1 files changed, 54 insertions, 87 deletions

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 0e67f1721a3d..6b9bb58a414f 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -106,6 +106,18 @@
 #define ARM_LPAE_PTE_HAP_FAULT		(((arm_lpae_iopte)0) << 6)
 #define ARM_LPAE_PTE_HAP_READ		(((arm_lpae_iopte)1) << 6)
 #define ARM_LPAE_PTE_HAP_WRITE		(((arm_lpae_iopte)2) << 6)
+/*
+ * For !FWB these code to:
+ *  1111 = Normal outer write back cachable / Inner Write Back Cachable
+ *         Permit S1 to override
+ *  0101 = Normal Non-cachable / Inner Non-cachable
+ *  0001 = Device / Device-nGnRE
+ * For S2FWB these code:
+ *  0110 Force Normal Write Back
+ *  0101 Normal* is forced Normal-NC, Device unchanged
+ *  0001 Force Device-nGnRE
+ */
+#define ARM_LPAE_PTE_MEMATTR_FWB_WB	(((arm_lpae_iopte)0x6) << 2)
 #define ARM_LPAE_PTE_MEMATTR_OIWB	(((arm_lpae_iopte)0xf) << 2)
 #define ARM_LPAE_PTE_MEMATTR_NC		(((arm_lpae_iopte)0x5) << 2)
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
@@ -199,6 +211,18 @@ static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte,
 	return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4);
 }
 
+/*
+ * Convert an index returned by ARM_LPAE_PGD_IDX(), which can point into
+ * a concatenated PGD, into the maximum number of entries that can be
+ * mapped in the same table page.
+ */
+static inline int arm_lpae_max_entries(int i, struct arm_lpae_io_pgtable *data)
+{
+	int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data);
+
+	return ptes_per_table - (i & (ptes_per_table - 1));
+}
+
 static bool selftest_running = false;
 
 static dma_addr_t __arm_lpae_dma_addr(void *pages)
@@ -390,7 +414,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 
 	/* If we can install a leaf entry at this level, then do so */
 	if (size == block_size) {
-		max_entries = ARM_LPAE_PTES_PER_TABLE(data) - map_idx_start;
+		max_entries = arm_lpae_max_entries(map_idx_start, data);
 		num_entries = min_t(int, pgcount, max_entries);
 		ret = arm_lpae_init_pte(data, iova, paddr, prot, lvl, num_entries, ptep);
 		if (!ret)
@@ -458,12 +482,16 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 	 */
 	if (data->iop.fmt == ARM_64_LPAE_S2 ||
 	    data->iop.fmt == ARM_32_LPAE_S2) {
-		if (prot & IOMMU_MMIO)
+		if (prot & IOMMU_MMIO) {
 			pte |= ARM_LPAE_PTE_MEMATTR_DEV;
-		else if (prot & IOMMU_CACHE)
-			pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
-		else
+		} else if (prot & IOMMU_CACHE) {
+			if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_S2FWB)
+				pte |= ARM_LPAE_PTE_MEMATTR_FWB_WB;
+			else
+				pte |= ARM_LPAE_PTE_MEMATTR_OIWB;
+		} else {
 			pte |= ARM_LPAE_PTE_MEMATTR_NC;
+		}
 	} else {
 		if (prot & IOMMU_MMIO)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
@@ -569,66 +597,6 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
 	kfree(data);
 }
 
-static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
-				       struct iommu_iotlb_gather *gather,
-				       unsigned long iova, size_t size,
-				       arm_lpae_iopte blk_pte, int lvl,
-				       arm_lpae_iopte *ptep, size_t pgcount)
-{
-	struct io_pgtable_cfg *cfg = &data->iop.cfg;
-	arm_lpae_iopte pte, *tablep;
-	phys_addr_t blk_paddr;
-	size_t tablesz = ARM_LPAE_GRANULE(data);
-	size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
-	int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data);
-	int i, unmap_idx_start = -1, num_entries = 0, max_entries;
-
-	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
-		return 0;
-
-	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie);
-	if (!tablep)
-		return 0; /* Bytes unmapped */
-
-	if (size == split_sz) {
-		unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
-		max_entries = ptes_per_table - unmap_idx_start;
-		num_entries = min_t(int, pgcount, max_entries);
-	}
-
-	blk_paddr = iopte_to_paddr(blk_pte, data);
-	pte = iopte_prot(blk_pte);
-
-	for (i = 0; i < ptes_per_table; i++, blk_paddr += split_sz) {
-		/* Unmap! */
-		if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries))
-			continue;
-
-		__arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]);
-	}
-
-	pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
-	if (pte != blk_pte) {
-		__arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie);
-		/*
-		 * We may race against someone unmapping another part of this
-		 * block, but anything else is invalid. We can't misinterpret
-		 * a page entry here since we're never at the last level.
-		 */
-		if (iopte_type(pte) != ARM_LPAE_PTE_TYPE_TABLE)
-			return 0;
-
-		tablep = iopte_deref(pte, data);
-	} else if (unmap_idx_start >= 0) {
-		for (i = 0; i < num_entries; i++)
-			io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size);
-
-		return num_entries * size;
-	}
-
-	return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl, tablep);
-}
-
 static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 			       struct iommu_iotlb_gather *gather,
 			       unsigned long iova, size_t size, size_t pgcount,
@@ -650,7 +618,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 
 	/* If the size matches this level, we're in the right place */
 	if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
-		max_entries = ARM_LPAE_PTES_PER_TABLE(data) - unmap_idx_start;
+		max_entries = arm_lpae_max_entries(unmap_idx_start, data);
 		num_entries = min_t(int, pgcount, max_entries);
 
 		/* Find and handle non-leaf entries */
@@ -678,12 +646,8 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 
 		return i * size;
 	} else if (iopte_leaf(pte, lvl, iop->fmt)) {
-		/*
-		 * Insert a table at the next level to map the old region,
-		 * minus the part we want to unmap
-		 */
-		return arm_lpae_split_blk_unmap(data, gather, iova, size, pte,
-						lvl + 1, ptep, pgcount);
+		WARN_ONCE(true, "Unmap of a partial large IOPTE is not allowed");
+		return 0;
 	}
 
 	/* Keep on walkin' */
@@ -1035,8 +999,7 @@ 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;
 
-	/* The NS quirk doesn't apply at stage 2 */
-	if (cfg->quirks)
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_S2FWB))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -1347,19 +1310,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 			iova += SZ_1G;
 		}
 
-		/* Partial unmap */
-		size = 1UL << __ffs(cfg->pgsize_bitmap);
-		if (ops->unmap_pages(ops, SZ_1G + size, size, 1, NULL) != size)
-			return __FAIL(ops, i);
-
-		/* Remap of partial unmap */
-		if (ops->map_pages(ops, SZ_1G + size, size, size, 1,
-				   IOMMU_READ, GFP_KERNEL, &mapped))
-			return __FAIL(ops, i);
-
-		if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42))
-			return __FAIL(ops, i);
-
 		/* Full unmap */
 		iova = 0;
 		for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
@@ -1382,6 +1332,23 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
 			iova += SZ_1G;
 		}
 
+		/*
+		 * Map/unmap the last largest supported page of the IAS, this can
+		 * trigger corner cases in the concatednated page tables.
+		 */
+		mapped = 0;
+		size = 1UL << __fls(cfg->pgsize_bitmap);
+		iova = (1UL << cfg->ias) - size;
+		if (ops->map_pages(ops, iova, iova, size, 1,
+				   IOMMU_READ | IOMMU_WRITE |
+				   IOMMU_NOEXEC | IOMMU_CACHE,
+				   GFP_KERNEL, &mapped))
+			return __FAIL(ops, i);
+		if (mapped != size)
+			return __FAIL(ops, i);
+		if (ops->unmap_pages(ops, iova, size, 1, NULL) != size)
+			return __FAIL(ops, i);
+
 		free_io_pgtable_ops(ops);
 	}