3 files changed, 108 insertions, 67 deletions

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 7ef12a3ace3a..8f19c8f9d660 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -68,9 +68,12 @@ static struct airq_struct zpci_airq = {
 	.isc = PCI_ISC,
 };
 
-/* I/O Map */
+#define ZPCI_IOMAP_ENTRIES						\
+	min(((unsigned long) CONFIG_PCI_NR_FUNCTIONS * PCI_BAR_COUNT),	\
+	    ZPCI_IOMAP_MAX_ENTRIES)
+
 static DEFINE_SPINLOCK(zpci_iomap_lock);
-static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+static unsigned long *zpci_iomap_bitmap;
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
@@ -265,27 +268,20 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev,
 			      unsigned long max)
 {
 	struct zpci_dev *zdev =	to_zpci(pdev);
-	u64 addr;
 	int idx;
 
-	if ((bar & 7) != bar)
+	if (!pci_resource_len(pdev, bar))
 		return NULL;
 
 	idx = zdev->bars[bar].map_idx;
 	spin_lock(&zpci_iomap_lock);
-	if (zpci_iomap_start[idx].count++) {
-		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
-		       zpci_iomap_start[idx].bar != bar);
-	} else {
-		zpci_iomap_start[idx].fh = zdev->fh;
-		zpci_iomap_start[idx].bar = bar;
-	}
 	/* Detect overrun */
-	BUG_ON(!zpci_iomap_start[idx].count);
+	WARN_ON(!++zpci_iomap_start[idx].count);
+	zpci_iomap_start[idx].fh = zdev->fh;
+	zpci_iomap_start[idx].bar = bar;
 	spin_unlock(&zpci_iomap_lock);
 
-	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
-	return (void __iomem *) addr + offset;
+	return (void __iomem *) ZPCI_ADDR(idx) + offset;
 }
 EXPORT_SYMBOL(pci_iomap_range);
 
@@ -297,12 +293,11 @@ EXPORT_SYMBOL(pci_iomap);
 
 void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 {
-	unsigned int idx;
+	unsigned int idx = ZPCI_IDX(addr);
 
-	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
 	spin_lock(&zpci_iomap_lock);
 	/* Detect underrun */
-	BUG_ON(!zpci_iomap_start[idx].count);
+	WARN_ON(!zpci_iomap_start[idx].count);
 	if (!--zpci_iomap_start[idx].count) {
 		zpci_iomap_start[idx].fh = 0;
 		zpci_iomap_start[idx].bar = 0;
@@ -544,15 +539,15 @@ static void zpci_irq_exit(void)
 
 static int zpci_alloc_iomap(struct zpci_dev *zdev)
 {
-	int entry;
+	unsigned long entry;
 
 	spin_lock(&zpci_iomap_lock);
-	entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
-	if (entry == ZPCI_IOMAP_MAX_ENTRIES) {
+	entry = find_first_zero_bit(zpci_iomap_bitmap, ZPCI_IOMAP_ENTRIES);
+	if (entry == ZPCI_IOMAP_ENTRIES) {
 		spin_unlock(&zpci_iomap_lock);
 		return -ENOSPC;
 	}
-	set_bit(entry, zpci_iomap);
+	set_bit(entry, zpci_iomap_bitmap);
 	spin_unlock(&zpci_iomap_lock);
 	return entry;
 }
@@ -561,7 +556,7 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 {
 	spin_lock(&zpci_iomap_lock);
 	memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry));
-	clear_bit(entry, zpci_iomap);
+	clear_bit(entry, zpci_iomap_bitmap);
 	spin_unlock(&zpci_iomap_lock);
 }
 
@@ -611,8 +606,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev,
 		if (zdev->bars[i].val & 4)
 			flags |= IORESOURCE_MEM_64;
 
-		addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48);
-
+		addr = ZPCI_ADDR(entry);
 		size = 1UL << zdev->bars[i].size;
 
 		res = __alloc_res(zdev, addr, size, flags);
@@ -701,8 +695,7 @@ static int zpci_restore(struct device *dev)
 		goto out;
 
 	zpci_map_resources(pdev);
-	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
-			   zdev->start_dma + zdev->iommu_size - 1,
+	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 			   (u64) zdev->dma_table);
 
 out:
@@ -874,23 +867,30 @@ static int zpci_mem_init(void)
 	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
 				16, 0, NULL);
 	if (!zdev_fmb_cache)
-		goto error_zdev;
+		goto error_fmb;
 
-	/* TODO: use realloc */
-	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
-				   GFP_KERNEL);
+	zpci_iomap_start = kcalloc(ZPCI_IOMAP_ENTRIES,
+				   sizeof(*zpci_iomap_start), GFP_KERNEL);
 	if (!zpci_iomap_start)
 		goto error_iomap;
-	return 0;
 
+	zpci_iomap_bitmap = kcalloc(BITS_TO_LONGS(ZPCI_IOMAP_ENTRIES),
+				    sizeof(*zpci_iomap_bitmap), GFP_KERNEL);
+	if (!zpci_iomap_bitmap)
+		goto error_iomap_bitmap;
+
+	return 0;
+error_iomap_bitmap:
+	kfree(zpci_iomap_start);
 error_iomap:
 	kmem_cache_destroy(zdev_fmb_cache);
-error_zdev:
+error_fmb:
 	return -ENOMEM;
 }
 
 static void zpci_mem_exit(void)
 {
+	kfree(zpci_iomap_bitmap);
 	kfree(zpci_iomap_start);
 	kmem_cache_destroy(zdev_fmb_cache);
 }
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 37d10f74425a..4638b93c7632 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -33,7 +33,7 @@ unsigned long *dma_alloc_cpu_table(void)
 		return NULL;
 
 	for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++)
-		*entry = ZPCI_TABLE_INVALID | ZPCI_TABLE_PROTECTED;
+		*entry = ZPCI_TABLE_INVALID;
 	return table;
 }
 
@@ -51,7 +51,7 @@ static unsigned long *dma_alloc_page_table(void)
 		return NULL;
 
 	for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++)
-		*entry = ZPCI_PTE_INVALID | ZPCI_TABLE_PROTECTED;
+		*entry = ZPCI_PTE_INVALID;
 	return table;
 }
 
@@ -95,7 +95,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *entry)
 	return pto;
 }
 
-static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
+unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
 {
 	unsigned long *sto, *pto;
 	unsigned int rtx, sx, px;
@@ -114,20 +114,10 @@ static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr
 	return &pto[px];
 }
 
-void dma_update_cpu_trans(unsigned long *dma_table, void *page_addr,
-			  dma_addr_t dma_addr, int flags)
+void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags)
 {
-	unsigned long *entry;
-
-	entry = dma_walk_cpu_trans(dma_table, dma_addr);
-	if (!entry) {
-		WARN_ON_ONCE(1);
-		return;
-	}
-
 	if (flags & ZPCI_PTE_INVALID) {
 		invalidate_pt_entry(entry);
-		return;
 	} else {
 		set_pt_pfaa(entry, page_addr);
 		validate_pt_entry(entry);
@@ -146,18 +136,25 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
 	u8 *page_addr = (u8 *) (pa & PAGE_MASK);
 	dma_addr_t start_dma_addr = dma_addr;
 	unsigned long irq_flags;
+	unsigned long *entry;
 	int i, rc = 0;
 
 	if (!nr_pages)
 		return -EINVAL;
 
 	spin_lock_irqsave(&zdev->dma_table_lock, irq_flags);
-	if (!zdev->dma_table)
+	if (!zdev->dma_table) {
+		rc = -EINVAL;
 		goto no_refresh;
+	}
 
 	for (i = 0; i < nr_pages; i++) {
-		dma_update_cpu_trans(zdev->dma_table, page_addr, dma_addr,
-				     flags);
+		entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+		if (!entry) {
+			rc = -ENOMEM;
+			goto undo_cpu_trans;
+		}
+		dma_update_cpu_trans(entry, page_addr, flags);
 		page_addr += PAGE_SIZE;
 		dma_addr += PAGE_SIZE;
 	}
@@ -176,6 +173,18 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
 
 	rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr,
 				nr_pages * PAGE_SIZE);
+undo_cpu_trans:
+	if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) {
+		flags = ZPCI_PTE_INVALID;
+		while (i-- > 0) {
+			page_addr -= PAGE_SIZE;
+			dma_addr -= PAGE_SIZE;
+			entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+			if (!entry)
+				break;
+			dma_update_cpu_trans(entry, page_addr, flags);
+		}
+	}
 
 no_refresh:
 	spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
@@ -260,6 +269,16 @@ out:
 	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
 }
 
+static inline void zpci_err_dma(unsigned long rc, unsigned long addr)
+{
+	struct {
+		unsigned long rc;
+		unsigned long addr;
+	} __packed data = {rc, addr};
+
+	zpci_err_hex(&data, sizeof(data));
+}
+
 static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 				     unsigned long offset, size_t size,
 				     enum dma_data_direction direction,
@@ -270,33 +289,40 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 	unsigned long pa = page_to_phys(page) + offset;
 	int flags = ZPCI_PTE_VALID;
 	dma_addr_t dma_addr;
+	int ret;
 
 	/* This rounds up number of pages based on size and offset */
 	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
 	iommu_page_index = dma_alloc_iommu(zdev, nr_pages);
-	if (iommu_page_index == -1)
+	if (iommu_page_index == -1) {
+		ret = -ENOSPC;
 		goto out_err;
+	}
 
 	/* Use rounded up size */
 	size = nr_pages * PAGE_SIZE;
 
 	dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE;
-	if (dma_addr + size > zdev->end_dma)
+	if (dma_addr + size > zdev->end_dma) {
+		ret = -ERANGE;
 		goto out_free;
+	}
 
 	if (direction == DMA_NONE || direction == DMA_TO_DEVICE)
 		flags |= ZPCI_TABLE_PROTECTED;
 
-	if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) {
-		atomic64_add(nr_pages, &zdev->mapped_pages);
-		return dma_addr + (offset & ~PAGE_MASK);
-	}
+	ret = dma_update_trans(zdev, pa, dma_addr, size, flags);
+	if (ret)
+		goto out_free;
+
+	atomic64_add(nr_pages, &zdev->mapped_pages);
+	return dma_addr + (offset & ~PAGE_MASK);
 
 out_free:
 	dma_free_iommu(zdev, iommu_page_index, nr_pages);
 out_err:
 	zpci_err("map error:\n");
-	zpci_err_hex(&pa, sizeof(pa));
+	zpci_err_dma(ret, pa);
 	return DMA_ERROR_CODE;
 }
 
@@ -306,14 +332,16 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
 {
 	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	unsigned long iommu_page_index;
-	int npages;
+	int npages, ret;
 
 	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	dma_addr = dma_addr & PAGE_MASK;
-	if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
-			     ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) {
+	ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
+			       ZPCI_PTE_INVALID);
+	if (ret) {
 		zpci_err("unmap error:\n");
-		zpci_err_hex(&dma_addr, sizeof(dma_addr));
+		zpci_err_dma(ret, dma_addr);
+		return;
 	}
 
 	atomic64_add(npages, &zdev->unmapped_pages);
@@ -338,8 +366,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
 	pa = page_to_phys(page);
 	memset((void *) pa, 0, size);
 
-	map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE,
-				 size, DMA_BIDIRECTIONAL, NULL);
+	map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, NULL);
 	if (dma_mapping_error(dev, map)) {
 		free_pages(pa, get_order(size));
 		return NULL;
@@ -430,7 +457,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_clean;
 	}
 
-	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	/*
+	 * Restrict the iommu bitmap size to the minimum of the following:
+	 * - main memory size
+	 * - 3-level pagetable address limit minus start_dma offset
+	 * - DMA address range allowed by the hardware (clp query pci fn)
+	 *
+	 * Also set zdev->end_dma to the actual end address of the usable
+	 * range, instead of the theoretical maximum as reported by hardware.
+	 */
+	zdev->iommu_size = min3((u64) high_memory,
+				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
+				zdev->end_dma - zdev->start_dma + 1);
+	zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
 	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
@@ -438,10 +477,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_reg;
 	}
 
-	rc = zpci_register_ioat(zdev,
-				0,
-				zdev->start_dma + PAGE_OFFSET,
-				zdev->start_dma + zdev->iommu_size - 1,
+	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
 		goto out_reg;
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 369a3e05d468..b0e04751c5d5 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -53,6 +53,11 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
 	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
+
+	if (!pdev)
+		return;
+
+	pdev->error_state = pci_channel_io_perm_failure;
 }
 
 void zpci_event_error(void *data)