1 files changed, 180 insertions, 103 deletions

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 6b9bb58a414f..96425e92f313 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -13,6 +13,7 @@
 #include <linux/bitops.h>
 #include <linux/io-pgtable.h>
 #include <linux/kernel.h>
+#include <linux/device/faux.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -223,7 +224,33 @@ static inline int arm_lpae_max_entries(int i, struct arm_lpae_io_pgtable *data)
 	return ptes_per_table - (i & (ptes_per_table - 1));
 }
 
-static bool selftest_running = false;
+/*
+ * Check if concatenated PGDs are mandatory according to Arm DDI0487 (K.a)
+ * 1) R_DXBSH: For 16KB, and 48-bit input size, use level 1 instead of 0.
+ * 2) R_SRKBC: After de-ciphering the table for PA size and valid initial lookup
+ *   a) 40 bits PA size with 4K: use level 1 instead of level 0 (2 tables for ias = oas)
+ *   b) 40 bits PA size with 16K: use level 2 instead of level 1 (16 tables for ias = oas)
+ *   c) 42 bits PA size with 4K: use level 1 instead of level 0 (8 tables for ias = oas)
+ *   d) 48 bits PA size with 16K: use level 1 instead of level 0 (2 tables for ias = oas)
+ */
+static inline bool arm_lpae_concat_mandatory(struct io_pgtable_cfg *cfg,
+					     struct arm_lpae_io_pgtable *data)
+{
+	unsigned int ias = cfg->ias;
+	unsigned int oas = cfg->oas;
+
+	/* Covers 1 and 2.d */
+	if ((ARM_LPAE_GRANULE(data) == SZ_16K) && (data->start_level == 0))
+		return (oas == 48) || (ias == 48);
+
+	/* Covers 2.a and 2.c */
+	if ((ARM_LPAE_GRANULE(data) == SZ_4K) && (data->start_level == 0))
+		return (oas == 40) || (oas == 42);
+
+	/* Case 2.b */
+	return (ARM_LPAE_GRANULE(data) == SZ_16K) &&
+	       (data->start_level == 1) && (oas == 40);
+}
 
 static dma_addr_t __arm_lpae_dma_addr(void *pages)
 {
@@ -235,16 +262,20 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 				    void *cookie)
 {
 	struct device *dev = cfg->iommu_dev;
-	int order = get_order(size);
+	size_t alloc_size;
 	dma_addr_t dma;
 	void *pages;
 
-	VM_BUG_ON((gfp & __GFP_HIGHMEM));
-
+	/*
+	 * For very small starting-level translation tables the HW requires a
+	 * minimum alignment of at least 64 to cover all cases.
+	 */
+	alloc_size = max(size, 64);
 	if (cfg->alloc)
-		pages = cfg->alloc(cookie, size, gfp);
+		pages = cfg->alloc(cookie, alloc_size, gfp);
 	else
-		pages = iommu_alloc_pages_node(dev_to_node(dev), gfp, order);
+		pages = iommu_alloc_pages_node_sz(dev_to_node(dev), gfp,
+						  alloc_size);
 
 	if (!pages)
 		return NULL;
@@ -272,7 +303,7 @@ out_free:
 	if (cfg->free)
 		cfg->free(cookie, pages, size);
 	else
-		iommu_free_pages(pages, order);
+		iommu_free_pages(pages);
 
 	return NULL;
 }
@@ -288,7 +319,7 @@ static void __arm_lpae_free_pages(void *pages, size_t size,
 	if (cfg->free)
 		cfg->free(cookie, pages, size);
 	else
-		iommu_free_pages(pages, get_order(size));
+		iommu_free_pages(pages);
 }
 
 static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
@@ -343,7 +374,7 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 	for (i = 0; i < num_entries; i++)
 		if (iopte_leaf(ptep[i], lvl, data->iop.fmt)) {
 			/* We require an unmap first */
-			WARN_ON(!selftest_running);
+			WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN));
 			return -EEXIST;
 		} else if (iopte_type(ptep[i]) == ARM_LPAE_PTE_TYPE_TABLE) {
 			/*
@@ -445,7 +476,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 		cptep = iopte_deref(pte, data);
 	} else if (pte) {
 		/* We require an unmap first */
-		WARN_ON(!selftest_running);
+		WARN_ON(!(cfg->quirks & IO_PGTABLE_QUIRK_NO_WARN));
 		return -EEXIST;
 	}
 
@@ -613,8 +644,10 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 	unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
 	ptep += unmap_idx_start;
 	pte = READ_ONCE(*ptep);
-	if (WARN_ON(!pte))
-		return 0;
+	if (!pte) {
+		WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN));
+		return -ENOENT;
+	}
 
 	/* If the size matches this level, we're in the right place */
 	if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
@@ -624,8 +657,10 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 		/* Find and handle non-leaf entries */
 		for (i = 0; i < num_entries; i++) {
 			pte = READ_ONCE(ptep[i]);
-			if (WARN_ON(!pte))
+			if (!pte) {
+				WARN_ON(!(data->iop.cfg.quirks & IO_PGTABLE_QUIRK_NO_WARN));
 				break;
+			}
 
 			if (!iopte_leaf(pte, lvl, iop->fmt)) {
 				__arm_lpae_clear_pte(&ptep[i], &iop->cfg, 1);
@@ -676,85 +711,107 @@ static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iov
 				data->start_level, ptep);
 }
 
+struct io_pgtable_walk_data {
+	struct io_pgtable		*iop;
+	void				*data;
+	int (*visit)(struct io_pgtable_walk_data *walk_data, int lvl,
+		     arm_lpae_iopte *ptep, size_t size);
+	unsigned long			flags;
+	u64				addr;
+	const u64			end;
+};
+
+static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
+				 struct io_pgtable_walk_data *walk_data,
+				 arm_lpae_iopte *ptep,
+				 int lvl);
+
+struct iova_to_phys_data {
+	arm_lpae_iopte pte;
+	int lvl;
+};
+
+static int visit_iova_to_phys(struct io_pgtable_walk_data *walk_data, int lvl,
+			      arm_lpae_iopte *ptep, size_t size)
+{
+	struct iova_to_phys_data *data = walk_data->data;
+	data->pte = *ptep;
+	data->lvl = lvl;
+	return 0;
+}
+
 static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 					 unsigned long iova)
 {
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	arm_lpae_iopte pte, *ptep = data->pgd;
-	int lvl = data->start_level;
-
-	do {
-		/* Valid IOPTE pointer? */
-		if (!ptep)
-			return 0;
-
-		/* Grab the IOPTE we're interested in */
-		ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
-		pte = READ_ONCE(*ptep);
-
-		/* Valid entry? */
-		if (!pte)
-			return 0;
+	struct iova_to_phys_data d;
+	struct io_pgtable_walk_data walk_data = {
+		.data = &d,
+		.visit = visit_iova_to_phys,
+		.addr = iova,
+		.end = iova + 1,
+	};
+	int ret;
 
-		/* Leaf entry? */
-		if (iopte_leaf(pte, lvl, data->iop.fmt))
-			goto found_translation;
+	ret = __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
+	if (ret)
+		return 0;
 
-		/* Take it to the next level */
-		ptep = iopte_deref(pte, data);
-	} while (++lvl < ARM_LPAE_MAX_LEVELS);
+	iova &= (ARM_LPAE_BLOCK_SIZE(d.lvl, data) - 1);
+	return iopte_to_paddr(d.pte, data) | iova;
+}
 
-	/* Ran out of page tables to walk */
+static int visit_pgtable_walk(struct io_pgtable_walk_data *walk_data, int lvl,
+			      arm_lpae_iopte *ptep, size_t size)
+{
+	struct arm_lpae_io_pgtable_walk_data *data = walk_data->data;
+	data->ptes[lvl] = *ptep;
 	return 0;
-
-found_translation:
-	iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1);
-	return iopte_to_paddr(pte, data) | iova;
 }
 
-struct io_pgtable_walk_data {
-	struct iommu_dirty_bitmap	*dirty;
-	unsigned long			flags;
-	u64				addr;
-	const u64			end;
-};
+static int arm_lpae_pgtable_walk(struct io_pgtable_ops *ops, unsigned long iova,
+				 void *wd)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_walk_data walk_data = {
+		.data = wd,
+		.visit = visit_pgtable_walk,
+		.addr = iova,
+		.end = iova + 1,
+	};
 
-static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
-				       struct io_pgtable_walk_data *walk_data,
-				       arm_lpae_iopte *ptep,
-				       int lvl);
+	return __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
+}
 
-static int io_pgtable_visit_dirty(struct arm_lpae_io_pgtable *data,
-				  struct io_pgtable_walk_data *walk_data,
-				  arm_lpae_iopte *ptep, int lvl)
+static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
+			    struct io_pgtable_walk_data *walk_data,
+			    arm_lpae_iopte *ptep, int lvl)
 {
 	struct io_pgtable *iop = &data->iop;
 	arm_lpae_iopte pte = READ_ONCE(*ptep);
 
-	if (iopte_leaf(pte, lvl, iop->fmt)) {
-		size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	int ret = walk_data->visit(walk_data, lvl, ptep, size);
+	if (ret)
+		return ret;
 
-		if (iopte_writeable_dirty(pte)) {
-			iommu_dirty_bitmap_record(walk_data->dirty,
-						  walk_data->addr, size);
-			if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR))
-				iopte_set_writeable_clean(ptep);
-		}
+	if (iopte_leaf(pte, lvl, iop->fmt)) {
 		walk_data->addr += size;
 		return 0;
 	}
 
-	if (WARN_ON(!iopte_table(pte, lvl)))
+	if (!iopte_table(pte, lvl)) {
 		return -EINVAL;
+	}
 
 	ptep = iopte_deref(pte, data);
-	return __arm_lpae_iopte_walk_dirty(data, walk_data, ptep, lvl + 1);
+	return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1);
 }
 
-static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
-				       struct io_pgtable_walk_data *walk_data,
-				       arm_lpae_iopte *ptep,
-				       int lvl)
+static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
+				 struct io_pgtable_walk_data *walk_data,
+				 arm_lpae_iopte *ptep,
+				 int lvl)
 {
 	u32 idx;
 	int max_entries, ret;
@@ -769,7 +826,7 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
 
 	for (idx = ARM_LPAE_LVL_IDX(walk_data->addr, lvl, data);
 	     (idx < max_entries) && (walk_data->addr < walk_data->end); ++idx) {
-		ret = io_pgtable_visit_dirty(data, walk_data, ptep + idx, lvl);
+		ret = io_pgtable_visit(data, walk_data, ptep + idx, lvl);
 		if (ret)
 			return ret;
 	}
@@ -777,6 +834,23 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
 	return 0;
 }
 
+static int visit_dirty(struct io_pgtable_walk_data *walk_data, int lvl,
+		       arm_lpae_iopte *ptep, size_t size)
+{
+	struct iommu_dirty_bitmap *dirty = walk_data->data;
+
+	if (!iopte_leaf(*ptep, lvl, walk_data->iop->fmt))
+		return 0;
+
+	if (iopte_writeable_dirty(*ptep)) {
+		iommu_dirty_bitmap_record(dirty, walk_data->addr, size);
+		if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR))
+			iopte_set_writeable_clean(ptep);
+	}
+
+	return 0;
+}
+
 static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
 					 unsigned long iova, size_t size,
 					 unsigned long flags,
@@ -785,7 +859,9 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	struct io_pgtable_walk_data walk_data = {
-		.dirty = dirty,
+		.iop = &data->iop,
+		.data = dirty,
+		.visit = visit_dirty,
 		.flags = flags,
 		.addr = iova,
 		.end = iova + size,
@@ -800,7 +876,7 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
 	if (data->iop.fmt != ARM_64_LPAE_S1)
 		return -EINVAL;
 
-	return __arm_lpae_iopte_walk_dirty(data, &walk_data, ptep, lvl);
+	return __arm_lpae_iopte_walk(data, &walk_data, ptep, lvl);
 }
 
 static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
@@ -882,6 +958,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 		.unmap_pages	= arm_lpae_unmap_pages,
 		.iova_to_phys	= arm_lpae_iova_to_phys,
 		.read_and_clear_dirty = arm_lpae_read_and_clear_dirty,
+		.pgtable_walk	= arm_lpae_pgtable_walk,
 	};
 
 	return data;
@@ -898,7 +975,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_ARM_TTBR1 |
 			    IO_PGTABLE_QUIRK_ARM_OUTER_WBWA |
-			    IO_PGTABLE_QUIRK_ARM_HD))
+			    IO_PGTABLE_QUIRK_ARM_HD |
+			    IO_PGTABLE_QUIRK_NO_WARN))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -999,25 +1077,20 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	struct arm_lpae_io_pgtable *data;
 	typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr;
 
-	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_S2FWB))
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_S2FWB |
+			    IO_PGTABLE_QUIRK_NO_WARN))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
 	if (!data)
 		return NULL;
 
-	/*
-	 * Concatenate PGDs at level 1 if possible in order to reduce
-	 * the depth of the stage-2 walk.
-	 */
-	if (data->start_level == 0) {
-		unsigned long pgd_pages;
-
-		pgd_pages = ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte);
-		if (pgd_pages <= ARM_LPAE_S2_MAX_CONCAT_PAGES) {
-			data->pgd_bits += data->bits_per_level;
-			data->start_level++;
-		}
+	if (arm_lpae_concat_mandatory(cfg, data)) {
+		if (WARN_ON((ARM_LPAE_PGD_SIZE(data) / sizeof(arm_lpae_iopte)) >
+			    ARM_LPAE_S2_MAX_CONCAT_PAGES))
+			return NULL;
+		data->pgd_bits += data->bits_per_level;
+		data->start_level++;
 	}
 
 	/* VTCR */
@@ -1246,7 +1319,6 @@ static void __init arm_lpae_dump_ops(struct io_pgtable_ops *ops)
 #define __FAIL(ops, i)	({						\
 		WARN(1, "selftest: test failed for fmt idx %d\n", (i));	\
 		arm_lpae_dump_ops(ops);					\
-		selftest_running = false;				\
 		-EFAULT;						\
 })
 
@@ -1262,8 +1334,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 	size_t size, mapped;
 	struct io_pgtable_ops *ops;
 
-	selftest_running = true;
-
 	for (i = 0; i < ARRAY_SIZE(fmts); ++i) {
 		cfg_cookie = cfg;
 		ops = alloc_io_pgtable_ops(fmts[i], cfg, cfg);
@@ -1352,7 +1422,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 		free_io_pgtable_ops(ops);
 	}
 
-	selftest_running = false;
 	return 0;
 }
 
@@ -1364,36 +1433,44 @@ static int __init arm_lpae_do_selftests(void)
 		SZ_64K | SZ_512M,
 	};
 
-	static const unsigned int ias[] __initconst = {
+	static const unsigned int address_size[] __initconst = {
 		32, 36, 40, 42, 44, 48,
 	};
 
-	int i, j, pass = 0, fail = 0;
-	struct device dev;
+	int i, j, k, pass = 0, fail = 0;
+	struct faux_device *dev;
 	struct io_pgtable_cfg cfg = {
 		.tlb = &dummy_tlb_ops,
-		.oas = 48,
 		.coherent_walk = true,
-		.iommu_dev = &dev,
+		.quirks = IO_PGTABLE_QUIRK_NO_WARN,
 	};
 
-	/* __arm_lpae_alloc_pages() merely needs dev_to_node() to work */
-	set_dev_node(&dev, NUMA_NO_NODE);
+	dev = faux_device_create("io-pgtable-test", NULL, 0);
+	if (!dev)
+		return -ENOMEM;
+
+	cfg.iommu_dev = &dev->dev;
 
 	for (i = 0; i < ARRAY_SIZE(pgsize); ++i) {
-		for (j = 0; j < ARRAY_SIZE(ias); ++j) {
-			cfg.pgsize_bitmap = pgsize[i];
-			cfg.ias = ias[j];
-			pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u\n",
-				pgsize[i], ias[j]);
-			if (arm_lpae_run_tests(&cfg))
-				fail++;
-			else
-				pass++;
+		for (j = 0; j < ARRAY_SIZE(address_size); ++j) {
+			/* Don't use ias > oas as it is not valid for stage-2. */
+			for (k = 0; k <= j; ++k) {
+				cfg.pgsize_bitmap = pgsize[i];
+				cfg.ias = address_size[k];
+				cfg.oas = address_size[j];
+				pr_info("selftest: pgsize_bitmap 0x%08lx, IAS %u OAS %u\n",
+					pgsize[i], cfg.ias, cfg.oas);
+				if (arm_lpae_run_tests(&cfg))
+					fail++;
+				else
+					pass++;
+			}
 		}
 	}
 
 	pr_info("selftest: completed with %d PASS %d FAIL\n", pass, fail);
+	faux_device_destroy(dev);
+
 	return fail ? -EFAULT : 0;
 }
 subsys_initcall(arm_lpae_do_selftests);