Merge branch 'scv' support into next

From Nick's cover letter:

Linux powerpc new system call instruction and ABI

System Call Vectored (scv) ABI
==============================

The scv instruction is introduced with POWER9 / ISA3, it comes with an
rfscv counter-part. The benefit of these instructions is
performance (trading slower SRR0/1 with faster LR/CTR registers, and
entering the kernel with MSR[EE] and MSR[RI] left enabled, which can
reduce MSR updates. The scv instruction has 128 levels (not enough to
cover the Linux system call space).

Assignment and advertisement
----------------------------
The proposal is to assign scv levels conservatively, and advertise
them with HWCAP feature bits as we add support for more.

Linux has not enabled FSCR[SCV] yet, so executing the scv instruction
will cause the kernel to log a "SCV facility unavilable" message, and
deliver a SIGILL with ILL_ILLOPC to the process. Linux has defined a
HWCAP2 bit PPC_FEATURE2_SCV for SCV support, but does not set it.

This change allocates the zero level ('scv 0'), advertised with
PPC_FEATURE2_SCV, which will be used to provide normal Linux system
calls (equivalent to 'sc').

Attempting to execute scv with other levels will cause a SIGILL to be
delivered the same as before, but will not log a "SCV facility
unavailable" message (because the processor facility is enabled).

Calling convention
------------------
The proposal is for scv 0 to provide the standard Linux system call
ABI with the following differences from sc convention[1]:

- LR is to be volatile across scv calls. This is necessary because the
  scv instruction clobbers LR. From previous discussion, this should
  be possible to deal with in GCC clobbers and CFI.

- cr1 and cr5-cr7 are volatile. This matches the C ABI and would allow
  the kernel system call exit to avoid restoring the volatile cr
  registers (although we probably still would anyway to avoid
  information leaks).

- Error handling: The consensus among kernel, glibc, and musl is to
  move to using negative return values in r3 rather than CR0[SO]=1 to
  indicate error, which matches most other architectures, and is
  closer to a function call.

Notes
-----
- r0,r4-r8 are documented as volatile in the ABI, but the kernel patch
  as submitted currently preserves them. This is to leave room for
  deciding which way to go with these. Some small benefit was found by
  preserving them[1] but I'm not convinced it's worth deviating from
  the C function call ABI just for this. Release code should follow
  the ABI.

Previous discussions:
https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-April/208691.html
https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-April/209268.html

[1] https://github.com/torvalds/linux/blob/master/Documentation/powerpc/syscall64-abi.rst
[2] https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-April/209263.html

19 files changed, 415 insertions, 35 deletions

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index fa9057360e88..de14b1a34d56 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -98,7 +98,7 @@ unsigned long __init early_init(unsigned long dt_ptr);
 void __init machine_init(u64 dt_ptr);
 #endif
 long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs);
-notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs);
+notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs, long scv);
 notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr);
 notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr);
 
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index d7a1a427a690..ebe95aa04d53 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -131,6 +131,12 @@
 	hrfid;								\
 	b	hrfi_flush_fallback
 
+#define RFSCV_TO_USER							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	RFSCV;								\
+	b	rfscv_flush_fallback
+
 #endif /* __ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_EXCEPTION_H */
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index 2dabcf668292..4cb9efa2eb21 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -128,7 +128,7 @@ name:
 	.if ((start) % (size) != 0);				\
 	.error "Fixed section exception vector misalignment";	\
 	.endif;							\
-	.if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100); \
+	.if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100) && ((size) != 0x1000); \
 	.error "Fixed section exception vector bad size";	\
 	.endif;							\
 	.if (start) < sname##_start;				\
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 6b03dff61a05..160f3bb77ea4 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -755,6 +755,8 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
 #define N_SLINE	68
 #define N_SO	100
 
+#define RFSCV	.long 0x4c0000a4
+
 /*
  * Create an endian fixup trampoline
  *
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index ac3970fff0d5..f194339cef3b 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -222,9 +222,14 @@ static inline void set_trap(struct pt_regs *regs, unsigned long val)
 	regs->trap = (regs->trap & TRAP_FLAGS_MASK) | (val & ~TRAP_FLAGS_MASK);
 }
 
+static inline bool trap_is_scv(struct pt_regs *regs)
+{
+	return (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x3000);
+}
+
 static inline bool trap_is_syscall(struct pt_regs *regs)
 {
-	return TRAP(regs) == 0xc00;
+	return (trap_is_scv(regs) || TRAP(regs) == 0xc00);
 }
 
 static inline bool trap_norestart(struct pt_regs *regs)
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 65676e2325b8..9efbddee2bca 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -30,12 +30,12 @@ void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
 
 #ifdef CONFIG_PPC_PSERIES
-extern void pseries_enable_reloc_on_exc(void);
+extern bool pseries_enable_reloc_on_exc(void);
 extern void pseries_disable_reloc_on_exc(void);
 extern void pseries_big_endian_exceptions(void);
 extern void pseries_little_endian_exceptions(void);
 #else
-static inline void pseries_enable_reloc_on_exc(void) {}
+static inline bool pseries_enable_reloc_on_exc(void) { return false; }
 static inline void pseries_disable_reloc_on_exc(void) {}
 static inline void pseries_big_endian_exceptions(void) {}
 static inline void pseries_little_endian_exceptions(void) {}
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index c8e37ef060c1..972ed0df154d 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -40,6 +40,7 @@ enum instruction_type {
 	CACHEOP,
 	BARRIER,
 	SYSCALL,
+	SYSCALL_VECTORED_0,
 	MFMSR,
 	MTMSR,
 	RFI,
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index efdcfa714106..86527d19348c 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -98,7 +98,7 @@ _GLOBAL(__setup_cpu_power10)
 
 _GLOBAL(__setup_cpu_power9)
 	mflr	r11
-	bl	__init_FSCR
+	bl	__init_FSCR_power9
 1:	bl	__init_PMU
 	bl	__init_hvmode_206
 	mtlr	r11
@@ -128,7 +128,7 @@ _GLOBAL(__restore_cpu_power10)
 
 _GLOBAL(__restore_cpu_power9)
 	mflr	r11
-	bl	__init_FSCR
+	bl	__init_FSCR_power9
 1:	bl	__init_PMU
 	mfmsr	r3
 	rldicl.	r0,r3,4,63
@@ -198,6 +198,12 @@ __init_FSCR_power10:
 	mtspr	SPRN_FSCR, r3
 	// fall through
 
+__init_FSCR_power9:
+	mfspr	r3, SPRN_FSCR
+	ori	r3, r3, FSCR_SCV
+	mtspr	SPRN_FSCR, r3
+	// fall through
+
 __init_FSCR:
 	mfspr	r3,SPRN_FSCR
 	ori	r3,r3,FSCR_TAR|FSCR_EBB
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index b4066354f073..3d406a9626e8 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -120,7 +120,8 @@ extern void __restore_cpu_e6500(void);
 #define COMMON_USER2_POWER9	(COMMON_USER2_POWER8 | \
 				 PPC_FEATURE2_ARCH_3_00 | \
 				 PPC_FEATURE2_HAS_IEEE128 | \
-				 PPC_FEATURE2_DARN )
+				 PPC_FEATURE2_DARN | \
+				 PPC_FEATURE2_SCV)
 #define COMMON_USER_POWER10	COMMON_USER_POWER9
 #define COMMON_USER2_POWER10	(COMMON_USER2_POWER9 | \
 				 PPC_FEATURE2_ARCH_3_1 | \
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 0a16bb6fa07d..22ba7fba1147 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -621,6 +621,7 @@ static struct dt_cpu_feature_match __initdata
 	{"little-endian", feat_enable_le, CPU_FTR_REAL_LE},
 	{"smt", feat_enable_smt, 0},
 	{"interrupt-facilities", feat_enable, 0},
+	{"system-call-vectored", feat_enable, 0},
 	{"timer-facilities", feat_enable, 0},
 	{"timer-facilities-v3", feat_enable, 0},
 	{"debug-facilities", feat_enable, 0},
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2547c5dac07a..33a42e42c56f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -64,15 +64,173 @@ exception_marker:
 	.section	".text"
 	.align 7
 
+#ifdef CONFIG_PPC_BOOK3S
+.macro system_call_vectored name trapnr
+	.globl system_call_vectored_\name
+system_call_vectored_\name:
+_ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+	bne	.Ltabort_syscall
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+	INTERRUPT_TO_KERNEL
+	mr	r10,r1
+	ld	r1,PACAKSAVE(r13)
+	std	r10,0(r1)
+	std	r11,_NIP(r1)
+	std	r12,_MSR(r1)
+	std	r0,GPR0(r1)
+	std	r10,GPR1(r1)
+	std	r2,GPR2(r1)
+	ld	r2,PACATOC(r13)
+	mfcr	r12
+	li	r11,0
+	/* Can we avoid saving r3-r8 in common case? */
+	std	r3,GPR3(r1)
+	std	r4,GPR4(r1)
+	std	r5,GPR5(r1)
+	std	r6,GPR6(r1)
+	std	r7,GPR7(r1)
+	std	r8,GPR8(r1)
+	/* Zero r9-r12, this should only be required when restoring all GPRs */
+	std	r11,GPR9(r1)
+	std	r11,GPR10(r1)
+	std	r11,GPR11(r1)
+	std	r11,GPR12(r1)
+	std	r9,GPR13(r1)
+	SAVE_NVGPRS(r1)
+	std	r11,_XER(r1)
+	std	r11,_LINK(r1)
+	std	r11,_CTR(r1)
+
+	li	r11,\trapnr
+	std	r11,_TRAP(r1)
+	std	r12,_CCR(r1)
+	std	r3,ORIG_GPR3(r1)
+	addi	r10,r1,STACK_FRAME_OVERHEAD
+	ld	r11,exception_marker@toc(r2)
+	std	r11,-16(r10)		/* "regshere" marker */
+
+	/*
+	 * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
+	 * would clobber syscall parameters. Also we always enter with IRQs
+	 * enabled and nothing pending. system_call_exception() will call
+	 * trace_hardirqs_off().
+	 *
+	 * scv enters with MSR[EE]=1, so don't set PACA_IRQ_HARD_DIS. The
+	 * entry vector already sets PACAIRQSOFTMASK to IRQS_ALL_DISABLED.
+	 */
+
+	/* Calling convention has r9 = orig r0, r10 = regs */
+	mr	r9,r0
+	bl	system_call_exception
+
+.Lsyscall_vectored_\name\()_exit:
+	addi    r4,r1,STACK_FRAME_OVERHEAD
+	li	r5,1 /* scv */
+	bl	syscall_exit_prepare
+
+	ld	r2,_CCR(r1)
+	ld	r4,_NIP(r1)
+	ld	r5,_MSR(r1)
+
+BEGIN_FTR_SECTION
+	stdcx.	r0,0,r1			/* to clear the reservation */
+END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+BEGIN_FTR_SECTION
+	HMT_MEDIUM_LOW
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+	cmpdi	r3,0
+	bne	.Lsyscall_vectored_\name\()_restore_regs
+
+	/* rfscv returns with LR->NIA and CTR->MSR */
+	mtlr	r4
+	mtctr	r5
+
+	/* Could zero these as per ABI, but we may consider a stricter ABI
+	 * which preserves these if libc implementations can benefit, so
+	 * restore them for now until further measurement is done. */
+	ld	r0,GPR0(r1)
+	ld	r4,GPR4(r1)
+	ld	r5,GPR5(r1)
+	ld	r6,GPR6(r1)
+	ld	r7,GPR7(r1)
+	ld	r8,GPR8(r1)
+	/* Zero volatile regs that may contain sensitive kernel data */
+	li	r9,0
+	li	r10,0
+	li	r11,0
+	li	r12,0
+	mtspr	SPRN_XER,r0
+
+	/*
+	 * We don't need to restore AMR on the way back to userspace for KUAP.
+	 * The value of AMR only matters while we're in the kernel.
+	 */
+	mtcr	r2
+	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r13,GPR13(r1)
+	ld	r1,GPR1(r1)
+	RFSCV_TO_USER
+	b	.	/* prevent speculative execution */
+
+.Lsyscall_vectored_\name\()_restore_regs:
+	li	r3,0
+	mtmsrd	r3,1
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r5
+
+	ld	r3,_CTR(r1)
+	ld	r4,_LINK(r1)
+	ld	r5,_XER(r1)
+
+	REST_NVGPRS(r1)
+	ld	r0,GPR0(r1)
+	mtcr	r2
+	mtctr	r3
+	mtlr	r4
+	mtspr	SPRN_XER,r5
+	REST_10GPRS(2, r1)
+	REST_2GPRS(12, r1)
+	ld	r1,GPR1(r1)
+	RFI_TO_USER
+.endm
+
+system_call_vectored common 0x3000
+/*
+ * We instantiate another entry copy for the SIGILL variant, with TRAP=0x7ff0
+ * which is tested by system_call_exception when r0 is -1 (as set by vector
+ * entry code).
+ */
+system_call_vectored sigill 0x7ff0
+
+
+/*
+ * Entered via kernel return set up by kernel/sstep.c, must match entry regs
+ */
+	.globl system_call_vectored_emulate
+system_call_vectored_emulate:
+_ASM_NOKPROBE_SYMBOL(system_call_vectored_emulate)
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+	b	system_call_vectored_common
+#endif
+
+	.balign IFETCH_ALIGN_BYTES
 	.globl system_call_common
 system_call_common:
+_ASM_NOKPROBE_SYMBOL(system_call_common)
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
 	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
 	bne	.Ltabort_syscall
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
-_ASM_NOKPROBE_SYMBOL(system_call_common)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
@@ -138,6 +296,7 @@ END_BTB_FLUSH_SECTION
 
 .Lsyscall_exit:
 	addi    r4,r1,STACK_FRAME_OVERHEAD
+	li	r5,0 /* !scv */
 	bl	syscall_exit_prepare
 
 	ld	r2,_CCR(r1)
@@ -224,10 +383,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	b	.	/* prevent speculative execution */
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S
+_GLOBAL(ret_from_fork_scv)
+	bl	schedule_tail
+	REST_NVGPRS(r1)
+	li	r3,0	/* fork() return value */
+	b	.Lsyscall_vectored_common_exit
+#endif
+
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
 	REST_NVGPRS(r1)
-	li	r3,0
+	li	r3,0	/* fork() return value */
 	b	.Lsyscall_exit
 
 _GLOBAL(ret_from_kernel_thread)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0fc8bad878b2..eda5ceef2381 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -508,8 +508,24 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 
 .macro __GEN_COMMON_BODY name
 	.if IMASK
+		.if ! ISTACK
+		.error "No support for masked interrupt to use custom stack"
+		.endif
+
+		/* If coming from user, skip soft-mask tests. */
+		andi.	r10,r12,MSR_PR
+		bne	2f
+
+		/* Kernel code running below __end_interrupts is implicitly
+		 * soft-masked */
+		LOAD_HANDLER(r10, __end_interrupts)
+		cmpld	r11,r10
+		li	r10,IMASK
+		blt-	1f
+
+		/* Test the soft mask state against our interrupt's bit */
 		lbz	r10,PACAIRQSOFTMASK(r13)
-		andi.	r10,r10,IMASK
+1:		andi.	r10,r10,IMASK
 		/* Associate vector numbers with bits in paca->irq_happened */
 		.if IVEC == 0x500 || IVEC == 0xea0
 		li	r10,PACA_IRQ_EE
@@ -540,7 +556,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 
 	.if ISTACK
 	andi.	r10,r12,MSR_PR		/* See if coming from user	*/
-	mr	r10,r1			/* Save r1			*/
+2:	mr	r10,r1			/* Save r1			*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc frame on kernel stack	*/
 	beq-	100f
 	ld	r1,PACAKSAVE(r13)	/* kernel stack to use		*/
@@ -740,6 +756,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
  * guarantee they will be delivered virtually. Some conditions (see the ISA)
  * cause exceptions to be delivered in real mode.
  *
+ * The scv instructions are a special case. They get a 0x3000 offset applied.
+ * scv exceptions have unique reentrancy properties, see below.
+ *
  * It's impossible to receive interrupts below 0x300 via AIL.
  *
  * KVM: None of the virtual exceptions are from the guest. Anything that
@@ -749,8 +768,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
  * We layout physical memory as follows:
  * 0x0000 - 0x00ff : Secondary processor spin code
  * 0x0100 - 0x18ff : Real mode pSeries interrupt vectors
- * 0x1900 - 0x3fff : Real mode trampolines
- * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
+ * 0x1900 - 0x2fff : Real mode trampolines
+ * 0x3000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
  * 0x5900 - 0x6fff : Relon mode trampolines
  * 0x7000 - 0x7fff : FWNMI data area
  * 0x8000 -   .... : Common interrupt handlers, remaining early
@@ -761,8 +780,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
  * vectors there.
  */
 OPEN_FIXED_SECTION(real_vectors,        0x0100, 0x1900)
-OPEN_FIXED_SECTION(real_trampolines,    0x1900, 0x4000)
-OPEN_FIXED_SECTION(virt_vectors,        0x4000, 0x5900)
+OPEN_FIXED_SECTION(real_trampolines,    0x1900, 0x3000)
+OPEN_FIXED_SECTION(virt_vectors,        0x3000, 0x5900)
 OPEN_FIXED_SECTION(virt_trampolines,    0x5900, 0x7000)
 
 #ifdef CONFIG_PPC_POWERNV
@@ -798,6 +817,77 @@ USE_FIXED_SECTION(real_vectors)
 	.globl __start_interrupts
 __start_interrupts:
 
+/**
+ * Interrupt 0x3000 - System Call Vectored Interrupt (syscall).
+ * This is a synchronous interrupt invoked with the "scv" instruction. The
+ * system call does not alter the HV bit, so it is directed to the OS.
+ *
+ * Handling:
+ * scv instructions enter the kernel without changing EE, RI, ME, or HV.
+ * In particular, this means we can take a maskable interrupt at any point
+ * in the scv handler, which is unlike any other interrupt. This is solved
+ * by treating the instruction addresses below __end_interrupts as being
+ * soft-masked.
+ *
+ * AIL-0 mode scv exceptions go to 0x17000-0x17fff, but we set AIL-3 and
+ * ensure scv is never executed with relocation off, which means AIL-0
+ * should never happen.
+ *
+ * Before leaving the below __end_interrupts text, at least of the following
+ * must be true:
+ * - MSR[PR]=1 (i.e., return to userspace)
+ * - MSR_EE|MSR_RI is set (no reentrant exceptions)
+ * - Standard kernel environment is set up (stack, paca, etc)
+ *
+ * Call convention:
+ *
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ */
+EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
+	/* SCV 0 */
+	mr	r9,r13
+	GET_PACA(r13)
+	mflr	r11
+	mfctr	r12
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+#ifdef CONFIG_RELOCATABLE
+	b	system_call_vectored_tramp
+#else
+	b	system_call_vectored_common
+#endif
+	nop
+
+	/* SCV 1 - 127 */
+	.rept	127
+	mr	r9,r13
+	GET_PACA(r13)
+	mflr	r11
+	mfctr	r12
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+	li	r0,-1 /* cause failure */
+#ifdef CONFIG_RELOCATABLE
+	b	system_call_vectored_sigill_tramp
+#else
+	b	system_call_vectored_sigill
+#endif
+	.endr
+EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
+
+#ifdef CONFIG_RELOCATABLE
+TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
+	__LOAD_HANDLER(r10, system_call_vectored_common)
+	mtctr	r10
+	bctr
+
+TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp)
+	__LOAD_HANDLER(r10, system_call_vectored_sigill)
+	mtctr	r10
+	bctr
+#endif
+
+
 /* No virt vectors corresponding with 0x0..0x100 */
 EXC_VIRT_NONE(0x4000, 0x100)
 
@@ -2838,7 +2928,8 @@ masked_interrupt:
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
-	/* returns to kernel where r13 must be set up, so don't restore it */
+	ld	r13,PACA_EXGEN+EX_R13(r13)
+	/* May return to masked low address where r13 is not set up */
 	.if \hsrr
 	HRFI_TO_KERNEL
 	.else
@@ -2946,6 +3037,47 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback)
 	GET_SCRATCH0(r13);
 	hrfid
 
+TRAMP_REAL_BEGIN(rfscv_flush_fallback)
+	/* system call volatile */
+	mr	r7,r13
+	GET_PACA(r13);
+	mr	r8,r1
+	ld	r1,PACAKSAVE(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
+	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+	mtctr	r11
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+1:
+	ld	r11,(0x80 + 8)*0(r10)
+	ld	r11,(0x80 + 8)*1(r10)
+	ld	r11,(0x80 + 8)*2(r10)
+	ld	r11,(0x80 + 8)*3(r10)
+	ld	r11,(0x80 + 8)*4(r10)
+	ld	r11,(0x80 + 8)*5(r10)
+	ld	r11,(0x80 + 8)*6(r10)
+	ld	r11,(0x80 + 8)*7(r10)
+	addi	r10,r10,0x80*8
+	bdnz	1b
+
+	mtctr	r9
+	li	r9,0
+	li	r10,0
+	li	r11,0
+	mr	r1,r8
+	mr	r13,r7
+	RFSCV
+
 USE_TEXT_SECTION()
 	MASKED_INTERRUPT
 	MASKED_INTERRUPT hsrr=1
@@ -2997,6 +3129,10 @@ EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline)
 
 USE_FIXED_SECTION(virt_trampolines)
 	/*
+	 * All code below __end_interrupts is treated as soft-masked. If
+	 * any code runs here with MSR[EE]=1, it must then cope with pending
+	 * soft interrupt being raised (i.e., by ensuring it is replayed).
+	 *
 	 * The __end_interrupts marker must be past the out-of-line (OOL)
 	 * handlers, so that they are copied to real address 0x100 when running
 	 * a relocatable kernel. This ensures they can be reached from the short
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9be4759f3bbb..e4fcc817c46c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1618,6 +1618,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
 {
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
+	extern void ret_from_fork_scv(void);
 	extern void ret_from_kernel_thread(void);
 	void (*f)(void);
 	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
@@ -1654,7 +1655,9 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
 		if (usp)
 			childregs->gpr[1] = usp;
 		p->thread.regs = childregs;
-		childregs->gpr[3] = 0;  /* Result from fork() */
+		/* 64s sets this in ret_from_fork */
+		if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+			childregs->gpr[3] = 0;  /* Result from fork() */
 		if (clone_flags & CLONE_SETTLS) {
 			if (!is_32bit_task())
 				childregs->gpr[13] = tls;
@@ -1662,7 +1665,10 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
 				childregs->gpr[2] = tls;
 		}
 
-		f = ret_from_fork;
+		if (trap_is_scv(regs))
+			f = ret_from_fork_scv;
+		else
+			f = ret_from_fork;
 	}
 	childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
 	sp -= STACK_FRAME_OVERHEAD;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0ba1ed77dc68..6be430107c6f 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -196,7 +196,10 @@ static void __init configure_exceptions(void)
 	/* Under a PAPR hypervisor, we need hypercalls */
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		/* Enable AIL if possible */
-		pseries_enable_reloc_on_exc();
+		if (!pseries_enable_reloc_on_exc()) {
+			init_task.thread.fscr &= ~FSCR_SCV;
+			cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
+		}
 
 		/*
 		 * Tell the hypervisor that we want our exceptions to
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index b4143b6ff093..d15a98c758b8 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -205,8 +205,14 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
 		return;
 
 	/* error signalled ? */
-	if (!(regs->ccr & 0x10000000))
+	if (trap_is_scv(regs)) {
+		/* 32-bit compat mode sign extend? */
+		if (!IS_ERR_VALUE(ret))
+			return;
+		ret = -ret;
+	} else if (!(regs->ccr & 0x10000000)) {
 		return;
+	}
 
 	switch (ret) {
 	case ERESTART_RESTARTBLOCK:
@@ -239,9 +245,14 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
 		regs->nip -= 4;
 		regs->result = 0;
 	} else {
-		regs->result = -EINTR;
-		regs->gpr[3] = EINTR;
-		regs->ccr |= 0x10000000;
+		if (trap_is_scv(regs)) {
+			regs->result = -EINTR;
+			regs->gpr[3] = -EINTR;
+		} else {
+			regs->result = -EINTR;
+			regs->gpr[3] = EINTR;
+			regs->ccr |= 0x10000000;
+		}
 	}
 }
 
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 5126f1d3184a..8e50818aa50b 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -60,6 +60,11 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	local_irq_enable();
 
 	if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {
+		if (unlikely(regs->trap == 0x7ff0)) {
+			/* Unsupported scv vector */
+			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+			return regs->gpr[3];
+		}
 		/*
 		 * We use the return value of do_syscall_trace_enter() as the
 		 * syscall number. If the syscall was rejected for any reason
@@ -78,6 +83,11 @@ notrace long system_call_exception(long r3, long r4, long r5,
 		r8 = regs->gpr[8];
 
 	} else if (unlikely(r0 >= NR_syscalls)) {
+		if (unlikely(regs->trap == 0x7ff0)) {
+			/* Unsupported scv vector */
+			_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+			return regs->gpr[3];
+		}
 		return -ENOSYS;
 	}
 
@@ -105,16 +115,20 @@ notrace long system_call_exception(long r3, long r4, long r5,
  * local irqs must be disabled. Returns false if the caller must re-enable
  * them, check for new work, and try again.
  */
-static notrace inline bool prep_irq_for_enabled_exit(void)
+static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri)
 {
 	/* This must be done with RI=1 because tracing may touch vmaps */
 	trace_hardirqs_on();
 
 	/* This pattern matches prep_irq_for_idle */
-	__hard_EE_RI_disable();
+	if (clear_ri)
+		__hard_EE_RI_disable();
+	else
+		__hard_irq_disable();
 	if (unlikely(lazy_irq_pending_nocheck())) {
 		/* Took an interrupt, may have more exit work to do. */
-		__hard_RI_enable();
+		if (clear_ri)
+			__hard_RI_enable();
 		trace_hardirqs_off();
 		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 
@@ -136,7 +150,8 @@ static notrace inline bool prep_irq_for_enabled_exit(void)
  * because RI=0 and soft mask state is "unreconciled", so it is marked notrace.
  */
 notrace unsigned long syscall_exit_prepare(unsigned long r3,
-					   struct pt_regs *regs)
+					   struct pt_regs *regs,
+					   long scv)
 {
 	unsigned long *ti_flagsp = &current_thread_info()->flags;
 	unsigned long ti_flags;
@@ -151,7 +166,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 
 	ti_flags = *ti_flagsp;
 
-	if (unlikely(r3 >= (unsigned long)-MAX_ERRNO)) {
+	if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && !scv) {
 		if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
 			r3 = -r3;
 			regs->ccr |= 0x10000000; /* Set SO bit in CR */
@@ -218,7 +233,8 @@ again:
 		}
 	}
 
-	if (unlikely(!prep_irq_for_enabled_exit())) {
+	/* scv need not set RI=0 because SRRs are not used */
+	if (unlikely(!prep_irq_for_enabled_exit(!scv))) {
 		local_irq_enable();
 		goto again;
 	}
@@ -290,7 +306,7 @@ again:
 		}
 	}
 
-	if (unlikely(!prep_irq_for_enabled_exit())) {
+	if (unlikely(!prep_irq_for_enabled_exit(true))) {
 		local_irq_enable();
 		local_irq_disable();
 		goto again;
@@ -353,7 +369,7 @@ again:
 			}
 		}
 
-		if (unlikely(!prep_irq_for_enabled_exit())) {
+		if (unlikely(!prep_irq_for_enabled_exit(true))) {
 			/*
 			 * Can't local_irq_restore to replay if we were in
 			 * interrupt context. Must replay directly.
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index fb4c5767663d..4194119eff82 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -16,6 +16,7 @@
 #include <asm/disassemble.h>
 
 extern char system_call_common[];
+extern char system_call_vectored_emulate[];
 
 #ifdef CONFIG_PPC64
 /* Bits in SRR1 that are copied from MSR */
@@ -1236,6 +1237,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 	case 17:	/* sc */
 		if ((word & 0xfe2) == 2)
 			op->type = SYSCALL;
+		else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) &&
+				(word & 0xfe3) == 1)
+			op->type = SYSCALL_VECTORED_0;
 		else
 			op->type = UNKNOWN;
 		return 0;
@@ -3378,6 +3382,18 @@ int emulate_step(struct pt_regs *regs, struct ppc_inst instr)
 		regs->msr = MSR_KERNEL;
 		return 1;
 
+#ifdef CONFIG_PPC64_BOOK3S
+	case SYSCALL_VECTORED_0:	/* scv 0 */
+		regs->gpr[9] = regs->gpr[13];
+		regs->gpr[10] = MSR_KERNEL;
+		regs->gpr[11] = regs->nip + 4;
+		regs->gpr[12] = regs->msr & MSR_MASK;
+		regs->gpr[13] = (unsigned long) get_paca();
+		regs->nip = (unsigned long) &system_call_vectored_emulate;
+		regs->msr = MSR_KERNEL;
+		return 1;
+#endif
+
 	case RFI:
 		return -1;
 #endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2db8469e475f..8c85466e0dd8 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -358,7 +358,7 @@ static void pseries_lpar_idle(void)
  * to ever be a problem in practice we can move this into a kernel thread to
  * finish off the process later in boot.
  */
-void pseries_enable_reloc_on_exc(void)
+bool pseries_enable_reloc_on_exc(void)
 {
 	long rc;
 	unsigned int delay, total_delay = 0;
@@ -369,11 +369,13 @@ void pseries_enable_reloc_on_exc(void)
 			if (rc == H_P2) {
 				pr_info("Relocation on exceptions not"
 					" supported\n");
+				return false;
 			} else if (rc != H_SUCCESS) {
 				pr_warn("Unable to enable relocation"
 					" on exceptions: %ld\n", rc);
+				return false;
 			}
-			break;
+			return true;
 		}
 
 		delay = get_longbusy_msecs(rc);
@@ -382,7 +384,7 @@ void pseries_enable_reloc_on_exc(void)
 			pr_warn("Warning: Giving up waiting to enable "
 				"relocation on exceptions (%u msec)!\n",
 				total_delay);
-			return;
+			return false;
 		}
 
 		mdelay(delay);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 1a240b4b76f9..8fb1f857c11c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1600,6 +1600,7 @@ const char *getvecname(unsigned long vec)
 	case 0x1300:	ret = "(Instruction Breakpoint)"; break;
 	case 0x1500:	ret = "(Denormalisation)"; break;
 	case 0x1700:	ret = "(Altivec Assist)"; break;
+	case 0x3000:	ret = "(System Call Vectored)"; break;
 	default: ret = "";
 	}
 	return ret;