diff options
Diffstat (limited to 'arch/arm64/kernel/vdso')
| -rw-r--r-- | arch/arm64/kernel/vdso/Makefile | 37 | ||||
| -rw-r--r-- | arch/arm64/kernel/vdso/vdso.lds.S | 7 | ||||
| -rw-r--r-- | arch/arm64/kernel/vdso/vgetrandom-chacha.S | 172 | ||||
| -rw-r--r-- | arch/arm64/kernel/vdso/vgetrandom.c | 15 |
4 files changed, 212 insertions, 19 deletions
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 8818287f1095..35685c036044 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -9,7 +9,7 @@ # Include the generic Makefile to check the built vdso. include $(srctree)/lib/vdso/Makefile -obj-vdso := vgettimeofday.o note.o sigreturn.o +obj-vdso := vgettimeofday.o note.o sigreturn.o vgetrandom.o vgetrandom-chacha.o # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg @@ -21,7 +21,7 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # potential future proofing if we end up with internal calls to the exported # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). -ldflags-y := -shared -soname=linux-vdso.so.1 --hash-style=sysv \ +ldflags-y := -shared -soname=linux-vdso.so.1 \ -Bsymbolic --build-id=sha1 -n $(btildflags-y) ifdef CONFIG_LD_ORPHAN_WARN @@ -34,26 +34,27 @@ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO # -Wmissing-prototypes and -Wmissing-declarations are removed from -# the CFLAGS of vgettimeofday.c to make possible to build the -# kernel with CONFIG_WERROR enabled. -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) \ - $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) \ - $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) \ - -Wmissing-prototypes -Wmissing-declarations -KASAN_SANITIZE := n -KCSAN_SANITIZE := n -UBSAN_SANITIZE := n -OBJECT_FILES_NON_STANDARD := y -KCOV_INSTRUMENT := n - -CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -fasynchronous-unwind-tables +# the CFLAGS to make possible to build the kernel with CONFIG_WERROR enabled. +CC_FLAGS_REMOVE_VDSO := $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) \ + $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) \ + $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) \ + -Wmissing-prototypes -Wmissing-declarations + +CC_FLAGS_ADD_VDSO := -O2 -mcmodel=tiny -fasynchronous-unwind-tables + +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_REMOVE_VDSO) +CFLAGS_REMOVE_vgetrandom.o = $(CC_FLAGS_REMOVE_VDSO) + +CFLAGS_vgettimeofday.o = $(CC_FLAGS_ADD_VDSO) +CFLAGS_vgetrandom.o = $(CC_FLAGS_ADD_VDSO) ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) endif -# Disable gcov profiling for VDSO code -GCOV_PROFILE := n +ifneq ($(c-getrandom-y),) + CFLAGS_vgetrandom.o += -include $(c-getrandom-y) +endif targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) @@ -68,7 +69,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +gen-vdsosym := $(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 45354f2ddf70..47ad6944f9f0 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -11,7 +11,9 @@ #include <linux/const.h> #include <asm/page.h> #include <asm/vdso.h> +#include <asm/vdso/vsyscall.h> #include <asm-generic/vmlinux.lds.h> +#include <vdso/datapage.h> OUTPUT_FORMAT("elf64-littleaarch64", "elf64-bigaarch64", "elf64-littleaarch64") OUTPUT_ARCH(aarch64) @@ -19,10 +21,11 @@ OUTPUT_ARCH(aarch64) SECTIONS { PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); + PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET); #ifdef CONFIG_TIME_NS PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); #endif - . = VDSO_LBASE + SIZEOF_HEADERS; + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text .gnu.hash : { *(.gnu.hash) } @@ -38,6 +41,7 @@ SECTIONS */ /DISCARD/ : { *(.note.GNU-stack .note.gnu.property) + *(.ARM.attributes) } .note : { *(.note.*) } :text :note @@ -102,6 +106,7 @@ VERSION __kernel_gettimeofday; __kernel_clock_gettime; __kernel_clock_getres; + __kernel_getrandom; local: *; }; } diff --git a/arch/arm64/kernel/vdso/vgetrandom-chacha.S b/arch/arm64/kernel/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000000..67890b445309 --- /dev/null +++ b/arch/arm64/kernel/vdso/vgetrandom-chacha.S @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/linkage.h> +#include <asm/cache.h> +#include <asm/assembler.h> + + .text + +#define state0 v0 +#define state1 v1 +#define state2 v2 +#define state3 v3 +#define copy0 v4 +#define copy0_q q4 +#define copy1 v5 +#define copy2 v6 +#define copy3 v7 +#define copy3_d d7 +#define one_d d16 +#define one_q q16 +#define one_v v16 +#define tmp v17 +#define rot8 v18 + +/* + * ARM64 ChaCha20 implementation meant for vDSO. Produces a given positive + * number of blocks of output with nonce 0, taking an input key and 8-bytes + * counter. Importantly does not spill to the stack. + * + * This implementation avoids d8-d15 because they are callee-save in user + * space. + * + * void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, + * const uint8_t *key, + * uint32_t *counter, + * size_t nblocks) + * + * x0: output bytes + * x1: 32-byte key input + * x2: 8-byte counter input/output + * x3: number of 64-byte block to write to output + */ +SYM_FUNC_START(__arch_chacha20_blocks_nostack) + + /* copy0 = "expand 32-byte k" */ + mov_q x8, 0x3320646e61707865 + mov_q x9, 0x6b20657479622d32 + mov copy0.d[0], x8 + mov copy0.d[1], x9 + + /* copy1,copy2 = key */ + ld1 { copy1.4s, copy2.4s }, [x1] + /* copy3 = counter || zero nonce */ + ld1 { copy3.2s }, [x2] + + movi one_v.2s, #1 + uzp1 one_v.4s, one_v.4s, one_v.4s + +.Lblock: + /* copy state to auxiliary vectors for the final add after the permute. */ + mov state0.16b, copy0.16b + mov state1.16b, copy1.16b + mov state2.16b, copy2.16b + mov state3.16b, copy3.16b + + mov w4, 20 +.Lpermute: + /* + * Permute one 64-byte block where the state matrix is stored in the four NEON + * registers state0-state3. It performs matrix operations on four words in parallel, + * but requires shuffling to rearrange the words after each round. + */ + +.Ldoubleround: + /* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */ + add state0.4s, state0.4s, state1.4s + eor state3.16b, state3.16b, state0.16b + rev32 state3.8h, state3.8h + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */ + add state2.4s, state2.4s, state3.4s + eor tmp.16b, state1.16b, state2.16b + shl state1.4s, tmp.4s, #12 + sri state1.4s, tmp.4s, #20 + + /* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */ + add state0.4s, state0.4s, state1.4s + eor tmp.16b, state3.16b, state0.16b + shl state3.4s, tmp.4s, #8 + sri state3.4s, tmp.4s, #24 + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */ + add state2.4s, state2.4s, state3.4s + eor tmp.16b, state1.16b, state2.16b + shl state1.4s, tmp.4s, #7 + sri state1.4s, tmp.4s, #25 + + /* state1[0,1,2,3] = state1[1,2,3,0] */ + ext state1.16b, state1.16b, state1.16b, #4 + /* state2[0,1,2,3] = state2[2,3,0,1] */ + ext state2.16b, state2.16b, state2.16b, #8 + /* state3[0,1,2,3] = state3[1,2,3,0] */ + ext state3.16b, state3.16b, state3.16b, #12 + + /* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */ + add state0.4s, state0.4s, state1.4s + eor state3.16b, state3.16b, state0.16b + rev32 state3.8h, state3.8h + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */ + add state2.4s, state2.4s, state3.4s + eor tmp.16b, state1.16b, state2.16b + shl state1.4s, tmp.4s, #12 + sri state1.4s, tmp.4s, #20 + + /* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */ + add state0.4s, state0.4s, state1.4s + eor tmp.16b, state3.16b, state0.16b + shl state3.4s, tmp.4s, #8 + sri state3.4s, tmp.4s, #24 + + /* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */ + add state2.4s, state2.4s, state3.4s + eor tmp.16b, state1.16b, state2.16b + shl state1.4s, tmp.4s, #7 + sri state1.4s, tmp.4s, #25 + + /* state1[0,1,2,3] = state1[3,0,1,2] */ + ext state1.16b, state1.16b, state1.16b, #12 + /* state2[0,1,2,3] = state2[2,3,0,1] */ + ext state2.16b, state2.16b, state2.16b, #8 + /* state3[0,1,2,3] = state3[1,2,3,0] */ + ext state3.16b, state3.16b, state3.16b, #4 + + subs w4, w4, #2 + b.ne .Ldoubleround + + /* output0 = state0 + state0 */ + add state0.4s, state0.4s, copy0.4s + /* output1 = state1 + state1 */ + add state1.4s, state1.4s, copy1.4s + /* output2 = state2 + state2 */ + add state2.4s, state2.4s, copy2.4s + /* output2 = state3 + state3 */ + add state3.4s, state3.4s, copy3.4s + st1 { state0.16b - state3.16b }, [x0] + + /* + * ++copy3.counter, the 'add' clears the upper half of the SIMD register + * which is the expected behaviour here. + */ + add copy3_d, copy3_d, one_d + + /* output += 64, --nblocks */ + add x0, x0, 64 + subs x3, x3, #1 + b.ne .Lblock + + /* counter = copy3.counter */ + st1 { copy3.2s }, [x2] + + /* Zero out the potentially sensitive regs, in case nothing uses these again. */ + movi state0.16b, #0 + movi state1.16b, #0 + movi state2.16b, #0 + movi state3.16b, #0 + movi copy1.16b, #0 + movi copy2.16b, #0 + ret +SYM_FUNC_END(__arch_chacha20_blocks_nostack) + +emit_aarch64_feature_1_and diff --git a/arch/arm64/kernel/vdso/vgetrandom.c b/arch/arm64/kernel/vdso/vgetrandom.c new file mode 100644 index 000000000000..832fe195292b --- /dev/null +++ b/arch/arm64/kernel/vdso/vgetrandom.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <uapi/asm-generic/errno.h> + +typeof(__cvdso_getrandom) __kernel_getrandom; + +ssize_t __kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + if (alternative_has_cap_likely(ARM64_HAS_FPSIMD)) + return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len); + + if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) + return -ENOSYS; + return getrandom_syscall(buffer, len, flags); +} |