.8b}, [x5] // load upper counter - rev x11, x11 - sub w0, w0, #2 - mov KS1.8b, KS0.8b - ins KS0.d[1], x9 // set lower counter - ins KS1.d[1], x11 + bl pmull_gcm_enc_4x - rev64 T1.16b, INP1.16b + tbnz x0, #63, 6f + st1 {INP0.16b-INP3.16b}, [x1], #64 + .if \enc == 1 + bl pmull_gcm_ghash_4x + .endif + bne 0b - cmp w7, #12 - b.ge 2f // AES-192/256? +3: ldp x19, x10, [sp, #24] + cbz x10, 5f // output tag? -1: enc_round KS0, v21 - ext IN1.16b, T1.16b, T1.16b, #8 + ld1 {INP3.16b}, [x10] // load lengths[] + mov w9, #1 + bl pmull_gcm_ghash_4x - enc_round KS1, v21 - pmull2 XH2.1q, SHASH.2d, IN1.2d // a1 * b1 + mov w11, #(0x1 << 24) // BE '1U' + ld1 {KS0.16b}, [x5] + mov KS0.s[3], w11 - enc_round KS0, v22 - eor T1.16b, T1.16b, IN1.16b + enc_block KS0, x7, x6, x12 - enc_round KS1, v22 - pmull XL2.1q, SHASH.1d, IN1.1d // a0 * b0 + ext XL.16b, XL.16b, XL.16b, #8 + rev64 XL.16b, XL.16b + eor XL.16b, XL.16b, KS0.16b + st1 {XL.16b}, [x10] // store tag - enc_round KS0, v23 - pmull XM2.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0) +4: ldp x29, x30, [sp], #32 + ret - enc_round KS1, v23 - rev64 T1.16b, INP0.16b - ext T2.16b, XL.16b, XL.16b, #8 +5: +CPU_LE( rev w8, w8 ) + str w8, [x5, #12] // store lower counter + st1 {XL.2d}, [x4] + b 4b + +6: ld1 {T1.16b-T2.16b}, [x17], #32 // permute vectors + sub x17, x17, x19, lsl #1 + + cmp w9, #1 + beq 7f + .subsection 1 +7: ld1 {INP2.16b}, [x1] + tbx INP2.16b, {INP3.16b}, T1.16b + mov INP3.16b, INP2.16b + b 8f + .previous + + st1 {INP0.16b}, [x1], x14 + st1 {INP1.16b}, [x1], x15 + st1 {INP2.16b}, [x1], x16 + tbl INP3.16b, {INP3.16b}, T1.16b + tbx INP3.16b, {INP2.16b}, T2.16b +8: st1 {INP3.16b}, [x1] - enc_round KS0, v24 - ext IN1.16b, T1.16b, T1.16b, #8 - eor T1.16b, T1.16b, T2.16b + .if \enc == 1 + ld1 {T1.16b}, [x17] + tbl INP3.16b, {INP3.16b}, T1.16b // clear non-data bits + bl pmull_gcm_ghash_4x + .endif + b 3b + .endm - enc_round KS1, v24 - eor XL.16b, XL.16b, IN1.16b + /* + * void pmull_gcm_encrypt(int blocks, u8 dst[], const u8 src[], + * struct ghash_key const *k, u64 dg[], u8 ctr[], + * int rounds, u8 tag) + */ +ENTRY(pmull_gcm_encrypt) + pmull_gcm_do_crypt 1 +ENDPROC(pmull_gcm_encrypt) - enc_round KS0, v25 - eor T1.16b, T1.16b, XL.16b + /* + * void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[], + * struct ghash_key const *k, u64 dg[], u8 ctr[], + * int rounds, u8 tag) + */ +ENTRY(pmull_gcm_decrypt) + pmull_gcm_do_crypt 0 +ENDPROC(pmull_gcm_decrypt) - enc_round KS1, v25 - pmull2 XH.1q, HH.2d, XL.2d // a1 * b1 +pmull_gcm_ghash_4x: + movi MASK.16b, #0xe1 + shl MASK.2d, MASK.2d, #57 - enc_round KS0, v26 - pmull XL.1q, HH.1d, XL.1d // a0 * b0 + rev64 T1.16b, INP0.16b + rev64 T2.16b, INP1.16b + rev64 TT3.16b, INP2.16b + rev64 TT4.16b, INP3.16b - enc_round KS1, v26 - pmull2 XM.1q, SHASH2.2d, T1.2d // (a1 + a0)(b1 + b0) + ext XL.16b, XL.16b, XL.16b, #8 - enc_round KS0, v27 - eor XL.16b, XL.16b, XL2.16b - eor XH.16b, XH.16b, XH2.16b + tbz w9, #2, 0f // <4 blocks? + .subsection 1 +0: movi XH2.16b, #0 + movi XM2.16b, #0 + movi XL2.16b, #0 - enc_round KS1, v27 - eor XM.16b, XM.16b, XM2.16b - ext T1.16b, XL.16b, XH.16b, #8 + tbz w9, #0, 1f // 2 blocks? + tbz w9, #1, 2f // 1 block? - enc_round KS0, v28 - eor T2.16b, XL.16b, XH.16b - eor XM.16b, XM.16b, T1.16b + eor T2.16b, T2.16b, XL.16b + ext T1.16b, T2.16b, T2.16b, #8 + b .Lgh3 - enc_round KS1, v28 - eor XM.16b, XM.16b, T2.16b +1: eor TT3.16b, TT3.16b, XL.16b + ext T2.16b, TT3.16b, TT3.16b, #8 + b .Lgh2 - enc_round KS0, v29 - pmull T2.1q, XL.1d, MASK.1d +2: eor TT4.16b, TT4.16b, XL.16b + ext IN1.16b, TT4.16b, TT4.16b, #8 + b .Lgh1 + .previous - enc_round KS1, v29 - mov XH.d[0], XM.d[1] - mov XM.d[1], XL.d[0] + eor T1.16b, T1.16b, XL.16b + ext IN1.16b, T1.16b, T1.16b, #8 - aese KS0.16b, v30.16b - eor XL.16b, XM.16b, T2.16b + pmull2 XH2.1q, HH4.2d, IN1.2d // a1 * b1 + eor T1.16b, T1.16b, IN1.16b + pmull XL2.1q, HH4.1d, IN1.1d // a0 * b0 + pmull2 XM2.1q, HH34.2d, T1.2d // (a1 + a0)(b1 + b0) - aese KS1.16b, v30.16b - ext T2.16b, XL.16b, XL.16b, #8 + ext T1.16b, T2.16b, T2.16b, #8 +.Lgh3: eor T2.16b, T2.16b, T1.16b + pmull2 XH.1q, HH3.2d, T1.2d // a1 * b1 + pmull XL.1q, HH3.1d, T1.1d // a0 * b0 + pmull XM.1q, HH34.1d, T2.1d // (a1 + a0)(b1 + b0) - eor KS0.16b, KS0.16b, v31.16b - pmull XL.1q, XL.1d, MASK.1d - eor T2.16b, T2.16b, XH.16b + eor XH2.16b, XH2.16b, XH.16b + eor XL2.16b, XL2.16b, XL.16b + eor XM2.16b, XM2.16b, XM.16b - eor KS1.16b, KS1.16b, v31.16b - eor XL.16b, XL.16b, T2.16b + ext T2.16b, TT3.16b, TT3.16b, #8 +.Lgh2: eor TT3.16b, TT3.16b, T2.16b + pmull2 XH.1q, HH.2d, T2.2d // a1 * b1 + pmull XL.1q, HH.1d, T2.1d // a0 * b0 + pmull2 XM.1q, SHASH2.2d, TT3.2d // (a1 + a0)(b1 + b0) - .if \enc == 0 - eor INP0.16b, INP0.16b, KS0.16b - eor INP1.16b, INP1.16b, KS1.16b - .endif + eor XH2.16b, XH2.16b, XH.16b + eor XL2.16b, XL2.16b, XL.16b + eor XM2.16b, XM2.16b, XM.16b - st1 {INP0.16b-INP1.16b}, [x2], #32 + ext IN1.16b, TT4.16b, TT4.16b, #8 +.Lgh1: eor TT4.16b, TT4.16b, IN1.16b + pmull XL.1q, SHASH.1d, IN1.1d // a0 * b0 + pmull2 XH.1q, SHASH.2d, IN1.2d // a1 * b1 + pmull XM.1q, SHASH2.1d, TT4.1d // (a1 + a0)(b1 + b0) - cbnz w0, 0b + eor XH.16b, XH.16b, XH2.16b + eor XL.16b, XL.16b, XL2.16b + eor XM.16b, XM.16b, XM2.16b -CPU_LE( rev x8, x8 ) - st1 {XL.2d}, [x1] - str x8, [x5, #8] // store lower counter + eor T2.16b, XL.16b, XH.16b + ext T1.16b, XL.16b, XH.16b, #8 + eor XM.16b, XM.16b, T2.16b - .if \enc == 1 - st1 {KS0.16b-KS1.16b}, [x10] - .endif + __pmull_reduce_p64 + + eor T2.16b, T2.16b, XH.16b + eor XL.16b, XL.16b, T2.16b ret +ENDPROC(pmull_gcm_ghash_4x) + +pmull_gcm_enc_4x: + ld1 {KS0.16b}, [x5] // load upper counter + sub w10, w8, #4 + sub w11, w8, #3 + sub w12, w8, #2 + sub w13, w8, #1 + rev w10, w10 + rev w11, w11 + rev w12, w12 + rev w13, w13 + mov KS1.16b, KS0.16b + mov KS2.16b, KS0.16b + mov KS3.16b, KS0.16b + ins KS0.s[3], w10 // set lower counter + ins KS1.s[3], w11 + ins KS2.s[3], w12 + ins KS3.s[3], w13 + + add x10, x6, #96 // round key pointer + ld1 {K6.4s-K7.4s}, [x10], #32 + .irp key, K0, K1, K2, K3, K4, K5 + enc_qround KS0, KS1, KS2, KS3, \key + .endr -2: b.eq 3f // AES-192? - enc_round KS0, v17 - enc_round KS1, v17 - enc_round KS0, v18 - enc_round KS1, v18 -3: enc_round KS0, v19 - enc_round KS1, v19 - enc_round KS0, v20 - enc_round KS1, v20 - b 1b + tbnz x7, #2, .Lnot128 + .subsection 1 +.Lnot128: + ld1 {K8.4s-K9.4s}, [x10], #32 + .irp key, K6, K7 + enc_qround KS0, KS1, KS2, KS3, \key + .endr + ld1 {K6.4s-K7.4s}, [x10] + .irp key, K8, K9 + enc_qround KS0, KS1, KS2, KS3, \key + .endr + tbz x7, #1, .Lout192 + b .Lout256 + .previous -4: load_round_keys w7, x6 - b 0b - .endm +.Lout256: + .irp key, K6, K7 + enc_qround KS0, KS1, KS2, KS3, \key + .endr - /* - * 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) +.Lout192: + enc_qround KS0, KS1, KS2, KS3, KK - /* - * 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) + aese KS0.16b, KL.16b + aese KS1.16b, KL.16b + aese KS2.16b, KL.16b + aese KS3.16b, KL.16b + + eor KS0.16b, KS0.16b, KM.16b + eor KS1.16b, KS1.16b, KM.16b + eor KS2.16b, KS2.16b, KM.16b + eor KS3.16b, KS3.16b, KM.16b + + eor INP0.16b, INP0.16b, KS0.16b + eor INP1.16b, INP1.16b, KS1.16b + eor INP2.16b, INP2.16b, KS2.16b + eor INP3.16b, INP3.16b, KS3.16b - /* - * 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_gcm_encrypt_block) +ENDPROC(pmull_gcm_enc_4x) + + .section ".rodata", "a" + .align 6 +.Lpermute_table: + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 + .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 + .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf + .previous diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 70b1469783f9..522cf004ce65 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -58,17 +58,15 @@ asmlinkage void pmull_ghash_update_p8(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, +asmlinkage void pmull_gcm_encrypt(int bytes, u8 dst[], const u8 src[], + struct ghash_key const *k, u64 dg[], u8 ctr[], u32 const rk[], int rounds, - u8 ks[]); + u8 tag[]); -asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[], - const u8 src[], struct ghash_key const *k, - u8 ctr[], u32 const rk[], int rounds); - -asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[], - u32 const rk[], int rounds); +asmlinkage void pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[], + struct ghash_key const *k, u64 dg[], + u8 ctr[], u32 const rk[], int rounds, + u8 tag[]); static int ghash_init(struct shash_desc *desc) { @@ -85,7 +83,7 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src, struct ghash_key const *k, const char *head)) { - if (likely(crypto_simd_usable())) { + if (likely(crypto_simd_usable() && simd_update)) { kernel_neon_begin(); simd_update(blocks, dg, src, key, head); kernel_neon_end(); @@ -398,136 +396,112 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[]) } } -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, - pmull_ghash_update_p64); - - 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); + int nrounds = num_rounds(&ctx->aes_key); struct skcipher_walk walk; + u8 buf[AES_BLOCK_SIZE]; u8 iv[AES_BLOCK_SIZE]; - u8 ks[2 * AES_BLOCK_SIZE]; - u8 tag[AES_BLOCK_SIZE]; u64 dg[2] = {}; - int nrounds = num_rounds(&ctx->aes_key); + u128 lengths; + u8 *tag; int err; + lengths.a = cpu_to_be64(req->assoclen * 8); + lengths.b = cpu_to_be64(req->cryptlen * 8); + if (req->assoclen) gcm_calculate_auth_mac(req, dg); memcpy(iv, req->iv, GCM_IV_SIZE); - put_unaligned_be32(1, iv + GCM_IV_SIZE); + put_unaligned_be32(2, iv + GCM_IV_SIZE); err = skcipher_walk_aead_encrypt(&walk, req, false); - if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) { - u32 const *rk = NULL; - - kernel_neon_begin(); - pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds); - put_unaligned_be32(2, iv + GCM_IV_SIZE); - pmull_gcm_encrypt_block(ks, iv, NULL, nrounds); - put_unaligned_be32(3, iv + GCM_IV_SIZE); - pmull_gcm_encrypt_block(ks + AES_BLOCK_SIZE, iv, NULL, nrounds); - put_unaligned_be32(4, iv + GCM_IV_SIZE); - + if (likely(crypto_simd_usable())) { do { - int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2; + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + int nbytes = walk.nbytes; + + tag = (u8 *)&lengths; - if (rk) - kernel_neon_begin(); + if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) { + src = dst = memcpy(buf + sizeof(buf) - nbytes, + src, nbytes); + } else if (nbytes < walk.total) { + nbytes &= ~(AES_BLOCK_SIZE - 1); + tag = NULL; + } - pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr, - walk.src.virt.addr, &ctx->ghash_key, - iv, rk, nrounds, ks); + kernel_neon_begin(); + pmull_gcm_encrypt(nbytes, dst, src, &ctx->ghash_key, dg, + iv, ctx->aes_key.key_enc, nrounds, + tag); kernel_neon_end(); - err = skcipher_walk_done(&walk, - walk.nbytes % (2 * AES_BLOCK_SIZE)); + if (unlikely(!nbytes)) + break; - rk = ctx->aes_key.key_enc; - } while (walk.nbytes >= 2 * AES_BLOCK_SIZE); - } else { - aes_encrypt(&ctx->aes_key, tag, iv); - put_unaligned_be32(2, iv + GCM_IV_SIZE); + if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) + memcpy(walk.dst.virt.addr, + buf + sizeof(buf) - nbytes, nbytes); - while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { - const int blocks = - walk.nbytes / (2 * AES_BLOCK_SIZE) * 2; + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } while (walk.nbytes); + } else { + while (walk.nbytes >= AES_BLOCK_SIZE) { + int blocks = walk.nbytes / AES_BLOCK_SIZE; + const u8 *src = walk.src.virt.addr; u8 *dst = walk.dst.virt.addr; - u8 *src = walk.src.virt.addr; int remaining = blocks; do { - aes_encrypt(&ctx->aes_key, ks, iv); - crypto_xor_cpy(dst, src, ks, AES_BLOCK_SIZE); + aes_encrypt(&ctx->aes_key, buf, iv); + crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE); crypto_inc(iv, AES_BLOCK_SIZE); dst += AES_BLOCK_SIZE; src += AES_BLOCK_SIZE; } while (--remaining > 0); - ghash_do_update(blocks, dg, - walk.dst.virt.addr, &ctx->ghash_key, - NULL, pmull_ghash_update_p64); + ghash_do_update(blocks, dg, walk.dst.virt.addr, + &ctx->ghash_key, NULL, NULL); err = skcipher_walk_done(&walk, - walk.nbytes % (2 * AES_BLOCK_SIZE)); - } - if (walk.nbytes) { - aes_encrypt(&ctx->aes_key, ks, iv); - if (walk.nbytes > AES_BLOCK_SIZE) { - crypto_inc(iv, AES_BLOCK_SIZE); - aes_encrypt(&ctx->aes_key, ks + AES_BLOCK_SIZE, iv); - } + walk.nbytes % AES_BLOCK_SIZE); } - } - /* handle the tail */ - if (walk.nbytes) { - u8 buf[GHASH_BLOCK_SIZE]; - unsigned int nbytes = walk.nbytes; - u8 *dst = walk.dst.virt.addr; - u8 *head = NULL; + /* handle the tail */ + if (walk.nbytes) { + aes_encrypt(&ctx->aes_key, buf, iv); - crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, ks, - walk.nbytes); + crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, + buf, walk.nbytes); - if (walk.nbytes > GHASH_BLOCK_SIZE) { - head = dst; - dst += GHASH_BLOCK_SIZE; - nbytes %= GHASH_BLOCK_SIZE; + memcpy(buf, walk.dst.virt.addr, walk.nbytes); + memset(buf + walk.nbytes, 0, sizeof(buf) - walk.nbytes); } - memcpy(buf, dst, nbytes); - memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes); - ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head, - pmull_ghash_update_p64); + tag = (u8 *)&lengths; + ghash_do_update(1, dg, tag, &ctx->ghash_key, + walk.nbytes ? buf : NULL, NULL); - err = skcipher_walk_done(&walk, 0); + if (walk.nbytes) + err = skcipher_walk_done(&walk, 0); + + put_unaligned_be64(dg[1], tag); + put_unaligned_be64(dg[0], tag + 8); + put_unaligned_be32(1, iv + GCM_IV_SIZE); + aes_encrypt(&ctx->aes_key, iv, iv); + crypto_xor(tag, iv, AES_BLOCK_SIZE); } 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); @@ -540,75 +514,65 @@ 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); + int nrounds = num_rounds(&ctx->aes_key); struct skcipher_walk walk; - u8 iv[2 * AES_BLOCK_SIZE]; - u8 tag[AES_BLOCK_SIZE]; - u8 buf[2 * GHASH_BLOCK_SIZE]; + u8 buf[AES_BLOCK_SIZE]; + u8 iv[AES_BLOCK_SIZE]; u64 dg[2] = {}; - int nrounds = num_rounds(&ctx->aes_key); + u128 lengths; + u8 *tag; int err; + lengths.a = cpu_to_be64(req->assoclen * 8); + lengths.b = cpu_to_be64((req->cryptlen - authsize) * 8); + if (req->assoclen) gcm_calculate_auth_mac(req, dg); memcpy(iv, req->iv, GCM_IV_SIZE); - put_unaligned_be32(1, iv + GCM_IV_SIZE); + put_unaligned_be32(2, iv + GCM_IV_SIZE); err = skcipher_walk_aead_decrypt(&walk, req, false); - if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) { - u32 const *rk = NULL; - - kernel_neon_begin(); - pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds); - put_unaligned_be32(2, iv + GCM_IV_SIZE); - + if (likely(crypto_simd_usable())) { do { - int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2; - int rem = walk.total - blocks * AES_BLOCK_SIZE; - - if (rk) - kernel_neon_begin(); - - pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr, - walk.src.virt.addr, &ctx->ghash_key, - iv, rk, nrounds); - - /* check if this is the final iteration of the loop */ - if (rem < (2 * AES_BLOCK_SIZE)) { - u8 *iv2 = iv + AES_BLOCK_SIZE; - - if (rem > AES_BLOCK_SIZE) { - memcpy(iv2, iv, AES_BLOCK_SIZE); - crypto_inc(iv2, AES_BLOCK_SIZE); - } + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + int nbytes = walk.nbytes; - pmull_gcm_encrypt_block(iv, iv, NULL, nrounds); + tag = (u8 *)&lengths; - if (rem > AES_BLOCK_SIZE) - pmull_gcm_encrypt_block(iv2, iv2, NULL, - nrounds); + if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) { + src = dst = memcpy(buf + sizeof(buf) - nbytes, + src, nbytes); + } else if (nbytes < walk.total) { + nbytes &= ~(AES_BLOCK_SIZE - 1); + tag = NULL; } + kernel_neon_begin(); + pmull_gcm_decrypt(nbytes, dst, src, &ctx->ghash_key, dg, + iv, ctx->aes_key.key_enc, nrounds, + tag); kernel_neon_end(); - err = skcipher_walk_done(&walk, - walk.nbytes % (2 * AES_BLOCK_SIZE)); + if (unlikely(!nbytes)) + break; - rk = ctx->aes_key.key_enc; - } while (walk.nbytes >= 2 * AES_BLOCK_SIZE); - } else { - aes_encrypt(&ctx->aes_key, tag, iv); - put_unaligned_be32(2, iv + GCM_IV_SIZE); + if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) + memcpy(walk.dst.virt.addr, + buf + sizeof(buf) - nbytes, nbytes); - while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { - int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2; + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } while (walk.nbytes); + } else { + while (walk.nbytes >= AES_BLOCK_SIZE) { + int blocks = walk.nbytes / AES_BLOCK_SIZE; + const u8 *src = walk.src.virt.addr; 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, - pmull_ghash_update_p64); + &ctx->ghash_key, NULL, NULL); do { aes_encrypt(&ctx->aes_key, buf, iv); @@ -620,49 +584,38 @@ static int gcm_decrypt(struct aead_request *req) } while (--blocks > 0); err = skcipher_walk_done(&walk, - walk.nbytes % (2 * AES_BLOCK_SIZE)); + walk.nbytes % AES_BLOCK_SIZE); } - if (walk.nbytes) { - if (walk.nbytes > AES_BLOCK_SIZE) { - u8 *iv2 = iv + AES_BLOCK_SIZE; - - memcpy(iv2, iv, AES_BLOCK_SIZE); - crypto_inc(iv2, AES_BLOCK_SIZE); - aes_encrypt(&ctx->aes_key, iv2, iv2); - } - aes_encrypt(&ctx->aes_key, iv, iv); + /* handle the tail */ + if (walk.nbytes) { + memcpy(buf, walk.src.virt.addr, walk.nbytes); + memset(buf + walk.nbytes, 0, sizeof(buf) - walk.nbytes); } - } - /* handle the tail */ - if (walk.nbytes) { - const u8 *src = walk.src.virt.addr; - const u8 *head = NULL; - unsigned int nbytes = walk.nbytes; + tag = (u8 *)&lengths; + ghash_do_update(1, dg, tag, &ctx->ghash_key, + walk.nbytes ? buf : NULL, NULL); - if (walk.nbytes > GHASH_BLOCK_SIZE) { - head = src; - src += GHASH_BLOCK_SIZE; - nbytes %= GHASH_BLOCK_SIZE; - } + if (walk.nbytes) { + aes_encrypt(&ctx->aes_key, buf, iv); - memcpy(buf, src, nbytes); - memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes); - ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head, - pmull_ghash_update_p64); + crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, + buf, walk.nbytes); - crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv, - walk.nbytes); + err = skcipher_walk_done(&walk, 0); + } - err = skcipher_walk_done(&walk, 0); + put_unaligned_be64(dg[1], tag); + put_unaligned_be64(dg[0], tag + 8); + put_unaligned_be32(1, iv + GCM_IV_SIZE); + aes_encrypt(&ctx->aes_key, iv, iv); + crypto_xor(tag, iv, AES_BLOCK_SIZE); } 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, @@ -675,7 +628,7 @@ static int gcm_decrypt(struct aead_request *req) static struct aead_alg gcm_aes_alg = { .ivsize = GCM_IV_SIZE, - .chunksize = 2 * AES_BLOCK_SIZE, + .chunksize = AES_BLOCK_SIZE, .maxauthsize = AES_BLOCK_SIZE, .setkey = gcm_setkey, .setauthsize = gcm_setauthsize, diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/crypto/poly1305-armv8.pl new file mode 100644 index 000000000000..6e5576d19af8 --- /dev/null +++ b/arch/arm64/crypto/poly1305-armv8.pl @@ -0,0 +1,913 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause +# +# ==================================================================== +# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL +# project. +# ==================================================================== +# +# This module implements Poly1305 hash for ARMv8. +# +# June 2015 +# +# Numbers are cycles per processed byte with poly1305_blocks alone. +# +# IALU/gcc-4.9 NEON +# +# Apple A7 1.86/+5% 0.72 +# Cortex-A53 2.69/+58% 1.47 +# Cortex-A57 2.70/+7% 1.14 +# Denver 1.64/+50% 1.18(*) +# X-Gene 2.13/+68% 2.27 +# Mongoose 1.77/+75% 1.12 +# Kryo 2.70/+55% 1.13 +# ThunderX2 1.17/+95% 1.36 +# +# (*) estimate based on resources availability is less than 1.0, +# i.e. measured result is worse than expected, presumably binary +# translator is not almighty; + +$flavour=shift; +$output=shift; + +if ($flavour && $flavour ne "void") { + $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; + ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or + ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or + die "can't locate arm-xlate.pl"; + + open STDOUT,"| \"$^X\" $xlate $flavour $output"; +} else { + open STDOUT,">$output"; +} + +my ($ctx,$inp,$len,$padbit) = map("x$_",(0..3)); +my ($mac,$nonce)=($inp,$len); + +my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14)); + +$code.=<<___; +#ifndef __KERNEL__ +# include "arm_arch.h" +.extern OPENSSL_armcap_P +#endif + +.text + +// forward "declarations" are required for Apple +.globl poly1305_blocks +.globl poly1305_emit + +.globl poly1305_init +.type poly1305_init,%function +.align 5 +poly1305_init: + cmp $inp,xzr + stp xzr,xzr,[$ctx] // zero hash value + stp xzr,xzr,[$ctx,#16] // [along with is_base2_26] + + csel x0,xzr,x0,eq + b.eq .Lno_key + +#ifndef __KERNEL__ + adrp x17,OPENSSL_armcap_P + ldr w17,[x17,#:lo12:OPENSSL_armcap_P] +#endif + + ldp $r0,$r1,[$inp] // load key + mov $s1,#0xfffffffc0fffffff + movk $s1,#0x0fff,lsl#48 +#ifdef __AARCH64EB__ + rev $r0,$r0 // flip bytes + rev $r1,$r1 +#endif + and $r0,$r0,$s1 // &=0ffffffc0fffffff + and $s1,$s1,#-4 + and $r1,$r1,$s1 // &=0ffffffc0ffffffc + mov w#$s1,#-1 + stp $r0,$r1,[$ctx,#32] // save key value + str w#$s1,[$ctx,#48] // impossible key power value + +#ifndef __KERNEL__ + tst w17,#ARMV7_NEON + + adr $d0,.Lpoly1305_blocks + adr $r0,.Lpoly1305_blocks_neon + adr $d1,.Lpoly1305_emit + + csel $d0,$d0,$r0,eq + +# ifdef __ILP32__ + stp w#$d0,w#$d1,[$len] +# else + stp $d0,$d1,[$len] +# endif +#endif + mov x0,#1 +.Lno_key: + ret +.size poly1305_init,.-poly1305_init + +.type poly1305_blocks,%function +.align 5 +poly1305_blocks: +.Lpoly1305_blocks: + ands $len,$len,#-16 + b.eq .Lno_data + + ldp $h0,$h1,[$ctx] // load hash value + ldp $h2,x17,[$ctx,#16] // [along with is_base2_26] + ldp $r0,$r1,[$ctx,#32] // load key value + +#ifdef __AARCH64EB__ + lsr $d0,$h0,#32 + mov w#$d1,w#$h0 + lsr $d2,$h1,#32 + mov w15,w#$h1 + lsr x16,$h2,#32 +#else + mov w#$d0,w#$h0 + lsr $d1,$h0,#32 + mov w#$d2,w#$h1 + lsr x15,$h1,#32 + mov w16,w#$h2 +#endif + + add $d0,$d0,$d1,lsl#26 // base 2^26 -> base 2^64 + lsr $d1,$d2,#12 + adds $d0,$d0,$d2,lsl#52 + add $d1,$d1,x15,lsl#14 + adc $d1,$d1,xzr + lsr $d2,x16,#24 + adds $d1,$d1,x16,lsl#40 + adc $d2,$d2,xzr + + cmp x17,#0 // is_base2_26? + add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) + csel $h0,$h0,$d0,eq // choose between radixes + csel $h1,$h1,$d1,eq + csel $h2,$h2,$d2,eq + +.Loop: + ldp $t0,$t1,[$inp],#16 // load input + sub $len,$len,#16 +#ifdef __AARCH64EB__ + rev $t0,$t0 + rev $t1,$t1 +#endif + adds $h0,$h0,$t0 // accumulate input + adcs $h1,$h1,$t1 + + mul $d0,$h0,$r0 // h0*r0 + adc $h2,$h2,$padbit + umulh $d1,$h0,$r0 + + mul $t0,$h1,$s1 // h1*5*r1 + umulh $t1,$h1,$s1 + + adds $d0,$d0,$t0 + mul $t0,$h0,$r1 // h0*r1 + adc $d1,$d1,$t1 + umulh $d2,$h0,$r1 + + adds $d1,$d1,$t0 + mul $t0,$h1,$r0 // h1*r0 + adc $d2,$d2,xzr + umulh $t1,$h1,$r0 + + adds $d1,$d1,$t0 + mul $t0,$h2,$s1 // h2*5*r1 + adc $d2,$d2,$t1 + mul $t1,$h2,$r0 // h2*r0 + + adds $d1,$d1,$t0 + adc $d2,$d2,$t1 + + and $t0,$d2,#-4 // final reduction + and $h2,$d2,#3 + add $t0,$t0,$d2,lsr#2 + adds $h0,$d0,$t0 + adcs $h1,$d1,xzr + adc $h2,$h2,xzr + + cbnz $len,.Loop + + stp $h0,$h1,[$ctx] // store hash value + stp $h2,xzr,[$ctx,#16] // [and clear is_base2_26] + +.Lno_data: + ret +.size poly1305_blocks,.-poly1305_blocks + +.type poly1305_emit,%function +.align 5 +poly1305_emit: +.Lpoly1305_emit: + ldp $h0,$h1,[$ctx] // load hash base 2^64 + ldp $h2,$r0,[$ctx,#16] // [along with is_base2_26] + ldp $t0,$t1,[$nonce] // load nonce + +#ifdef __AARCH64EB__ + lsr $d0,$h0,#32 + mov w#$d1,w#$h0 + lsr $d2,$h1,#32 + mov w15,w#$h1 + lsr x16,$h2,#32 +#else + mov w#$d0,w#$h0 + lsr $d1,$h0,#32 + mov w#$d2,w#$h1 + lsr x15,$h1,#32 + mov w16,w#$h2 +#endif + + add $d0,$d0,$d1,lsl#26 // base 2^26 -> base 2^64 + lsr $d1,$d2,#12 + adds $d0,$d0,$d2,lsl#52 + add $d1,$d1,x15,lsl#14 + adc $d1,$d1,xzr + lsr $d2,x16,#24 + adds $d1,$d1,x16,lsl#40 + adc $d2,$d2,xzr + + cmp $r0,#0 // is_base2_26? + csel $h0,$h0,$d0,eq // choose between radixes + csel $h1,$h1,$d1,eq + csel $h2,$h2,$d2,eq + + adds $d0,$h0,#5 // compare to modulus + adcs $d1,$h1,xzr + adc $d2,$h2,xzr + + tst $d2,#-4 // see if it's carried/borrowed + + csel $h0,$h0,$d0,eq + csel $h1,$h1,$d1,eq + +#ifdef __AARCH64EB__ + ror $t0,$t0,#32 // flip nonce words + ror $t1,$t1,#32 +#endif + adds $h0,$h0,$t0 // accumulate nonce + adc $h1,$h1,$t1 +#ifdef __AARCH64EB__ + rev $h0,$h0 // flip output bytes + rev $h1,$h1 +#endif + stp $h0,$h1,[$mac] // write result + + ret +.size poly1305_emit,.-poly1305_emit +___ +my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("v$_.4s",(0..8)); +my ($IN01_0,$IN01_1,$IN01_2,$IN01_3,$IN01_4) = map("v$_.2s",(9..13)); +my ($IN23_0,$IN23_1,$IN23_2,$IN23_3,$IN23_4) = map("v$_.2s",(14..18)); +my ($ACC0,$ACC1,$ACC2,$ACC3,$ACC4) = map("v$_.2d",(19..23)); +my ($H0,$H1,$H2,$H3,$H4) = map("v$_.2s",(24..28)); +my ($T0,$T1,$MASK) = map("v$_",(29..31)); + +my ($in2,$zeros)=("x16","x17"); +my $is_base2_26 = $zeros; # borrow + +$code.=<<___; +.type poly1305_mult,%function +.align 5 +poly1305_mult: + mul $d0,$h0,$r0 // h0*r0 + umulh $d1,$h0,$r0 + + mul $t0,$h1,$s1 // h1*5*r1 + umulh $t1,$h1,$s1 + + adds $d0,$d0,$t0 + mul $t0,$h0,$r1 // h0*r1 + adc $d1,$d1,$t1 + umulh $d2,$h0,$r1 + + adds $d1,$d1,$t0 + mul $t0,$h1,$r0 // h1*r0 + adc $d2,$d2,xzr + umulh $t1,$h1,$r0 + + adds $d1,$d1,$t0 + mul $t0,$h2,$s1 // h2*5*r1 + adc $d2,$d2,$t1 + mul $t1,$h2,$r0 // h2*r0 + + adds $d1,$d1,$t0 + adc $d2,$d2,$t1 + + and $t0,$d2,#-4 // final reduction + and $h2,$d2,#3 + add $t0,$t0,$d2,lsr#2 + adds $h0,$d0,$t0 + adcs $h1,$d1,xzr + adc $h2,$h2,xzr + + ret +.size poly1305_mult,.-poly1305_mult + +.type poly1305_splat,%function +.align 4 +poly1305_splat: + and x12,$h0,#0x03ffffff // base 2^64 -> base 2^26 + ubfx x13,$h0,#26,#26 + extr x14,$h1,$h0,#52 + and x14,x14,#0x03ffffff + ubfx x15,$h1,#14,#26 + extr x16,$h2,$h1,#40 + + str w12,[$ctx,#16*0] // r0 + add w12,w13,w13,lsl#2 // r1*5 + str w13,[$ctx,#16*1] // r1 + add w13,w14,w14,lsl#2 // r2*5 + str w12,[$ctx,#16*2] // s1 + str w14,[$ctx,#16*3] // r2 + add w14,w15,w15,lsl#2 // r3*5 + str w13,[$ctx,#16*4] // s2 + str w15,[$ctx,#16*5] // r3 + add w15,w16,w16,lsl#2 // r4*5 + str w14,[$ctx,#16*6] // s3 + str w16,[$ctx,#16*7] // r4 + str w15,[$ctx,#16*8] // s4 + + ret +.size poly1305_splat,.-poly1305_splat + +#ifdef __KERNEL__ +.globl poly1305_blocks_neon +#endif +.type poly1305_blocks_neon,%function +.align 5 +poly1305_blocks_neon: +.Lpoly1305_blocks_neon: + ldr $is_base2_26,[$ctx,#24] + cmp $len,#128 + b.lo .Lpoly1305_blocks + + .inst 0xd503233f // paciasp + stp x29,x30,[sp,#-80]! + add x29,sp,#0 + + stp d8,d9,[sp,#16] // meet ABI requirements + stp d10,d11,[sp,#32] + stp d12,d13,[sp,#48] + stp d14,d15,[sp,#64] + + cbz $is_base2_26,.Lbase2_64_neon + + ldp w10,w11,[$ctx] // load hash value base 2^26 + ldp w12,w13,[$ctx,#8] + ldr w14,[$ctx,#16] + + tst $len,#31 + b.eq .Leven_neon + + ldp $r0,$r1,[$ctx,#32] // load key value + + add $h0,x10,x11,lsl#26 // base 2^26 -> base 2^64 + lsr $h1,x12,#12 + adds $h0,$h0,x12,lsl#52 + add $h1,$h1,x13,lsl#14 + adc $h1,$h1,xzr + lsr $h2,x14,#24 + adds $h1,$h1,x14,lsl#40 + adc $d2,$h2,xzr // can be partially reduced... + + ldp $d0,$d1,[$inp],#16 // load input + sub $len,$len,#16 + add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) + +#ifdef __AARCH64EB__ + rev $d0,$d0 + rev $d1,$d1 +#endif + adds $h0,$h0,$d0 // accumulate input + adcs $h1,$h1,$d1 + adc $h2,$h2,$padbit + + bl poly1305_mult + + and x10,$h0,#0x03ffffff // base 2^64 -> base 2^26 + ubfx x11,$h0,#26,#26 + extr x12,$h1,$h0,#52 + and x12,x12,#0x03ffffff + ubfx x13,$h1,#14,#26 + extr x14,$h2,$h1,#40 + + b .Leven_neon + +.align 4 +.Lbase2_64_neon: + ldp $r0,$r1,[$ctx,#32] // load key value + + ldp $h0,$h1,[$ctx] // load hash value base 2^64 + ldr $h2,[$ctx,#16] + + tst $len,#31 + b.eq .Linit_neon + + ldp $d0,$d1,[$inp],#16 // load input + sub $len,$len,#16 + add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) +#ifdef __AARCH64EB__ + rev $d0,$d0 + rev $d1,$d1 +#endif + adds $h0,$h0,$d0 // accumulate input + adcs $h1,$h1,$d1 + adc $h2,$h2,$padbit + + bl poly1305_mult + +.Linit_neon: + ldr w17,[$ctx,#48] // first table element + and x10,$h0,#0x03ffffff // base 2^64 -> base 2^26 + ubfx x11,$h0,#26,#26 + extr x12,$h1,$h0,#52 + and x12,x12,#0x03ffffff + ubfx x13,$h1,#14,#26 + extr x14,$h2,$h1,#40 + + cmp w17,#-1 // is value impossible? + b.ne .Leven_neon + + fmov ${H0},x10 + fmov ${H1},x11 + fmov ${H2},x12 + fmov ${H3},x13 + fmov ${H4},x14 + + ////////////////////////////////// initialize r^n table + mov $h0,$r0 // r^1 + add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) + mov $h1,$r1 + mov $h2,xzr + add $ctx,$ctx,#48+12 + bl poly1305_splat + + bl poly1305_mult // r^2 + sub $ctx,$ctx,#4 + bl poly1305_splat + + bl poly1305_mult // r^3 + sub $ctx,$ctx,#4 + bl poly1305_splat + + bl poly1305_mult // r^4 + sub $ctx,$ctx,#4 + bl poly1305_splat + sub $ctx,$ctx,#48 // restore original $ctx + b .Ldo_neon + +.align 4 +.Leven_neon: + fmov ${H0},x10 + fmov ${H1},x11 + fmov ${H2},x12 + fmov ${H3},x13 + fmov ${H4},x14 + +.Ldo_neon: + ldp x8,x12,[$inp,#32] // inp[2:3] + subs $len,$len,#64 + ldp x9,x13,[$inp,#48] + add $in2,$inp,#96 + adr $zeros,.Lzeros + + lsl $padbit,$padbit,#24 + add x15,$ctx,#48 + +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + and x5,x9,#0x03ffffff + ubfx x6,x8,#26,#26 + ubfx x7,x9,#26,#26 + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + extr x8,x12,x8,#52 + extr x9,x13,x9,#52 + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + fmov $IN23_0,x4 + and x8,x8,#0x03ffffff + and x9,x9,#0x03ffffff + ubfx x10,x12,#14,#26 + ubfx x11,x13,#14,#26 + add x12,$padbit,x12,lsr#40 + add x13,$padbit,x13,lsr#40 + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + fmov $IN23_1,x6 + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + fmov $IN23_2,x8 + fmov $IN23_3,x10 + fmov $IN23_4,x12 + + ldp x8,x12,[$inp],#16 // inp[0:1] + ldp x9,x13,[$inp],#48 + + ld1 {$R0,$R1,$S1,$R2},[x15],#64 + ld1 {$S2,$R3,$S3,$R4},[x15],#64 + ld1 {$S4},[x15] + +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + and x5,x9,#0x03ffffff + ubfx x6,x8,#26,#26 + ubfx x7,x9,#26,#26 + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + extr x8,x12,x8,#52 + extr x9,x13,x9,#52 + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + fmov $IN01_0,x4 + and x8,x8,#0x03ffffff + and x9,x9,#0x03ffffff + ubfx x10,x12,#14,#26 + ubfx x11,x13,#14,#26 + add x12,$padbit,x12,lsr#40 + add x13,$padbit,x13,lsr#40 + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + fmov $IN01_1,x6 + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + movi $MASK.2d,#-1 + fmov $IN01_2,x8 + fmov $IN01_3,x10 + fmov $IN01_4,x12 + ushr $MASK.2d,$MASK.2d,#38 + + b.ls .Lskip_loop + +.align 4 +.Loop_neon: + //////////////////////////////////////////////////////////////// + // ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2 + // ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r + // \___________________/ + // ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2 + // ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r + // \___________________/ \____________________/ + // + // Note that we start with inp[2:3]*r^2. This is because it + // doesn't depend on reduction in previous iteration. + //////////////////////////////////////////////////////////////// + // d4 = h0*r4 + h1*r3 + h2*r2 + h3*r1 + h4*r0 + // d3 = h0*r3 + h1*r2 + h2*r1 + h3*r0 + h4*5*r4 + // d2 = h0*r2 + h1*r1 + h2*r0 + h3*5*r4 + h4*5*r3 + // d1 = h0*r1 + h1*r0 + h2*5*r4 + h3*5*r3 + h4*5*r2 + // d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1 + + subs $len,$len,#64 + umull $ACC4,$IN23_0,${R4}[2] + csel $in2,$zeros,$in2,lo + umull $ACC3,$IN23_0,${R3}[2] + umull $ACC2,$IN23_0,${R2}[2] + ldp x8,x12,[$in2],#16 // inp[2:3] (or zero) + umull $ACC1,$IN23_0,${R1}[2] + ldp x9,x13,[$in2],#48 + umull $ACC0,$IN23_0,${R0}[2] +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + + umlal $ACC4,$IN23_1,${R3}[2] + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + umlal $ACC3,$IN23_1,${R2}[2] + and x5,x9,#0x03ffffff + umlal $ACC2,$IN23_1,${R1}[2] + ubfx x6,x8,#26,#26 + umlal $ACC1,$IN23_1,${R0}[2] + ubfx x7,x9,#26,#26 + umlal $ACC0,$IN23_1,${S4}[2] + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + + umlal $ACC4,$IN23_2,${R2}[2] + extr x8,x12,x8,#52 + umlal $ACC3,$IN23_2,${R1}[2] + extr x9,x13,x9,#52 + umlal $ACC2,$IN23_2,${R0}[2] + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + umlal $ACC1,$IN23_2,${S4}[2] + fmov $IN23_0,x4 + umlal $ACC0,$IN23_2,${S3}[2] + and x8,x8,#0x03ffffff + + umlal $ACC4,$IN23_3,${R1}[2] + and x9,x9,#0x03ffffff + umlal $ACC3,$IN23_3,${R0}[2] + ubfx x10,x12,#14,#26 + umlal $ACC2,$IN23_3,${S4}[2] + ubfx x11,x13,#14,#26 + umlal $ACC1,$IN23_3,${S3}[2] + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + umlal $ACC0,$IN23_3,${S2}[2] + fmov $IN23_1,x6 + + add $IN01_2,$IN01_2,$H2 + add x12,$padbit,x12,lsr#40 + umlal $ACC4,$IN23_4,${R0}[2] + add x13,$padbit,x13,lsr#40 + umlal $ACC3,$IN23_4,${S4}[2] + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + umlal $ACC2,$IN23_4,${S3}[2] + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + umlal $ACC1,$IN23_4,${S2}[2] + fmov $IN23_2,x8 + umlal $ACC0,$IN23_4,${S1}[2] + fmov $IN23_3,x10 + + //////////////////////////////////////////////////////////////// + // (hash+inp[0:1])*r^4 and accumulate + + add $IN01_0,$IN01_0,$H0 + fmov $IN23_4,x12 + umlal $ACC3,$IN01_2,${R1}[0] + ldp x8,x12,[$inp],#16 // inp[0:1] + umlal $ACC0,$IN01_2,${S3}[0] + ldp x9,x13,[$inp],#48 + umlal $ACC4,$IN01_2,${R2}[0] + umlal $ACC1,$IN01_2,${S4}[0] + umlal $ACC2,$IN01_2,${R0}[0] +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + + add $IN01_1,$IN01_1,$H1 + umlal $ACC3,$IN01_0,${R3}[0] + umlal $ACC4,$IN01_0,${R4}[0] + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + umlal $ACC2,$IN01_0,${R2}[0] + and x5,x9,#0x03ffffff + umlal $ACC0,$IN01_0,${R0}[0] + ubfx x6,x8,#26,#26 + umlal $ACC1,$IN01_0,${R1}[0] + ubfx x7,x9,#26,#26 + + add $IN01_3,$IN01_3,$H3 + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + umlal $ACC3,$IN01_1,${R2}[0] + extr x8,x12,x8,#52 + umlal $ACC4,$IN01_1,${R3}[0] + extr x9,x13,x9,#52 + umlal $ACC0,$IN01_1,${S4}[0] + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + umlal $ACC2,$IN01_1,${R1}[0] + fmov $IN01_0,x4 + umlal $ACC1,$IN01_1,${R0}[0] + and x8,x8,#0x03ffffff + + add $IN01_4,$IN01_4,$H4 + and x9,x9,#0x03ffffff + umlal $ACC3,$IN01_3,${R0}[0] + ubfx x10,x12,#14,#26 + umlal $ACC0,$IN01_3,${S2}[0] + ubfx x11,x13,#14,#26 + umlal $ACC4,$IN01_3,${R1}[0] + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + umlal $ACC1,$IN01_3,${S3}[0] + fmov $IN01_1,x6 + umlal $ACC2,$IN01_3,${S4}[0] + add x12,$padbit,x12,lsr#40 + + umlal $ACC3,$IN01_4,${S4}[0] + add x13,$padbit,x13,lsr#40 + umlal $ACC0,$IN01_4,${S1}[0] + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + umlal $ACC4,$IN01_4,${R0}[0] + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + umlal $ACC1,$IN01_4,${S2}[0] + fmov $IN01_2,x8 + umlal $ACC2,$IN01_4,${S3}[0] + fmov $IN01_3,x10 + fmov $IN01_4,x12 + + ///////////////////////////////////////////////////////////////// + // lazy reduction as discussed in "NEON crypto" by D.J. Bernstein + // and P. Schwabe + // + // [see discussion in poly1305-armv4 module] + + ushr $T0.2d,$ACC3,#26 + xtn $H3,$ACC3 + ushr $T1.2d,$ACC0,#26 + and $ACC0,$ACC0,$MASK.2d + add $ACC4,$ACC4,$T0.2d // h3 -> h4 + bic $H3,#0xfc,lsl#24 // &=0x03ffffff + add $ACC1,$ACC1,$T1.2d // h0 -> h1 + + ushr $T0.2d,$ACC4,#26 + xtn $H4,$ACC4 + ushr $T1.2d,$ACC1,#26 + xtn $H1,$ACC1 + bic $H4,#0xfc,lsl#24 + add $ACC2,$ACC2,$T1.2d // h1 -> h2 + + add $ACC0,$ACC0,$T0.2d + shl $T0.2d,$T0.2d,#2 + shrn $T1.2s,$ACC2,#26 + xtn $H2,$ACC2 + add $ACC0,$ACC0,$T0.2d // h4 -> h0 + bic $H1,#0xfc,lsl#24 + add $H3,$H3,$T1.2s // h2 -> h3 + bic $H2,#0xfc,lsl#24 + + shrn $T0.2s,$ACC0,#26 + xtn $H0,$ACC0 + ushr $T1.2s,$H3,#26 + bic $H3,#0xfc,lsl#24 + bic $H0,#0xfc,lsl#24 + add $H1,$H1,$T0.2s // h0 -> h1 + add $H4,$H4,$T1.2s // h3 -> h4 + + b.hi .Loop_neon + +.Lskip_loop: + dup $IN23_2,${IN23_2}[0] + add $IN01_2,$IN01_2,$H2 + + //////////////////////////////////////////////////////////////// + // multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 + + adds $len,$len,#32 + b.ne .Long_tail + + dup $IN23_2,${IN01_2}[0] + add $IN23_0,$IN01_0,$H0 + add $IN23_3,$IN01_3,$H3 + add $IN23_1,$IN01_1,$H1 + add $IN23_4,$IN01_4,$H4 + +.Long_tail: + dup $IN23_0,${IN23_0}[0] + umull2 $ACC0,$IN23_2,${S3} + umull2 $ACC3,$IN23_2,${R1} + umull2 $ACC4,$IN23_2,${R2} + umull2 $ACC2,$IN23_2,${R0} + umull2 $ACC1,$IN23_2,${S4} + + dup $IN23_1,${IN23_1}[0] + umlal2 $ACC0,$IN23_0,${R0} + umlal2 $ACC2,$IN23_0,${R2} + umlal2 $ACC3,$IN23_0,${R3} + umlal2 $ACC4,$IN23_0,${R4} + umlal2 $ACC1,$IN23_0,${R1} + + dup $IN23_3,${IN23_3}[0] + umlal2 $ACC0,$IN23_1,${S4} + umlal2 $ACC3,$IN23_1,${R2} + umlal2 $ACC2,$IN23_1,${R1} + umlal2 $ACC4,$IN23_1,${R3} + umlal2 $ACC1,$IN23_1,${R0} + + dup $IN23_4,${IN23_4}[0] + umlal2 $ACC3,$IN23_3,${R0} + umlal2 $ACC4,$IN23_3,${R1} + umlal2 $ACC0,$IN23_3,${S2} + umlal2 $ACC1,$IN23_3,${S3} + umlal2 $ACC2,$IN23_3,${S4} + + umlal2 $ACC3,$IN23_4,${S4} + umlal2 $ACC0,$IN23_4,${S1} + umlal2 $ACC4,$IN23_4,${R0} + umlal2 $ACC1,$IN23_4,${S2} + umlal2 $ACC2,$IN23_4,${S3} + + b.eq .Lshort_tail + + //////////////////////////////////////////////////////////////// + // (hash+inp[0:1])*r^4:r^3 and accumulate + + add $IN01_0,$IN01_0,$H0 + umlal $ACC3,$IN01_2,${R1} + umlal $ACC0,$IN01_2,${S3} + umlal $ACC4,$IN01_2,${R2} + umlal $ACC1,$IN01_2,${S4} + umlal $ACC2,$IN01_2,${R0} + + add $IN01_1,$IN01_1,$H1 + umlal $ACC3,$IN01_0,${R3} + umlal $ACC0,$IN01_0,${R0} + umlal $ACC4,$IN01_0,${R4} + umlal $ACC1,$IN01_0,${R1} + umlal $ACC2,$IN01_0,${R2} + + add $IN01_3,$IN01_3,$H3 + umlal $ACC3,$IN01_1,${R2} + umlal $ACC0,$IN01_1,${S4} + umlal $ACC4,$IN01_1,${R3} + umlal $ACC1,$IN01_1,${R0} + umlal $ACC2,$IN01_1,${R1} + + add $IN01_4,$IN01_4,$H4 + umlal $ACC3,$IN01_3,${R0} + umlal $ACC0,$IN01_3,${S2} + umlal $ACC4,$IN01_3,${R1} + umlal $ACC1,$IN01_3,${S3} + umlal $ACC2,$IN01_3,${S4} + + umlal $ACC3,$IN01_4,${S4} + umlal $ACC0,$IN01_4,${S1} + umlal $ACC4,$IN01_4,${R0} + umlal $ACC1,$IN01_4,${S2} + umlal $ACC2,$IN01_4,${S3} + +.Lshort_tail: + //////////////////////////////////////////////////////////////// + // horizontal add + + addp $ACC3,$ACC3,$ACC3 + ldp d8,d9,[sp,#16] // meet ABI requirements + addp $ACC0,$ACC0,$ACC0 + ldp d10,d11,[sp,#32] + addp $ACC4,$ACC4,$ACC4 + ldp d12,d13,[sp,#48] + addp $ACC1,$ACC1,$ACC1 + ldp d14,d15,[sp,#64] + addp $ACC2,$ACC2,$ACC2 + ldr x30,[sp,#8] + .inst 0xd50323bf // autiasp + + //////////////////////////////////////////////////////////////// + // lazy reduction, but without narrowing + + ushr $T0.2d,$ACC3,#26 + and $ACC3,$ACC3,$MASK.2d + ushr $T1.2d,$ACC0,#26 + and $ACC0,$ACC0,$MASK.2d + + add $ACC4,$ACC4,$T0.2d // h3 -> h4 + add $ACC1,$ACC1,$T1.2d // h0 -> h1 + + ushr $T0.2d,$ACC4,#26 + and $ACC4,$ACC4,$MASK.2d + ushr $T1.2d,$ACC1,#26 + and $ACC1,$ACC1,$MASK.2d + add $ACC2,$ACC2,$T1.2d // h1 -> h2 + + add $ACC0,$ACC0,$T0.2d + shl $T0.2d,$T0.2d,#2 + ushr $T1.2d,$ACC2,#26 + and $ACC2,$ACC2,$MASK.2d + add $ACC0,$ACC0,$T0.2d // h4 -> h0 + add $ACC3,$ACC3,$T1.2d // h2 -> h3 + + ushr $T0.2d,$ACC0,#26 + and $ACC0,$ACC0,$MASK.2d + ushr $T1.2d,$ACC3,#26 + and $ACC3,$ACC3,$MASK.2d + add $ACC1,$ACC1,$T0.2d // h0 -> h1 + add $ACC4,$ACC4,$T1.2d // h3 -> h4 + + //////////////////////////////////////////////////////////////// + // write the result, can be partially reduced + + st4 {$ACC0,$ACC1,$ACC2,$ACC3}[0],[$ctx],#16 + mov x4,#1 + st1 {$ACC4}[0],[$ctx] + str x4,[$ctx,#8] // set is_base2_26 + + ldr x29,[sp],#80 + ret +.size poly1305_blocks_neon,.-poly1305_blocks_neon + +.align 5 +.Lzeros: +.long 0,0,0,0,0,0,0,0 +.asciz "Poly1305 for ARMv8, CRYPTOGAMS by \@dot-asm" +.align 2 +#if !defined(__KERNEL__) && !defined(_WIN64) +.comm OPENSSL_armcap_P,4,4 +.hidden OPENSSL_armcap_P +#endif +___ + +foreach (split("\n",$code)) { + s/\b(shrn\s+v[0-9]+)\.[24]d/$1.2s/ or + s/\b(fmov\s+)v([0-9]+)[^,]*,\s*x([0-9]+)/$1d$2,x$3/ or + (m/\bdup\b/ and (s/\.[24]s/.2d/g or 1)) or + (m/\b(eor|and)/ and (s/\.[248][sdh]/.16b/g or 1)) or + (m/\bum(ul|la)l\b/ and (s/\.4s/.2s/g or 1)) or + (m/\bum(ul|la)l2\b/ and (s/\.2s/.4s/g or 1)) or + (m/\bst[1-4]\s+{[^}]+}\[/ and (s/\.[24]d/.s/g or 1)); + + s/\.[124]([sd])\[/.$1\[/; + s/w#x([0-9]+)/w$1/g; + + print $_,"\n"; +} +close STDOUT; diff --git a/arch/arm64/crypto/poly1305-core.S_shipped b/arch/arm64/crypto/poly1305-core.S_shipped new file mode 100644 index 000000000000..8d1c4e420ccd --- /dev/null +++ b/arch/arm64/crypto/poly1305-core.S_shipped @@ -0,0 +1,835 @@ +#ifndef __KERNEL__ +# include "arm_arch.h" +.extern OPENSSL_armcap_P +#endif + +.text + +// forward "declarations" are required for Apple +.globl poly1305_blocks +.globl poly1305_emit + +.globl poly1305_init +.type poly1305_init,%function +.align 5 +poly1305_init: + cmp x1,xzr + stp xzr,xzr,[x0] // zero hash value + stp xzr,xzr,[x0,#16] // [along with is_base2_26] + + csel x0,xzr,x0,eq + b.eq .Lno_key + +#ifndef __KERNEL__ + adrp x17,OPENSSL_armcap_P + ldr w17,[x17,#:lo12:OPENSSL_armcap_P] +#endif + + ldp x7,x8,[x1] // load key + mov x9,#0xfffffffc0fffffff + movk x9,#0x0fff,lsl#48 +#ifdef __AARCH64EB__ + rev x7,x7 // flip bytes + rev x8,x8 +#endif + and x7,x7,x9 // &=0ffffffc0fffffff + and x9,x9,#-4 + and x8,x8,x9 // &=0ffffffc0ffffffc + mov w9,#-1 + stp x7,x8,[x0,#32] // save key value + str w9,[x0,#48] // impossible key power value + +#ifndef __KERNEL__ + tst w17,#ARMV7_NEON + + adr x12,.Lpoly1305_blocks + adr x7,.Lpoly1305_blocks_neon + adr x13,.Lpoly1305_emit + + csel x12,x12,x7,eq + +# ifdef __ILP32__ + stp w12,w13,[x2] +# else + stp x12,x13,[x2] +# endif +#endif + mov x0,#1 +.Lno_key: + ret +.size poly1305_init,.-poly1305_init + +.type poly1305_blocks,%function +.align 5 +poly1305_blocks: +.Lpoly1305_blocks: + ands x2,x2,#-16 + b.eq .Lno_data + + ldp x4,x5,[x0] // load hash value + ldp x6,x17,[x0,#16] // [along with is_base2_26] + ldp x7,x8,[x0,#32] // load key value + +#ifdef __AARCH64EB__ + lsr x12,x4,#32 + mov w13,w4 + lsr x14,x5,#32 + mov w15,w5 + lsr x16,x6,#32 +#else + mov w12,w4 + lsr x13,x4,#32 + mov w14,w5 + lsr x15,x5,#32 + mov w16,w6 +#endif + + add x12,x12,x13,lsl#26 // base 2^26 -> base 2^64 + lsr x13,x14,#12 + adds x12,x12,x14,lsl#52 + add x13,x13,x15,lsl#14 + adc x13,x13,xzr + lsr x14,x16,#24 + adds x13,x13,x16,lsl#40 + adc x14,x14,xzr + + cmp x17,#0 // is_base2_26? + add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) + csel x4,x4,x12,eq // choose between radixes + csel x5,x5,x13,eq + csel x6,x6,x14,eq + +.Loop: + ldp x10,x11,[x1],#16 // load input + sub x2,x2,#16 +#ifdef __AARCH64EB__ + rev x10,x10 + rev x11,x11 +#endif + adds x4,x4,x10 // accumulate input + adcs x5,x5,x11 + + mul x12,x4,x7 // h0*r0 + adc x6,x6,x3 + umulh x13,x4,x7 + + mul x10,x5,x9 // h1*5*r1 + umulh x11,x5,x9 + + adds x12,x12,x10 + mul x10,x4,x8 // h0*r1 + adc x13,x13,x11 + umulh x14,x4,x8 + + adds x13,x13,x10 + mul x10,x5,x7 // h1*r0 + adc x14,x14,xzr + umulh x11,x5,x7 + + adds x13,x13,x10 + mul x10,x6,x9 // h2*5*r1 + adc x14,x14,x11 + mul x11,x6,x7 // h2*r0 + + adds x13,x13,x10 + adc x14,x14,x11 + + and x10,x14,#-4 // final reduction + and x6,x14,#3 + add x10,x10,x14,lsr#2 + adds x4,x12,x10 + adcs x5,x13,xzr + adc x6,x6,xzr + + cbnz x2,.Loop + + stp x4,x5,[x0] // store hash value + stp x6,xzr,[x0,#16] // [and clear is_base2_26] + +.Lno_data: + ret +.size poly1305_blocks,.-poly1305_blocks + +.type poly1305_emit,%function +.align 5 +poly1305_emit: +.Lpoly1305_emit: + ldp x4,x5,[x0] // load hash base 2^64 + ldp x6,x7,[x0,#16] // [along with is_base2_26] + ldp x10,x11,[x2] // load nonce + +#ifdef __AARCH64EB__ + lsr x12,x4,#32 + mov w13,w4 + lsr x14,x5,#32 + mov w15,w5 + lsr x16,x6,#32 +#else + mov w12,w4 + lsr x13,x4,#32 + mov w14,w5 + lsr x15,x5,#32 + mov w16,w6 +#endif + + add x12,x12,x13,lsl#26 // base 2^26 -> base 2^64 + lsr x13,x14,#12 + adds x12,x12,x14,lsl#52 + add x13,x13,x15,lsl#14 + adc x13,x13,xzr + lsr x14,x16,#24 + adds x13,x13,x16,lsl#40 + adc x14,x14,xzr + + cmp x7,#0 // is_base2_26? + csel x4,x4,x12,eq // choose between radixes + csel x5,x5,x13,eq + csel x6,x6,x14,eq + + adds x12,x4,#5 // compare to modulus + adcs x13,x5,xzr + adc x14,x6,xzr + + tst x14,#-4 // see if it's carried/borrowed + + csel x4,x4,x12,eq + csel x5,x5,x13,eq + +#ifdef __AARCH64EB__ + ror x10,x10,#32 // flip nonce words + ror x11,x11,#32 +#endif + adds x4,x4,x10 // accumulate nonce + adc x5,x5,x11 +#ifdef __AARCH64EB__ + rev x4,x4 // flip output bytes + rev x5,x5 +#endif + stp x4,x5,[x1] // write result + + ret +.size poly1305_emit,.-poly1305_emit +.type poly1305_mult,%function +.align 5 +poly1305_mult: + mul x12,x4,x7 // h0*r0 + umulh x13,x4,x7 + + mul x10,x5,x9 // h1*5*r1 + umulh x11,x5,x9 + + adds x12,x12,x10 + mul x10,x4,x8 // h0*r1 + adc x13,x13,x11 + umulh x14,x4,x8 + + adds x13,x13,x10 + mul x10,x5,x7 // h1*r0 + adc x14,x14,xzr + umulh x11,x5,x7 + + adds x13,x13,x10 + mul x10,x6,x9 // h2*5*r1 + adc x14,x14,x11 + mul x11,x6,x7 // h2*r0 + + adds x13,x13,x10 + adc x14,x14,x11 + + and x10,x14,#-4 // final reduction + and x6,x14,#3 + add x10,x10,x14,lsr#2 + adds x4,x12,x10 + adcs x5,x13,xzr + adc x6,x6,xzr + + ret +.size poly1305_mult,.-poly1305_mult + +.type poly1305_splat,%function +.align 4 +poly1305_splat: + and x12,x4,#0x03ffffff // base 2^64 -> base 2^26 + ubfx x13,x4,#26,#26 + extr x14,x5,x4,#52 + and x14,x14,#0x03ffffff + ubfx x15,x5,#14,#26 + extr x16,x6,x5,#40 + + str w12,[x0,#16*0] // r0 + add w12,w13,w13,lsl#2 // r1*5 + str w13,[x0,#16*1] // r1 + add w13,w14,w14,lsl#2 // r2*5 + str w12,[x0,#16*2] // s1 + str w14,[x0,#16*3] // r2 + add w14,w15,w15,lsl#2 // r3*5 + str w13,[x0,#16*4] // s2 + str w15,[x0,#16*5] // r3 + add w15,w16,w16,lsl#2 // r4*5 + str w14,[x0,#16*6] // s3 + str w16,[x0,#16*7] // r4 + str w15,[x0,#16*8] // s4 + + ret +.size poly1305_splat,.-poly1305_splat + +#ifdef __KERNEL__ +.globl poly1305_blocks_neon +#endif +.type poly1305_blocks_neon,%function +.align 5 +poly1305_blocks_neon: +.Lpoly1305_blocks_neon: + ldr x17,[x0,#24] + cmp x2,#128 + b.lo .Lpoly1305_blocks + + .inst 0xd503233f // paciasp + stp x29,x30,[sp,#-80]! + add x29,sp,#0 + + stp d8,d9,[sp,#16] // meet ABI requirements + stp d10,d11,[sp,#32] + stp d12,d13,[sp,#48] + stp d14,d15,[sp,#64] + + cbz x17,.Lbase2_64_neon + + ldp w10,w11,[x0] // load hash value base 2^26 + ldp w12,w13,[x0,#8] + ldr w14,[x0,#16] + + tst x2,#31 + b.eq .Leven_neon + + ldp x7,x8,[x0,#32] // load key value + + add x4,x10,x11,lsl#26 // base 2^26 -> base 2^64 + lsr x5,x12,#12 + adds x4,x4,x12,lsl#52 + add x5,x5,x13,lsl#14 + adc x5,x5,xzr + lsr x6,x14,#24 + adds x5,x5,x14,lsl#40 + adc x14,x6,xzr // can be partially reduced... + + ldp x12,x13,[x1],#16 // load input + sub x2,x2,#16 + add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) + +#ifdef __AARCH64EB__ + rev x12,x12 + rev x13,x13 +#endif + adds x4,x4,x12 // accumulate input + adcs x5,x5,x13 + adc x6,x6,x3 + + bl poly1305_mult + + and x10,x4,#0x03ffffff // base 2^64 -> base 2^26 + ubfx x11,x4,#26,#26 + extr x12,x5,x4,#52 + and x12,x12,#0x03ffffff + ubfx x13,x5,#14,#26 + extr x14,x6,x5,#40 + + b .Leven_neon + +.align 4 +.Lbase2_64_neon: + ldp x7,x8,[x0,#32] // load key value + + ldp x4,x5,[x0] // load hash value base 2^64 + ldr x6,[x0,#16] + + tst x2,#31 + b.eq .Linit_neon + + ldp x12,x13,[x1],#16 // load input + sub x2,x2,#16 + add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) +#ifdef __AARCH64EB__ + rev x12,x12 + rev x13,x13 +#endif + adds x4,x4,x12 // accumulate input + adcs x5,x5,x13 + adc x6,x6,x3 + + bl poly1305_mult + +.Linit_neon: + ldr w17,[x0,#48] // first table element + and x10,x4,#0x03ffffff // base 2^64 -> base 2^26 + ubfx x11,x4,#26,#26 + extr x12,x5,x4,#52 + and x12,x12,#0x03ffffff + ubfx x13,x5,#14,#26 + extr x14,x6,x5,#40 + + cmp w17,#-1 // is value impossible? + b.ne .Leven_neon + + fmov d24,x10 + fmov d25,x11 + fmov d26,x12 + fmov d27,x13 + fmov d28,x14 + + ////////////////////////////////// initialize r^n table + mov x4,x7 // r^1 + add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) + mov x5,x8 + mov x6,xzr + add x0,x0,#48+12 + bl poly1305_splat + + bl poly1305_mult // r^2 + sub x0,x0,#4 + bl poly1305_splat + + bl poly1305_mult // r^3 + sub x0,x0,#4 + bl poly1305_splat + + bl poly1305_mult // r^4 + sub x0,x0,#4 + bl poly1305_splat + sub x0,x0,#48 // restore original x0 + b .Ldo_neon + +.align 4 +.Leven_neon: + fmov d24,x10 + fmov d25,x11 + fmov d26,x12 + fmov d27,x13 + fmov d28,x14 + +.Ldo_neon: + ldp x8,x12,[x1,#32] // inp[2:3] + subs x2,x2,#64 + ldp x9,x13,[x1,#48] + add x16,x1,#96 + adr x17,.Lzeros + + lsl x3,x3,#24 + add x15,x0,#48 + +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + and x5,x9,#0x03ffffff + ubfx x6,x8,#26,#26 + ubfx x7,x9,#26,#26 + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + extr x8,x12,x8,#52 + extr x9,x13,x9,#52 + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + fmov d14,x4 + and x8,x8,#0x03ffffff + and x9,x9,#0x03ffffff + ubfx x10,x12,#14,#26 + ubfx x11,x13,#14,#26 + add x12,x3,x12,lsr#40 + add x13,x3,x13,lsr#40 + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + fmov d15,x6 + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + fmov d16,x8 + fmov d17,x10 + fmov d18,x12 + + ldp x8,x12,[x1],#16 // inp[0:1] + ldp x9,x13,[x1],#48 + + ld1 {v0.4s,v1.4s,v2.4s,v3.4s},[x15],#64 + ld1 {v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64 + ld1 {v8.4s},[x15] + +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + and x5,x9,#0x03ffffff + ubfx x6,x8,#26,#26 + ubfx x7,x9,#26,#26 + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + extr x8,x12,x8,#52 + extr x9,x13,x9,#52 + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + fmov d9,x4 + and x8,x8,#0x03ffffff + and x9,x9,#0x03ffffff + ubfx x10,x12,#14,#26 + ubfx x11,x13,#14,#26 + add x12,x3,x12,lsr#40 + add x13,x3,x13,lsr#40 + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + fmov d10,x6 + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + movi v31.2d,#-1 + fmov d11,x8 + fmov d12,x10 + fmov d13,x12 + ushr v31.2d,v31.2d,#38 + + b.ls .Lskip_loop + +.align 4 +.Loop_neon: + //////////////////////////////////////////////////////////////// + // ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2 + // ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r + // ___________________/ + // ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2 + // ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r + // ___________________/ ____________________/ + // + // Note that we start with inp[2:3]*r^2. This is because it + // doesn't depend on reduction in previous iteration. + //////////////////////////////////////////////////////////////// + // d4 = h0*r4 + h1*r3 + h2*r2 + h3*r1 + h4*r0 + // d3 = h0*r3 + h1*r2 + h2*r1 + h3*r0 + h4*5*r4 + // d2 = h0*r2 + h1*r1 + h2*r0 + h3*5*r4 + h4*5*r3 + // d1 = h0*r1 + h1*r0 + h2*5*r4 + h3*5*r3 + h4*5*r2 + // d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1 + + subs x2,x2,#64 + umull v23.2d,v14.2s,v7.s[2] + csel x16,x17,x16,lo + umull v22.2d,v14.2s,v5.s[2] + umull v21.2d,v14.2s,v3.s[2] + ldp x8,x12,[x16],#16 // inp[2:3] (or zero) + umull v20.2d,v14.2s,v1.s[2] + ldp x9,x13,[x16],#48 + umull v19.2d,v14.2s,v0.s[2] +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + + umlal v23.2d,v15.2s,v5.s[2] + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + umlal v22.2d,v15.2s,v3.s[2] + and x5,x9,#0x03ffffff + umlal v21.2d,v15.2s,v1.s[2] + ubfx x6,x8,#26,#26 + umlal v20.2d,v15.2s,v0.s[2] + ubfx x7,x9,#26,#26 + umlal v19.2d,v15.2s,v8.s[2] + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + + umlal v23.2d,v16.2s,v3.s[2] + extr x8,x12,x8,#52 + umlal v22.2d,v16.2s,v1.s[2] + extr x9,x13,x9,#52 + umlal v21.2d,v16.2s,v0.s[2] + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + umlal v20.2d,v16.2s,v8.s[2] + fmov d14,x4 + umlal v19.2d,v16.2s,v6.s[2] + and x8,x8,#0x03ffffff + + umlal v23.2d,v17.2s,v1.s[2] + and x9,x9,#0x03ffffff + umlal v22.2d,v17.2s,v0.s[2] + ubfx x10,x12,#14,#26 + umlal v21.2d,v17.2s,v8.s[2] + ubfx x11,x13,#14,#26 + umlal v20.2d,v17.2s,v6.s[2] + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + umlal v19.2d,v17.2s,v4.s[2] + fmov d15,x6 + + add v11.2s,v11.2s,v26.2s + add x12,x3,x12,lsr#40 + umlal v23.2d,v18.2s,v0.s[2] + add x13,x3,x13,lsr#40 + umlal v22.2d,v18.2s,v8.s[2] + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + umlal v21.2d,v18.2s,v6.s[2] + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + umlal v20.2d,v18.2s,v4.s[2] + fmov d16,x8 + umlal v19.2d,v18.2s,v2.s[2] + fmov d17,x10 + + //////////////////////////////////////////////////////////////// + // (hash+inp[0:1])*r^4 and accumulate + + add v9.2s,v9.2s,v24.2s + fmov d18,x12 + umlal v22.2d,v11.2s,v1.s[0] + ldp x8,x12,[x1],#16 // inp[0:1] + umlal v19.2d,v11.2s,v6.s[0] + ldp x9,x13,[x1],#48 + umlal v23.2d,v11.2s,v3.s[0] + umlal v20.2d,v11.2s,v8.s[0] + umlal v21.2d,v11.2s,v0.s[0] +#ifdef __AARCH64EB__ + rev x8,x8 + rev x12,x12 + rev x9,x9 + rev x13,x13 +#endif + + add v10.2s,v10.2s,v25.2s + umlal v22.2d,v9.2s,v5.s[0] + umlal v23.2d,v9.2s,v7.s[0] + and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 + umlal v21.2d,v9.2s,v3.s[0] + and x5,x9,#0x03ffffff + umlal v19.2d,v9.2s,v0.s[0] + ubfx x6,x8,#26,#26 + umlal v20.2d,v9.2s,v1.s[0] + ubfx x7,x9,#26,#26 + + add v12.2s,v12.2s,v27.2s + add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 + umlal v22.2d,v10.2s,v3.s[0] + extr x8,x12,x8,#52 + umlal v23.2d,v10.2s,v5.s[0] + extr x9,x13,x9,#52 + umlal v19.2d,v10.2s,v8.s[0] + add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 + umlal v21.2d,v10.2s,v1.s[0] + fmov d9,x4 + umlal v20.2d,v10.2s,v0.s[0] + and x8,x8,#0x03ffffff + + add v13.2s,v13.2s,v28.2s + and x9,x9,#0x03ffffff + umlal v22.2d,v12.2s,v0.s[0] + ubfx x10,x12,#14,#26 + umlal v19.2d,v12.2s,v4.s[0] + ubfx x11,x13,#14,#26 + umlal v23.2d,v12.2s,v1.s[0] + add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 + umlal v20.2d,v12.2s,v6.s[0] + fmov d10,x6 + umlal v21.2d,v12.2s,v8.s[0] + add x12,x3,x12,lsr#40 + + umlal v22.2d,v13.2s,v8.s[0] + add x13,x3,x13,lsr#40 + umlal v19.2d,v13.2s,v2.s[0] + add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 + umlal v23.2d,v13.2s,v0.s[0] + add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 + umlal v20.2d,v13.2s,v4.s[0] + fmov d11,x8 + umlal v21.2d,v13.2s,v6.s[0] + fmov d12,x10 + fmov d13,x12 + + ///////////////////////////////////////////////////////////////// + // lazy reduction as discussed in "NEON crypto" by D.J. Bernstein + // and P. Schwabe + // + // [see discussion in poly1305-armv4 module] + + ushr v29.2d,v22.2d,#26 + xtn v27.2s,v22.2d + ushr v30.2d,v19.2d,#26 + and v19.16b,v19.16b,v31.16b + add v23.2d,v23.2d,v29.2d // h3 -> h4 + bic v27.2s,#0xfc,lsl#24 // &=0x03ffffff + add v20.2d,v20.2d,v30.2d // h0 -> h1 + + ushr v29.2d,v23.2d,#26 + xtn v28.2s,v23.2d + ushr v30.2d,v20.2d,#26 + xtn v25.2s,v20.2d + bic v28.2s,#0xfc,lsl#24 + add v21.2d,v21.2d,v30.2d // h1 -> h2 + + add v19.2d,v19.2d,v29.2d + shl v29.2d,v29.2d,#2 + shrn v30.2s,v21.2d,#26 + xtn v26.2s,v21.2d + add v19.2d,v19.2d,v29.2d // h4 -> h0 + bic v25.2s,#0xfc,lsl#24 + add v27.2s,v27.2s,v30.2s // h2 -> h3 + bic v26.2s,#0xfc,lsl#24 + + shrn v29.2s,v19.2d,#26 + xtn v24.2s,v19.2d + ushr v30.2s,v27.2s,#26 + bic v27.2s,#0xfc,lsl#24 + bic v24.2s,#0xfc,lsl#24 + add v25.2s,v25.2s,v29.2s // h0 -> h1 + add v28.2s,v28.2s,v30.2s // h3 -> h4 + + b.hi .Loop_neon + +.Lskip_loop: + dup v16.2d,v16.d[0] + add v11.2s,v11.2s,v26.2s + + //////////////////////////////////////////////////////////////// + // multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 + + adds x2,x2,#32 + b.ne .Long_tail + + dup v16.2d,v11.d[0] + add v14.2s,v9.2s,v24.2s + add v17.2s,v12.2s,v27.2s + add v15.2s,v10.2s,v25.2s + add v18.2s,v13.2s,v28.2s + +.Long_tail: + dup v14.2d,v14.d[0] + umull2 v19.2d,v16.4s,v6.4s + umull2 v22.2d,v16.4s,v1.4s + umull2 v23.2d,v16.4s,v3.4s + umull2 v21.2d,v16.4s,v0.4s + umull2 v20.2d,v16.4s,v8.4s + + dup v15.2d,v15.d[0] + umlal2 v19.2d,v14.4s,v0.4s + umlal2 v21.2d,v14.4s,v3.4s + umlal2 v22.2d,v14.4s,v5.4s + umlal2 v23.2d,v14.4s,v7.4s + umlal2 v20.2d,v14.4s,v1.4s + + dup v17.2d,v17.d[0] + umlal2 v19.2d,v15.4s,v8.4s + umlal2 v22.2d,v15.4s,v3.4s + umlal2 v21.2d,v15.4s,v1.4s + umlal2 v23.2d,v15.4s,v5.4s + umlal2 v20.2d,v15.4s,v0.4s + + dup v18.2d,v18.d[0] + umlal2 v22.2d,v17.4s,v0.4s + umlal2 v23.2d,v17.4s,v1.4s + umlal2 v19.2d,v17.4s,v4.4s + umlal2 v20.2d,v17.4s,v6.4s + umlal2 v21.2d,v17.4s,v8.4s + + umlal2 v22.2d,v18.4s,v8.4s + umlal2 v19.2d,v18.4s,v2.4s + umlal2 v23.2d,v18.4s,v0.4s + umlal2 v20.2d,v18.4s,v4.4s + umlal2 v21.2d,v18.4s,v6.4s + + b.eq .Lshort_tail + + //////////////////////////////////////////////////////////////// + // (hash+inp[0:1])*r^4:r^3 and accumulate + + add v9.2s,v9.2s,v24.2s + umlal v22.2d,v11.2s,v1.2s + umlal v19.2d,v11.2s,v6.2s + umlal v23.2d,v11.2s,v3.2s + umlal v20.2d,v11.2s,v8.2s + umlal v21.2d,v11.2s,v0.2s + + add v10.2s,v10.2s,v25.2s + umlal v22.2d,v9.2s,v5.2s + umlal v19.2d,v9.2s,v0.2s + umlal v23.2d,v9.2s,v7.2s + umlal v20.2d,v9.2s,v1.2s + umlal v21.2d,v9.2s,v3.2s + + add v12.2s,v12.2s,v27.2s + umlal v22.2d,v10.2s,v3.2s + umlal v19.2d,v10.2s,v8.2s + umlal v23.2d,v10.2s,v5.2s + umlal v20.2d,v10.2s,v0.2s + umlal v21.2d,v10.2s,v1.2s + + add v13.2s,v13.2s,v28.2s + umlal v22.2d,v12.2s,v0.2s + umlal v19.2d,v12.2s,v4.2s + umlal v23.2d,v12.2s,v1.2s + umlal v20.2d,v12.2s,v6.2s + umlal v21.2d,v12.2s,v8.2s + + umlal v22.2d,v13.2s,v8.2s + umlal v19.2d,v13.2s,v2.2s + umlal v23.2d,v13.2s,v0.2s + umlal v20.2d,v13.2s,v4.2s + umlal v21.2d,v13.2s,v6.2s + +.Lshort_tail: + //////////////////////////////////////////////////////////////// + // horizontal add + + addp v22.2d,v22.2d,v22.2d + ldp d8,d9,[sp,#16] // meet ABI requirements + addp v19.2d,v19.2d,v19.2d + ldp d10,d11,[sp,#32] + addp v23.2d,v23.2d,v23.2d + ldp d12,d13,[sp,#48] + addp v20.2d,v20.2d,v20.2d + ldp d14,d15,[sp,#64] + addp v21.2d,v21.2d,v21.2d + ldr x30,[sp,#8] + .inst 0xd50323bf // autiasp + + //////////////////////////////////////////////////////////////// + // lazy reduction, but without narrowing + + ushr v29.2d,v22.2d,#26 + and v22.16b,v22.16b,v31.16b + ushr v30.2d,v19.2d,#26 + and v19.16b,v19.16b,v31.16b + + add v23.2d,v23.2d,v29.2d // h3 -> h4 + add v20.2d,v20.2d,v30.2d // h0 -> h1 + + ushr v29.2d,v23.2d,#26 + and v23.16b,v23.16b,v31.16b + ushr v30.2d,v20.2d,#26 + and v20.16b,v20.16b,v31.16b + add v21.2d,v21.2d,v30.2d // h1 -> h2 + + add v19.2d,v19.2d,v29.2d + shl v29.2d,v29.2d,#2 + ushr v30.2d,v21.2d,#26 + and v21.16b,v21.16b,v31.16b + add v19.2d,v19.2d,v29.2d // h4 -> h0 + add v22.2d,v22.2d,v30.2d // h2 -> h3 + + ushr v29.2d,v19.2d,#26 + and v19.16b,v19.16b,v31.16b + ushr v30.2d,v22.2d,#26 + and v22.16b,v22.16b,v31.16b + add v20.2d,v20.2d,v29.2d // h0 -> h1 + add v23.2d,v23.2d,v30.2d // h3 -> h4 + + //////////////////////////////////////////////////////////////// + // write the result, can be partially reduced + + st4 {v19.s,v20.s,v21.s,v22.s}[0],[x0],#16 + mov x4,#1 + st1 {v23.s}[0],[x0] + str x4,[x0,#8] // set is_base2_26 + + ldr x29,[sp],#80 + ret +.size poly1305_blocks_neon,.-poly1305_blocks_neon + +.align 5 +.Lzeros: +.long 0,0,0,0,0,0,0,0 +.asciz "Poly1305 for ARMv8, CRYPTOGAMS by @dot-asm" +.align 2 +#if !defined(__KERNEL__) && !defined(_WIN64) +.comm OPENSSL_armcap_P,4,4 +.hidden OPENSSL_armcap_P +#endif diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c new file mode 100644 index 000000000000..dd843d0ee83a --- /dev/null +++ b/arch/arm64/crypto/poly1305-glue.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64 + * + * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org> + */ + +#include <asm/hwcap.h> +#include <asm/neon.h> +#include <asm/simd.h> +#include <asm/unaligned.h> +#include <crypto/algapi.h> +#include <crypto/internal/hash.h> +#include <crypto/internal/poly1305.h> +#include <crypto/internal/simd.h> +#include <linux/cpufeature.h> +#include <linux/crypto.h> +#include <linux/jump_label.h> +#include <linux/module.h> + +asmlinkage void poly1305_init_arm64(void *state, const u8 *key); +asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit); +asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit); +asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); + +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +{ + poly1305_init_arm64(&dctx->h, key); + dctx->s[0] = get_unaligned_le32(key + 16); + dctx->s[1] = get_unaligned_le32(key + 20); + dctx->s[2] = get_unaligned_le32(key + 24); + dctx->s[3] = get_unaligned_le32(key + 28); + dctx->buflen = 0; +} +EXPORT_SYMBOL(poly1305_init_arch); + +static int neon_poly1305_init(struct shash_desc *desc) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + dctx->buflen = 0; + dctx->rset = 0; + dctx->sset = false; + + return 0; +} + +static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src, + u32 len, u32 hibit, bool do_neon) +{ + if (unlikely(!dctx->sset)) { + if (!dctx->rset) { + poly1305_init_arch(dctx, src); + src += POLY1305_BLOCK_SIZE; + len -= POLY1305_BLOCK_SIZE; + dctx->rset = 1; + } + if (len >= POLY1305_BLOCK_SIZE) { + dctx->s[0] = get_unaligned_le32(src + 0); + dctx->s[1] = get_unaligned_le32(src + 4); + dctx->s[2] = get_unaligned_le32(src + 8); + dctx->s[3] = get_unaligned_le32(src + 12); + src += POLY1305_BLOCK_SIZE; + len -= POLY1305_BLOCK_SIZE; + dctx->sset = true; + } + if (len < POLY1305_BLOCK_SIZE) + return; + } + + len &= ~(POLY1305_BLOCK_SIZE - 1); + + if (static_branch_likely(&have_neon) && likely(do_neon)) + poly1305_blocks_neon(&dctx->h, src, len, hibit); + else + poly1305_blocks(&dctx->h, src, len, hibit); +} + +static void neon_poly1305_do_update(struct poly1305_desc_ctx *dctx, + const u8 *src, u32 len, bool do_neon) +{ + if (unlikely(dctx->buflen)) { + u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen); + + memcpy(dctx->buf + dctx->buflen, src, bytes); + src += bytes; + len -= bytes; + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { + neon_poly1305_blocks(dctx, dctx->buf, + POLY1305_BLOCK_SIZE, 1, false); + dctx->buflen = 0; + } + } + + if (likely(len >= POLY1305_BLOCK_SIZE)) { + neon_poly1305_blocks(dctx, src, len, 1, do_neon); + src += round_down(len, POLY1305_BLOCK_SIZE); + len %= POLY1305_BLOCK_SIZE; + } + + if (unlikely(len)) { + dctx->buflen = len; + memcpy(dctx->buf, src, len); + } +} + +static int neon_poly1305_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + bool do_neon = crypto_simd_usable() && srclen > 128; + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + if (static_branch_likely(&have_neon) && do_neon) + kernel_neon_begin(); + neon_poly1305_do_update(dctx, src, srclen, do_neon); + if (static_branch_likely(&have_neon) && do_neon) + kernel_neon_end(); + return 0; +} + +void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, + unsigned int nbytes) +{ + if (unlikely(dctx->buflen)) { + u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen); + + memcpy(dctx->buf + dctx->buflen, src, bytes); + src += bytes; + nbytes -= bytes; + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { + poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1); + dctx->buflen = 0; + } + } + + if (likely(nbytes >= POLY1305_BLOCK_SIZE)) { + unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); + + if (static_branch_likely(&have_neon) && crypto_simd_usable()) { + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, len, 1); + kernel_neon_end(); + } else { + poly1305_blocks(&dctx->h, src, len, 1); + } + src += len; + nbytes %= POLY1305_BLOCK_SIZE; + } + + if (unlikely(nbytes)) { + dctx->buflen = nbytes; + memcpy(dctx->buf, src, nbytes); + } +} +EXPORT_SYMBOL(poly1305_update_arch); + +void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst) +{ + __le32 digest[4]; + u64 f = 0; + + if (unlikely(dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, + POLY1305_BLOCK_SIZE - dctx->buflen); + poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + + poly1305_emit(&dctx->h, digest, dctx->s); + + /* mac = (h + s) % (2^128) */ + f = (f >> 32) + le32_to_cpu(digest[0]); + put_unaligned_le32(f, dst); + f = (f >> 32) + le32_to_cpu(digest[1]); + put_unaligned_le32(f, dst + 4); + f = (f >> 32) + le32_to_cpu(digest[2]); + put_unaligned_le32(f, dst + 8); + f = (f >> 32) + le32_to_cpu(digest[3]); + put_unaligned_le32(f, dst + 12); + + *dctx = (struct poly1305_desc_ctx){}; +} +EXPORT_SYMBOL(poly1305_final_arch); + +static int neon_poly1305_final(struct shash_desc *desc, u8 *dst) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + + if (unlikely(!dctx->sset)) + return -ENOKEY; + + poly1305_final_arch(dctx, dst); + return 0; +} + +static struct shash_alg neon_poly1305_alg = { + .init = neon_poly1305_init, + .update = neon_poly1305_update, + .final = neon_poly1305_final, + .digestsize = POLY1305_DIGEST_SIZE, + .descsize = sizeof(struct poly1305_desc_ctx), + + .base.cra_name = "poly1305", + .base.cra_driver_name = "poly1305-neon", + .base.cra_priority = 200, + .base.cra_blocksize = POLY1305_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, +}; + +static int __init neon_poly1305_mod_init(void) +{ + if (!cpu_have_named_feature(ASIMD)) + return 0; + + static_branch_enable(&have_neon); + + return crypto_register_shash(&neon_poly1305_alg); +} + +static void __exit neon_poly1305_mod_exit(void) +{ + if (cpu_have_named_feature(ASIMD)) + crypto_unregister_shash(&neon_poly1305_alg); +} + +module_init(neon_poly1305_mod_init); +module_exit(neon_poly1305_mod_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("poly1305"); +MODULE_ALIAS_CRYPTO("poly1305-neon"); diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index 5bf963830b17..f68a0e64482a 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -58,29 +58,4 @@ alternative_else_nop_endif .endm #endif -/* - * These macros are no-ops when UAO is present. - */ - .macro uaccess_disable_not_uao, tmp1, tmp2 - uaccess_ttbr0_disable \tmp1, \tmp2 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(1) -alternative_else_nop_endif - .endm - - .macro uaccess_enable_not_uao, tmp1, tmp2, tmp3 - uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(0) -alternative_else_nop_endif - .endm - -/* - * Remove the address tag from a virtual address, if present. - */ - .macro untagged_addr, dst, addr - sbfx \dst, \addr, #0, #56 - and \dst, \dst, \addr - .endm - #endif diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index e0e2b1946f42..7d9cc5ec4971 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -29,6 +29,18 @@ SB_BARRIER_INSN"nop\n", \ ARM64_HAS_SB)) +#ifdef CONFIG_ARM64_PSEUDO_NMI +#define pmr_sync() \ + do { \ + extern struct static_key_false gic_pmr_sync; \ + \ + if (static_branch_unlikely(&gic_pmr_sync)) \ + dsb(sy); \ + } while(0) +#else +#define pmr_sync() do {} while (0) +#endif + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 43da6dd29592..806e9dc2a852 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -11,6 +11,7 @@ #define CTR_L1IP_MASK 3 #define CTR_DMINLINE_SHIFT 16 #define CTR_IMINLINE_SHIFT 0 +#define CTR_IMINLINE_MASK 0xf #define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 @@ -18,7 +19,7 @@ #define CTR_DIC_SHIFT 29 #define CTR_CACHE_MINLINE_MASK \ - (0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT) + (0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT) #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index ac1dbca3d0cd..b92683871119 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -54,7 +54,9 @@ #define ARM64_WORKAROUND_1463225 44 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 +#define ARM64_WORKAROUND_1542419 47 +#define ARM64_WORKAROUND_1319367 48 -#define ARM64_NCAPS 47 +#define ARM64_NCAPS 49 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9cde5d2e768f..4261d55e8506 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -659,6 +659,20 @@ static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) default: return CONFIG_ARM64_PA_BITS; } } + +/* Check whether hardware update of the Access flag is supported */ +static inline bool cpu_has_hw_af(void) +{ + u64 mmfr1; + + if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) + return false; + + mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_HADBS_SHIFT); +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 063c964af705..72acd2db167f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -8,7 +8,9 @@ #include <linux/irqflags.h> #include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/ptrace.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT @@ -65,7 +67,7 @@ static inline void local_daif_restore(unsigned long flags) if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); - dsb(sy); + pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; @@ -109,4 +111,19 @@ static inline void local_daif_restore(unsigned long flags) trace_hardirqs_off(); } +/* + * Called by synchronous exception handlers to restore the DAIF bits that were + * modified by taking an exception. + */ +static inline void local_daif_inherit(struct pt_regs *regs) +{ + unsigned long flags = regs->pstate & DAIF_MASK; + + /* + * We can't use local_daif_restore(regs->pstate) here as + * system_has_prio_mask_debugging() won't restore the I bit if it can + * use the pmr instead. + */ + write_sysreg(flags, daif); +} #endif diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index a17393ff6677..4d5f3b5f50cd 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -8,14 +8,15 @@ #define __ASM_EXCEPTION_H #include <asm/esr.h> +#include <asm/kprobes.h> +#include <asm/ptrace.h> #include <linux/interrupt.h> -#define __exception __attribute__((section(".exception.text"))) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry #else -#define __exception_irq_entry __exception +#define __exception_irq_entry __kprobes #endif static inline u32 disr_to_esr(u64 disr) @@ -31,5 +32,22 @@ static inline u32 disr_to_esr(u64 disr) } asmlinkage void enter_from_user_mode(void); +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_undefinstr(struct pt_regs *regs); +asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs); +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); +void do_sve_acc(unsigned int esr, struct pt_regs *regs); +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); +void do_sysinstr(unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); +void do_cp15instr(unsigned int esr, struct pt_regs *regs); +void el0_svc_handler(struct pt_regs *regs); +void el0_svc_compat_handler(struct pt_regs *regs); +void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, + struct pt_regs *regs); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index d48667b04c41..91fa4baa1a93 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -11,9 +11,20 @@ #include <asm/insn.h> #define HAVE_FUNCTION_GRAPH_FP_TEST + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#else #define MCOUNT_ADDR ((unsigned long)_mcount) +#endif + +/* The BL at the callsite's adjusted rec->ip */ #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +#define FTRACE_PLT_IDX 0 +#define FTRACE_REGS_PLT_IDX 1 +#define NR_FTRACE_PLTS 2 + /* * Currently, gcc tends to save the link register after the local variables * on the stack. This causes the max stack tracer to report the function @@ -44,12 +55,24 @@ extern void return_to_handler(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* + * Adjust addr to point at the BL in the callsite. + * See ftrace_init_nop() for the callsite sequence. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return addr + AARCH64_INSN_SIZE; + /* * addr is the address of the mcount call instruction. * recordmcount does the necessary offset calculation. */ return addr; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #define ftrace_return_address(n) return_address(n) /* diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39e7780bedd6..bb313dde58a4 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant); u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 1a59f0ed1ae3..aa4b6521ef14 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -6,6 +6,7 @@ #define __ASM_IRQFLAGS_H #include <asm/alternative.h> +#include <asm/barrier.h> #include <asm/ptrace.h> #include <asm/sysreg.h> @@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void) } asm volatile(ALTERNATIVE( - "msr daifclr, #2 // arch_local_irq_enable\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", + "msr daifclr, #2 // arch_local_irq_enable", + __msr_s(SYS_ICC_PMR_EL1, "%0"), ARM64_HAS_IRQ_PRIO_MASKING) : : "r" ((unsigned long) GIC_PRIO_IRQON) : "memory"); + + pmr_sync(); } static inline void arch_local_irq_disable(void) @@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile(ALTERNATIVE( - "msr daif, %0\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", - ARM64_HAS_IRQ_PRIO_MASKING) + "msr daif, %0", + __msr_s(SYS_ICC_PMR_EL1, "%0"), + ARM64_HAS_IRQ_PRIO_MASKING) : : "r" (flags) : "memory"); + + pmr_sync(); } #endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index ddf9d762ac62..6e5d839f42b5 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -61,7 +61,6 @@ * RW: 64bit by default, can be overridden for 32bit VMs * TAC: Trap ACTLR * TSC: Trap SMC - * TVM: Trap VM ops (until M+C set in SCTLR_EL1) * TSW: Trap cache operations by set/way * TWE: Trap WFE * TWI: Trap WFI @@ -74,7 +73,7 @@ * SWIO: Turn set/way invalidates into set/way clean+invalidate */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ - HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ HCR_FMO | HCR_IMO) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index d69c1efc63e7..5efe5ca8fecf 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -53,8 +53,18 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) /* trap error record accesses */ vcpu->arch.hcr_el2 |= HCR_TERR; } - if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + + if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) { vcpu->arch.hcr_el2 |= HCR_FWB; + } else { + /* + * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C + * get set in SCTLR_EL1 such that we can detect when the guest + * MMU gets turned on and do the necessary cache maintenance + * then. + */ + vcpu->arch.hcr_el2 |= HCR_TVM; + } if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) vcpu->arch.hcr_el2 &= ~HCR_RW; @@ -77,14 +87,19 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr_el2; } -static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 &= ~HCR_TWE; + if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count)) + vcpu->arch.hcr_el2 &= ~HCR_TWI; + else + vcpu->arch.hcr_el2 |= HCR_TWI; } -static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 |= HCR_TWE; + vcpu->arch.hcr_el2 |= HCR_TWI; } static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu) @@ -258,6 +273,11 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); } +static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC); +} + static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..c61260cf63c5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -44,6 +44,7 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) +#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -83,6 +84,14 @@ struct kvm_arch { /* Mandated version of PSCI */ u32 psci_version; + + /* + * If we encounter a data abort without valid instruction syndrome + * information, report this to user space. User space can (and + * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is + * supported. + */ + bool return_nisv_io_abort_to_user; }; #define KVM_NR_MEM_OBJS 40 @@ -338,6 +347,13 @@ struct kvm_vcpu_arch { /* True when deferrable sysregs are loaded on the physical CPU, * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ bool sysregs_loaded_on_cpu; + + /* Guest PV state */ + struct { + u64 steal; + u64 last_steal; + gpa_t base; + } steal; }; /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ @@ -478,6 +494,27 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run, int kvm_perf_init(void); int kvm_perf_teardown(void); +long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); +void kvm_update_stolen_time(struct kvm_vcpu *vcpu); + +int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr); +int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr); +int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr); + +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) +{ + vcpu_arch->steal.base = GPA_INVALID; +} + +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) +{ + return (vcpu_arch->steal.base != GPA_INVALID); +} + void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); @@ -600,8 +637,7 @@ static inline void kvm_arm_vhe_guest_enter(void) * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) - dsb(sy); + pmr_sync(); } static inline void kvm_arm_vhe_guest_exit(void) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index c23c47360664..a4f9ca5479b0 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -69,12 +69,6 @@ #define KERNEL_START _text #define KERNEL_END _end -#ifdef CONFIG_ARM64_VA_BITS_52 -#define MAX_USER_VA_BITS 52 -#else -#define MAX_USER_VA_BITS VA_BITS -#endif - /* * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual * address space for the shadow region respectively. They can bloat the stack diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index f80e13cbf8ec..1e93de68c044 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -21,7 +21,7 @@ struct mod_arch_specific { struct mod_plt_sec init; /* for CONFIG_DYNAMIC_FTRACE */ - struct plt_entry *ftrace_trampoline; + struct plt_entry *ftrace_trampolines; }; #endif diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h index 799d9dd6f7cc..cf3a0fd7c1a7 100644 --- a/arch/arm64/include/asm/paravirt.h +++ b/arch/arm64/include/asm/paravirt.h @@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu) { return pv_ops.time.steal_clock(cpu); } -#endif + +int __init pv_time_init(void); + +#else + +#define pv_time_init() do {} while (0) + +#endif // CONFIG_PARAVIRT #endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 3df60f97da1f..d9fbd433cc17 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -69,7 +69,7 @@ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT)) +#define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT)) /* * Section address mask and size definitions. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 565aa45ef134..5d15b4735a0e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -17,7 +17,7 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space + * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space * and fixed mappings */ #define VMALLOC_START (MODULES_END) @@ -865,6 +865,20 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define phys_to_ttbr(addr) (addr) #endif +/* + * On arm64 without hardware Access Flag, copying from user will fail because + * the pte is old and cannot be marked young. So we always end up with zeroed + * page after fork() + CoW for pfn mappings. We don't always have a + * hardware-managed access flag on arm64. + */ +static inline bool arch_faults_on_old_pte(void) +{ + WARN_ON(preemptible()); + + return !cpu_has_hw_af(); +} +#define arch_faults_on_old_pte arch_faults_on_old_pte + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5623685c7d13..5ba63204d078 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -9,7 +9,7 @@ #define __ASM_PROCESSOR_H #define KERNEL_DS UL(-1) -#define USER_DS ((UL(1) << MAX_USER_VA_BITS) - 1) +#define USER_DS ((UL(1) << VA_BITS) - 1) /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is @@ -26,10 +26,12 @@ #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/thread_info.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> +#include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> @@ -214,6 +216,18 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->sp = sp; } +static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; +} + #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) diff --git a/arch/arm64/include/asm/pvclock-abi.h b/arch/arm64/include/asm/pvclock-abi.h new file mode 100644 index 000000000000..c4f1c0a0789c --- /dev/null +++ b/arch/arm64/include/asm/pvclock-abi.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 Arm Ltd. */ + +#ifndef __ASM_PVCLOCK_ABI_H +#define __ASM_PVCLOCK_ABI_H + +/* The below structure is defined in ARM DEN0057A */ + +struct pvclock_vcpu_stolen_time { + __le32 revision; + __le32 attributes; + __le64 stolen_time; + /* Structure must be 64 byte aligned, pad to that size */ + u8 padding[48]; +} __packed; + +#endif diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index 06d880b3526c..b383b4802a7b 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -66,24 +66,18 @@ struct pt_regs; } \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused); \ ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused) -#endif -#ifndef COND_SYSCALL #define COND_SYSCALL(name) \ asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs) \ { \ return sys_ni_syscall(); \ } -#endif -#ifndef SYS_NI #define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); -#endif #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 59690613ac31..cee5928e1b7d 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -42,16 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr) ptr < (unsigned long)&__irqentry_text_end; } -static inline int in_exception_text(unsigned long ptr) -{ - int in; - - in = ptr >= (unsigned long)&__exception_text_start && - ptr < (unsigned long)&__exception_text_end; - - return in ? : __in_irqentry_text(ptr); -} - static inline int in_entry_text(unsigned long ptr) { return ptr >= (unsigned long)&__entry_text_start && diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 097d6bfac0b7..127712b0b970 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -378,20 +378,34 @@ do { \ extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); #define raw_copy_from_user(to, from, n) \ ({ \ - __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \ + unsigned long __acfu_ret; \ + uaccess_enable_not_uao(); \ + __acfu_ret = __arch_copy_from_user((to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __acfu_ret; \ }) extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); #define raw_copy_to_user(to, from, n) \ ({ \ - __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \ + unsigned long __actu_ret; \ + uaccess_enable_not_uao(); \ + __actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to), \ + (from), (n)); \ + uaccess_disable_not_uao(); \ + __actu_ret; \ }) extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); #define raw_copy_in_user(to, from, n) \ ({ \ - __arch_copy_in_user(__uaccess_mask_ptr(to), \ - __uaccess_mask_ptr(from), (n)); \ + unsigned long __aciu_ret; \ + uaccess_enable_not_uao(); \ + __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __aciu_ret; \ }) #define INLINE_COPY_TO_USER @@ -400,8 +414,11 @@ extern unsigned long __must_check __arch_copy_in_user(void __user *to, const voi extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { - if (access_ok(to, n)) + if (access_ok(to, n)) { + uaccess_enable_not_uao(); n = __arch_clear_user(__uaccess_mask_ptr(to), n); + uaccess_disable_not_uao(); + } return n; } #define clear_user __clear_user diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 67c21f9bdbad..820e5751ada7 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -164,8 +164,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; @@ -323,6 +324,8 @@ struct kvm_vcpu_events { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_PVTIME_CTRL 2 +#define KVM_ARM_VCPU_PVTIME_IPA 0 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_VCPU2_SHIFT 28 diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 478491f07b4f..fc6488660f64 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) # Object file lists. obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ - entry-fpsimd.o process.o ptrace.o setup.o signal.o \ - sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o \ + entry-common.o entry-fpsimd.o process.o ptrace.o \ + setup.o signal.o sys.o stacktrace.o time.o traps.o \ + io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 214685760e1c..a5bdce8af65b 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -56,6 +56,7 @@ int main(void) DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); + DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 93f34b4eca25..6a09ca7644ea 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -6,7 +6,6 @@ */ #include <linux/arm-smccc.h> -#include <linux/psci.h> #include <linux/types.h> #include <linux/cpu.h> #include <asm/cpu.h> @@ -88,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, } static void -cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused) +cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap) { u64 mask = arm64_ftr_reg_ctrel0.strict_mask; + bool enable_uct_trap = false; /* Trap CTR_EL0 access on this CPU, only if it has a mismatch */ if ((read_cpuid_cachetype() & mask) != (arm64_ftr_reg_ctrel0.sys_val & mask)) + enable_uct_trap = true; + + /* ... or if the system is affected by an erratum */ + if (cap->capability == ARM64_WORKAROUND_1542419) + enable_uct_trap = true; + + if (enable_uct_trap) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); } @@ -167,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, } #endif /* CONFIG_KVM_INDIRECT_VECTORS */ -#include <uapi/linux/psci.h> #include <linux/arm-smccc.h> -#include <linux/psci.h> static void call_smc_arch_workaround_1(void) { @@ -213,43 +218,31 @@ static int detect_harden_bp_fw(void) struct arm_smccc_res res; u32 midr = read_cpuid_id(); - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + + switch ((int)res.a0) { + case 1: + /* Firmware says we're just fine */ + return 0; + case 0: + break; + default: return -1; + } - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - switch ((int)res.a0) { - case 1: - /* Firmware says we're just fine */ - return 0; - case 0: - cb = call_hvc_arch_workaround_1; - /* This is a guest, no need to patch KVM vectors */ - smccc_start = NULL; - smccc_end = NULL; - break; - default: - return -1; - } + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: + cb = call_hvc_arch_workaround_1; + /* This is a guest, no need to patch KVM vectors */ + smccc_start = NULL; + smccc_end = NULL; break; - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - switch ((int)res.a0) { - case 1: - /* Firmware says we're just fine */ - return 0; - case 0: - cb = call_smc_arch_workaround_1; - smccc_start = __smccc_workaround_1_smc_start; - smccc_end = __smccc_workaround_1_smc_end; - break; - default: - return -1; - } + case SMCCC_CONDUIT_SMC: + cb = call_smc_arch_workaround_1; + smccc_start = __smccc_workaround_1_smc_start; + smccc_end = __smccc_workaround_1_smc_end; break; default: @@ -309,11 +302,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt, BUG_ON(nr_inst != 1); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: insn = aarch64_insn_get_hvc_value(); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: insn = aarch64_insn_get_smc_value(); break; default: @@ -339,6 +332,8 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt, void arm64_set_ssbd_mitigation(bool state) { + int conduit; + if (!IS_ENABLED(CONFIG_ARM64_SSBD)) { pr_info_once("SSBD disabled by kernel configuration\n"); return; @@ -352,19 +347,10 @@ void arm64_set_ssbd_mitigation(bool state) return; } - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); - break; - - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); - break; + conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, state, + NULL); - default: - WARN_ON_ONCE(1); - break; - } + WARN_ON_ONCE(conduit == SMCCC_CONDUIT_NONE); } static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, @@ -374,6 +360,7 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, bool required = true; s32 val; bool this_cpu_safe = false; + int conduit; WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); @@ -391,25 +378,10 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, goto out_printmsg; } - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { - ssbd_state = ARM64_SSBD_UNKNOWN; - if (!this_cpu_safe) - __ssb_safe = false; - return false; - } - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_2, &res); - break; - - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_2, &res); - break; + conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_2, &res); - default: + if (conduit == SMCCC_CONDUIT_NONE) { ssbd_state = ARM64_SSBD_UNKNOWN; if (!this_cpu_safe) __ssb_safe = false; @@ -650,9 +622,21 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry, return false; } -#ifdef CONFIG_HARDEN_EL2_VECTORS +static bool __maybe_unused +has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT); + const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && has_dic; +} + +#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367) -static const struct midr_range arm64_harden_el2_vectors[] = { +static const struct midr_range ca57_a72[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), {}, @@ -881,7 +865,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "EL2 vector hardening", .capability = ARM64_HARDEN_EL2_VECTORS, - ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors), + ERRATA_MIDR_RANGE_LIST(ca57_a72), }, #endif { @@ -927,6 +911,23 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1542419 + { + /* we depend on the firmware portion for correctness */ + .desc = "ARM erratum 1542419 (kernel portion)", + .capability = ARM64_WORKAROUND_1542419, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_neoverse_n1_erratum_1542419, + .cpu_enable = cpu_enable_trap_ctr_access, + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1319367 + { + .desc = "ARM erratum 1319367", + .capability = ARM64_WORKAROUND_1319367, + ERRATA_MIDR_RANGE_LIST(ca57_a72), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 80f459ad0190..04cf64e9f0c9 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -982,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), { /* sentinel */ } }; char const *str = "kpti command line option"; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 05933c065732..56bba746da1c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_cntfrq = arch_timer_get_cntfrq(); /* * Use the effective value of the CTR_EL0 than the raw value - * exposed by the CPU. CTR_E0.IDC field value must be interpreted + * exposed by the CPU. CTR_EL0.IDC field value must be interpreted * with the CLIDR_EL1 fields to avoid triggering false warnings * when there is a mismatch across the CPUs. Keep track of the * effective value of the CTR_EL0 in our internal records for diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c new file mode 100644 index 000000000000..5dce5e56995a --- /dev/null +++ b/arch/arm64/kernel/entry-common.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Exception handling code + * + * Copyright (C) 2019 ARM Ltd. + */ + +#include <linux/context_tracking.h> +#include <linux/ptrace.h> +#include <linux/thread_info.h> + +#include <asm/cpufeature.h> +#include <asm/daifflags.h> +#include <asm/esr.h> +#include <asm/exception.h> +#include <asm/kprobes.h> +#include <asm/mmu.h> +#include <asm/sysreg.h> + +static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_abort); + +static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_pc); + +static void el1_undef(struct pt_regs *regs) +{ + local_daif_inherit(regs); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el1_undef); + +static void el1_inv(struct pt_regs *regs, unsigned long esr) +{ + local_daif_inherit(regs); + bad_mode(regs, 0, esr); +} +NOKPROBE_SYMBOL(el1_inv); + +static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * The CPU masked interrupts, and we are leaving them masked during + * do_debug_exception(). Update PMR as if we had called + * local_mask_daif(). + */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + do_debug_exception(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_dbg); + +asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_DABT_CUR: + case ESR_ELx_EC_IABT_CUR: + el1_abort(regs, esr); + break; + /* + * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a + * recursive exception when trying to push the initial pt_regs. + */ + case ESR_ELx_EC_PC_ALIGN: + el1_pc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_UNKNOWN: + el1_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_CUR: + case ESR_ELx_EC_SOFTSTP_CUR: + case ESR_ELx_EC_WATCHPT_CUR: + case ESR_ELx_EC_BRK64: + el1_dbg(regs, esr); + break; + default: + el1_inv(regs, esr); + }; +} +NOKPROBE_SYMBOL(el1_sync_handler); + +static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_da); + +static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * We've taken an instruction abort from userspace and not yet + * re-enabled IRQs. If the address is a kernel address, apply + * BP hardening prior to enabling IRQs and pre-emption. + */ + if (!is_ttbr0_addr(far)) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_ia); + +static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_acc); + +static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sve_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_sve_acc); + +static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_exc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_exc); + +static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sysinstr(esr, regs); +} +NOKPROBE_SYMBOL(el0_sys); + +static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + if (!is_ttbr0_addr(instruction_pointer(regs))) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_pc); + +static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX_NOIRQ); + do_sp_pc_abort(regs->sp, esr, regs); +} +NOKPROBE_SYMBOL(el0_sp); + +static void notrace el0_undef(struct pt_regs *regs) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el0_undef); + +static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + bad_el0_sync(regs, 0, esr); +} +NOKPROBE_SYMBOL(el0_inv); + +static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +{ + /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ + unsigned long far = read_sysreg(far_el1); + + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + user_exit_irqoff(); + do_debug_exception(far, esr, regs); + local_daif_restore(DAIF_PROCCTX_NOIRQ); +} +NOKPROBE_SYMBOL(el0_dbg); + +static void notrace el0_svc(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc); + +asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC64: + el0_svc(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_SVE: + el0_sve_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC64: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_WFx: + el0_sys(regs, esr); + break; + case ESR_ELx_EC_SP_ALIGN: + el0_sp(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + el0_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BRK64: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_handler); + +#ifdef CONFIG_COMPAT +static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_cp15instr(esr, regs); +} +NOKPROBE_SYMBOL(el0_cp15); + +static void notrace el0_svc_compat(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_compat_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc_compat); + +asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC32: + el0_svc_compat(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC32: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_CP14_64: + el0_undef(regs); + break; + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + el0_cp15(regs, esr); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BKPT32: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_compat_handler); +#endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 33d003d80121..4fe1514fcbfd 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,10 +7,137 @@ */ #include <linux/linkage.h> +#include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/insn.h> +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +/* + * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before + * the regular function prologue. For an enabled callsite, ftrace_init_nop() and + * ftrace_make_call() have patched those NOPs to: + * + * MOV X9, LR + * BL <entry> + * + * ... where <entry> is either ftrace_caller or ftrace_regs_caller. + * + * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are + * live, and x9-x18 are safe to clobber. + * + * We save the callsite's context into a pt_regs before invoking any ftrace + * callbacks. So that we can get a sensible backtrace, we create a stack record + * for the callsite and the ftrace entry assembly. This is not sufficient for + * reliable stacktrace: until we create the callsite stack record, its caller + * is missing from the LR and existing chain of frame records. + */ + .macro ftrace_regs_entry, allregs=0 + /* Make room for pt_regs, plus a callee frame */ + sub sp, sp, #(S_FRAME_SIZE + 16) + + /* Save function arguments (and x9 for simplicity) */ + stp x0, x1, [sp, #S_X0] + stp x2, x3, [sp, #S_X2] + stp x4, x5, [sp, #S_X4] + stp x6, x7, [sp, #S_X6] + stp x8, x9, [sp, #S_X8] + + /* Optionally save the callee-saved registers, always save the FP */ + .if \allregs == 1 + stp x10, x11, [sp, #S_X10] + stp x12, x13, [sp, #S_X12] + stp x14, x15, [sp, #S_X14] + stp x16, x17, [sp, #S_X16] + stp x18, x19, [sp, #S_X18] + stp x20, x21, [sp, #S_X20] + stp x22, x23, [sp, #S_X22] + stp x24, x25, [sp, #S_X24] + stp x26, x27, [sp, #S_X26] + stp x28, x29, [sp, #S_X28] + .else + str x29, [sp, #S_FP] + .endif + + /* Save the callsite's SP and LR */ + add x10, sp, #(S_FRAME_SIZE + 16) + stp x9, x10, [sp, #S_LR] + + /* Save the PC after the ftrace callsite */ + str x30, [sp, #S_PC] + + /* Create a frame record for the callsite above pt_regs */ + stp x29, x9, [sp, #S_FRAME_SIZE] + add x29, sp, #S_FRAME_SIZE + + /* Create our frame record within pt_regs. */ + stp x29, x30, [sp, #S_STACKFRAME] + add x29, sp, #S_STACKFRAME + .endm + +ENTRY(ftrace_regs_caller) + ftrace_regs_entry 1 + b ftrace_common +ENDPROC(ftrace_regs_caller) + +ENTRY(ftrace_caller) + ftrace_regs_entry 0 + b ftrace_common +ENDPROC(ftrace_caller) + +ENTRY(ftrace_common) + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + ldr_l x2, function_trace_op // op + mov x3, sp // regs + +GLOBAL(ftrace_call) + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); + nop // If enabled, this will be replaced + // "b ftrace_graph_caller" +#endif + +/* + * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved + * x19-x29 per the AAPCS, and we created frame records upon entry, so we need + * to restore x0-x8, x29, and x30. + */ +ftrace_common_return: + /* Restore function arguments */ + ldp x0, x1, [sp] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + ldr x8, [sp, #S_X8] + + /* Restore the callsite's FP, LR, PC */ + ldr x29, [sp, #S_FP] + ldr x30, [sp, #S_LR] + ldr x9, [sp, #S_PC] + + /* Restore the callsite's SP */ + add sp, sp, #S_FRAME_SIZE + 16 + + ret x9 +ENDPROC(ftrace_common) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + ldr x0, [sp, #S_PC] + sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + add x1, sp, #S_LR // parent_ip (callsite's LR) + ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + bl prepare_ftrace_return + b ftrace_common_return +ENDPROC(ftrace_graph_caller) +#else +#endif + +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + /* * Gcc with -pg will put the following code in the beginning of each function: * mov x0, x30 @@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); mcount_exit ENDPROC(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ - -ENTRY(ftrace_stub) - ret -ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller) mcount_exit ENDPROC(ftrace_graph_caller) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) * diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index cf3bd2976e57..583f71abbe98 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -269,8 +269,10 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - /* Ensure priority change is seen by redistributor */ - dsb sy + mrs_s x21, SYS_ICC_CTLR_EL1 + tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE + dsb sy // Ensure priority change is seen by redistributor +.L__skip_pmr_sync\@: alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR @@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid) .align 6 el1_sync: kernel_entry 1 - mrs x1, esr_el1 // read the syndrome register - lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 - b.eq el1_da - cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 - b.eq el1_ia - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - b.eq el1_undef - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 - b.eq el1_undef - cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 - b.ge el1_dbg - b el1_inv - -el1_ia: - /* - * Fall through to the Data abort case - */ -el1_da: - /* - * Data abort handling - */ - mrs x3, far_el1 - inherit_daif pstate=x23, tmp=x2 - untagged_addr x0, x3 - mov x2, sp // struct pt_regs - bl do_mem_abort - - kernel_exit 1 -el1_pc: - /* - * PC alignment exception handling. We don't handle SP alignment faults, - * since we will have hit a recursive exception when trying to push the - * initial pt_regs. - */ - mrs x0, far_el1 - inherit_daif pstate=x23, tmp=x2 - mov x2, sp - bl do_sp_pc_abort - ASM_BUG() -el1_undef: - /* - * Undefined instruction - */ - inherit_daif pstate=x23, tmp=x2 mov x0, sp - bl do_undefinstr + bl el1_sync_handler kernel_exit 1 -el1_dbg: - /* - * Debug exception handling - */ - cmp x24, #ESR_ELx_EC_BRK64 // if BRK64 - cinc x24, x24, eq // set bit '0' - tbz x24, #0, el1_inv // EL1 only - gic_prio_kentry_setup tmp=x3 - mrs x0, far_el1 - mov x2, sp // struct pt_regs - bl do_debug_exception - kernel_exit 1 -el1_inv: - // TODO: add support for undefined instructions in kernel mode - inherit_daif pstate=x23, tmp=x2 - mov x0, sp - mov x2, x1 - mov x1, #BAD_SYNC - bl bad_mode - ASM_BUG() ENDPROC(el1_sync) .align 6 @@ -714,71 +649,18 @@ ENDPROC(el1_irq) .align 6 el0_sync: kernel_entry 0 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC64 // SVC in 64-bit state - b.eq el0_svc - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_SVE // SVE access - b.eq el0_sve_acc - cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - ccmp x24, #ESR_ELx_EC_WFx, #4, ne - b.eq el0_sys - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv + mov x0, sp + bl el0_sync_handler + b ret_to_user #ifdef CONFIG_COMPAT .align 6 el0_sync_compat: kernel_entry 0, 32 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC32 // SVC in 32-bit state - b.eq el0_svc_compat - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP15_64 // CP15 MRRC/MCRR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP14_MR // CP14 MRC/MCR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_LS // CP14 LDC/STC trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_64 // CP14 MRRC/MCRR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv -el0_svc_compat: - gic_prio_kentry_setup tmp=x1 mov x0, sp - bl el0_svc_compat_handler + bl el0_sync_compat_handler b ret_to_user +ENDPROC(el0_sync) .align 6 el0_irq_compat: @@ -788,139 +670,7 @@ el0_irq_compat: el0_error_compat: kernel_entry 0, 32 b el0_error_naked - -el0_cp15: - /* - * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_cp15instr - b ret_to_user -#endif - -el0_da: - /* - * Data abort handling - */ - mrs x26, far_el1 - ct_user_exit_irqoff - enable_daif - untagged_addr x0, x26 - mov x1, x25 - mov x2, sp - bl do_mem_abort - b ret_to_user -el0_ia: - /* - * Instruction abort handling - */ - mrs x26, far_el1 - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_el0_ia_bp_hardening - b ret_to_user -el0_fpsimd_acc: - /* - * Floating Point or Advanced SIMD access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_acc - b ret_to_user -el0_sve_acc: - /* - * Scalable Vector Extension access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sve_acc - b ret_to_user -el0_fpsimd_exc: - /* - * Floating Point, Advanced SIMD or SVE exception - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_exc - b ret_to_user -el0_sp: - ldr x26, [sp, #S_SP] - b el0_sp_pc -el0_pc: - mrs x26, far_el1 -el0_sp_pc: - /* - * Stack or PC alignment exception handling - */ - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off #endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_sp_pc_abort - b ret_to_user -el0_undef: - /* - * Undefined instruction - */ - ct_user_exit_irqoff - enable_daif - mov x0, sp - bl do_undefinstr - b ret_to_user -el0_sys: - /* - * System instructions, for trapped cache maintenance instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sysinstr - b ret_to_user -el0_dbg: - /* - * Debug exception handling - */ - tbnz x24, #0, el0_inv // EL0 only - mrs x24, far_el1 - gic_prio_kentry_setup tmp=x3 - ct_user_exit_irqoff - mov x0, x24 - mov x1, x25 - mov x2, sp - bl do_debug_exception - enable_da_f - b ret_to_user -el0_inv: - ct_user_exit_irqoff - enable_daif - mov x0, sp - mov x1, #BAD_SYNC - mov x2, x25 - bl bad_el0_sync - b ret_to_user -ENDPROC(el0_sync) .align 6 el0_irq: @@ -999,17 +749,6 @@ finish_ret_to_user: kernel_exit 0 ENDPROC(ret_to_user) -/* - * SVC handler. - */ - .align 6 -el0_svc: - gic_prio_kentry_setup tmp=x1 - mov x0, sp - bl el0_svc_handler - b ret_to_user -ENDPROC(el0_svc) - .popsection // .entry.text #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 37d3912cfe06..3eb338f14386 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task) * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ -asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) +void do_sve_acc(unsigned int esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { @@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) /* * Trapped FP/ASIMD access. */ -asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) { /* TODO: implement lazy context saving/restoring */ WARN_ON(1); @@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) /* * Raise a SIGFPE for the current process. */ -asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 06e56b470315..8618faa82e6d 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +{ +#ifdef CONFIG_ARM64_MODULE_PLTS + struct plt_entry *plt = mod->arch.ftrace_trampolines; + + if (addr == FTRACE_ADDR) + return &plt[FTRACE_PLT_IDX]; + if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS)) + return &plt[FTRACE_REGS_PLT_IDX]; +#endif + return NULL; +} + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline, *dst; struct module *mod; + struct plt_entry *plt; + + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; /* * On kernels that support module PLTs, the offset between the @@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (WARN_ON(!mod)) return -EINVAL; - /* - * There is only one ftrace trampoline per module. For now, - * this is not a problem since on arm64, all dynamic ftrace - * invocations are routed via ftrace_caller(). This will need - * to be revisited if support for multiple ftrace entry points - * is added in the future, but for now, the pr_err() below - * deals with a theoretical issue only. - * - * Note that PLTs are place relative, and plt_entries_equal() - * checks whether they point to the same target. Here, we need - * to check if the actual opcodes are in fact identical, - * regardless of the offset in memory so use memcmp() instead. - */ - dst = mod->arch.ftrace_trampoline; - trampoline = get_plt_entry(addr, dst); - if (memcmp(dst, &trampoline, sizeof(trampoline))) { - if (plt_entry_is_initialized(dst)) { - pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); - return -EINVAL; - } - - /* point the trampoline to our ftrace entry point */ - module_disable_ro(mod); - *dst = trampoline; - module_enable_ro(mod, true); - - /* - * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. Although the - * architecture doesn't require an IPI in this case, - * Neoverse-N1 erratum #1542419 does require one - * if the TLB maintenance in module_enable_ro() is - * skipped due to rodata_enabled. It doesn't seem worth - * it to make it conditional given that this is - * certainly not a fast-path. - */ - flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + plt = get_ftrace_plt(mod, addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)addr); + return -EINVAL; } - addr = (unsigned long)dst; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ + + addr = (unsigned long)plt; } old = aarch64_insn_gen_nop(); @@ -144,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_branch_imm(pc, old_addr, + AARCH64_INSN_BRANCH_LINK); + new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); + + return ftrace_modify_code(pc, old, new, true); +} + +/* + * The compiler has inserted two NOPs before the regular function prologue. + * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live, + * and x9-x18 are free for our use. + * + * At runtime we want to be able to swing a single NOP <-> BL to enable or + * disable the ftrace call. The BL requires us to save the original LR value, + * so here we insert a <MOV X9, LR> over the first NOP so the instructions + * before the regular prologue are: + * + * | Compiled | Disabled | Enabled | + * +----------+------------+------------+ + * | NOP | MOV X9, LR | MOV X9, LR | + * | NOP | NOP | BL <entry> | + * + * The LR value will be recovered by ftrace_regs_entry, and restored into LR + * before returning to the regular function prologue. When a function is not + * being traced, the MOV is not harmful given x9 is not live per the AAPCS. + * + * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of + * the BL. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + unsigned long pc = rec->ip - AARCH64_INSN_SIZE; + u32 old, new; + + old = aarch64_insn_gen_nop(); + new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, + AARCH64_INSN_REG_LR, + AARCH64_INSN_VARIANT_64BIT); + return ftrace_modify_code(pc, old, new, true); +} +#endif + /* * Turn off the call to ftrace_caller() in instrumented function */ @@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS u32 replaced; + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; + /* * 'mod' is only set at module load time, but if we end up * dealing with an out-of-range condition, we can assume it @@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EINVAL; validate = false; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ } else { old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 38ee1514cd9c..0b727edf4104 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -51,7 +51,7 @@ int hw_breakpoint_slots(int type) case TYPE_DATA: return get_num_wrps(); default: - pr_warning("unknown slot type: %d\n", type); + pr_warn("unknown slot type: %d\n", type); return 0; } } @@ -112,7 +112,7 @@ static u64 read_wb_reg(int reg, int n) GEN_READ_WB_REG_CASES(AARCH64_DBG_REG_WVR, AARCH64_DBG_REG_NAME_WVR, val); GEN_READ_WB_REG_CASES(AARCH64_DBG_REG_WCR, AARCH64_DBG_REG_NAME_WCR, val); default: - pr_warning("attempt to read from unknown breakpoint register %d\n", n); + pr_warn("attempt to read from unknown breakpoint register %d\n", n); } return val; @@ -127,7 +127,7 @@ static void write_wb_reg(int reg, int n, u64 val) GEN_WRITE_WB_REG_CASES(AARCH64_DBG_REG_WVR, AARCH64_DBG_REG_NAME_WVR, val); GEN_WRITE_WB_REG_CASES(AARCH64_DBG_REG_WCR, AARCH64_DBG_REG_NAME_WCR, val); default: - pr_warning("attempt to write to unknown breakpoint register %d\n", n); + pr_warn("attempt to write to unknown breakpoint register %d\n", n); } isb(); } @@ -145,7 +145,7 @@ static enum dbg_active_el debug_exception_level(int privilege) case AARCH64_BREAKPOINT_EL1: return DBG_ACTIVE_EL1; default: - pr_warning("invalid breakpoint privilege level %d\n", privilege); + pr_warn("invalid breakpoint privilege level %d\n", privilege); return -EINVAL; } } diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index d801a7094076..513b29c3e735 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +/* + * MOV (register) is architecturally an alias of ORR (shifted register) where + * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m> + */ +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant) +{ + return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR, + src, 0, variant, + AARCH64_INSN_LOGIC_ORR); +} + u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_adr_type type) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 416f537bf614..2a11a962e571 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -19,6 +19,14 @@ #include <asm/pgtable.h> #include <asm/sections.h> +enum kaslr_status { + KASLR_ENABLED, + KASLR_DISABLED_CMDLINE, + KASLR_DISABLED_NO_SEED, + KASLR_DISABLED_FDT_REMAP, +}; + +static enum kaslr_status __initdata kaslr_status; u64 __ro_after_init module_alloc_base; u16 __initdata memstart_offset_seed; @@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ early_fixmap_init(); fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); - if (!fdt) + if (!fdt) { + kaslr_status = KASLR_DISABLED_FDT_REMAP; return 0; + } /* * Retrieve (and wipe) the seed from the FDT */ seed = get_kaslr_seed(fdt); - if (!seed) - return 0; /* * Check if 'nokaslr' appears on the command line, and @@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ cmdline = kaslr_get_cmdline(fdt); str = strstr(cmdline, "nokaslr"); - if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) + if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) { + kaslr_status = KASLR_DISABLED_CMDLINE; + return 0; + } + + if (!seed) { + kaslr_status = KASLR_DISABLED_NO_SEED; return 0; + } /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable @@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys) return offset; } + +static int __init kaslr_init(void) +{ + switch (kaslr_status) { + case KASLR_ENABLED: + pr_info("KASLR enabled\n"); + break; + case KASLR_DISABLED_CMDLINE: + pr_info("KASLR disabled on command line\n"); + break; + case KASLR_DISABLED_NO_SEED: + pr_warn("KASLR disabled due to lack of seed\n"); + break; + case KASLR_DISABLED_FDT_REMAP: + pr_warn("KASLR disabled due to FDT remapping failure\n"); + break; + } + + return 0; +} +core_initcall(kaslr_init) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index b182442b87a3..65b08a74aec6 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -4,6 +4,7 @@ */ #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sort.h> @@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, tramp->sh_type = SHT_NOBITS; tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; tramp->sh_addralign = __alignof__(struct plt_entry); - tramp->sh_size = sizeof(struct plt_entry); + tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); } return 0; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 03ff15bffbb6..1cd1a4d0ed30 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -9,6 +9,7 @@ #include <linux/bitops.h> #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/gfp.h> #include <linux/kasan.h> #include <linux/kernel.h> @@ -470,22 +471,58 @@ overflow: return -ENOEXEC; } -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *me) +static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) { const Elf_Shdr *s, *se; const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { - if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); -#ifdef CONFIG_ARM64_MODULE_PLTS - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name)) - me->arch.ftrace_trampoline = (void *)s->sh_addr; -#endif + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; } + return NULL; +} + +static inline void __init_plt(struct plt_entry *plt, unsigned long addr) +{ + *plt = get_plt_entry(addr, plt); +} + +static int module_init_ftrace_plt(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE) + const Elf_Shdr *s; + struct plt_entry *plts; + + s = find_section(hdr, sechdrs, ".text.ftrace_trampoline"); + if (!s) + return -ENOEXEC; + + plts = (void *)s->sh_addr; + + __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + __init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR); + + mod->arch.ftrace_trampolines = plts; +#endif return 0; } + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + s = find_section(hdr, sechdrs, ".altinstructions"); + if (s) + apply_alternatives_module((void *)s->sh_addr, s->sh_size); + + return module_init_ftrace_plt(hdr, sechdrs, me); +} diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 4cfed91fe256..1ef702b0be2d 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -6,13 +6,153 @@ * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com> */ +#define pr_fmt(fmt) "arm-pv: " fmt + +#include <linux/arm-smccc.h> +#include <linux/cpuhotplug.h> #include <linux/export.h> +#include <linux/io.h> #include <linux/jump_label.h> +#include <linux/printk.h> +#include <linux/psci.h> +#include <linux/reboot.h> +#include <linux/slab.h> #include <linux/types.h> + #include <asm/paravirt.h> +#include <asm/pvclock-abi.h> +#include <asm/smp_plat.h> struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; struct paravirt_patch_template pv_ops; EXPORT_SYMBOL_GPL(pv_ops); + +struct pv_time_stolen_time_region { + struct pvclock_vcpu_stolen_time *kaddr; +}; + +static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); + +static bool steal_acc = true; +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); + +/* return stolen time in ns by asking the hypervisor */ +static u64 pv_steal_clock(int cpu) +{ + struct pv_time_stolen_time_region *reg; + + reg = per_cpu_ptr(&stolen_time_region, cpu); + if (!reg->kaddr) { + pr_warn_once("stolen time enabled but not configured for cpu %d\n", + cpu); + return 0; + } + + return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); +} + +static int stolen_time_dying_cpu(unsigned int cpu) +{ + struct pv_time_stolen_time_region *reg; + + reg = this_cpu_ptr(&stolen_time_region); + if (!reg->kaddr) + return 0; + + memunmap(reg->kaddr); + memset(reg, 0, sizeof(*reg)); + + return 0; +} + +static int init_stolen_time_cpu(unsigned int cpu) +{ + struct pv_time_stolen_time_region *reg; + struct arm_smccc_res res; + + reg = this_cpu_ptr(&stolen_time_region); + + arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res); + + if (res.a0 == SMCCC_RET_NOT_SUPPORTED) + return -EINVAL; + + reg->kaddr = memremap(res.a0, + sizeof(struct pvclock_vcpu_stolen_time), + MEMREMAP_WB); + + if (!reg->kaddr) { + pr_warn("Failed to map stolen time data structure\n"); + return -ENOMEM; + } + + if (le32_to_cpu(reg->kaddr->revision) != 0 || + le32_to_cpu(reg->kaddr->attributes) != 0) { + pr_warn_once("Unexpected revision or attributes in stolen time data\n"); + return -ENXIO; + } + + return 0; +} + +static int pv_time_init_stolen_time(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING, + "hypervisor/arm/pvtime:starting", + init_stolen_time_cpu, stolen_time_dying_cpu); + if (ret < 0) + return ret; + return 0; +} + +static bool has_pv_steal_clock(void) +{ + struct arm_smccc_res res; + + /* To detect the presence of PV time support we require SMCCC 1.1+ */ + if (psci_ops.smccc_version < SMCCC_VERSION_1_1) + return false; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_HV_PV_TIME_FEATURES, &res); + + if (res.a0 != SMCCC_RET_SUCCESS) + return false; + + arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES, + ARM_SMCCC_HV_PV_TIME_ST, &res); + + return (res.a0 == SMCCC_RET_SUCCESS); +} + +int __init pv_time_init(void) +{ + int ret; + + if (!has_pv_steal_clock()) + return 0; + + ret = pv_time_init_stolen_time(); + if (ret) + return ret; + + pv_ops.time.steal_clock = pv_steal_clock; + + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + + pr_info("using stolen time PV\n"); + + return 0; +} diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index a0b4f1bca491..e40b65645c86 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev, return sprintf(page, "event=0x%03llx\n", pmu_attr->id); } -#define ARMV8_EVENT_ATTR(name, config) \ - PMU_EVENT_ATTR(name, armv8_event_attr_##name, \ - config, armv8pmu_events_sysfs_show) - -ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR); -ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL); -ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE); -ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL); -ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED); -ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED); -ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED); -ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN); -ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN); -ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED); -ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED); -ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED); -ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED); -ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED); -ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES); -ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED); -ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS); -ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE); -ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE); -ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB); -ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS); -ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR); -ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC); -ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED); -ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES); -/* Don't expose the chain event in /sys, since it's useless in isolation */ -ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED); -ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND); -ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND); -ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB); -ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB); -ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE); -ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE); -ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL); -ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL); -ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB); -ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB); -ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS); -ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE); -ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS); -ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK); -ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK); -ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD); -ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD); -ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD); -ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP); -ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED); -ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE); -ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION); +#define ARMV8_EVENT_ATTR(name, config) \ + (&((struct perf_pmu_events_attr) { \ + .attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL), \ + .id = config, \ + }).attr.attr) static struct attribute *armv8_pmuv3_event_attrs[] = { - &armv8_event_attr_sw_incr.attr.attr, - &armv8_event_attr_l1i_cache_refill.attr.attr, - &armv8_event_attr_l1i_tlb_refill.attr.attr, - &armv8_event_attr_l1d_cache_refill.attr.attr, - &armv8_event_attr_l1d_cache.attr.attr, - &armv8_event_attr_l1d_tlb_refill.attr.attr, - &armv8_event_attr_ld_retired.attr.attr, - &armv8_event_attr_st_retired.attr.attr, - &armv8_event_attr_inst_retired.attr.attr, - &armv8_event_attr_exc_taken.attr.attr, - &armv8_event_attr_exc_return.attr.attr, - &armv8_event_attr_cid_write_retired.attr.attr, - &armv8_event_attr_pc_write_retired.attr.attr, - &armv8_event_attr_br_immed_retired.attr.attr, - &armv8_event_attr_br_return_retired.attr.attr, - &armv8_event_attr_unaligned_ldst_retired.attr.attr, - &armv8_event_attr_br_mis_pred.attr.attr, - &armv8_event_attr_cpu_cycles.attr.attr, - &armv8_event_attr_br_pred.attr.attr, - &armv8_event_attr_mem_access.attr.attr, - &armv8_event_attr_l1i_cache.attr.attr, - &armv8_event_attr_l1d_cache_wb.attr.attr, - &armv8_event_attr_l2d_cache.attr.attr, - &armv8_event_attr_l2d_cache_refill.attr.attr, - &armv8_event_attr_l2d_cache_wb.attr.attr, - &armv8_event_attr_bus_access.attr.attr, - &armv8_event_attr_memory_error.attr.attr, - &armv8_event_attr_inst_spec.attr.attr, - &armv8_event_attr_ttbr_write_retired.attr.attr, - &armv8_event_attr_bus_cycles.attr.attr, - &armv8_event_attr_l1d_cache_allocate.attr.attr, - &armv8_event_attr_l2d_cache_allocate.attr.attr, - &armv8_event_attr_br_retired.attr.attr, - &armv8_event_attr_br_mis_pred_retired.attr.attr, - &armv8_event_attr_stall_frontend.attr.attr, - &armv8_event_attr_stall_backend.attr.attr, - &armv8_event_attr_l1d_tlb.attr.attr, - &armv8_event_attr_l1i_tlb.attr.attr, - &armv8_event_attr_l2i_cache.attr.attr, - &armv8_event_attr_l2i_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache_allocate.attr.attr, - &armv8_event_attr_l3d_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache.attr.attr, - &armv8_event_attr_l3d_cache_wb.attr.attr, - &armv8_event_attr_l2d_tlb_refill.attr.attr, - &armv8_event_attr_l2i_tlb_refill.attr.attr, - &armv8_event_attr_l2d_tlb.attr.attr, - &armv8_event_attr_l2i_tlb.attr.attr, - &armv8_event_attr_remote_access.attr.attr, - &armv8_event_attr_ll_cache.attr.attr, - &armv8_event_attr_ll_cache_miss.attr.attr, - &armv8_event_attr_dtlb_walk.attr.attr, - &armv8_event_attr_itlb_walk.attr.attr, - &armv8_event_attr_ll_cache_rd.attr.attr, - &armv8_event_attr_ll_cache_miss_rd.attr.attr, - &armv8_event_attr_remote_access_rd.attr.attr, - &armv8_event_attr_sample_pop.attr.attr, - &armv8_event_attr_sample_feed.attr.attr, - &armv8_event_attr_sample_filtrate.attr.attr, - &armv8_event_attr_sample_collision.attr.attr, + ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), + ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE), + ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL), + ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED), + ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED), + ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED), + ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN), + ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN), + ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED), + ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED), + ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED), + ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED), + ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED), + ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES), + ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED), + ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS), + ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE), + ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE), + ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB), + ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS), + ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR), + ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC), + ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED), + ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES), + /* Don't expose the chain event in /sys, since it's useless in isolation */ + ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED), + ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND), + ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND), + ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB), + ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB), + ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE), + ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE), + ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL), + ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL), + ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB), + ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB), + ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS), + ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE), + ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS), + ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK), + ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK), + ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), + ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), + ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), + ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), + ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), + ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), + ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), NULL, }; diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c4452827419b..d1c95dcf1d78 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void) (unsigned long)__irqentry_text_end); if (ret) return ret; - ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start, - (unsigned long)__exception_text_end); - if (ret) - return ret; ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start, (unsigned long)__idmap_text_end); if (ret) diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index c9f72b2665f1..43ae4e0c968f 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) static int cpu_psci_cpu_kill(unsigned int cpu) { - int err, i; + int err; + unsigned long start, end; if (!psci_ops.affinity_info) return 0; @@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu) * while it is dying. So, try again a few times. */ - for (i = 0; i < 10; i++) { + start = jiffies; + end = start + msecs_to_jiffies(100); + do { err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { - pr_info("CPU%d killed.\n", cpu); + pr_info("CPU%d killed (polled %d ms)\n", cpu, + jiffies_to_msecs(jiffies - start)); return 0; } - msleep(10); - pr_info("Retrying again to check for CPU kill\n"); - } + usleep_range(100, 1000); + } while (time_before(jiffies, end)); pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index ea94cf8f9dc6..d6259dac62b6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -2,6 +2,7 @@ // Copyright (C) 2017 Arm Ltd. #define pr_fmt(fmt) "sdei: " fmt +#include <linux/arm-smccc.h> #include <linux/arm_sdei.h> #include <linux/hardirq.h> #include <linux/irqflags.h> @@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit) return 0; } - sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; + sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 if (arm64_kernel_unmapped_at_el0()) { diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index dc9fe879c279..ab149bcc3dc7 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -345,8 +345,7 @@ void __cpu_die(unsigned int cpu) */ err = op_cpu_kill(cpu); if (err) - pr_warn("CPU%d may not have shut down cleanly: %d\n", - cpu, err); + pr_warn("CPU%d may not have shut down cleanly: %d\n", cpu, err); } /* @@ -976,8 +975,8 @@ void smp_send_stop(void) udelay(1); if (num_online_cpus() > 1) - pr_warning("SMP: failed to stop secondary CPUs %*pbl\n", - cpumask_pr_args(cpu_online_mask)); + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(cpu_online_mask)); sdei_mask_local_cpu(); } @@ -1017,8 +1016,8 @@ void crash_smp_send_stop(void) udelay(1); if (atomic_read(&waiting_for_crash_ipi) > 0) - pr_warning("SMP: failed to stop secondary CPUs %*pbl\n", - cpumask_pr_args(&mask)); + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(&mask)); sdei_mask_local_cpu(); } diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index f1cb64959427..3c18c2454089 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -8,6 +8,7 @@ */ #include <linux/compat.h> +#include <linux/cpufeature.h> #include <linux/personality.h> #include <linux/sched.h> #include <linux/sched/signal.h> @@ -17,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/system_misc.h> +#include <asm/tlbflush.h> #include <asm/unistd.h> static long @@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end) if (fatal_signal_pending(current)) return 0; + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* + * The workaround requires an inner-shareable tlbi. + * We pick the reserved-ASID to minimise the impact. + */ + __tlbi(aside1is, __TLBI_VADDR(0, 0)); + dsb(ish); + } + ret = __flush_cache_user_range(start, start + chunk); if (ret) return ret; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 871c739f060a..9a9d98a443fc 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -154,14 +154,14 @@ static inline void sve_user_discard(void) sve_user_disable(); } -asmlinkage void el0_svc_handler(struct pt_regs *regs) +void el0_svc_handler(struct pt_regs *regs) { sve_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT -asmlinkage void el0_svc_compat_handler(struct pt_regs *regs) +void el0_svc_compat_handler(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, compat_sys_call_table); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 0b2946414dc9..73f06d4b3aae 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -30,6 +30,7 @@ #include <asm/thread_info.h> #include <asm/stacktrace.h> +#include <asm/paravirt.h> unsigned long profile_pc(struct pt_regs *regs) { @@ -65,4 +66,6 @@ void __init time_init(void) /* Calibrate the delay loop directly */ lpj_fine = arch_timer_rate / HZ; + + pv_time_init(); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 34739e80211b..73caf35c2262 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -35,6 +35,7 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/insn.h> +#include <asm/kprobes.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> @@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr) force_signal_inject(SIGSEGV, code, addr); } -asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +void do_undefinstr(struct pt_regs *regs) { /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) @@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) BUG_ON(!user_mode(regs)); force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc); } +NOKPROBE_SYMBOL(do_undefinstr); #define __user_cache_maint(insn, address, res) \ if (address >= user_addr_max()) { \ @@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) int rt = ESR_ELx_SYS64_ISS_RT(esr); unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* Hide DIC so that we can trap the unnecessary maintenance...*/ + val &= ~BIT(CTR_DIC_SHIFT); + + /* ... and fake IminLine to reduce the number of traps. */ + val &= ~CTR_IMINLINE_MASK; + val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK; + } + pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); @@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = { {}, }; -asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) +void do_cp15instr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; @@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_cp15instr); #endif -asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +void do_sysinstr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook; @@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_sysinstr); static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", @@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. Unlike bad_mode, this returns. */ -asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) { void __user *pc = (void __user *)instruction_pointer(regs); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index aa76f7259668..009057517bdd 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -111,9 +111,6 @@ SECTIONS } .text : { /* Real text segment */ _stext = .; /* Text and read-only data */ - __exception_text_start = .; - *(.exception.text) - __exception_text_end = .; IRQENTRY_TEXT SOFTIRQENTRY_TEXT ENTRY_TEXT diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index a67121d419a2..a475c68cbfec 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,8 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" depends on OF + # for TASKSTATS/TASK_DELAY_ACCT: + depends on NET && MULTIUSER select MMU_NOTIFIER select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT @@ -39,6 +41,8 @@ config KVM select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE + select TASKSTATS + select TASK_DELAY_ACCT ---help--- Support hosting virtualized guest machines. We don't support KVM with 16K page tables yet, due to the multiple diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 3ac1a64d2fb9..5ffbdc39e780 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -13,6 +13,8 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index dfd626447482..2fff06114a8f 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -34,6 +34,10 @@ #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } struct kvm_stats_debugfs_item debugfs_entries[] = { + VCPU_STAT(halt_successful_poll), + VCPU_STAT(halt_attempted_poll), + VCPU_STAT(halt_poll_invalid), + VCPU_STAT(halt_wakeup), VCPU_STAT(hvc_exit_stat), VCPU_STAT(wfe_exit_stat), VCPU_STAT(wfi_exit_stat), @@ -712,6 +716,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, if (events->exception.serror_pending && events->exception.serror_has_esr) events->exception.serror_esr = vcpu_get_vsesr(vcpu); + /* + * We never return a pending ext_dabt here because we deliver it to + * the virtual CPU directly when setting the event and it's no longer + * 'pending' at this point. + */ + return 0; } @@ -720,6 +730,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, { bool serror_pending = events->exception.serror_pending; bool has_esr = events->exception.serror_has_esr; + bool ext_dabt_pending = events->exception.ext_dabt_pending; if (serror_pending && has_esr) { if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) @@ -733,6 +744,9 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, kvm_inject_vabt(vcpu); } + if (ext_dabt_pending) + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + return 0; } @@ -858,6 +872,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_set_attr(vcpu, attr); break; + case KVM_ARM_VCPU_PVTIME_CTRL: + ret = kvm_arm_pvtime_set_attr(vcpu, attr); + break; default: ret = -ENXIO; break; @@ -878,6 +895,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_get_attr(vcpu, attr); break; + case KVM_ARM_VCPU_PVTIME_CTRL: + ret = kvm_arm_pvtime_get_attr(vcpu, attr); + break; default: ret = -ENXIO; break; @@ -898,6 +918,9 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_has_attr(vcpu, attr); break; + case KVM_ARM_VCPU_PVTIME_CTRL: + ret = kvm_arm_pvtime_has_attr(vcpu, attr); + break; default: ret = -ENXIO; break; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 706cca23f0d2..aacfc55de44c 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -11,8 +11,6 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> -#include <kvm/arm_psci.h> - #include <asm/esr.h> #include <asm/exception.h> #include <asm/kvm_asm.h> @@ -22,6 +20,8 @@ #include <asm/debug-monitors.h> #include <asm/traps.h> +#include <kvm/arm_hypercalls.h> + #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 799e84a40335..72fbbd86eb5e 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -12,7 +12,7 @@ #include <kvm/arm_psci.h> -#include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> @@ -118,6 +118,20 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) } write_sysreg(val, cptr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; + + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * configured and enabled. We can now restore the guest's S1 + * configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } } static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) @@ -159,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void) { u64 mdcr_el2 = read_sysreg(mdcr_el2); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * Set the TCR and SCTLR registers in the exact opposite + * sequence as __activate_traps_nvhe (first prevent walks, + * then force the MMU on). A generous sprinkling of isb() + * ensure that things happen in this exact order. + */ + val = read_sysreg_el1(SYS_TCR); + write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); + isb(); + val = read_sysreg_el1(SYS_SCTLR); + write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); + isb(); + } + __deactivate_traps_common(); mdcr_el2 &= MDCR_EL2_HPMN_MASK; @@ -657,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) */ if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - dsb(sy); + pmr_sync(); } vcpu = kern_hyp_va(vcpu); @@ -670,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_save_state_nvhe(host_ctxt); - __activate_vm(kern_hyp_va(vcpu->kvm)); - __activate_traps(vcpu); - - __hyp_vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - /* * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + * + * Also, and in order to be able to deal with erratum #1319537 (A57) + * and #1319367 (A72), we must ensure that all VM-related sysreg are + * restored before we enable S2 translation. */ __sysreg32_restore_state(vcpu); __sysreg_restore_state_nvhe(guest_ctxt); + + __activate_vm(kern_hyp_va(vcpu->kvm)); + __activate_traps(vcpu); + + __hyp_vgic_restore_state(vcpu); + __timer_enable_traps(vcpu); + __debug_switch_to_guest(vcpu); __set_guest_arch_workaround_state(vcpu); diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 7ddbc849b580..22b8128d19f6 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -117,12 +117,26 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + + if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } else if (!ctxt->__hyp_running_vcpu) { + /* + * Must only be done for guest registers, hence the context + * test. We're coming from the host, so SCTLR.M is already + * set. Pairs with __activate_traps_nvhe(). + */ + write_sysreg_el1((ctxt->sys_regs[TCR_EL1] | + TCR_EPD1_MASK | TCR_EPD0_MASK), + SYS_TCR); + isb(); + } + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); @@ -135,6 +149,23 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) && + ctxt->__hyp_running_vcpu) { + /* + * Must only be done for host registers, hence the context + * test. Pairs with __deactivate_traps_nvhe(). + */ + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * deconfigured and disabled. We can now restore the host's + * S1 configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } + write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index eb0efc5557f3..c2bc17ca6430 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -63,6 +63,22 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * For CPUs that are affected by ARM 1319367, we need to + * avoid a host Stage-1 walk while we have the guest's + * VMID set in the VTTBR in order to invalidate TLBs. + * We're guaranteed that the S1 MMU is enabled, so we can + * simply set the EPD bits to avoid any further TLB fill. + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + isb(); + } + __load_guest_stage2(kvm); isb(); } @@ -100,6 +116,13 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { write_sysreg(0, vttbr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + /* Ensure write of the host VMID */ + isb(); + /* Restore the host's TCR_EL1 */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + } } static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index a9d25a305af5..ccdb6a051ab2 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -109,7 +109,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu) /** * kvm_inject_dabt - inject a data abort into the guest - * @vcpu: The VCPU to receive the undefined exception + * @vcpu: The VCPU to receive the data abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the @@ -125,7 +125,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) /** * kvm_inject_pabt - inject a prefetch abort into the guest - * @vcpu: The VCPU to receive the undefined exception + * @vcpu: The VCPU to receive the prefetch abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 10415572e82f..aeafc03e961a 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -20,7 +20,6 @@ * Alignment fixed up by hardware. */ ENTRY(__arch_clear_user) - uaccess_enable_not_uao x2, x3, x4 mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f @@ -40,7 +39,6 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 b.mi 5f uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 - uaccess_disable_not_uao x2, x3 ret ENDPROC(__arch_clear_user) EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 680e74409ff9..ebb3c06cbb5d 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -54,10 +54,8 @@ end .req x5 ENTRY(__arch_copy_from_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 // Nothing to copy ret ENDPROC(__arch_copy_from_user) diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 0bedae3f3792..3d8153a1ebce 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -56,10 +56,8 @@ end .req x5 ENTRY(__arch_copy_in_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_in_user) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 2d88c736e8f2..357eae2c18eb 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -53,10 +53,8 @@ end .req x5 ENTRY(__arch_copy_to_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_to_user) diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c index cbfcbe6470a5..bfa30b75b2b8 100644 --- a/arch/arm64/lib/uaccess_flushcache.c +++ b/arch/arm64/lib/uaccess_flushcache.c @@ -28,7 +28,11 @@ void memcpy_page_flushcache(char *to, struct page *page, size_t offset, unsigned long __copy_user_flushcache(void *to, const void __user *from, unsigned long n) { - unsigned long rc = __arch_copy_from_user(to, from, n); + unsigned long rc; + + uaccess_enable_not_uao(); + rc = __arch_copy_from_user(to, from, n); + uaccess_disable_not_uao(); /* See above */ __clean_dcache_area_pop(to, n - rc); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9fc6db0bcbad..077b02a2d4d3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -32,7 +32,8 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> -#include <asm/kasan.h> +#include <asm/kprobes.h> +#include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/pgtable.h> @@ -101,18 +102,6 @@ static void mem_abort_decode(unsigned int esr) data_abort_decode(esr); } -static inline bool is_ttbr0_addr(unsigned long addr) -{ - /* entry assembly clears tags for TTBR0 addrs */ - return addr < TASK_SIZE; -} - -static inline bool is_ttbr1_addr(unsigned long addr) -{ - /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ - return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; -} - static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ @@ -318,6 +307,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; + else if (is_el1_instruction_abort(esr)) + msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { @@ -736,8 +727,7 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, - struct pt_regs *regs) +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); @@ -753,43 +743,21 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, arm64_notify_die(inf->name, regs, inf->sig, inf->code, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_mem_abort); -asmlinkage void __exception do_el0_irq_bp_hardening(void) +void do_el0_irq_bp_hardening(void) { /* PC has already been checked in entry.S */ arm64_apply_bp_hardening(); } +NOKPROBE_SYMBOL(do_el0_irq_bp_hardening); -asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) -{ - /* - * We've taken an instruction abort from userspace and not yet - * re-enabled IRQs. If the address is a kernel address, apply - * BP hardening prior to enabling IRQs and pre-emption. - */ - if (!is_ttbr0_addr(addr)) - arm64_apply_bp_hardening(); - - local_daif_restore(DAIF_PROCCTX); - do_mem_abort(addr, esr, regs); -} - - -asmlinkage void __exception do_sp_pc_abort(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - if (user_mode(regs)) { - if (!is_ttbr0_addr(instruction_pointer(regs))) - arm64_apply_bp_hardening(); - local_daif_restore(DAIF_PROCCTX); - } - arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_sp_pc_abort); int __init early_brk64(unsigned long addr, unsigned int esr, struct pt_regs *regs); @@ -872,8 +840,7 @@ NOKPROBE_SYMBOL(debug_exception_exit); #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (user_mode(regs)) return 0; @@ -892,16 +859,15 @@ cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) return 1; } #else -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { return 0; } #endif /* CONFIG_ARM64_ERRATUM_1463225 */ +NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler); -asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, - unsigned int esr, - struct pt_regs *regs) +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 45c00a54909c..be9481cdf3b9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -20,6 +20,7 @@ #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> +#include <linux/dma-direct.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> @@ -41,6 +42,8 @@ #include <asm/tlb.h> #include <asm/alternative.h> +#define ARM64_ZONE_DMA_BITS 30 + /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() @@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset); struct page *vmemmap __ro_after_init; EXPORT_SYMBOL(vmemmap); +/* + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of + * memory as some devices, namely the Raspberry Pi 4, have peripherals with + * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 + * bit addressable memory area. + */ phys_addr_t arm64_dma_phys_limit __ro_after_init; +static phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT, + crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void) { } #endif /* CONFIG_CRASH_DUMP */ + /* - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It - * currently assumes that for memory starting above 4G, 32-bit devices will - * use a DMA offset. + * Return the maximum physical address for a zone with a given address size + * limit. It currently assumes that for memory starting above 4G, 32-bit + * devices will use a DMA offset. */ -static phys_addr_t __init max_zone_dma_phys(void) +static phys_addr_t __init max_zone_phys(unsigned int zone_bits) { - phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); - return min(offset + (1ULL << 32), memblock_end_of_DRAM()); + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits); + return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM()); } #ifdef CONFIG_NUMA @@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); +#endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys()); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); #endif max_zone_pfns[ZONE_NORMAL] = max; @@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { struct memblock_region *reg; unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; - unsigned long max_dma = min; + unsigned long max_dma32 = min; + unsigned long __maybe_unused max_dma = min; memset(zone_size, 0, sizeof(zone_size)); - /* 4GB maximum for 32-bit only capable devices */ -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA max_dma = PFN_DOWN(arm64_dma_phys_limit); - zone_size[ZONE_DMA32] = max_dma - min; + zone_size[ZONE_DMA] = max_dma - min; + max_dma32 = max_dma; +#endif +#ifdef CONFIG_ZONE_DMA32 + max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); + zone_size[ZONE_DMA32] = max_dma32 - max_dma; #endif - zone_size[ZONE_NORMAL] = max - max_dma; + zone_size[ZONE_NORMAL] = max - max_dma32; memcpy(zhole_size, zone_size, sizeof(zhole_size)); @@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA if (start < max_dma) { - unsigned long dma_end = min(end, max_dma); - zhole_size[ZONE_DMA32] -= dma_end - start; + unsigned long dma_end = min_not_zero(end, max_dma); + zhole_size[ZONE_DMA] -= dma_end - start; } #endif - if (end > max_dma) { +#ifdef CONFIG_ZONE_DMA32 + if (start < max_dma32) { + unsigned long dma32_end = min(end, max_dma32); + unsigned long dma32_start = max(start, max_dma); + zhole_size[ZONE_DMA32] -= dma32_end - dma32_start; + } +#endif + if (end > max_dma32) { unsigned long normal_end = min(end, max); - unsigned long normal_start = max(start, max_dma); + unsigned long normal_start = max(start, max_dma32); zhole_size[ZONE_NORMAL] -= normal_end - normal_start; } } @@ -418,11 +443,15 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - /* 4GB maximum for 32-bit only capable devices */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) { + zone_dma_bits = ARM64_ZONE_DMA_BITS; + arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS); + } + if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma_phys_limit = max_zone_dma_phys(); + arm64_dma32_phys_limit = max_zone_phys(32); else - arm64_dma_phys_limit = PHYS_MASK + 1; + arm64_dma32_phys_limit = PHYS_MASK + 1; reserve_crashkernel(); @@ -430,7 +459,7 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - dma_contiguous_reserve(arm64_dma_phys_limit); + dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -534,7 +563,7 @@ static void __init free_unused_memmap(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; @@ -571,7 +600,7 @@ void free_initmem(void) { free_reserved_area(lm_alias(__init_begin), lm_alias(__init_end), - 0, "unused kernel"); + POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which @@ -580,18 +609,6 @@ void free_initmem(void) unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init free_initrd_mem(unsigned long start, unsigned long end) -{ - unsigned long aligned_start, aligned_end; - - aligned_start = __virt_to_phys(start) & PAGE_MASK; - aligned_end = PAGE_ALIGN(__virt_to_phys(end)); - memblock_free(aligned_start, aligned_end - aligned_start); - free_reserved_area((void *)start, (void *)end, 0, "initrd"); -} -#endif - /* * Dump out memory limit information on panic. */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 60c929f3683b..a9f541912289 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -338,7 +338,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys_addr_t (*pgtable_alloc)(int), int flags) { - unsigned long addr, length, end, next; + unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* @@ -350,9 +350,8 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys &= PAGE_MASK; addr = virt & PAGE_MASK; - length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); + end = PAGE_ALIGN(virt + size); - end = addr + length; do { next = pgd_addr_end(addr, end); alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, |