--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#ifndef _ASM_POWERPC_VDSO_GETRANDOM_H
+#define _ASM_POWERPC_VDSO_GETRANDOM_H
+
+#ifndef __ASSEMBLY__
+
+static __always_inline int do_syscall_3(const unsigned long _r0, const unsigned long _r3,
+ const unsigned long _r4, const unsigned long _r5)
+{
+ register long r0 asm("r0") = _r0;
+ register unsigned long r3 asm("r3") = _r3;
+ register unsigned long r4 asm("r4") = _r4;
+ register unsigned long r5 asm("r5") = _r5;
+ register int ret asm ("r3");
+
+ asm volatile(
+ " sc\n"
+ " bns+ 1f\n"
+ " neg %0, %0\n"
+ "1:\n"
+ : "=r" (ret), "+r" (r4), "+r" (r5), "+r" (r0)
+ : "r" (r3)
+ : "memory", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr");
+
+ return ret;
+}
+
+/**
+ * getrandom_syscall - Invoke the getrandom() syscall.
+ * @buffer: Destination buffer to fill with random bytes.
+ * @len: Size of @buffer in bytes.
+ * @flags: Zero or more GRND_* flags.
+ * Returns: The number of bytes written to @buffer, or a negative value indicating an error.
+ */
+static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsigned int flags)
+{
+ return do_syscall_3(__NR_getrandom, (unsigned long)buffer,
+ (unsigned long)len, (unsigned long)flags);
+}
+
+static __always_inline struct vdso_rng_data *__arch_get_vdso_rng_data(void)
+{
+ return NULL;
+}
+
+ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
+ size_t opaque_len, const struct vdso_rng_data *vd);
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_VDSO_GETRANDOM_H */
obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
+obj-vdso32 += getrandom-32.o vgetrandom-chacha-32.o
+
ifneq ($(c-gettimeofday-y),)
CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y)
# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) $(call cc-option, -ffixed-r30)
endif
+ifneq ($(c-getrandom-y),)
+ CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y)
+endif
+
# Build rules
ifdef CROSS32_COMPILE
VDSOCC := $(CC)
endif
-targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o
+targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o vgetrandom-32.o
targets += crtsavres-32.o
obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o
obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
-ccflags-y := -fno-common -fno-builtin
+ccflags-y := -fno-common -fno-builtin -DBUILD_VDSO
ccflags-y += $(DISABLE_LATENT_ENTROPY_PLUGIN)
ccflags-y += $(call cc-option, -fno-stack-protector)
ccflags-y += -DDISABLE_BRANCH_PROFILING
CPPFLAGS_vdso64.lds += -P -C
# link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o $(obj)/crtsavres-32.o FORCE
+$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o $(obj)/vgetrandom-32.o $(obj)/crtsavres-32.o FORCE
$(call if_changed,vdso32ld_and_check)
$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE
$(call if_changed,vdso64ld_and_check)
$(call if_changed_dep,vdso32as)
$(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE
$(call if_changed_dep,vdso32cc)
+$(obj)/vgetrandom-32.o: %-32.o: %.c FORCE
+ $(call if_changed_dep,vdso32cc)
$(obj-vdso64): %-64.o: %.S FORCE
$(call if_changed_dep,vdso64as)
$(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/ppc_asm.h>
+
+#define dst_bytes r3
+#define key r4
+#define counter r5
+#define nblocks r6
+
+#define idx_r0 r0
+#define val4 r4
+
+#define const0 0x61707865
+#define const1 0x3320646e
+#define const2 0x79622d32
+#define const3 0x6b206574
+
+#define key0 r5
+#define key1 r6
+#define key2 r7
+#define key3 r8
+#define key4 r9
+#define key5 r10
+#define key6 r11
+#define key7 r12
+
+#define counter0 r14
+#define counter1 r15
+
+#define state0 r16
+#define state1 r17
+#define state2 r18
+#define state3 r19
+#define state4 r20
+#define state5 r21
+#define state6 r22
+#define state7 r23
+#define state8 r24
+#define state9 r25
+#define state10 r26
+#define state11 r27
+#define state12 r28
+#define state13 r29
+#define state14 r30
+#define state15 r31
+
+.macro quarterround4 a1 b1 c1 d1 a2 b2 c2 d2 a3 b3 c3 d3 a4 b4 c4 d4
+ add \a1, \a1, \b1
+ add \a2, \a2, \b2
+ add \a3, \a3, \b3
+ add \a4, \a4, \b4
+ xor \d1, \d1, \a1
+ xor \d2, \d2, \a2
+ xor \d3, \d3, \a3
+ xor \d4, \d4, \a4
+ rotlwi \d1, \d1, 16
+ rotlwi \d2, \d2, 16
+ rotlwi \d3, \d3, 16
+ rotlwi \d4, \d4, 16
+ add \c1, \c1, \d1
+ add \c2, \c2, \d2
+ add \c3, \c3, \d3
+ add \c4, \c4, \d4
+ xor \b1, \b1, \c1
+ xor \b2, \b2, \c2
+ xor \b3, \b3, \c3
+ xor \b4, \b4, \c4
+ rotlwi \b1, \b1, 12
+ rotlwi \b2, \b2, 12
+ rotlwi \b3, \b3, 12
+ rotlwi \b4, \b4, 12
+ add \a1, \a1, \b1
+ add \a2, \a2, \b2
+ add \a3, \a3, \b3
+ add \a4, \a4, \b4
+ xor \d1, \d1, \a1
+ xor \d2, \d2, \a2
+ xor \d3, \d3, \a3
+ xor \d4, \d4, \a4
+ rotlwi \d1, \d1, 8
+ rotlwi \d2, \d2, 8
+ rotlwi \d3, \d3, 8
+ rotlwi \d4, \d4, 8
+ add \c1, \c1, \d1
+ add \c2, \c2, \d2
+ add \c3, \c3, \d3
+ add \c4, \c4, \d4
+ xor \b1, \b1, \c1
+ xor \b2, \b2, \c2
+ xor \b3, \b3, \c3
+ xor \b4, \b4, \c4
+ rotlwi \b1, \b1, 7
+ rotlwi \b2, \b2, 7
+ rotlwi \b3, \b3, 7
+ rotlwi \b4, \b4, 7
+.endm
+
+#define QUARTERROUND4(a1,b1,c1,d1,a2,b2,c2,d2,a3,b3,c3,d3,a4,b4,c4,d4) \
+ quarterround4 state##a1 state##b1 state##c1 state##d1 \
+ state##a2 state##b2 state##c2 state##d2 \
+ state##a3 state##b3 state##c3 state##d3 \
+ state##a4 state##b4 state##c4 state##d4
+
+/*
+ * Very basic 32 bits implementation of ChaCha20. Produces a given positive number
+ * of blocks of output with a nonce of 0, taking an input key and 8-byte
+ * counter. Importantly does not spill to the stack. Its arguments are:
+ *
+ * r3: output bytes
+ * r4: 32-byte key input
+ * r5: 8-byte counter input/output (saved on stack)
+ * r6: number of 64-byte blocks to write to output
+ *
+ * r0: counter of blocks (initialised with r6)
+ * r4: Value '4' after key has been read.
+ * r5-r12: key
+ * r14-r15: counter
+ * r16-r31: state
+ */
+SYM_FUNC_START(__arch_chacha20_blocks_nostack)
+#ifdef __powerpc64__
+#else
+ stwu r1, -96(r1)
+ stw counter, 20(r1)
+#ifdef __BIG_ENDIAN__
+ stmw r14, 24(r1)
+#else
+ stw r14, 24(r1)
+ stw r15, 28(r1)
+ stw r16, 32(r1)
+ stw r17, 36(r1)
+ stw r18, 40(r1)
+ stw r19, 44(r1)
+ stw r20, 48(r1)
+ stw r21, 52(r1)
+ stw r22, 56(r1)
+ stw r23, 60(r1)
+ stw r24, 64(r1)
+ stw r25, 68(r1)
+ stw r26, 72(r1)
+ stw r27, 76(r1)
+ stw r28, 80(r1)
+ stw r29, 84(r1)
+ stw r30, 88(r1)
+ stw r31, 92(r1)
+#endif
+
+ lwz counter0, 0(counter)
+ lwz counter1, 4(counter)
+ mr idx_r0, nblocks
+ subi dst_bytes, dst_bytes, 4
+
+ lwz key0, 0(key)
+ lwz key1, 4(key)
+ lwz key2, 8(key)
+ lwz key3, 12(key)
+ lwz key4, 16(key)
+ lwz key5, 20(key)
+ lwz key6, 24(key)
+ lwz key7, 28(key)
+
+ li val4, 4
+.Lblock:
+ li r31, 10
+
+ lis state0, const0@ha
+ lis state1, const1@ha
+ lis state2, const2@ha
+ lis state3, const3@ha
+ addi state0, state0, const0@l
+ addi state1, state1, const1@l
+ addi state2, state2, const2@l
+ addi state3, state3, const3@l
+
+ mtctr r31
+
+ mr state4, key0
+ mr state5, key1
+ mr state6, key2
+ mr state7, key3
+ mr state8, key4
+ mr state9, key5
+ mr state10, key6
+ mr state11, key7
+
+ mr state12, counter0
+ mr state13, counter1
+
+ li state14, 0
+ li state15, 0
+
+.Lpermute:
+ QUARTERROUND4( 0, 4, 8,12, 1, 5, 9,13, 2, 6,10,14, 3, 7,11,15)
+ QUARTERROUND4( 0, 5,10,15, 1, 6,11,12, 2, 7, 8,13, 3, 4, 9,14)
+
+ bdnz .Lpermute
+
+ addis state0, state0, const0@ha
+ addis state1, state1, const1@ha
+ addis state2, state2, const2@ha
+ addis state3, state3, const3@ha
+ addi state0, state0, const0@l
+ addi state1, state1, const1@l
+ addi state2, state2, const2@l
+ addi state3, state3, const3@l
+
+ add state4, state4, key0
+ add state5, state5, key1
+ add state6, state6, key2
+ add state7, state7, key3
+ add state8, state8, key4
+ add state9, state9, key5
+ add state10, state10, key6
+ add state11, state11, key7
+
+ add state12, state12, counter0
+ add state13, state13, counter1
+
+#ifdef __BIG_ENDIAN__
+ stwbrx state0, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state1, 0, dst_bytes
+ stwbrx state2, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state3, 0, dst_bytes
+ stwbrx state4, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state5, 0, dst_bytes
+ stwbrx state6, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state7, 0, dst_bytes
+ stwbrx state8, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state9, 0, dst_bytes
+ stwbrx state10, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state11, 0, dst_bytes
+ stwbrx state12, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state13, 0, dst_bytes
+ stwbrx state14, val4, dst_bytes
+ addi dst_bytes, dst_bytes, 8
+ stwbrx state15, 0, dst_bytes
+#else
+ stw state0, 4(dst_bytes)
+ stw state1, 8(dst_bytes)
+ stw state2, 12(dst_bytes)
+ stw state3, 16(dst_bytes)
+ stw state4, 20(dst_bytes)
+ stw state5, 24(dst_bytes)
+ stw state6, 28(dst_bytes)
+ stw state7, 32(dst_bytes)
+ stw state8, 36(dst_bytes)
+ stw state9, 40(dst_bytes)
+ stw state10, 44(dst_bytes)
+ stw state11, 48(dst_bytes)
+ stw state12, 52(dst_bytes)
+ stw state13, 56(dst_bytes)
+ stw state14, 60(dst_bytes)
+ stwu state15, 64(dst_bytes)
+#endif
+
+ subic. idx_r0, idx_r0, 1 /* subi. can't use r0 as source */
+
+ addic counter0, counter0, 1
+ addze counter1, counter1
+
+ bne .Lblock
+
+ lwz counter, 20(r1)
+ stw counter0, 0(counter)
+ stw counter1, 4(counter)
+
+ li r6, 0
+ li r7, 0
+ li r8, 0
+ li r9, 0
+ li r10, 0
+ li r11, 0
+ li r12, 0
+
+#ifdef __BIG_ENDIAN__
+ lmw r14, 24(r1)
+#else
+ lwz r14, 24(r1)
+ lwz r15, 28(r1)
+ lwz r16, 32(r1)
+ lwz r17, 36(r1)
+ lwz r18, 40(r1)
+ lwz r19, 44(r1)
+ lwz r20, 48(r1)
+ lwz r21, 52(r1)
+ lwz r22, 56(r1)
+ lwz r23, 60(r1)
+ lwz r24, 64(r1)
+ lwz r25, 68(r1)
+ lwz r26, 72(r1)
+ lwz r27, 76(r1)
+ lwz r28, 80(r1)
+ lwz r29, 84(r1)
+ lwz r30, 88(r1)
+ lwz r31, 92(r1)
+#endif
+ addi r1, r1, 96
+#endif /* __powerpc64__ */
+ blr
+SYM_FUNC_END(__arch_chacha20_blocks_nostack)