Merge tag 'random-6.12-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random

Pull random number generator updates from Jason Donenfeld:
 "Originally I'd planned on sending each of the vDSO getrandom()
  architecture ports to their respective arch trees. But as we started
  to work on this, we found lots of interesting issues in the shared
  code and infrastructure, the fixes for which the various archs needed
  to base their work.

  So in the end, this turned into a nice collaborative effort fixing up
  issues and porting to 5 new architectures -- arm64, powerpc64,
  powerpc32, s390x, and loongarch64 -- with everybody pitching in and
  commenting on each other's code. It was a fun development cycle.

  This contains:

   - Numerous fixups to the vDSO selftest infrastructure, getting it
     running successfully on more platforms, and fixing bugs in it.

   - Additions to the vDSO getrandom & chacha selftests. Basically every
     time manual review unearthed a bug in a revision of an arch patch,
     or an ambiguity, the tests were augmented.

     By the time the last arch was submitted for review, s390x, v1 of
     the series was essentially fine right out of the gate.

   - Fixes to the the generic C implementation of vDSO getrandom, to
     build and run successfully on all archs, decoupling it from
     assumptions we had (unintentionally) made on x86_64 that didn't
     carry through to the other architectures.

   - Port of vDSO getrandom to LoongArch64, from Xi Ruoyao and acked by
     Huacai Chen.

   - Port of vDSO getrandom to ARM64, from Adhemerval Zanella and acked
     by Will Deacon.

   - Port of vDSO getrandom to PowerPC, in both 32-bit and 64-bit
     varieties, from Christophe Leroy and acked by Michael Ellerman.

   - Port of vDSO getrandom to S390X from Heiko Carstens, the arch
     maintainer.

  While it'd be natural for there to be things to fix up over the course
  of the development cycle, these patches got a decent amount of review
  from a fairly diverse crew of folks on the mailing lists, and, for the
  most part, they've been cooking in linux-next, which has been helpful
  for ironing out build issues.

  In terms of architectures, I think that mostly takes care of the
  important 64-bit archs with hardware still being produced and running
  production loads in settings where vDSO getrandom is likely to help.

  Arguably there's still RISC-V left, and we'll see for 6.13 whether
  they find it useful and submit a port"

* tag 'random-6.12-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random: (47 commits)
  selftests: vDSO: check cpu caps before running chacha test
  s390/vdso: Wire up getrandom() vdso implementation
  s390/vdso: Move vdso symbol handling to separate header file
  s390/vdso: Allow alternatives in vdso code
  s390/module: Provide find_section() helper
  s390/facility: Let test_facility() generate static branch if possible
  s390/alternatives: Remove ALT_FACILITY_EARLY
  s390/facility: Disable compile time optimization for decompressor code
  selftests: vDSO: fix vdso_config for s390
  selftests: vDSO: fix ELF hash table entry size for s390x
  powerpc/vdso: Wire up getrandom() vDSO implementation on VDSO64
  powerpc/vdso: Wire up getrandom() vDSO implementation on VDSO32
  powerpc/vdso: Refactor CFLAGS for CVDSO build
  powerpc/vdso32: Add crtsavres
  mm: Define VM_DROPPABLE for powerpc/32
  powerpc/vdso: Fix VDSO data access when running in a non-root time namespace
  selftests: vDSO: don't include generated headers for chacha test
  arm64: vDSO: Wire up getrandom() vDSO implementation
  arm64: alternative: make alternative_has_cap_likely() VDSO compatible
  selftests: vDSO: also test counter in vdso_test_chacha
  ...

9 files changed, 475 insertions, 40 deletions

diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 1425b6edc66b..56fb1633529a 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -8,30 +8,21 @@ 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
+obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o
+
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y)
-  CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
-  CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector)
-  CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING
-  CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables
-  CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE)
-  CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
-  # This flag is supported by clang for 64-bit but not 32-bit so it will cause
-  # an unused command line flag warning for this file.
-  ifdef CONFIG_CC_IS_CLANG
-  CFLAGS_REMOVE_vgettimeofday-32.o += -fno-stack-clash-protection
-  endif
-  CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y)
-  CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
-  CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector)
-  CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING
-  CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables
-  CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE)
 # Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
 # by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
 # compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
 # generation is minimal, it will just use r29 instead.
-  CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30)
+  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)
+  CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y) $(call cc-option, -ffixed-r30)
 endif
 
 # Build rules
@@ -42,12 +33,18 @@ 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
+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
+ccflags-y += -ffreestanding -fasynchronous-unwind-tables
+ccflags-remove-y := $(CC_FLAGS_FTRACE)
 ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS)
 ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld)
 ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
@@ -56,6 +53,12 @@ ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WAR
 ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CFLAGS))
 
 CC32FLAGS := -m32
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
+  # This flag is supported by clang for 64-bit but not 32-bit so it will cause
+  # an unused command line flag warning for this file.
+ifdef CONFIG_CC_IS_CLANG
+CC32FLAGSREMOVE += -fno-stack-clash-protection
+endif
 LD32FLAGS := -Wl,-soname=linux-vdso32.so.1
 AS32FLAGS := -D__VDSO32__
 
@@ -68,20 +71,26 @@ 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)/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
 $(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)/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
 	$(call if_changed_dep,cc_o_c)
+$(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
@@ -102,7 +111,7 @@ quiet_cmd_vdso32ld_and_check = VDSO32L $@
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $<
 quiet_cmd_vdso32cc = VDSO32C $@
-      cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
+      cmd_vdso32cc = $(VDSOCC) $(filter-out $(CC32FLAGSREMOVE), $(c_flags)) $(CC32FLAGS) -c -o $@ $<
 
 quiet_cmd_vdso64ld_and_check = VDSO64L $@
       cmd_vdso64ld_and_check = $(VDSOCC) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
index 0085ae464dac..3b2479bd2f9a 100644
--- a/arch/powerpc/kernel/vdso/cacheflush.S
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 #ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r10
+	get_realdatapage	r10, r11
 	mtlr	r12
   .cfi_restore	lr
 #endif
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
index db8e167f0166..2b19b6201a33 100644
--- a/arch/powerpc/kernel/vdso/datapage.S
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	mflr	r12
   .cfi_register lr,r12
 	mr.	r4,r3
-	get_datapage	r3
+	get_realdatapage	r3, r11
 	mtlr	r12
 #ifdef __powerpc64__
 	addi	r3,r3,CFG_SYSCALL_MAP64
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r3
+	get_realdatapage	r3, r11
 #ifndef __powerpc64__
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 #endif
diff --git a/arch/powerpc/kernel/vdso/getrandom.S b/arch/powerpc/kernel/vdso/getrandom.S
new file mode 100644
index 000000000000..f3bbf931931c
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/getrandom.S
@@ -0,0 +1,58 @@
+/* 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
+#ifdef __powerpc64__
+	PPC_STL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
+#endif
+	get_realdatapage	r8, r11
+	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
+  .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/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
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/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
new file mode 100644
index 000000000000..7f9061a9e8b4
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S
@@ -0,0 +1,365 @@
+/* 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__
+	std	counter, -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	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
+#endif	/* __powerpc64__ */
+
+	lwz	counter0, 0(counter)
+	lwz	counter1, 4(counter)
+#ifdef __powerpc64__
+	rldimi	counter0, counter1, 32, 0
+#endif
+	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 */
+
+#ifdef __powerpc64__
+	addi	counter0, counter0, 1
+	srdi	counter1, counter0, 32
+#else
+	addic	counter0, counter0, 1
+	addze	counter1, counter1
+#endif
+
+	bne	.Lblock
+
+#ifdef __powerpc64__
+	ld	counter, -216(r1)
+#else
+	lwz	counter, 20(r1)
+#endif
+	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 __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
+#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)
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);
+}