Merge branch 'fixes' into next

Merge our fixes branch from the 4.18 cycle to resolve some minor
conflicts.

arch/powerpc/Makefile

@@ -237,6 +237,7 @@ endif
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 cpu-as-$(CONFIG_PPC_E500MC)	+= $(call as-option,-Wa$(comma)-me500mc)
 

arch/powerpc/include/asm/mmu_context.h

@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
@@ -143,23 +143,32 @@ 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
-	 * local and the nMMU and/or PSL need to be cleaned up.
-	 * Should be rare enough so that it's acceptable.
+	 * When removing the last copro, we need to broadcast a global
+	 * flush of the full mm, as the next TLBI may be local and the
+	 * nMMU and/or PSL need to be cleaned up.
+	 *
+	 * Both the 'copros' and 'active_cpus' counts are looked at in
+	 * flush_all_mm() to determine the scope (local/global) of the
+	 * TLBIs, so we need to flush first before decrementing
+	 * 'copros'. If this API is used by several callers for the
+	 * same context, it can lead to over-flushing. It's hopefully
+	 * not common enough to be a problem.
 	 *
 	 * Skip on hash, as we don't know how to do the proper flush
 	 * for the time being. Invalidations will remain global if
-	 * used on hash.
+	 * used on hash. Note that we can't drop 'copros' either, as
+	 * it could make some invalidations local with no flush
+	 * in-between.
 	 */
-	if (c == 0 && radix_enabled()) {
+	if (radix_enabled()) {
 		flush_all_mm(mm);
+
+		c = atomic_dec_if_positive(&mm->context.copros);
+		/* Detect imbalance between add and remove */
+		WARN_ON(c < 0);
+
+		if (c == 0)
 			dec_mm_active_cpus(mm);
 	}
 }

arch/powerpc/kernel/idle_book3s.S

@@ -146,7 +146,9 @@ power9_restore_additional_sprs:
 	mtspr	SPRN_MMCR1, r4
 
 	ld	r3, STOP_MMCR2(r13)
+	ld	r4, PACA_SPRG_VDSO(r13)
 	mtspr	SPRN_MMCR2, r3
+	mtspr	SPRN_SPRG3, r4
 	blr
 
 /*

arch/powerpc/kvm/book3s_64_vio.c

@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
 		return H_HARDWARE;
 
 	if (mm_iommu_mapped_inc(mem))

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -275,7 +275,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (!mem)
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+			&hpa)))
 		return H_HARDWARE;
 
 	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
@@ -461,7 +462,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
 		if (mem)
-			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
 	}
 
 	if (!prereg) {

arch/powerpc/mm/mmu_context_iommu.c

@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
@@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t {
 	struct rcu_head rcu;
 	unsigned long used;
 	atomic64_t mapped;
+	unsigned int pageshift;
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
@@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
+	unsigned int pageshift;
+	unsigned long flags;
 	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
@@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	/*
+	 * For a starting point for a maximum page size calculation
+	 * we use @ua and @entries natural alignment to allow IOMMU pages
+	 * smaller than huge pages but still bigger than PAGE_SIZE.
+	 */
+	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
 	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
 	if (!mem->hpas) {
 		kfree(mem);
@@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 			}
 		}
 populate:
+		pageshift = PAGE_SHIFT;
+		if (PageCompound(page)) {
+			pte_t *pte;
+			struct page *head = compound_head(page);
+			unsigned int compshift = compound_order(head);
+
+			local_irq_save(flags); /* disables as well */
+			pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
+			local_irq_restore(flags);
+
+			/* Double check it is still the same pinned page */
+			if (pte && pte_page(*pte) == head &&
+					pageshift == compshift)
+				pageshift = max_t(unsigned int, pageshift,
+						PAGE_SHIFT);
+		}
+		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
@@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 EXPORT_SYMBOL_GPL(mm_iommu_find);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	u64 *va = &mem->hpas[entry];
@@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	*hpa = *va | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
 long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	void *va = &mem->hpas[entry];
@@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	pa = (void *) vmalloc_to_phys(va);
 	if (!pa)
 		return -EFAULT;

arch/powerpc/xmon/xmon.c

@@ -2735,7 +2735,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 {
 	int nr, dotted;
 	unsigned long first_adr;
-	unsigned long inst, last_inst = 0;
+	unsigned int inst, last_inst = 0;
 	unsigned char val[4];
 
 	dotted = 0;
@@ -2759,7 +2759,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 		dotted = 0;
 		last_inst = inst;
 		if (praddr)
-			printf(REG"  %.8lx", adr, inst);
+			printf(REG"  %.8x", adr, inst);
 		printf("\t");
 		dump_func(inst, adr);
 		printf("\n");

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -419,17 +419,17 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 }
 
 static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
-		unsigned long tce, unsigned long size,
+		unsigned long tce, unsigned long shift,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(container->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
 	if (!mem)
 		return -EINVAL;
 
-	ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+	ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
 	if (ret)
 		return -EINVAL;
 
@@ -450,7 +450,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container,
 		return;
 
 	ret = tce_iommu_prereg_ua_to_hpa(container, be64_to_cpu(*pua),
-			IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+			tbl->it_page_shift, &hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %llx at #%lx was not cached, ret=%d\n",
 				__func__, be64_to_cpu(*pua), entry, ret);
@@ -566,7 +566,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry + i);
 
 		ret = tce_iommu_prereg_ua_to_hpa(container,
-				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+				tce, tbl->it_page_shift, &hpa, &mem);
 		if (ret)
 			break;