Merge branch 'fixes' into next

Merge our fixes branch into next, this brings in a number of commits
that fix bugs we don't want to hit in next, in particular the fix for
CVE-2019-12817.

arch/powerpc/mm/book3s64/mmu_context.c

@@ -55,20 +55,52 @@ EXPORT_SYMBOL_GPL(hash__alloc_context_id);
 
 void slb_setup_new_exec(void);
 
+static int realloc_context_ids(mm_context_t *ctx)
+{
+	int i, id;
+
+	/*
+	 * id 0 (aka. ctx->id) is special, we always allocate a new one, even if
+	 * there wasn't one allocated previously (which happens in the exec
+	 * case where ctx is newly allocated).
+	 *
+	 * We have to be a bit careful here. We must keep the existing ids in
+	 * the array, so that we can test if they're non-zero to decide if we
+	 * need to allocate a new one. However in case of error we must free the
+	 * ids we've allocated but *not* any of the existing ones (or risk a
+	 * UAF). That's why we decrement i at the start of the error handling
+	 * loop, to skip the id that we just tested but couldn't reallocate.
+	 */
+	for (i = 0; i < ARRAY_SIZE(ctx->extended_id); i++) {
+		if (i == 0 || ctx->extended_id[i]) {
+			id = hash__alloc_context_id();
+			if (id < 0)
+				goto error;
+
+			ctx->extended_id[i] = id;
+		}
+	}
+
+	/* The caller expects us to return id */
+	return ctx->id;
+
+error:
+	for (i--; i >= 0; i--) {
+		if (ctx->extended_id[i])
+			ida_free(&mmu_context_ida, ctx->extended_id[i]);
+	}
+
+	return id;
+}
+
 static int hash__init_new_context(struct mm_struct *mm)
 {
 	int index;
 
-	index = hash__alloc_context_id();
-	if (index < 0)
-		return index;
-
 	mm->context.hash_context = kmalloc(sizeof(struct hash_mm_context),
 					   GFP_KERNEL);
-	if (!mm->context.hash_context) {
-		ida_free(&mmu_context_ida, index);
+	if (!mm->context.hash_context)
 		return -ENOMEM;
-	}
 
 	/*
 	 * The old code would re-promote on fork, we don't do that when using
@@ -96,13 +128,20 @@ static int hash__init_new_context(struct mm_struct *mm)
 			mm->context.hash_context->spt = kmalloc(sizeof(struct subpage_prot_table),
 								GFP_KERNEL);
 			if (!mm->context.hash_context->spt) {
-				ida_free(&mmu_context_ida, index);
 				kfree(mm->context.hash_context);
 				return -ENOMEM;
 			}
 		}
 #endif
+	}
 
+	index = realloc_context_ids(&mm->context);
+	if (index < 0) {
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+		kfree(mm->context.hash_context->spt);
+#endif
+		kfree(mm->context.hash_context);
+		return index;
 	}
 
 	pkey_mm_init(mm);

arch/powerpc/mm/book3s64/pgtable.c

@@ -116,6 +116,9 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
 	 * to prevent a parallel THP split work as expected.
+	 *
+	 * Marking the entry with _PAGE_INVALID && ~_PAGE_PRESENT requires
+	 * a special case check in pmd_access_permitted.
 	 */
 	serialize_against_pte_lookup(vma->vm_mm);
 	return __pmd(old_pmd);

arch/powerpc/mm/mem.c

@@ -253,7 +253,8 @@ void __init paging_init(void)
 	       (long int)((top_of_ram - total_ram) >> 20));
 
 #ifdef CONFIG_ZONE_DMA
-	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn, 0x7fffffffUL >> PAGE_SHIFT);
+	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn,
+			((1UL << ARCH_ZONE_DMA_BITS) - 1) >> PAGE_SHIFT);
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 #ifdef CONFIG_HIGHMEM

arch/powerpc/mm/pgtable.c

@@ -372,13 +372,25 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 	pdshift = PMD_SHIFT;
 	pmdp = pmd_offset(&pud, ea);
 	pmd  = READ_ONCE(*pmdp);
+
 	/*
-	 * A hugepage collapse is captured by pmd_none, because
-	 * it mark the pmd none and do a hpte invalidate.
+	 * A hugepage collapse is captured by this condition, see
+	 * pmdp_collapse_flush.
 	 */
 	if (pmd_none(pmd))
 		return NULL;
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * A hugepage split is captured by this condition, see
+	 * pmdp_invalidate.
+	 *
+	 * Huge page modification can be caught here too.
+	 */
+	if (pmd_is_serializing(pmd))
+		return NULL;
+#endif
+
 	if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
 		if (is_thp)
 			*is_thp = true;