Merge tag 'powerpc-4.16-6' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Some more powerpc fixes for 4.16. Apologies if this is a bit big at
  rc7, but they're all reasonably important fixes. None are actually for
  new code, so they aren't indicative of 4.16 being in bad shape from
  our point of view.

   - Fix missing AT_BASE_PLATFORM (in auxv) when we're using a new
     firmware interface for describing CPU features.

   - Fix lost pending interrupts due to a race in our interrupt
     soft-masking code.

   - A workaround for a nest MMU bug with TLB invalidations on Power9.

   - A workaround for broadcast TLB invalidations on Power9.

   - Fix a bug in our instruction SLB miss handler, when handling bad
     addresses (eg. >= TASK_SIZE), which could corrupt non-volatile user
     GPRs.

  Thanks to: Aneesh Kumar K.V, Balbir Singh, Benjamin Herrenschmidt,
  Nicholas Piggin"

* tag 'powerpc-4.16-6' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s: Fix i-side SLB miss bad address handler saving nonvolatile GPRs
  powerpc/mm: Fixup tlbie vs store ordering issue on POWER9
  powerpc/mm/radix: Move the functions that does the actual tlbie closer
  powerpc/mm/radix: Remove unused code
  powerpc/mm: Workaround Nest MMU bug with TLB invalidations
  powerpc/mm: Add tracking of the number of coprocessors using a context
  powerpc/64s: Fix lost pending interrupt due to race causing lost update to irq_happened
  powerpc/64s: Fix NULL AT_BASE_PLATFORM when using DT CPU features

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

@@ -87,6 +87,9 @@ typedef struct {
 	/* Number of bits in the mm_cpumask */
 	atomic_t active_cpus;
 
+	/* Number of users of the external (Nest) MMU */
+	atomic_t copros;
+
 	/* NPU NMMU context */
 	struct npu_context *npu_context;
 

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

@@ -47,9 +47,6 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad
 #endif
 extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
-extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-				     unsigned long page_size);
-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);

arch/powerpc/include/asm/cputable.h

@@ -203,6 +203,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x2000000000000000)
 #define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x4000000000000000)
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x8000000000000000)
 
@@ -465,7 +466,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
-	    CPU_FTR_PKEY)
+	    CPU_FTR_PKEY | CPU_FTR_P9_TLBIE_BUG)
 #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
 			     (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9

arch/powerpc/include/asm/mmu_context.h

@@ -92,15 +92,23 @@ static inline void dec_mm_active_cpus(struct mm_struct *mm)
 static inline void mm_context_add_copro(struct mm_struct *mm)
 {
 	/*
-	 * On hash, should only be called once over the lifetime of
-	 * the context, as we can't decrement the active cpus count
-	 * and flush properly for the time being.
+	 * If any copro is in use, increment the active CPU count
+	 * in order to force TLB invalidations to be global as to
+	 * propagate to the Nest MMU.
 	 */
-	inc_mm_active_cpus(mm);
+	if (atomic_inc_return(&mm->context.copros) == 1)
+		inc_mm_active_cpus(mm);
 }
 
 static inline void mm_context_remove_copro(struct mm_struct *mm)
 {
+	int c;
+
+	c = atomic_dec_if_positive(&mm->context.copros);
+
+	/* Detect imbalance between add and remove */
+	WARN_ON(c < 0);
+
 	/*
 	 * Need to broadcast a global flush of the full mm before
 	 * decrementing active_cpus count, as the next TLBI may be
@@ -111,7 +119,7 @@ static inline void mm_context_remove_copro(struct mm_struct *mm)
 	 * for the time being. Invalidations will remain global if
 	 * used on hash.
 	 */
-	if (radix_enabled()) {
+	if (c == 0 && radix_enabled()) {
 		flush_all_mm(mm);
 		dec_mm_active_cpus(mm);
 	}

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -709,6 +709,9 @@ static __init void cpufeatures_cpu_quirks(void)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
 	else if ((version & 0xffffefff) == 0x004e0201)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+
+	if ((version & 0xffff0000) == 0x004e0000)
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
 }
 
 static void __init cpufeatures_setup_finished(void)
@@ -720,6 +723,9 @@ static void __init cpufeatures_setup_finished(void)
 		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
 	}
 
+	/* Make sure powerpc_base_platform is non-NULL */
+	powerpc_base_platform = cur_cpu_spec->platform;
+
 	system_registers.lpcr = mfspr(SPRN_LPCR);
 	system_registers.hfscr = mfspr(SPRN_HFSCR);
 	system_registers.fscr = mfspr(SPRN_FSCR);

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

@@ -706,7 +706,7 @@ EXC_COMMON_BEGIN(bad_addr_slb)
 	ld	r3, PACA_EXSLB+EX_DAR(r13)
 	std	r3, _DAR(r1)
 	beq	cr6, 2f
-	li	r10, 0x480		/* fix trap number for I-SLB miss */
+	li	r10, 0x481		/* fix trap number for I-SLB miss */
 	std	r10, _TRAP(r1)
 2:	bl	save_nvgprs
 	addi	r3, r1, STACK_FRAME_OVERHEAD

arch/powerpc/kernel/irq.c

@@ -476,6 +476,14 @@ void force_external_irq_replay(void)
 	 */
 	WARN_ON(!arch_irqs_disabled());
 
+	/*
+	 * Interrupts must always be hard disabled before irq_happened is
+	 * modified (to prevent lost update in case of interrupt between
+	 * load and store).
+	 */
+	__hard_irq_disable();
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
 	/* Indicate in the PACA that we have an interrupt to replay */
 	local_paca->irq_happened |= PACA_IRQ_EE;
 }

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -157,6 +157,9 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
 		     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
+		asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
+			     : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
 

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -473,6 +473,17 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 			trace_tlbie(kvm->arch.lpid, 0, rbvalues[i],
 				kvm->arch.lpid, 0, 0, 0);
 		}
+
+		if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+			/*
+			 * Need the extra ptesync to make sure we don't
+			 * re-order the tlbie
+			 */
+			asm volatile("ptesync": : :"memory");
+			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+				     "r" (rbvalues[0]), "r" (kvm->arch.lpid));
+		}
+
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 		kvm->arch.tlbie_lock = 0;
 	} else {

arch/powerpc/mm/hash_native_64.c

@@ -201,6 +201,15 @@ static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 	return va;
 }
 
+static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		/* Need the extra ptesync to ensure we don't reorder tlbie*/
+		asm volatile("ptesync": : :"memory");
+		___tlbie(vpn, psize, apsize, ssize);
+	}
+}
+
 static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long rb;
@@ -278,6 +287,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
 		asm volatile("ptesync": : :"memory");
 	} else {
 		__tlbie(vpn, psize, apsize, ssize);
+		fixup_tlbie(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -771,7 +781,7 @@ static void native_hpte_clear(void)
  */
 static void native_flush_hash_range(unsigned long number, int local)
 {
-	unsigned long vpn;
+	unsigned long vpn = 0;
 	unsigned long hash, index, hidx, shift, slot;
 	struct hash_pte *hptep;
 	unsigned long hpte_v;
@@ -843,6 +853,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 				__tlbie(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
+		/*
+		 * Just do one more with the last used values.
+		 */
+		fixup_tlbie(vpn, psize, psize, ssize);
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
 
 		if (lock_tlbie)

arch/powerpc/mm/mmu_context_book3s64.c

@@ -173,6 +173,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	mm_iommu_init(mm);
 #endif
 	atomic_set(&mm->context.active_cpus, 0);
+	atomic_set(&mm->context.copros, 0);
 
 	return 0;
 }

arch/powerpc/mm/pgtable_64.c

@@ -481,6 +481,7 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
 	}
+	/* do we need fixup here ?*/
 	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);

arch/powerpc/mm/tlb-radix.c

@@ -119,6 +119,49 @@ static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbiel_va(unsigned long va, unsigned long pid,
+			       unsigned long ap, unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = pid << PPC_BITLSHIFT(31);
+	prs = 1; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 1, rb, rs, ric, prs, r);
+}
+
+static inline void __tlbie_va(unsigned long va, unsigned long pid,
+			      unsigned long ap, unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = pid << PPC_BITLSHIFT(31);
+	prs = 1; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static inline void fixup_tlbie(void)
+{
+	unsigned long pid = 0;
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+	}
+}
+
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
@@ -151,24 +194,25 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
 	asm volatile("ptesync": : :"memory");
-	__tlbie_pid(pid, ric);
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-}
 
-static inline void __tlbiel_va(unsigned long va, unsigned long pid,
-			       unsigned long ap, unsigned long ric)
-{
-	unsigned long rb,rs,prs,r;
-
-	rb = va & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = pid << PPC_BITLSHIFT(31);
-	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
-
-	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 1, rb, rs, ric, prs, r);
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid(pid, RIC_FLUSH_TLB);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid(pid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid(pid, RIC_FLUSH_ALL);
+	}
+	fixup_tlbie();
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
 static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
@@ -203,22 +247,6 @@ static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
 	asm volatile("ptesync": : :"memory");
 }
 
-static inline void __tlbie_va(unsigned long va, unsigned long pid,
-			     unsigned long ap, unsigned long ric)
-{
-	unsigned long rb,rs,prs,r;
-
-	rb = va & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = pid << PPC_BITLSHIFT(31);
-	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
-
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
-
 static inline void __tlbie_va_range(unsigned long start, unsigned long end,
 				    unsigned long pid, unsigned long page_size,
 				    unsigned long psize)
@@ -237,6 +265,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 
 	asm volatile("ptesync": : :"memory");
 	__tlbie_va(va, pid, ap, ric);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -248,6 +277,7 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	if (also_pwc)
 		__tlbie_pid(pid, RIC_FLUSH_PWC);
 	__tlbie_va_range(start, end, pid, page_size, psize);
+	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -311,6 +341,16 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
+static bool mm_needs_flush_escalation(struct mm_struct *mm)
+{
+	/*
+	 * P9 nest MMU has issues with the page walk cache
+	 * caching PTEs and not flushing them properly when
+	 * RIC = 0 for a PID/LPID invalidate
+	 */
+	return atomic_read(&mm->context.copros) != 0;
+}
+
 #ifdef CONFIG_SMP
 void radix__flush_tlb_mm(struct mm_struct *mm)
 {
@@ -321,9 +361,12 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 		return;
 
 	preempt_disable();
-	if (!mm_is_thread_local(mm))
-		_tlbie_pid(pid, RIC_FLUSH_TLB);
-	else
+	if (!mm_is_thread_local(mm)) {
+		if (mm_needs_flush_escalation(mm))
+			_tlbie_pid(pid, RIC_FLUSH_ALL);
+		else
+			_tlbie_pid(pid, RIC_FLUSH_TLB);
+	} else
 		_tlbiel_pid(pid, RIC_FLUSH_TLB);
 	preempt_enable();
 }
@@ -435,10 +478,14 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	}
 
 	if (full) {
-		if (local)
+		if (local) {
 			_tlbiel_pid(pid, RIC_FLUSH_TLB);
-		else
-			_tlbie_pid(pid, RIC_FLUSH_TLB);
+		} else {
+			if (mm_needs_flush_escalation(mm))
+				_tlbie_pid(pid, RIC_FLUSH_ALL);
+			else
+				_tlbie_pid(pid, RIC_FLUSH_TLB);
+		}
 	} else {
 		bool hflush = false;
 		unsigned long hstart, hend;
@@ -465,6 +512,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
 						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+			fixup_tlbie();
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
 		}
 	}
@@ -548,6 +596,9 @@ static inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
 	}
 
 	if (full) {
+		if (!local && mm_needs_flush_escalation(mm))
+			also_pwc = true;
+
 		if (local)
 			_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
 		else
@@ -603,46 +654,6 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
-			      unsigned long page_size)
-{
-	unsigned long rb,rs,prs,r;
-	unsigned long ap;
-	unsigned long ric = RIC_FLUSH_TLB;
-
-	ap = mmu_get_ap(radix_get_mmu_psize(page_size));
-	rb = gpa & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = lpid & ((1UL << 32) - 1);
-	prs = 0; /* process scoped */
-	r = 1;   /* raidx format */
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
-}
-EXPORT_SYMBOL(radix__flush_tlb_lpid_va);
-
-void radix__flush_tlb_lpid(unsigned long lpid)
-{
-	unsigned long rb,rs,prs,r;
-	unsigned long ric = RIC_FLUSH_ALL;
-
-	rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
-	rs = lpid & ((1UL << 32) - 1);
-	prs = 0; /* partition scoped */
-	r = 1;   /* raidx format */
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
-}
-EXPORT_SYMBOL(radix__flush_tlb_lpid);
-
 void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
 				unsigned long start, unsigned long end)
 {