Merge tag 'powerpc-4.15-7' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "One fix for an oops at boot if we take a hotplug interrupt before we
  are ready to handle it.

  The bulk is patches to implement mitigation for Meltdown, see the
  change logs for more details.

  Thanks to: Nicholas Piggin, Michael Neuling, Oliver O'Halloran, Jon
  Masters, Jose Ricardo Ziviani, David Gibson"

* tag 'powerpc-4.15-7' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/powernv: Check device-tree for RFI flush settings
  powerpc/pseries: Query hypervisor for RFI flush settings
  powerpc/64s: Support disabling RFI flush with no_rfi_flush and nopti
  powerpc/64s: Add support for RFI flush of L1-D cache
  powerpc/64s: Convert slb_miss_common to use RFI_TO_USER/KERNEL
  powerpc/64: Convert fast_exception_return to use RFI_TO_USER/KERNEL
  powerpc/64: Convert the syscall exit path to use RFI_TO_USER/KERNEL
  powerpc/64s: Simple RFI macro conversions
  powerpc/64: Add macros for annotating the destination of rfid/hrfid
  powerpc/pseries: Add H_GET_CPU_CHARACTERISTICS flags & wrapper
  powerpc/pseries: Make RAS IRQ explicitly dependent on DLPAR WQ

arch/powerpc/include/asm/exception-64e.h

@@ -209,5 +209,11 @@ exc_##label##_book3e:
 	ori	r3,r3,vector_offset@l;		\
 	mtspr	SPRN_IVOR##vector_number,r3;
 
+#define RFI_TO_KERNEL							\
+	rfi
+
+#define RFI_TO_USER							\
+	rfi
+
 #endif /* _ASM_POWERPC_EXCEPTION_64E_H */
 

arch/powerpc/include/asm/exception-64s.h

@@ -74,6 +74,59 @@
  */
 #define EX_R3		EX_DAR
 
+/*
+ * Macros for annotating the expected destination of (h)rfid
+ *
+ * The nop instructions allow us to insert one or more instructions to flush the
+ * L1-D cache when returning to userspace or a guest.
+ */
+#define RFI_FLUSH_SLOT							\
+	RFI_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop
+
+#define RFI_TO_KERNEL							\
+	rfid
+
+#define RFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define HRFI_TO_KERNEL							\
+	hrfid
+
+#define HRFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_UNKNOWN							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
 #ifdef CONFIG_RELOCATABLE
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
 	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
@@ -218,7 +271,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 #define EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	__EXCEPTION_PROLOG_PSERIES_1(label, h)
@@ -232,7 +285,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 
 #define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h)			\

arch/powerpc/include/asm/feature-fixups.h

@@ -187,7 +187,20 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET label##1b-label##3b;		\
 	.popsection;
 
+#define RFI_FLUSH_FIXUP_SECTION				\
+951:							\
+	.pushsection __rfi_flush_fixup,"a";		\
+	.align 2;					\
+952:							\
+	FTR_ENTRY_OFFSET 951b-952b;			\
+	.popsection;
+
+
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
+
 void apply_feature_fixups(void);
 void setup_feature_keys(void);
 #endif

arch/powerpc/include/asm/hvcall.h

@@ -241,6 +241,7 @@
 #define H_GET_HCA_INFO          0x1B8
 #define H_GET_PERF_COUNT        0x1BC
 #define H_MANAGE_TRACE          0x1C0
+#define H_GET_CPU_CHARACTERISTICS 0x1C8
 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
@@ -330,6 +331,17 @@
 #define H_SIGNAL_SYS_RESET_ALL_OTHERS		-2
 /* >= 0 values are CPU number */
 
+/* H_GET_CPU_CHARACTERISTICS return values */
+#define H_CPU_CHAR_SPEC_BAR_ORI31	(1ull << 63) // IBM bit 0
+#define H_CPU_CHAR_BCCTRL_SERIALISED	(1ull << 62) // IBM bit 1
+#define H_CPU_CHAR_L1D_FLUSH_ORI30	(1ull << 61) // IBM bit 2
+#define H_CPU_CHAR_L1D_FLUSH_TRIG2	(1ull << 60) // IBM bit 3
+#define H_CPU_CHAR_L1D_THREAD_PRIV	(1ull << 59) // IBM bit 4
+
+#define H_CPU_BEHAV_FAVOUR_SECURITY	(1ull << 63) // IBM bit 0
+#define H_CPU_BEHAV_L1D_FLUSH_PR	(1ull << 62) // IBM bit 1
+#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ull << 61) // IBM bit 2
+
 /* Flag values used in H_REGISTER_PROC_TBL hcall */
 #define PROC_TABLE_OP_MASK	0x18
 #define PROC_TABLE_DEREG	0x10
@@ -436,6 +448,11 @@ static inline unsigned int get_longbusy_msecs(int longbusy_rc)
 	}
 }
 
+struct h_cpu_char_result {
+	u64 character;
+	u64 behaviour;
+};
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */

arch/powerpc/include/asm/paca.h

@@ -232,6 +232,16 @@ struct paca_struct {
 	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * rfi fallback flush must be in its own cacheline to prevent
+	 * other paca data leaking into the L1d
+	 */
+	u64 exrfi[EX_SIZE] __aligned(0x80);
+	void *rfi_flush_fallback_area;
+	u64 l1d_flush_congruence;
+	u64 l1d_flush_sets;
+#endif
 };
 
 extern void copy_mm_to_paca(struct mm_struct *mm);

arch/powerpc/include/asm/plpar_wrappers.h

@@ -326,4 +326,18 @@ static inline long plapr_signal_sys_reset(long cpu)
 	return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu);
 }
 
+static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf);
+	if (rc == H_SUCCESS) {
+		p->character = retbuf[0];
+		p->behaviour = retbuf[1];
+	}
+
+	return rc;
+}
+
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */

arch/powerpc/include/asm/setup.h

@@ -39,6 +39,19 @@ static inline void pseries_big_endian_exceptions(void) {}
 static inline void pseries_little_endian_exceptions(void) {}
 #endif /* CONFIG_PPC_PSERIES */
 
+void rfi_flush_enable(bool enable);
+
+/* These are bit flags */
+enum l1d_flush_type {
+	L1D_FLUSH_NONE		= 0x1,
+	L1D_FLUSH_FALLBACK	= 0x2,
+	L1D_FLUSH_ORI		= 0x4,
+	L1D_FLUSH_MTTRIG	= 0x8,
+};
+
+void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void do_rfi_flush_fixups(enum l1d_flush_type types);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */

arch/powerpc/kernel/asm-offsets.c

@@ -237,6 +237,11 @@ int main(void)
 	OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
 	OFFSET(PACA_IN_MCE, paca_struct, in_mce);
 	OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
+	OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area);
+	OFFSET(PACA_EXRFI, paca_struct, exrfi);
+	OFFSET(PACA_L1D_FLUSH_CONGRUENCE, paca_struct, l1d_flush_congruence);
+	OFFSET(PACA_L1D_FLUSH_SETS, paca_struct, l1d_flush_sets);
+
 #endif
 	OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
 	OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);

arch/powerpc/kernel/entry_64.S

@@ -37,6 +37,11 @@
 #include <asm/tm.h>
 #include <asm/ppc-opcode.h>
 #include <asm/export.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
 
 /*
  * System calls.
@@ -262,13 +267,23 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	ld	r2,GPR2(r1)
+	ld	r1,GPR1(r1)
+	mtlr	r4
+	mtcr	r5
+	mtspr	SPRN_SRR0,r7
+	mtspr	SPRN_SRR1,r8
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+
+	/* exit to kernel */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
 	mtlr	r4
 	mtcr	r5
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
-	RFI
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 .Lsyscall_error:
@@ -397,8 +412,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12
-
-	rfid
+	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
 _ASM_NOKPROBE_SYMBOL(system_call_common);
@@ -878,7 +892,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
-1:
+
 	mtspr	SPRN_SRR1,r3
 
 	ld	r2,_CCR(r1)
@@ -891,8 +905,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ld	r3,GPR3(r1)
 	ld	r4,GPR4(r1)
 	ld	r1,GPR1(r1)
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
 
-	rfid
+1:	mtspr	SPRN_SRR1,r3
+
+	ld	r2,_CCR(r1)
+	mtcrf	0xFF,r2
+	ld	r2,_NIP(r1)
+	mtspr	SPRN_SRR0,r2
+
+	ld	r0,GPR0(r1)
+	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r4,GPR4(r1)
+	ld	r1,GPR1(r1)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 #endif /* CONFIG_PPC_BOOK3E */
@@ -1073,7 +1101,7 @@ __enter_rtas:
 	
 	mtspr	SPRN_SRR0,r5
 	mtspr	SPRN_SRR1,r6
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 rtas_return_loc:
@@ -1098,7 +1126,7 @@ rtas_return_loc:
 
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 _ASM_NOKPROBE_SYMBOL(__enter_rtas)
 _ASM_NOKPROBE_SYMBOL(rtas_return_loc)
@@ -1171,7 +1199,7 @@ _GLOBAL(enter_prom)
 	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
 	andc	r11,r11,r12
 	mtsrr1	r11
-	rfid
+	RFI_TO_KERNEL
 #endif /* CONFIG_PPC_BOOK3E */
 
 1:	/* Return from OF */

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

@@ -256,7 +256,7 @@ BEGIN_FTR_SECTION
 	LOAD_HANDLER(r12, machine_check_handle_early)
 1:	mtspr	SPRN_SRR0,r12
 	mtspr	SPRN_SRR1,r11
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 2:
 	/* Stack overflow. Stay on emergency stack and panic.
@@ -445,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	li	r3,MSR_ME
 	andc	r10,r10,r3		/* Turn off MSR_ME */
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 2:
 	/*
@@ -463,7 +463,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	 */
 	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
-	rfid
+	RFI_TO_USER_OR_KERNEL
 9:
 	/* Deliver the machine check to host kernel in V mode. */
 	MACHINE_CHECK_HANDLER_WINDUP
@@ -598,6 +598,9 @@ EXC_COMMON_BEGIN(slb_miss_common)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
 
+	andi.	r9,r11,MSR_PR	// Check for exception from userspace
+	cmpdi	cr4,r9,MSR_PR	// And save the result in CR4 for later
+
 	/*
 	 * Test MSR_RI before calling slb_allocate_realmode, because the
 	 * MSR in r11 gets clobbered. However we still want to allocate
@@ -624,9 +627,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	/* All done -- return from exception. */
 
+	bne	cr4,1f		/* returning to kernel */
+
 .machine	push
 .machine	"power4"
 	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
@@ -640,9 +646,30 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	ld	r11,PACA_EXSLB+EX_R11(r13)
 	ld	r12,PACA_EXSLB+EX_R12(r13)
 	ld	r13,PACA_EXSLB+EX_R13(r13)
-	rfid
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+1:
+.machine	push
+.machine	"power4"
+	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
+	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
+	mtcrf	0x02,r9		/* I/D indication is in cr6 */
+	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
+.machine	pop
+
+	RESTORE_CTR(r9, PACA_EXSLB)
+	RESTORE_PPR_PACA(PACA_EXSLB, r9)
+	mr	r3,r12
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
+
 2:	std     r3,PACA_EXSLB+EX_DAR(r13)
 	mr	r3,r12
 	mfspr	r11,SPRN_SRR0
@@ -651,7 +678,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 8:	std     r3,PACA_EXSLB+EX_DAR(r13)
@@ -662,7 +689,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 EXC_COMMON_BEGIN(unrecov_slb)
@@ -901,7 +928,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 	mtspr	SPRN_SRR0,r10 ; 				\
 	ld	r10,PACAKMSR(r13) ;				\
 	mtspr	SPRN_SRR1,r10 ; 				\
-	rfid ; 							\
+	RFI_TO_KERNEL ;						\
 	b	. ;	/* prevent speculative execution */
 
 #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
@@ -917,7 +944,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	xori	r12,r12,MSR_LE ;				\
 	mtspr	SPRN_SRR1,r12 ;					\
 	mr	r13,r9 ;					\
-	rfid ;		/* return to userspace */		\
+	RFI_TO_USER ;	/* return to userspace */		\
 	b	. ;	/* prevent speculative execution */
 #else
 #define SYSCALL_FASTENDIAN_TEST
@@ -1063,7 +1090,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early)
 	mtcr	r11
 	REST_GPR(11, r1)
 	ld	r1,GPR1(r1)
-	hrfid
+	HRFI_TO_USER_OR_KERNEL
 
 1:	mtcr	r11
 	REST_GPR(11, r1)
@@ -1314,7 +1341,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
 	ld	r13,PACA_EXGEN+EX_R13(r13)
-	HRFID
+	HRFI_TO_UNKNOWN
 	b	.
 #endif
 
@@ -1418,10 +1445,94 @@ masked_##_H##interrupt:					\
 	ld	r10,PACA_EXGEN+EX_R10(r13);		\
 	ld	r11,PACA_EXGEN+EX_R11(r13);		\
 	/* returns to kernel where r13 must be set up, so don't restore it */ \
-	##_H##rfid;					\
+	##_H##RFI_TO_KERNEL;				\
 	b	.;					\
 	MASKED_DEC_HANDLER(_H)
 
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	std	r12,PACA_EXRFI+EX_R12(r13)
+	std	r8,PACA_EXRFI+EX_R13(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SETS(r13)
+	ld	r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+	addi	r12,r12,8
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+1:	li	r8,0
+	.rept	8 /* 8-way set associative */
+	ldx	r11,r10,r8
+	add	r8,r8,r12
+	xor	r11,r11,r11	// Ensure r11 is 0 even if fallback area is not
+	add	r8,r8,r11	// Add 0, this creates a dependency on the ldx
+	.endr
+	addi	r10,r10,128 /* 128 byte cache line */
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	ld	r12,PACA_EXRFI+EX_R12(r13)
+	ld	r8,PACA_EXRFI+EX_R13(r13)
+	GET_SCRATCH0(r13);
+	rfid
+
+TRAMP_REAL_BEGIN(hrfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	std	r12,PACA_EXRFI+EX_R12(r13)
+	std	r8,PACA_EXRFI+EX_R13(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SETS(r13)
+	ld	r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+	addi	r12,r12,8
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+1:	li	r8,0
+	.rept	8 /* 8-way set associative */
+	ldx	r11,r10,r8
+	add	r8,r8,r12
+	xor	r11,r11,r11	// Ensure r11 is 0 even if fallback area is not
+	add	r8,r8,r11	// Add 0, this creates a dependency on the ldx
+	.endr
+	addi	r10,r10,128 /* 128 byte cache line */
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	ld	r12,PACA_EXRFI+EX_R12(r13)
+	ld	r8,PACA_EXRFI+EX_R13(r13)
+	GET_SCRATCH0(r13);
+	hrfid
+
 /*
  * Real mode exceptions actually use this too, but alternate
  * instruction code patches (which end up in the common .text area)
@@ -1441,7 +1552,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_SRR0, r13
 	GET_SCRATCH0(r13)
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
@@ -1453,7 +1564,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_HSRR0, r13
 	GET_SCRATCH0(r13)
-	hrfid
+	HRFI_TO_KERNEL
 	b	.
 #endif
 

arch/powerpc/kernel/setup_64.c

@@ -801,3 +801,104 @@ static int __init disable_hardlockup_detector(void)
 	return 0;
 }
 early_initcall(disable_hardlockup_detector);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+static enum l1d_flush_type enabled_flush_types;
+static void *l1d_flush_fallback_area;
+static bool no_rfi_flush;
+bool rfi_flush;
+
+static int __init handle_no_rfi_flush(char *p)
+{
+	pr_info("rfi-flush: disabled on command line.");
+	no_rfi_flush = true;
+	return 0;
+}
+early_param("no_rfi_flush", handle_no_rfi_flush);
+
+/*
+ * The RFI flush is not KPTI, but because users will see doco that says to use
+ * nopti we hijack that option here to also disable the RFI flush.
+ */
+static int __init handle_no_pti(char *p)
+{
+	pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
+	handle_no_rfi_flush(NULL);
+	return 0;
+}
+early_param("nopti", handle_no_pti);
+
+static void do_nothing(void *unused)
+{
+	/*
+	 * We don't need to do the flush explicitly, just enter+exit kernel is
+	 * sufficient, the RFI exit handlers will do the right thing.
+	 */
+}
+
+void rfi_flush_enable(bool enable)
+{
+	if (rfi_flush == enable)
+		return;
+
+	if (enable) {
+		do_rfi_flush_fixups(enabled_flush_types);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else
+		do_rfi_flush_fixups(L1D_FLUSH_NONE);
+
+	rfi_flush = enable;
+}
+
+static void init_fallback_flush(void)
+{
+	u64 l1d_size, limit;
+	int cpu;
+
+	l1d_size = ppc64_caches.l1d.size;
+	limit = min(safe_stack_limit(), ppc64_rma_size);
+
+	/*
+	 * Align to L1d size, and size it at 2x L1d size, to catch possible
+	 * hardware prefetch runoff. We don't have a recipe for load patterns to
+	 * reliably avoid the prefetcher.
+	 */
+	l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
+	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * The fallback flush is currently coded for 8-way
+		 * associativity. Different associativity is possible, but it
+		 * will be treated as 8-way and may not evict the lines as
+		 * effectively.
+		 *
+		 * 128 byte lines are mandatory.
+		 */
+		u64 c = l1d_size / 8;
+
+		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca[cpu].l1d_flush_congruence = c;
+		paca[cpu].l1d_flush_sets = c / 128;
+	}
+}
+
+void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+{
+	if (types & L1D_FLUSH_FALLBACK) {
+		pr_info("rfi-flush: Using fallback displacement flush\n");
+		init_fallback_flush();
+	}
+
+	if (types & L1D_FLUSH_ORI)
+		pr_info("rfi-flush: Using ori type flush\n");
+
+	if (types & L1D_FLUSH_MTTRIG)
+		pr_info("rfi-flush: Using mttrig type flush\n");
+
+	enabled_flush_types = types;
+
+	if (!no_rfi_flush)
+		rfi_flush_enable(enable);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/kernel/vmlinux.lds.S

@@ -132,6 +132,15 @@ SECTIONS
 	/* Read-only data */
 	RO_DATA(PAGE_SIZE)
 
+#ifdef CONFIG_PPC64
+	. = ALIGN(8);
+	__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
+		__start___rfi_flush_fixup = .;
+		*(__rfi_flush_fixup)
+		__stop___rfi_flush_fixup = .;
+	}
+#endif
+
 	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -79,7 +79,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mtmsrd	r0,1		/* clear RI in MSR */
 	mtsrr0	r5
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 kvmppc_call_hv_entry:
 BEGIN_FTR_SECTION
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtmsrd	r6, 1			/* Clear RI in MSR */
 	mtsrr0	r8
 	mtsrr1	r7
-	RFI
+	RFI_TO_KERNEL
 
 	/* Virtual-mode return */
 .Lvirt_return:
@@ -1167,8 +1167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
-
-	hrfid
+	HRFI_TO_GUEST
 	b	.
 
 secondary_too_late:
@@ -3320,7 +3319,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	ld	r4, PACAKMSR(r13)
 	mtspr	SPRN_SRR0, r3
 	mtspr	SPRN_SRR1, r4
-	rfid
+	RFI_TO_KERNEL
 9:	addi	r3, r1, STACK_FRAME_OVERHEAD
 	bl	kvmppc_bad_interrupt
 	b	9b

arch/powerpc/kvm/book3s_rmhandlers.S

@@ -46,6 +46,9 @@
 
 #define FUNC(name)		name
 
+#define RFI_TO_KERNEL	RFI
+#define RFI_TO_GUEST	RFI
+
 .macro INTERRUPT_TRAMPOLINE intno
 
 .global kvmppc_trampoline_\intno
@@ -141,7 +144,7 @@ kvmppc_handler_skip_ins:
 	GET_SCRATCH0(r13)
 
 	/* And get back into the code */
-	RFI
+	RFI_TO_KERNEL
 #endif
 
 /*
@@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline)
 	ori	r5, r5, MSR_EE
 	mtsrr0	r7
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 #include "book3s_segment.S"

arch/powerpc/kvm/book3s_segment.S

@@ -156,7 +156,7 @@ no_dcbz32_on:
 	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
-	RFI
+	RFI_TO_GUEST
 kvmppc_handler_trampoline_enter_end:
 
 
@@ -407,5 +407,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	cmpwi	r12, BOOK3S_INTERRUPT_DOORBELL
 	beqa	BOOK3S_INTERRUPT_DOORBELL
 
-	RFI
+	RFI_TO_KERNEL
 kvmppc_handler_trampoline_exit_end:

arch/powerpc/lib/feature-fixups.c

@@ -116,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_rfi_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___rfi_flush_fixup),
+	end = PTRRELOC(&__stop___rfi_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	if (types & L1D_FLUSH_FALLBACK)
+		/* b .+16 to fallback flush */
+		instrs[0] = 0x48000010;
+
+	i = 0;
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 {
 	long *start, *end;

arch/powerpc/platforms/powernv/setup.c

@@ -37,13 +37,62 @@
 #include <asm/kexec.h>
 #include <asm/smp.h>
 #include <asm/tm.h>
+#include <asm/setup.h>
 
 #include "powernv.h"
 
+static void pnv_setup_rfi_flush(void)
+{
+	struct device_node *np, *fw_features;
+	enum l1d_flush_type type;
+	int enable;
+
+	/* Default to fallback in case fw-features are not available */
+	type = L1D_FLUSH_FALLBACK;
+	enable = 1;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	fw_features = of_get_child_by_name(np, "fw-features");
+	of_node_put(np);
+
+	if (fw_features) {
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_MTTRIG;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_ORI;
+
+		of_node_put(np);
+
+		/* Enable unless firmware says NOT to */
+		enable = 2;
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+		of_node_put(fw_features);
+	}
+
+	setup_rfi_flush(type, enable > 0);
+}
+
 static void __init pnv_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
+	pnv_setup_rfi_flush();
+
 	/* Initialize SMP */
 	pnv_smp_init();
 

arch/powerpc/platforms/pseries/dlpar.c

@@ -574,11 +574,26 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr,
 
 static CLASS_ATTR_RW(dlpar);
 
-static int __init pseries_dlpar_init(void)
+int __init dlpar_workqueue_init(void)
 {
+	if (pseries_hp_wq)
+		return 0;
+
 	pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
 			WQ_UNBOUND, 1);
+
+	return pseries_hp_wq ? 0 : -ENOMEM;
+}
+
+static int __init dlpar_sysfs_init(void)
+{
+	int rc;
+
+	rc = dlpar_workqueue_init();
+	if (rc)
+		return rc;
+
 	return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
 }
-machine_device_initcall(pseries, pseries_dlpar_init);
+machine_device_initcall(pseries, dlpar_sysfs_init);
 

arch/powerpc/platforms/pseries/pseries.h

@@ -98,4 +98,6 @@ static inline unsigned long cmo_get_page_size(void)
 	return CMO_PageSize;
 }
 
+int dlpar_workqueue_init(void);
+
 #endif /* _PSERIES_PSERIES_H */

arch/powerpc/platforms/pseries/ras.c

@@ -69,6 +69,7 @@ static int __init init_ras_IRQ(void)
 	/* Hotplug Events */
 	np = of_find_node_by_path("/event-sources/hot-plug-events");
 	if (np != NULL) {
+		if (dlpar_workqueue_init() == 0)
 			request_event_sources_irqs(np, ras_hotplug_interrupt,
 					   "RAS_HOTPLUG");
 		of_node_put(np);

arch/powerpc/platforms/pseries/setup.c

@@ -459,6 +459,39 @@ static void __init find_and_init_phbs(void)
 	of_pci_check_probe_only();
 }
 
+static void pseries_setup_rfi_flush(void)
+{
+	struct h_cpu_char_result result;
+	enum l1d_flush_type types;
+	bool enable;
+	long rc;
+
+	/* Enable by default */
+	enable = true;
+
+	rc = plpar_get_cpu_characteristics(&result);
+	if (rc == H_SUCCESS) {
+		types = L1D_FLUSH_NONE;
+
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
+			types |= L1D_FLUSH_MTTRIG;
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30)
+			types |= L1D_FLUSH_ORI;
+
+		/* Use fallback if nothing set in hcall */
+		if (types == L1D_FLUSH_NONE)
+			types = L1D_FLUSH_FALLBACK;
+
+		if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+			enable = false;
+	} else {
+		/* Default to fallback if case hcall is not available */
+		types = L1D_FLUSH_FALLBACK;
+	}
+
+	setup_rfi_flush(types, enable);
+}
+
 static void __init pSeries_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
@@ -476,6 +509,8 @@ static void __init pSeries_setup_arch(void)
 
 	fwnmi_init();
 
+	pseries_setup_rfi_flush();
+
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);