powerpc/64s: Improve local TLB flush for boot and MCE on POWER9

There are several cases outside the normal address space management
where a CPU's entire local TLB is to be flushed:

  1. Booting the kernel, in case something has left stale entries in
     the TLB (e.g., kexec).

  2. Machine check, to clean corrupted TLB entries.

One other place where the TLB is flushed, is waking from deep idle
states. The flush is a side-effect of calling ->cpu_restore with the
intention of re-setting various SPRs. The flush itself is unnecessary
because in the first case, the TLB should not acquire new corrupted
TLB entries as part of sleep/wake (though they may be lost).

This type of TLB flush is coded inflexibly, several times for each CPU
type, and they have a number of problems with ISA v3.0B:

- The current radix mode of the MMU is not taken into account, it is
  always done as a hash flushn For IS=2 (LPID-matching flush from host)
  and IS=3 with HV=0 (guest kernel flush), tlbie(l) is undefined if
  the R field does not match the current radix mode.

- ISA v3.0B hash must flush the partition and process table caches as
  well.

- ISA v3.0B radix must flush partition and process scoped translations,
  partition and process table caches, and also the page walk cache.

So consolidate the flushing code and implement it in C and inline asm
under the mm/ directory with the rest of the flush code. Add ISA v3.0B
cases for radix and hash, and use the radix flush in radix environment.

Provide a way for IS=2 (LPID flush) to specify the radix mode of the
partition. Have KVM pass in the radix mode of the guest.

Take out the flushes from early cputable/dt_cpu_ftrs detection hooks,
and move it later in the boot process after, the MMU registers are set
up and before relocation is first turned on.

The TLB flush is no longer called when restoring from deep idle states.
This was not be done as a separate step because booting secondaries
uses the same cpu_restore as idle restore, which needs the TLB flush.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/book3s/64/tlbflush-hash.h

@@ -51,6 +51,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 
 #define arch_flush_lazy_mmu_mode()      do {} while (0)
 
+extern void hash__tlbiel_all(unsigned int action);
 
 extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
 			    int ssize, unsigned long flags);

arch/powerpc/include/asm/book3s/64/tlbflush-radix.h

@@ -11,6 +11,8 @@ static inline int mmu_get_ap(int psize)
 	return mmu_psize_defs[psize].ap;
 }
 
+extern void radix__tlbiel_all(unsigned int action);
+
 extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 					   unsigned long start, unsigned long end);
 extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
@@ -47,4 +49,5 @@ extern void radix__flush_tlb_lpid(unsigned long lpid);
 extern void radix__flush_tlb_all(void);
 extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 					unsigned long address);
+
 #endif

arch/powerpc/include/asm/book3s/64/tlbflush.h

@@ -8,6 +8,40 @@
 #include <asm/book3s/64/tlbflush-hash.h>
 #include <asm/book3s/64/tlbflush-radix.h>
 
+/* TLB flush actions. Used as argument to tlbiel_all() */
+enum {
+	TLB_INVAL_SCOPE_GLOBAL = 0,	/* invalidate all TLBs */
+	TLB_INVAL_SCOPE_LPID = 1,	/* invalidate TLBs for current LPID */
+};
+
+static inline void tlbiel_all(void)
+{
+	/*
+	 * This is used for host machine check and bootup.
+	 *
+	 * This uses early_radix_enabled and implementations use
+	 * early_cpu_has_feature etc because that works early in boot
+	 * and this is the machine check path which is not performance
+	 * critical.
+	 */
+	if (early_radix_enabled())
+		radix__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL);
+	else
+		hash__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL);
+}
+
+static inline void tlbiel_all_lpid(bool radix)
+{
+	/*
+	 * This is used for guest machine check.
+	 */
+	if (radix)
+		radix__tlbiel_all(TLB_INVAL_SCOPE_LPID);
+	else
+		hash__tlbiel_all(TLB_INVAL_SCOPE_LPID);
+}
+
+
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
 				       unsigned long start, unsigned long end)

arch/powerpc/include/asm/cputable.h

@@ -107,12 +107,6 @@ struct cpu_spec {
 	 * called in real mode to handle SLB and TLB errors.
 	 */
 	long		(*machine_check_early)(struct pt_regs *regs);
-
-	/*
-	 * Processor specific routine to flush tlbs.
-	 */
-	void		(*flush_tlb)(unsigned int action);
-
 };
 
 extern struct cpu_spec		*cur_cpu_spec;
@@ -133,12 +127,6 @@ extern void cpu_feature_keys_init(void);
 static inline void cpu_feature_keys_init(void) { }
 #endif
 
-/* TLB flush actions. Used as argument to cpu_spec.flush_tlb() hook */
-enum {
-	TLB_INVAL_SCOPE_GLOBAL = 0,	/* invalidate all TLBs */
-	TLB_INVAL_SCOPE_LPID = 1,	/* invalidate TLBs for current LPID */
-};
-
 #endif /* __ASSEMBLY__ */
 
 /* CPU kernel features */

arch/powerpc/kernel/cpu_setup_power.S

@@ -31,7 +31,6 @@ _GLOBAL(__setup_cpu_power7)
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
 	bl	__init_LPCR_ISA206
-	bl	__init_tlb_power7
 	mtlr	r11
 	blr
 
@@ -45,7 +44,6 @@ _GLOBAL(__restore_cpu_power7)
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
 	bl	__init_LPCR_ISA206
-	bl	__init_tlb_power7
 	mtlr	r11
 	blr
 
@@ -64,7 +62,6 @@ _GLOBAL(__setup_cpu_power8)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA206
 	bl	__init_HFSCR
-	bl	__init_tlb_power8
 	bl	__init_PMU_HV
 	bl	__init_PMU_HV_ISA207
 	mtlr	r11
@@ -86,7 +83,6 @@ _GLOBAL(__restore_cpu_power8)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA206
 	bl	__init_HFSCR
-	bl	__init_tlb_power8
 	bl	__init_PMU_HV
 	bl	__init_PMU_HV_ISA207
 	mtlr	r11
@@ -110,7 +106,6 @@ _GLOBAL(__setup_cpu_power9)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA300
 	bl	__init_HFSCR
-	bl	__init_tlb_power9
 	bl	__init_PMU_HV
 	mtlr	r11
 	blr
@@ -134,7 +129,6 @@ _GLOBAL(__restore_cpu_power9)
 	li	r4,0 /* LPES = 0 */
 	bl	__init_LPCR_ISA300
 	bl	__init_HFSCR
-	bl	__init_tlb_power9
 	bl	__init_PMU_HV
 	mtlr	r11
 	blr
@@ -192,50 +186,6 @@ __init_HFSCR:
 	mtspr	SPRN_HFSCR,r3
 	blr
 
-/*
- * Clear the TLB using the specified IS form of tlbiel instruction
- * (invalidate by congruence class). P7 has 128 CCs., P8 has 512.
- */
-__init_tlb_power7:
-	li	r6,POWER7_TLB_SETS
-	mtctr	r6
-	li	r7,0xc00	/* IS field = 0b11 */
-	ptesync
-2:	tlbiel	r7
-	addi	r7,r7,0x1000
-	bdnz	2b
-	ptesync
-1:	blr
-
-__init_tlb_power8:
-	li	r6,POWER8_TLB_SETS
-	mtctr	r6
-	li	r7,0xc00	/* IS field = 0b11 */
-	ptesync
-2:	tlbiel	r7
-	addi	r7,r7,0x1000
-	bdnz	2b
-	ptesync
-1:	blr
-
-/*
- * Flush the TLB in hash mode. Hash must flush with RIC=2 once for process
- * and one for partition scope to clear process and partition table entries.
- */
-__init_tlb_power9:
-	li	r6,POWER9_TLB_SETS_HASH - 1
-	mtctr	r6
-	li	r7,0xc00	/* IS field = 0b11 */
-	li	r8,0
-	ptesync
-	PPC_TLBIEL(7, 8, 2, 1, 0)
-	PPC_TLBIEL(7, 8, 2, 0, 0)
-2:	addi	r7,r7,0x1000
-	PPC_TLBIEL(7, 8, 0, 0, 0)
-	bdnz	2b
-	ptesync
-1:	blr
-
 __init_PMU_HV:
 	li	r5,0
 	mtspr	SPRN_MMCRC,r5

arch/powerpc/kernel/cputable.c

@@ -74,9 +74,6 @@ extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power8(void);
 extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power9(void);
-extern void __flush_tlb_power7(unsigned int action);
-extern void __flush_tlb_power8(unsigned int action);
-extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
@@ -368,7 +365,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power7,
 		.cpu_restore		= __restore_cpu_power7,
-		.flush_tlb		= __flush_tlb_power7,
 		.machine_check_early	= __machine_check_early_realmode_p7,
 		.platform		= "power7",
 	},
@@ -386,7 +382,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -404,7 +399,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.platform		= "power9",
 	},
 	{	/* Power7 */
@@ -423,7 +417,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.cpu_setup		= __setup_cpu_power7,
 		.cpu_restore		= __restore_cpu_power7,
-		.flush_tlb		= __flush_tlb_power7,
 		.machine_check_early	= __machine_check_early_realmode_p7,
 		.platform		= "power7",
 	},
@@ -443,7 +436,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.cpu_setup		= __setup_cpu_power7,
 		.cpu_restore		= __restore_cpu_power7,
-		.flush_tlb		= __flush_tlb_power7,
 		.machine_check_early	= __machine_check_early_realmode_p7,
 		.platform		= "power7+",
 	},
@@ -463,7 +455,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -483,7 +474,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -503,7 +493,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -523,7 +512,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
-		.flush_tlb		= __flush_tlb_power8,
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
@@ -543,7 +531,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
@@ -563,7 +550,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
@@ -583,7 +569,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
-		.flush_tlb		= __flush_tlb_power9,
 		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -77,8 +77,6 @@ struct dt_cpu_feature {
  * Set up the base CPU
  */
 
-extern void __flush_tlb_power8(unsigned int action);
-extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 
@@ -92,27 +90,6 @@ static struct {
 
 static void (*init_pmu_registers)(void);
 
-static void cpufeatures_flush_tlb(void)
-{
-	/*
-	 * This is a temporary measure to keep equivalent TLB flush as the
-	 * cputable based setup code.
-	 */
-	switch (PVR_VER(mfspr(SPRN_PVR))) {
-	case PVR_POWER8:
-	case PVR_POWER8E:
-	case PVR_POWER8NVL:
-		__flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL);
-		break;
-	case PVR_POWER9:
-		__flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL);
-		break;
-	default:
-		pr_err("unknown CPU version for boot TLB flush\n");
-		break;
-	}
-}
-
 static void __restore_cpu_cpufeatures(void)
 {
 	/*
@@ -137,8 +114,6 @@ static void __restore_cpu_cpufeatures(void)
 
 	if (init_pmu_registers)
 		init_pmu_registers();
-
-	cpufeatures_flush_tlb();
 }
 
 static char dt_cpu_name[64];
@@ -157,7 +132,6 @@ static struct cpu_spec __initdata base_cpu_spec = {
 	.oprofile_type		= PPC_OPROFILE_INVALID,
 	.cpu_setup		= NULL,
 	.cpu_restore		= __restore_cpu_cpufeatures,
-	.flush_tlb		= NULL,
 	.machine_check_early	= NULL,
 	.platform		= NULL,
 };
@@ -412,7 +386,6 @@ static void init_pmu_power8(void)
 static int __init feat_enable_mce_power8(struct dt_cpu_feature *f)
 {
 	cur_cpu_spec->platform = "power8";
-	cur_cpu_spec->flush_tlb = __flush_tlb_power8;
 	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8;
 
 	return 1;
@@ -451,7 +424,6 @@ static void init_pmu_power9(void)
 static int __init feat_enable_mce_power9(struct dt_cpu_feature *f)
 {
 	cur_cpu_spec->platform = "power9";
-	cur_cpu_spec->flush_tlb = __flush_tlb_power9;
 	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9;
 
 	return 1;
@@ -752,8 +724,6 @@ static void __init cpufeatures_setup_finished(void)
 	system_registers.hfscr = mfspr(SPRN_HFSCR);
 	system_registers.fscr = mfspr(SPRN_FSCR);
 
-	cpufeatures_flush_tlb();
-
 	pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n",
 		cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
 }

arch/powerpc/kernel/mce_power.c

@@ -58,115 +58,6 @@ static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 	return pte_pfn(*ptep);
 }
 
-static void flush_tlb_206(unsigned int num_sets, unsigned int action)
-{
-	unsigned long rb;
-	unsigned int i;
-
-	switch (action) {
-	case TLB_INVAL_SCOPE_GLOBAL:
-		rb = TLBIEL_INVAL_SET;
-		break;
-	case TLB_INVAL_SCOPE_LPID:
-		rb = TLBIEL_INVAL_SET_LPID;
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	asm volatile("ptesync" : : : "memory");
-	for (i = 0; i < num_sets; i++) {
-		asm volatile("tlbiel %0" : : "r" (rb));
-		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
-	}
-	asm volatile("ptesync" : : : "memory");
-}
-
-static void flush_tlb_300(unsigned int num_sets, unsigned int action)
-{
-	unsigned long rb;
-	unsigned int i;
-	unsigned int r;
-
-	switch (action) {
-	case TLB_INVAL_SCOPE_GLOBAL:
-		rb = TLBIEL_INVAL_SET;
-		break;
-	case TLB_INVAL_SCOPE_LPID:
-		rb = TLBIEL_INVAL_SET_LPID;
-		break;
-	default:
-		BUG();
-		break;
-	}
-
-	asm volatile("ptesync" : : : "memory");
-
-	if (early_radix_enabled())
-		r = 1;
-	else
-		r = 0;
-
-	/*
-	 * First flush table/PWC caches with set 0, then flush the
-	 * rest of the sets, partition scope. Radix must then do it
-	 * all again with process scope. Hash just has to flush
-	 * process table.
-	 */
-	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-			"r"(rb), "r"(0), "i"(2), "i"(0), "r"(r));
-	for (i = 1; i < num_sets; i++) {
-		unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);
-
-		asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-				"r"(rb+set), "r"(0), "i"(2), "i"(0), "r"(r));
-	}
-
-	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-			"r"(rb), "r"(0), "i"(2), "i"(1), "r"(r));
-	if (early_radix_enabled()) {
-		for (i = 1; i < num_sets; i++) {
-			unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT);
-
-			asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : :
-				"r"(rb+set), "r"(0), "i"(2), "i"(1), "r"(r));
-		}
-	}
-
-	asm volatile("ptesync" : : : "memory");
-}
-
-/*
- * Generic routines to flush TLB on POWER processors. These routines
- * are used as flush_tlb hook in the cpu_spec.
- *
- * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
- *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
- */
-void __flush_tlb_power7(unsigned int action)
-{
-	flush_tlb_206(POWER7_TLB_SETS, action);
-}
-
-void __flush_tlb_power8(unsigned int action)
-{
-	flush_tlb_206(POWER8_TLB_SETS, action);
-}
-
-void __flush_tlb_power9(unsigned int action)
-{
-	unsigned int num_sets;
-
-	if (early_radix_enabled())
-		num_sets = POWER9_TLB_SETS_RADIX;
-	else
-		num_sets = POWER9_TLB_SETS_HASH;
-
-	flush_tlb_300(num_sets, action);
-}
-
-
 /* flush SLBs and reload */
 #ifdef CONFIG_PPC_BOOK3S_64
 static void flush_and_reload_slb(void)
@@ -226,10 +117,8 @@ static int mce_flush(int what)
 		return 1;
 	}
 	if (what == MCE_FLUSH_TLB) {
-		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
-			return 1;
-		}
+		tlbiel_all();
+		return 1;
 	}
 
 	return 0;

arch/powerpc/kvm/book3s_hv_ras.c

@@ -87,8 +87,7 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 				   DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI);
 		}
 		if (dsisr & DSISR_MC_TLB_MULTI) {
-			if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-				cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_LPID);
+			tlbiel_all_lpid(vcpu->kvm->arch.radix);
 			dsisr &= ~DSISR_MC_TLB_MULTI;
 		}
 		/* Any other errors we don't understand? */
@@ -105,8 +104,7 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 		reload_slb(vcpu);
 		break;
 	case SRR1_MC_IFETCH_TLBMULTI:
-		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_LPID);
+		tlbiel_all_lpid(vcpu->kvm->arch.radix);
 		break;
 	default:
 		handled = 0;

arch/powerpc/mm/hash_native_64.c

@@ -47,6 +47,103 @@
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
+static inline void tlbiel_hash_set_isa206(unsigned int set, unsigned int is)
+{
+	unsigned long rb;
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+
+	asm volatile("tlbiel %0" : : "r" (rb));
+}
+
+/*
+ * tlbiel instruction for hash, set invalidation
+ * i.e., r=1 and is=01 or is=10 or is=11
+ */
+static inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is,
+					unsigned int pid,
+					unsigned int ric, unsigned int prs)
+{
+	unsigned long rb;
+	unsigned long rs;
+	unsigned int r = 0; /* hash format */
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : "memory");
+}
+
+
+static void tlbiel_all_isa206(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	for (set = 0; set < num_sets; set++)
+		tlbiel_hash_set_isa206(set, is);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and any caching of partition table
+	 * entries. Then flush the remaining sets of the TLB. Hash mode uses
+	 * partition scoped TLB translations.
+	 */
+	tlbiel_hash_set_isa300(0, is, 0, 2, 0);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+
+	/*
+	 * Now invalidate the process table cache.
+	 *
+	 * From ISA v3.0B p. 1078:
+	 *     The following forms are invalid.
+	 *      * PRS=1, R=0, and RIC!=2 (The only process-scoped
+	 *        HPT caching is of the Process Table.)
+	 */
+	tlbiel_hash_set_isa300(0, is, 0, 2, 1);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+void hash__tlbiel_all(unsigned int action)
+{
+	unsigned int is;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		is = 3;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		is = 2;
+		break;
+	default:
+		BUG();
+	}
+
+	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
+		tlbiel_all_isa300(POWER9_TLB_SETS_HASH, is);
+	else if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
+		tlbiel_all_isa206(POWER8_TLB_SETS, is);
+	else if (early_cpu_has_feature(CPU_FTR_ARCH_206))
+		tlbiel_all_isa206(POWER7_TLB_SETS, is);
+	else
+		WARN(1, "%s called on pre-POWER7 CPU\n", __func__);
+
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
 static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 						int apsize, int ssize)
 {

arch/powerpc/mm/hash_utils_64.c

@@ -1051,6 +1051,10 @@ void __init hash__early_init_mmu(void)
 	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206)
+			&& cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 #ifdef CONFIG_SMP
@@ -1070,6 +1074,10 @@ void hash__early_init_mmu_secondary(void)
 	}
 	/* Initialize SLB */
 	slb_initialize();
+
+	if (cpu_has_feature(CPU_FTR_ARCH_206)
+			&& cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 #endif /* CONFIG_SMP */
 

arch/powerpc/mm/pgtable-radix.c

@@ -579,6 +579,9 @@ void __init radix__early_init_mmu(void)
 
 	radix_init_iamr();
 	radix_init_pgtable();
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 void radix__early_init_mmu_secondary(void)
@@ -600,6 +603,9 @@ void radix__early_init_mmu_secondary(void)
 		radix_init_amor();
 	}
 	radix_init_iamr();
+
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_all();
 }
 
 void radix__mmu_cleanup_all(void)

arch/powerpc/mm/tlb-radix.c

@@ -23,6 +23,72 @@
 #define RIC_FLUSH_PWC 1
 #define RIC_FLUSH_ALL 2
 
+/*
+ * tlbiel instruction for radix, set invalidation
+ * i.e., r=1 and is=01 or is=10 or is=11
+ */
+static inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is,
+					unsigned int pid,
+					unsigned int ric, unsigned int prs)
+{
+	unsigned long rb;
+	unsigned long rs;
+	unsigned int r = 1; /* radix format */
+
+	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
+	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
+
+	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : "memory");
+}
+
+static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
+{
+	unsigned int set;
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and the entire Page Walk Cache
+	 * and partition table entries. Then flush the remaining sets of the
+	 * TLB.
+	 */
+	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
+
+	/* Do the same for process scoped entries. */
+	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
+	for (set = 1; set < num_sets; set++)
+		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+void radix__tlbiel_all(unsigned int action)
+{
+	unsigned int is;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		is = 3;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		is = 2;
+		break;
+	default:
+		BUG();
+	}
+
+	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
+		tlbiel_all_isa300(POWER9_TLB_SETS_RADIX, is);
+	else
+		WARN(1, "%s called on pre-POWER9 CPU\n", __func__);
+
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
 static inline void __tlbiel_pid(unsigned long pid, int set,
 				unsigned long ric)
 {