powerpc/64s: avoid reloading (H)SRR registers if they are still valid

When an interrupt is taken, the SRR registers are set to return to where
it left off. Unless they are modified in the meantime, or the return
address or MSR are modified, there is no need to reload these registers
when returning from interrupt.

Introduce per-CPU flags that track the validity of SRR and HSRR
registers. These are cleared when returning from interrupt, when
using the registers for something else (e.g., OPAL calls), when
adjusting the return address or MSR of a context, and when context
switching (which changes the return address and MSR).

This improves the performance of interrupt returns.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fold in fixup patch from Nick]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210617155116.2167984-5-npiggin@gmail.com

arch/powerpc/Kconfig.debug

@@ -85,6 +85,10 @@ config MSI_BITMAP_SELFTEST
 config PPC_IRQ_SOFT_MASK_DEBUG
 	bool "Include extra checks for powerpc irq soft masking"
 
+config PPC_RFI_SRR_DEBUG
+	bool "Include extra checks for RFI SRR register validity"
+	depends on PPC_BOOK3S_64
+
 config XMON
 	bool "Include xmon kernel debugger"
 	depends on DEBUG_KERNEL

arch/powerpc/include/asm/hw_irq.h

@@ -389,7 +389,15 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 	return !(regs->msr & MSR_EE);
 }
 
-static inline void may_hard_irq_enable(void) { }
+static inline bool may_hard_irq_enable(void)
+{
+	return false;
+}
+
+static inline void do_hard_irq_enable(void)
+{
+	BUILD_BUG();
+}
 
 static inline void irq_soft_mask_regs_set_state(struct pt_regs *regs, unsigned long val)
 {

arch/powerpc/include/asm/interrupt.h

@@ -73,13 +73,25 @@
 #include <asm/kprobes.h>
 #include <asm/runlatch.h>
 
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void srr_regs_clobbered(void)
+{
+	local_paca->srr_valid = 0;
+	local_paca->hsrr_valid = 0;
+}
+#else
+static inline void srr_regs_clobbered(void)
+{
+}
+#endif
+
 static inline void nap_adjust_return(struct pt_regs *regs)
 {
 #ifdef CONFIG_PPC_970_NAP
 	if (unlikely(test_thread_local_flags(_TLF_NAPPING))) {
 		/* Can avoid a test-and-clear because NMIs do not call this */
 		clear_thread_local_flags(_TLF_NAPPING);
-		regs->nip = (unsigned long)power4_idle_nap_return;
+		regs_set_return_ip(regs, (unsigned long)power4_idle_nap_return);
 	}
 #endif
 }

arch/powerpc/include/asm/livepatch.h

@@ -16,7 +16,7 @@ static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
 {
 	struct pt_regs *regs = ftrace_get_regs(fregs);
 
-	regs->nip = ip;
+	regs_set_return_ip(regs, ip);
 }
 
 #define klp_get_ftrace_location klp_get_ftrace_location

arch/powerpc/include/asm/paca.h

@@ -167,6 +167,10 @@ struct paca_struct {
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
 #ifdef CONFIG_PPC_BOOK3E
 	u16 trap_save;			/* Used when bad stack is encountered */
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	u8 hsrr_valid;			/* HSRRs set for HRFID */
+	u8 srr_valid;			/* SRRs set for RFID */
 #endif
 	u8 irq_soft_mask;		/* mask for irq soft masking */
 	u8 irq_happened;		/* irq happened while soft-disabled */

arch/powerpc/include/asm/probes.h

@@ -34,14 +34,14 @@ typedef u32 ppc_opcode_t;
 /* Enable single stepping for the current task */
 static inline void enable_single_step(struct pt_regs *regs)
 {
-	regs->msr |= MSR_SINGLESTEP;
+	regs_set_return_msr(regs, regs->msr | MSR_SINGLESTEP);
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/*
 	 * We turn off Critical Input Exception(CE) to ensure that the single
 	 * step will be for the instruction we have the probe on; if we don't,
 	 * it is possible we'd get the single step reported for CE.
 	 */
-	regs->msr &= ~MSR_CE;
+	regs_set_return_msr(regs, regs->msr & ~MSR_CE);
 	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
 #ifdef CONFIG_PPC_47x
 	isync();

arch/powerpc/include/asm/ptrace.h

@@ -123,6 +123,47 @@ struct pt_regs
 #endif /* __powerpc64__ */
 
 #ifndef __ASSEMBLY__
+#include <asm/paca.h>
+
+#ifdef CONFIG_SMP
+extern unsigned long profile_pc(struct pt_regs *regs);
+#else
+#define profile_pc(regs) instruction_pointer(regs)
+#endif
+
+long do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_leave(struct pt_regs *regs);
+
+static inline void regs_set_return_ip(struct pt_regs *regs, unsigned long ip)
+{
+	regs->nip = ip;
+#ifdef CONFIG_PPC_BOOK3S_64
+	local_paca->hsrr_valid = 0;
+	local_paca->srr_valid = 0;
+#endif
+}
+
+static inline void regs_set_return_msr(struct pt_regs *regs, unsigned long msr)
+{
+	regs->msr = msr;
+#ifdef CONFIG_PPC_BOOK3S_64
+	local_paca->hsrr_valid = 0;
+	local_paca->srr_valid = 0;
+#endif
+}
+
+static inline void set_return_regs_changed(void)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	local_paca->hsrr_valid = 0;
+	local_paca->srr_valid = 0;
+#endif
+}
+
+static inline void regs_add_return_ip(struct pt_regs *regs, long offset)
+{
+	regs_set_return_ip(regs, regs->nip + offset);
+}
 
 static inline unsigned long instruction_pointer(struct pt_regs *regs)
 {
@@ -132,7 +173,7 @@ static inline unsigned long instruction_pointer(struct pt_regs *regs)
 static inline void instruction_pointer_set(struct pt_regs *regs,
 		unsigned long val)
 {
-	regs->nip = val;
+	regs_set_return_ip(regs, val);
 }
 
 static inline unsigned long user_stack_pointer(struct pt_regs *regs)
@@ -145,15 +186,6 @@ static inline unsigned long frame_pointer(struct pt_regs *regs)
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
-
-long do_syscall_trace_enter(struct pt_regs *regs);
-void do_syscall_trace_leave(struct pt_regs *regs);
-
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else

arch/powerpc/kernel/asm-offsets.c

@@ -190,6 +190,10 @@ int main(void)
 	OFFSET(PACATOC, paca_struct, kernel_toc);
 	OFFSET(PACAKBASE, paca_struct, kernelbase);
 	OFFSET(PACAKMSR, paca_struct, kernel_msr);
+#ifdef CONFIG_PPC_BOOK3S_64
+	OFFSET(PACAHSRR_VALID, paca_struct, hsrr_valid);
+	OFFSET(PACASRR_VALID, paca_struct, srr_valid);
+#endif
 	OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask);
 	OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened);
 	OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled);

arch/powerpc/kernel/entry_64.S

@@ -64,6 +64,30 @@ exception_marker:
 	.section	".text"
 	.align 7
 
+.macro DEBUG_SRR_VALID srr
+#ifdef CONFIG_PPC_RFI_SRR_DEBUG
+	.ifc \srr,srr
+	mfspr	r11,SPRN_SRR0
+	ld	r12,_NIP(r1)
+100:	tdne	r11,r12
+	EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+	mfspr	r11,SPRN_SRR1
+	ld	r12,_MSR(r1)
+100:	tdne	r11,r12
+	EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+	.else
+	mfspr	r11,SPRN_HSRR0
+	ld	r12,_NIP(r1)
+100:	tdne	r11,r12
+	EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+	mfspr	r11,SPRN_HSRR1
+	ld	r12,_MSR(r1)
+100:	tdne	r11,r12
+	EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+	.endif
+#endif
+.endm
+
 #ifdef CONFIG_PPC_BOOK3S
 .macro system_call_vectored name trapnr
 	.globl system_call_vectored_\name
@@ -286,6 +310,11 @@ END_BTB_FLUSH_SECTION
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r10)		/* "regshere" marker */
 
+#ifdef CONFIG_PPC_BOOK3S
+	li	r11,1
+	stb	r11,PACASRR_VALID(r13)
+#endif
+
 	/*
 	 * We always enter kernel from userspace with irq soft-mask enabled and
 	 * nothing pending. system_call_exception() will call
@@ -306,18 +335,27 @@ END_BTB_FLUSH_SECTION
 	bl	syscall_exit_prepare
 
 	ld	r2,_CCR(r1)
+	ld	r6,_LINK(r1)
+	mtlr	r6
+
+#ifdef CONFIG_PPC_BOOK3S
+	lbz	r4,PACASRR_VALID(r13)
+	cmpdi	r4,0
+	bne	1f
+	li	r4,0
+	stb	r4,PACASRR_VALID(r13)
+#endif
 	ld	r4,_NIP(r1)
 	ld	r5,_MSR(r1)
-	ld	r6,_LINK(r1)
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r5
+1:
+	DEBUG_SRR_VALID srr
 
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1			/* to clear the reservation */
 END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
-	mtspr	SPRN_SRR0,r4
-	mtspr	SPRN_SRR1,r5
-	mtlr	r6
-
 	cmpdi	r3,0
 	bne	.Lsyscall_restore_regs
 	/* Zero volatile regs that may contain sensitive kernel data */
@@ -673,19 +711,40 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\())
 	kuap_user_restore r3, r4
 #endif
 .Lfast_user_interrupt_return_\srr\():
-	ld	r11,_NIP(r1)
-	ld	r12,_MSR(r1)
+
 BEGIN_FTR_SECTION
 	ld	r10,_PPR(r1)
 	mtspr	SPRN_PPR,r10
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+#ifdef CONFIG_PPC_BOOK3S
+	.ifc \srr,srr
+	lbz	r4,PACASRR_VALID(r13)
+	.else
+	lbz	r4,PACAHSRR_VALID(r13)
+	.endif
+	cmpdi	r4,0
+	li	r4,0
+	bne	1f
+#endif
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
 	.ifc \srr,srr
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+	stb	r4,PACASRR_VALID(r13)
+#endif
 	.else
 	mtspr	SPRN_HSRR0,r11
 	mtspr	SPRN_HSRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+	stb	r4,PACAHSRR_VALID(r13)
+#endif
 	.endif
+	DEBUG_SRR_VALID \srr
 
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */
@@ -730,15 +789,34 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 .Lfast_kernel_interrupt_return_\srr\():
 	cmpdi	cr1,r3,0
+#ifdef CONFIG_PPC_BOOK3S
+	.ifc \srr,srr
+	lbz	r4,PACASRR_VALID(r13)
+	.else
+	lbz	r4,PACAHSRR_VALID(r13)
+	.endif
+	cmpdi	r4,0
+	li	r4,0
+	bne	1f
+#endif
 	ld	r11,_NIP(r1)
 	ld	r12,_MSR(r1)
 	.ifc \srr,srr
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+	stb	r4,PACASRR_VALID(r13)
+#endif
 	.else
 	mtspr	SPRN_HSRR0,r11
 	mtspr	SPRN_HSRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+	stb	r4,PACAHSRR_VALID(r13)
+#endif
 	.endif
+	DEBUG_SRR_VALID \srr
 
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */

arch/powerpc/kernel/exceptions-64s.S

@@ -485,6 +485,20 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 	std	r0,GPR0(r1)		/* save r0 in stackframe	*/
 	std	r10,GPR1(r1)		/* save r1 in stackframe	*/
 
+	/* Mark our [H]SRRs valid for return */
+	li	r10,1
+	.if IHSRR_IF_HVMODE
+	BEGIN_FTR_SECTION
+	stb	r10,PACAHSRR_VALID(r13)
+	FTR_SECTION_ELSE
+	stb	r10,PACASRR_VALID(r13)
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif IHSRR
+	stb	r10,PACAHSRR_VALID(r13)
+	.else
+	stb	r10,PACASRR_VALID(r13)
+	.endif
+
 	.if ISET_RI
 	li	r10,MSR_RI
 	mtmsrd	r10,1			/* Set MSR_RI */
@@ -584,10 +598,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 .macro EXCEPTION_RESTORE_REGS hsrr=0
 	/* Move original SRR0 and SRR1 into the respective regs */
 	ld	r9,_MSR(r1)
+	li	r10,0
 	.if \hsrr
 	mtspr	SPRN_HSRR1,r9
+	stb	r10,PACAHSRR_VALID(r13)
 	.else
 	mtspr	SPRN_SRR1,r9
+	stb	r10,PACASRR_VALID(r13)
 	.endif
 	ld	r9,_NIP(r1)
 	.if \hsrr
@@ -1718,6 +1735,8 @@ EXC_COMMON_BEGIN(hdecrementer_common)
 	 *
 	 * Be careful to avoid touching the kernel stack.
 	 */
+	li	r10,0
+	stb	r10,PACAHSRR_VALID(r13)
 	ld	r10,PACA_EXGEN+EX_CTR(r13)
 	mtctr	r10
 	mtcrf	0x80,r9
@@ -2513,6 +2532,8 @@ BEGIN_FTR_SECTION
 	ld	r10,PACA_EXGEN+EX_CFAR(r13)
 	mtspr	SPRN_CFAR,r10
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+	li	r10,0
+	stb	r10,PACAHSRR_VALID(r13)
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
@@ -2673,6 +2694,12 @@ masked_interrupt:
 	ori	r11,r11,PACA_IRQ_HARD_DIS
 	stb	r11,PACAIRQHAPPENED(r13)
 2:	/* done */
+	li	r10,0
+	.if \hsrr
+	stb	r10,PACAHSRR_VALID(r13)
+	.else
+	stb	r10,PACASRR_VALID(r13)
+	.endif
 	ld	r10,PACA_EXGEN+EX_CTR(r13)
 	mtctr	r10
 	mtcrf	0x80,r9