Merge branch 'fixes' into next

Merge our fixes branch from the 4.16 cycle.

There were a number of important fixes merged, in particular some Power9
workarounds that we want in next for testing purposes. There's also been
some conflicting changes in the CPU features code which are best merged
and tested before going upstream.

4 files changed, 19 insertions, 9 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 777778579305..c8c836e8ad1b 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -97,6 +97,9 @@ 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;
 
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 8eea90f80e45..19b45ba6caf9 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/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);
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 734ff976b82f..66eba1e0007b 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -215,6 +215,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
 #define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
 #define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
+#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x0000400000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -465,7 +466,8 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
-	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY)
+	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | 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
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 051b3d63afe3..3a15b6db9501 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/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);
 	}