powerpc/mm: Add tracking of the number of coprocessors using a context

Currently, when using coprocessors (which use the Nest MMU), we
simply increment the active_cpu count to force all TLB invalidations
to be come broadcast.

Unfortunately, due to an errata in POWER9, we will need to know
more specifically that coprocessors are in use.

This maintains a separate copros counter in the MMU context for
that purpose.

NB. The commit mentioned in the fixes tag below is not at fault for
the bug we're fixing in this commit and the next, but this fix applies
on top the infrastructure it introduced.

Fixes: 03b8abed ("cxl: Enable global TLBIs for cxl contexts")
Cc: stable@vger.kernel.org # v4.15+
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Tested-by: NBalbir Singh <bsingharora@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

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/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/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;
 }