Commit 9651fcedf7b9 ("mm: add MAP_DROPPABLE for designating always lazily freeable mappings") only adds VM_DROPPABLE for 64 bits architectures.

In order to also use the getrandom vDSO implementation on powerpc/32, use VM_ARCH_1 for VM_DROPPABLE on powerpc/32. This is possible because VM_ARCH_1 is used for VM_SAO on powerpc and VM_SAO is only for powerpc/64.

Signed-off-by: Christophe Leroy christophe.leroy@csgroup.eu --- v3: Fixed build failure reported by robots. --- fs/proc/task_mmu.c | 4 +++- include/linux/mm.h | 4 +++- include/trace/events/mmflags.h | 4 ++-- 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5f171ad7b436..3a07e13e2f81 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -987,8 +987,10 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #ifdef CONFIG_X86_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", #endif -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) [ilog2(VM_DROPPABLE)] = "dp", +#endif +#ifdef CONFIG_64BIT [ilog2(VM_SEALED)] = "sl", #endif }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 6549d0979b28..028847f39442 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -359,7 +359,7 @@ extern unsigned int kobjsize(const void *objp);

#if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC) +#elif defined(CONFIG_PPC64) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 @@ -409,6 +409,8 @@ extern unsigned int kobjsize(const void *objp); #ifdef CONFIG_64BIT #define VM_DROPPABLE_BIT 40 #define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#elif defined(CONFIG_PPC32) +#define VM_DROPPABLE VM_ARCH_1 #else #define VM_DROPPABLE VM_NONE #endif diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index b63d211bd141..37265977d524 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -143,7 +143,7 @@ IF_HAVE_PG_ARCH_X(arch_3)

#if defined(CONFIG_X86) #define __VM_ARCH_SPECIFIC_1 {VM_PAT, "pat" } -#elif defined(CONFIG_PPC) +#elif defined(CONFIG_PPC64) #define __VM_ARCH_SPECIFIC_1 {VM_SAO, "sao" } #elif defined(CONFIG_PARISC) #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP, "growsup" } @@ -165,7 +165,7 @@ IF_HAVE_PG_ARCH_X(arch_3) # define IF_HAVE_UFFD_MINOR(flag, name) #endif

-#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) # define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name}, #else # define IF_HAVE_VM_DROPPABLE(flag, name)

Commit 08c18b63d965 ("powerpc/vdso32: Add missing _restgpr_31_x to fix build failure") added _restgpr_31_x to the vdso for gettimeofday, but the work on getrandom shows that we will need more of those functions.

Remove _restgpr_31_x and link in crtsavres.o so that we get all save/restore functions when optimising the kernel for size.

Signed-off-by: Christophe Leroy christophe.leroy@csgroup.eu --- arch/powerpc/kernel/vdso/Makefile | 5 ++++- arch/powerpc/kernel/vdso/gettimeofday.S | 13 ------------- 2 files changed, 4 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 1425b6edc66b..c07a425b8f78 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -43,6 +43,7 @@ else endif

targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-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)) @@ -68,7 +69,7 @@ targets += vdso64.lds 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) $(obj)/vgettimeofday-32.o FORCE +$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-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) @@ -76,6 +77,8 @@ $(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o # assembly rules for the .S files $(obj-vdso32): %-32.o: %.S FORCE $(call if_changed_dep,vdso32as) +$(obj)/crtsavres-32.o: %-32.o: $(srctree)/arch/powerpc/lib/crtsavres.S FORCE + $(call if_changed_dep,vdso32as) $(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE $(call if_changed_dep,vdso32cc) $(obj-vdso64): %-64.o: %.S FORCE diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index 48fc6658053a..67254ac9c8bb 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -118,16 +118,3 @@ V_FUNCTION_END(__kernel_clock_getres) V_FUNCTION_BEGIN(__kernel_time) cvdso_call __c_kernel_time call_time=1 V_FUNCTION_END(__kernel_time) - -/* Routines for restoring integer registers, called by the compiler. */ -/* Called with r11 pointing to the stack header word of the caller of the */ -/* function, just beyond the end of the integer restore area. */ -#ifndef __powerpc64__ -_GLOBAL(_restgpr_31_x) -_GLOBAL(_rest32gpr_31_x) - lwz r0,4(r11) - lwz r31,-4(r11) - mtlr r0 - mr r1,r11 - blr -#endif

To be consistent with other VDSO functions, the function is called __kernel_getrandom()

__arch_chacha20_blocks_nostack() fonction is implemented basically with 32 bits operations. It performs 4 QUARTERROUND operations in parallele. There are enough registers to avoid using the stack:

On input: r3: output bytes r4: 32-byte key input r5: 8-byte counter input/output r6: number of 64-byte blocks to write to output

During operation: stack: pointer to counter (r5) and non-volatile registers (r14-131) r0: counter of blocks (initialised with r6) r4: Value '4' after key has been read, used for indexing r5-r12: key r14-r15: block counter r16-r31: chacha state

At the end: r0, r6-r12: Zeroised r5, r14-r31: Restored

Performance on powerpc 885 (using kernel selftest): ~# ./vdso_test_getrandom bench-single vdso: 25000000 times in 62.938002291 seconds libc: 25000000 times in 535.581916866 seconds syscall: 25000000 times in 531.525042806 seconds

Performance on powerpc 8321 (using kernel selftest): ~# ./vdso_test_getrandom bench-single vdso: 25000000 times in 16.899318858 seconds libc: 25000000 times in 131.050596522 seconds syscall: 25000000 times in 129.794790389 seconds

Signed-off-by: Christophe Leroy christophe.leroy@csgroup.eu --- v3: - Preserve r13, implies saving r5 on stack - Split PPC64 implementation out. --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/asm-compat.h | 8 + arch/powerpc/include/asm/vdso/getrandom.h | 54 +++++ arch/powerpc/include/asm/vdso/vsyscall.h | 6 + arch/powerpc/include/asm/vdso_datapage.h | 2 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/vdso/Makefile | 12 +- arch/powerpc/kernel/vdso/getrandom.S | 50 +++++ arch/powerpc/kernel/vdso/vdso32.lds.S | 1 + arch/powerpc/kernel/vdso/vgetrandom-chacha.S | 201 +++++++++++++++++++ arch/powerpc/kernel/vdso/vgetrandom.c | 14 ++ tools/arch/powerpc/vdso | 1 + tools/testing/selftests/vDSO/Makefile | 4 + 13 files changed, 353 insertions(+), 2 deletions(-) create mode 100644 arch/powerpc/include/asm/vdso/getrandom.h create mode 100644 arch/powerpc/kernel/vdso/getrandom.S create mode 100644 arch/powerpc/kernel/vdso/vgetrandom-chacha.S create mode 100644 arch/powerpc/kernel/vdso/vgetrandom.c create mode 120000 tools/arch/powerpc/vdso

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d7b09b064a8a..54b270ef18b1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -311,6 +311,7 @@ config PPC select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT + select VDSO_GETRANDOM if PPC32 # # Please keep this list sorted alphabetically. # diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index b0b209c1df50..cce8c31b1b33 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -59,4 +59,12 @@

#endif

+#ifdef __BIG_ENDIAN__ +#define LWZX_LE stringify_in_c(lwbrx) +#define STWX_LE stringify_in_c(stwbrx) +#else +#define LWZX_LE stringify_in_c(lwzx) +#define STWX_LE stringify_in_c(stwx) +#endif + #endif /* _ASM_POWERPC_ASM_COMPAT_H */ diff --git a/arch/powerpc/include/asm/vdso/getrandom.h b/arch/powerpc/include/asm/vdso/getrandom.h new file mode 100644 index 000000000000..501d6bb14e8a --- /dev/null +++ b/arch/powerpc/include/asm/vdso/getrandom.h @@ -0,0 +1,54 @@ +/* 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 */ diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h index 48cf23f1e273..92f480d8cc6d 100644 --- a/arch/powerpc/include/asm/vdso/vsyscall.h +++ b/arch/powerpc/include/asm/vdso/vsyscall.h @@ -17,6 +17,12 @@ struct vdso_data *__arch_get_k_vdso_data(void) } #define __arch_get_k_vdso_data __arch_get_k_vdso_data

+static __always_inline +struct vdso_rng_data *__arch_get_k_vdso_rng_data(void) +{ + return &vdso_data->rng_data; +} + /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h>

diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index a585c8e538ff..e17500c5237e 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -83,6 +83,7 @@ struct vdso_arch_data { __u32 compat_syscall_map[SYSCALL_MAP_SIZE]; /* Map of compat syscalls */

struct vdso_data data[CS_BASES]; + struct vdso_rng_data rng_data; };

#else /* CONFIG_PPC64 */ @@ -95,6 +96,7 @@ struct vdso_arch_data { __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ __u32 compat_syscall_map[0]; /* No compat syscalls on PPC32 */ struct vdso_data data[CS_BASES]; + struct vdso_rng_data rng_data; };

#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 23733282de4d..eedb2e04c785 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -335,6 +335,7 @@ int main(void)

/* datapage offsets for use by vdso */ OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data); + OFFSET(VDSO_RNG_DATA_OFFSET, vdso_arch_data, rng_data); OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec); #ifdef CONFIG_PPC64 OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size); diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 67fe79d26fae..fa0b9b3b51af 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -8,6 +8,8 @@ include $(srctree)/lib/vdso/Makefile 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 $(c-gettimeofday-y) # Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true @@ -17,6 +19,10 @@ ifneq ($(c-gettimeofday-y),) 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 @@ -25,7 +31,7 @@ else 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 @@ -63,7 +69,7 @@ targets += vdso64.lds 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) @@ -75,6 +81,8 @@ $(obj)/crtsavres-32.o: %-32.o: $(srctree)/arch/powerpc/lib/crtsavres.S FORCE $(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 diff --git a/arch/powerpc/kernel/vdso/getrandom.S b/arch/powerpc/kernel/vdso/getrandom.S new file mode 100644 index 000000000000..21773ef3fc1d --- /dev/null +++ b/arch/powerpc/kernel/vdso/getrandom.S @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Userland implementation of getrandom() for processes + * for use in the vDSO + * + * Copyright (C) 2024 Christophe Leroy christophe.leroy@csgroup.eu, CS GROUP France + */ +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/vdso_datapage.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + +/* + * The macro sets two stack frames, one for the caller and one for the callee + * because there are no requirement for the caller to set a stack frame when + * calling VDSO so it may have omitted to set one, especially on PPC64 + */ + +.macro cvdso_call funct + .cfi_startproc + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM + mflr r0 + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM + PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF + get_datapage r8 + addi r8, r8, VDSO_RNG_DATA_OFFSET + bl CFUNC(DOTSYM(\funct)) + PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + cmpwi r3, 0 + mtlr r0 + addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 + crclr so + bgelr+ + crset so + neg r3, r3 + blr + .cfi_endproc +.endm + + .text +V_FUNCTION_BEGIN(__kernel_getrandom) + cvdso_call __c_kernel_getrandom +V_FUNCTION_END(__kernel_getrandom) diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 8f57107000a2..7b41d5d256e8 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -130,6 +130,7 @@ VERSION #if defined(CONFIG_PPC64) || !defined(CONFIG_SMP) __kernel_getcpu; #endif + __kernel_getrandom;

local: *; }; diff --git a/arch/powerpc/kernel/vdso/vgetrandom-chacha.S b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000000..a3475b9e8c10 --- /dev/null +++ b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S @@ -0,0 +1,201 @@ +/* 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> + +.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 16+a1 16+b1 16+c1 16+d1 16+a2 16+b2 16+c2 16+d2 \ + 16+a3 16+b3 16+c3 16+d3 16+a4 16+b4 16+c4 16+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) + stwu r1, -96(r1) + stw r5, 20(r1) + stmw r14, 24(r1) + li r31, 4 + LWZX_LE r14, 0, r5 + LWZX_LE r15, r31, r5 + mr r0, r6 + + lwz r5, 0(r4) + lwz r6, 4(r4) + lwz r7, 8(r4) + lwz r8, 12(r4) + lwz r9, 16(r4) + lwz r10, 20(r4) + lwz r11, 24(r4) + lwz r12, 28(r4) + + li r4, 4 +.Lblock: + li r31, 10 + + lis r16, 0x6170 + lis r17, 0x3320 + lis r18, 0x7962 + lis r19, 0x6b20 + addi r16, r16, 0x7865 + addi r17, r17, 0x646e + addi r18, r18, 0x2d32 + addi r19, r19, 0x6574 + + mtctr r31 + + mr r20, r5 + mr r21, r6 + mr r22, r7 + mr r23, r8 + mr r24, r9 + mr r25, r10 + mr r26, r11 + mr r27, r12 + + mr r28, r14 + mr r29, r15 + li r30, 0 + li r31, 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 r16, r16, 0x6170 + addis r17, r17, 0x3320 + addis r18, r18, 0x7962 + addis r19, r19, 0x6b20 + addi r16, r16, 0x7865 + addi r17, r17, 0x646e + addi r18, r18, 0x2d32 + addi r19, r19, 0x6574 + + add r20, r20, r5 + add r21, r21, r6 + add r22, r22, r7 + add r23, r23, r8 + add r24, r24, r9 + add r25, r25, r10 + add r26, r26, r11 + add r27, r27, r12 + + add r28, r28, r14 + add r29, r29, r15 + + STWX_LE r16, 0, r3 + STWX_LE r17, r4, r3 + addi r3, r3, 8 + STWX_LE r18, 0, r3 + STWX_LE r19, r4, r3 + addi r3, r3, 8 + STWX_LE r20, 0, r3 + STWX_LE r21, r4, r3 + addi r3, r3, 8 + STWX_LE r22, 0, r3 + STWX_LE r23, r4, r3 + addi r3, r3, 8 + STWX_LE r24, 0, r3 + STWX_LE r25, r4, r3 + addi r3, r3, 8 + STWX_LE r26, 0, r3 + STWX_LE r27, r4, r3 + addi r3, r3, 8 + STWX_LE r28, 0, r3 + STWX_LE r29, r4, r3 + addi r3, r3, 8 + STWX_LE r30, 0, r3 + STWX_LE r31, r4, r3 + addi r3, r3, 8 + + addic r14, r14, 1 + addze r15, r15 + + subic. r0, r0, 1 /* subi. can't use r0 as source */ + bne .Lblock + + lwz r5, 20(r1) + STWX_LE r14, 0, r5 + STWX_LE r15, r4, r5 + + li r6, 0 + li r7, 0 + li r8, 0 + li r9, 0 + li r10, 0 + li r11, 0 + li r12, 0 + + lmw r14, 24(r1) + addi r1, r1, 96 + blr +SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/powerpc/kernel/vdso/vgetrandom.c b/arch/powerpc/kernel/vdso/vgetrandom.c new file mode 100644 index 000000000000..5f855d45fb7b --- /dev/null +++ b/arch/powerpc/kernel/vdso/vgetrandom.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Powerpc userspace implementation of getrandom() + * + * Copyright (C) 2024 Christophe Leroy christophe.leroy@csgroup.eu, CS GROUP France + */ +#include <linux/time.h> +#include <linux/types.h> + +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) +{ + return __cvdso_getrandom_data(vd, buffer, len, flags, opaque_state, opaque_len); +} diff --git a/tools/arch/powerpc/vdso b/tools/arch/powerpc/vdso new file mode 120000 index 000000000000..d31004bf8f55 --- /dev/null +++ b/tools/arch/powerpc/vdso @@ -0,0 +1 @@ +../../../arch/powerpc/kernel/vdso/ \ No newline at end of file diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index e21e78aae24d..e57dcefa1988 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -14,6 +14,10 @@ ifeq ($(uname_M),x86_64) TEST_GEN_PROGS += vdso_test_getrandom TEST_GEN_PROGS += vdso_test_chacha endif +ifeq ($(ARCH),powerpc) +TEST_GEN_PROGS += vdso_test_getrandom +TEST_GEN_PROGS += vdso_test_chacha +endif

CFLAGS := -std=gnu99

Extend getrandom() vDSO implementation to powerpc64.

Tested on QEMU on both ppc64_defconfig and ppc64le_defconfig.

The results are not precise as it is QEMU on an x86 laptop, but no need to be precise to see the benefit.

~ # ./vdso_test_getrandom bench-single vdso: 25000000 times in 4.977777162 seconds libc: 25000000 times in 75.516749981 seconds syscall: 25000000 times in 86.842242014 seconds

~ # ./vdso_test_getrandom bench-single vdso: 25000000 times in 6.473814156 seconds libc: 25000000 times in 73.875109463 seconds syscall: 25000000 times in 71.805066229 seconds

Signed-off-by: Christophe Leroy christophe.leroy@csgroup.eu --- v3: New (split out of previous patch) --- arch/powerpc/Kconfig | 2 +- arch/powerpc/include/asm/mman.h | 2 +- arch/powerpc/kernel/vdso/Makefile | 10 +- arch/powerpc/kernel/vdso/getrandom.S | 8 ++ arch/powerpc/kernel/vdso/vdso64.lds.S | 1 + arch/powerpc/kernel/vdso/vgetrandom-chacha.S | 98 ++++++++++++++++++++ 6 files changed, 116 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 54b270ef18b1..b45452ac4a73 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -311,7 +311,7 @@ config PPC select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT - select VDSO_GETRANDOM if PPC32 + select VDSO_GETRANDOM # # Please keep this list sorted alphabetically. # diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 17a77d47ed6d..42a51a993d94 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -6,7 +6,7 @@

#include <uapi/asm/mman.h>

-#ifdef CONFIG_PPC64 +#if defined(CONFIG_PPC64) && !defined(BUILD_VDSO)

#include <asm/cputable.h> #include <linux/mm.h> diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index fa0b9b3b51af..56fb1633529a 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -9,6 +9,7 @@ obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o not 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 +obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o

ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y) @@ -21,6 +22,7 @@ endif

ifneq ($(c-getrandom-y),) CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y) + CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y) $(call cc-option, -ffixed-r30) endif

# Build rules @@ -34,10 +36,10 @@ endif 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 +targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o vgetrandom-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 @@ -71,7 +73,7 @@ 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)/vgetrandom-32.o $(obj)/crtsavres-32.o FORCE $(call if_changed,vdso32ld_and_check) -$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE +$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o $(obj)/vgetrandom-64.o FORCE $(call if_changed,vdso64ld_and_check)

# assembly rules for the .S files @@ -87,6 +89,8 @@ $(obj-vdso64): %-64.o: %.S FORCE $(call if_changed_dep,vdso64as) $(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE $(call if_changed_dep,cc_o_c) +$(obj)/vgetrandom-64.o: %-64.o: %.c FORCE + $(call if_changed_dep,cc_o_c)

# Generate VDSO offsets using helper script gen-vdso32sym := $(src)/gen_vdso32_offsets.sh diff --git a/arch/powerpc/kernel/vdso/getrandom.S b/arch/powerpc/kernel/vdso/getrandom.S index 21773ef3fc1d..a957cd2b2b03 100644 --- a/arch/powerpc/kernel/vdso/getrandom.S +++ b/arch/powerpc/kernel/vdso/getrandom.S @@ -27,10 +27,18 @@ .cfi_adjust_cfa_offset PPC_MIN_STKFRM PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF +#ifdef __powerpc64__ + PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT +#endif get_datapage r8 addi r8, r8, VDSO_RNG_DATA_OFFSET bl CFUNC(DOTSYM(\funct)) PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) +#ifdef __powerpc64__ + PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 +#endif cmpwi r3, 0 mtlr r0 addi r1, r1, 2 * PPC_MIN_STKFRM diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index 400819258c06..9481e4b892ed 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -123,6 +123,7 @@ VERSION __kernel_sigtramp_rt64; __kernel_getcpu; __kernel_time; + __kernel_getrandom;

local: *; }; diff --git a/arch/powerpc/kernel/vdso/vgetrandom-chacha.S b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S index a3475b9e8c10..c9d4c5b38242 100644 --- a/arch/powerpc/kernel/vdso/vgetrandom-chacha.S +++ b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S @@ -79,12 +79,59 @@ * r16-r31: state */ SYM_FUNC_START(__arch_chacha20_blocks_nostack) +#ifdef __powerpc64__ + std r5, -216(r1) + + std r14, -144(r1) + std r15, -136(r1) + std r16, -128(r1) + std r17, -120(r1) + std r18, -112(r1) + std r19, -104(r1) + std r20, -96(r1) + std r21, -88(r1) + std r22, -80(r1) + std r23, -72(r1) + std r24, -64(r1) + std r25, -56(r1) + std r26, -48(r1) + std r27, -40(r1) + std r28, -32(r1) + std r29, -24(r1) + std r30, -16(r1) + std r31, -8(r1) +#else stwu r1, -96(r1) stw r5, 20(r1) +#if defined(CONFIG_CPU_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 +#endif li r31, 4 LWZX_LE r14, 0, r5 LWZX_LE r15, r31, r5 +#ifdef __powerpc64__ + rldimi r14, r15, 32, 0 +#endif mr r0, r6

lwz r5, 0(r4) @@ -177,13 +224,22 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) STWX_LE r31, r4, r3 addi r3, r3, 8

+#ifdef __powerpc64__ + addi r14, r14, 1 + srdi r15, r14, 32 +#else addic r14, r14, 1 addze r15, r15 +#endif

subic. r0, r0, 1 /* subi. can't use r0 as source */ bne .Lblock

+#ifdef __powerpc64__ + ld r5, -216(r1) +#else lwz r5, 20(r1) +#endif STWX_LE r14, 0, r5 STWX_LE r15, r4, r5

@@ -195,7 +251,49 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) li r11, 0 li r12, 0

+#ifdef __powerpc64__ + ld r14, -144(r1) + ld r15, -136(r1) + ld r16, -128(r1) + ld r17, -120(r1) + ld r18, -112(r1) + ld r19, -104(r1) + ld r20, -96(r1) + ld r21, -88(r1) + ld r22, -80(r1) + ld r23, -72(r1) + ld r24, -64(r1) + ld r25, -56(r1) + ld r26, -48(r1) + ld r27, -40(r1) + ld r28, -32(r1) + ld r29, -24(r1) + ld r30, -16(r1) + ld r31, -8(r1) +#else +#if defined(CONFIG_CPU_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 blr SYM_FUNC_END(__arch_chacha20_blocks_nostack)