Merge tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Enable THREAD_INFO_IN_TASK to move thread_info off the stack.

   - A big series from Christoph reworking our DMA code to use more of
     the generic infrastructure, as he said:
       "This series switches the powerpc port to use the generic swiotlb
        and noncoherent dma ops, and to use more generic code for the
        coherent direct mapping, as well as removing a lot of dead
        code."

   - Increase our vmalloc space to 512T with the Hash MMU on modern
     CPUs, allowing us to support machines with larger amounts of total
     RAM or distance between nodes.

   - Two series from Christophe, one to optimise TLB miss handlers on
     6xx, and another to optimise the way STRICT_KERNEL_RWX is
     implemented on some 32-bit CPUs.

   - Support for KCOV coverage instrumentation which means we can run
     syzkaller and discover even more bugs in our code.

  And as always many clean-ups, reworks and minor fixes etc.

  Thanks to: Alan Modra, Alexey Kardashevskiy, Alistair Popple, Andrea
  Arcangeli, Andrew Donnellan, Aneesh Kumar K.V, Aravinda Prasad, Balbir
  Singh, Brajeswar Ghosh, Breno Leitao, Christian Lamparter, Christian
  Zigotzky, Christophe Leroy, Christoph Hellwig, Corentin Labbe, Daniel
  Axtens, David Gibson, Diana Craciun, Firoz Khan, Gustavo A. R. Silva,
  Igor Stoppa, Joe Lawrence, Joel Stanley, Jonathan Neuschäfer, Jordan
  Niethe, Laurent Dufour, Madhavan Srinivasan, Mahesh Salgaonkar, Mark
  Cave-Ayland, Masahiro Yamada, Mathieu Malaterre, Matteo Croce, Meelis
  Roos, Michael W. Bringmann, Nathan Chancellor, Nathan Fontenot,
  Nicholas Piggin, Nick Desaulniers, Nicolai Stange, Oliver O'Halloran,
  Paul Mackerras, Peter Xu, PrasannaKumar Muralidharan, Qian Cai,
  Rashmica Gupta, Reza Arbab, Robert P. J. Day, Russell Currey,
  Sabyasachi Gupta, Sam Bobroff, Sandipan Das, Sergey Senozhatsky,
  Souptick Joarder, Stewart Smith, Tyrel Datwyler, Vaibhav Jain,
  YueHaibing"

* tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
  powerpc/32: Clear on-stack exception marker upon exception return
  powerpc: Remove export of save_stack_trace_tsk_reliable()
  powerpc/mm: fix "section_base" set but not used
  powerpc/mm: Fix "sz" set but not used warning
  powerpc/mm: Check secondary hash page table
  powerpc: remove nargs from __SYSCALL
  powerpc/64s: Fix unrelocated interrupt trampoline address test
  powerpc/powernv/ioda: Fix locked_vm counting for memory used by IOMMU tables
  powerpc/fsl: Fix the flush of branch predictor.
  powerpc/powernv: Make opal log only readable by root
  powerpc/xmon: Fix opcode being uninitialized in print_insn_powerpc
  powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
  powerpc/64s: Fix data interrupts vs d-side MCE reentrancy
  powerpc/64s: Prepare to handle data interrupts vs d-side MCE reentrancy
  powerpc/64s: system reset interrupt preserve HSRRs
  powerpc/64s: Fix HV NMI vs HV interrupt recoverability test
  powerpc/mm/hash: Handle mmap_min_addr correctly in get_unmapped_area topdown search
  powerpc/hugetlb: Handle mmap_min_addr correctly in get_unmapped_area callback
  selftests/powerpc: Remove duplicate header
  powerpc sstep: Add support for modsd, modud instructions
  ...

4 files changed, 88 insertions, 126 deletions

diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 2f8e62163602..97feb6e79f1a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -802,6 +802,25 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add)
 	return rc;
 }
 
+int dlpar_cpu_readd(int cpu)
+{
+	struct device_node *dn;
+	struct device *dev;
+	u32 drc_index;
+	int rc;
+
+	dev = get_cpu_device(cpu);
+	dn = dev->of_node;
+
+	rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
+
+	rc = dlpar_cpu_remove_by_index(drc_index);
+	if (!rc)
+		rc = dlpar_cpu_add(drc_index);
+
+	return rc;
+}
+
 int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 {
 	u32 count, drc_index;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 8fc8fe0b9848..36eb1ddbac69 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -978,7 +978,7 @@ static phys_addr_t ddw_memory_hotplug_max(void)
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by dma_set_mask
+ * returns the dma offset for use by the direct mapped DMA code.
  */
 static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
@@ -1198,87 +1198,37 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	iommu_add_device(pci->table_group, &dev->dev);
 }
 
-static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
+static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 {
-	bool ddw_enabled = false;
-	struct device_node *pdn, *dn;
-	struct pci_dev *pdev;
+	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
 	const __be32 *dma_window = NULL;
-	u64 dma_offset;
-
-	if (!dev->dma_mask)
-		return -EIO;
-
-	if (!dev_is_pci(dev))
-		goto check_mask;
-
-	pdev = to_pci_dev(dev);
 
 	/* only attempt to use a new window if 64-bit DMA is requested */
-	if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) {
-		dn = pci_device_to_OF_node(pdev);
-		dev_dbg(dev, "node is %pOF\n", dn);
+	if (dma_mask < DMA_BIT_MASK(64))
+		return false;
 
-		/*
-		 * the device tree might contain the dma-window properties
-		 * per-device and not necessarily for the bus. So we need to
-		 * search upwards in the tree until we either hit a dma-window
-		 * property, OR find a parent with a table already allocated.
-		 */
-		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
-				pdn = pdn->parent) {
-			dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
-			if (dma_window)
-				break;
-		}
-		if (pdn && PCI_DN(pdn)) {
-			dma_offset = enable_ddw(pdev, pdn);
-			if (dma_offset != 0) {
-				dev_info(dev, "Using 64-bit direct DMA at offset %llx\n", dma_offset);
-				set_dma_offset(dev, dma_offset);
-				set_dma_ops(dev, &dma_nommu_ops);
-				ddw_enabled = true;
-			}
-		}
-	}
+	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
 
-	/* fall back on iommu ops */
-	if (!ddw_enabled && get_dma_ops(dev) != &dma_iommu_ops) {
-		dev_info(dev, "Restoring 32-bit DMA via iommu\n");
-		set_dma_ops(dev, &dma_iommu_ops);
+	/*
+	 * the device tree might contain the dma-window properties
+	 * per-device and not necessarily for the bus. So we need to
+	 * search upwards in the tree until we either hit a dma-window
+	 * property, OR find a parent with a table already allocated.
+	 */
+	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
+			pdn = pdn->parent) {
+		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
+		if (dma_window)
+			break;
 	}
 
-check_mask:
-	if (!dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-
-static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!disable_ddw && dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct device_node *dn;
-
-		dn = pci_device_to_OF_node(pdev);
-
-		/* search upwards for ibm,dma-window */
-		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
-				dn = dn->parent)
-			if (of_get_property(dn, "ibm,dma-window", NULL))
-				break;
-		/* if there is a ibm,ddw-applicable property require 64 bits */
-		if (dn && PCI_DN(dn) &&
-				of_get_property(dn, "ibm,ddw-applicable", NULL))
-			return DMA_BIT_MASK(64);
+	if (pdn && PCI_DN(pdn)) {
+		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
+		if (pdev->dev.archdata.dma_offset)
+			return true;
 	}
 
-	return dma_iommu_ops.get_required_mask(dev);
+	return false;
 }
 
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1373,8 +1323,9 @@ void iommu_init_early_pSeries(void)
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
-		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
-		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
+		if (!disable_ddw)
+			pseries_pci_controller_ops.iommu_bypass_supported =
+				iommu_bypass_supported_pSeriesLP;
 	} else {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 794487313cc8..e73c7e30efe6 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -475,6 +475,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 		splpar_dispatch_data(m);
 
 		seq_printf(m, "purr=%ld\n", get_purr());
+		seq_printf(m, "tbr=%ld\n", mftb());
 	} else {		/* non SPLPAR case */
 
 		seq_printf(m, "system_active_processors=%d\n",
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 1fad4649735b..141795275ccb 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -492,7 +492,9 @@ static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size,
 		return NULL;
 	}
 
-	ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
+	ret = iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
+				    dma_handle, dev->coherent_dma_mask, flag,
+				    dev_to_node(dev));
 	if (unlikely(ret == NULL)) {
 		vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -507,8 +509,7 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 
-	dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-
+	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
 
@@ -518,22 +519,22 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
                                          unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	dma_addr_t ret = DMA_MAPPING_ERROR;
 
-	tbl = get_iommu_table_base(dev);
-	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
-
-	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
-	if (unlikely(dma_mapping_error(dev, ret))) {
-		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
-		atomic_inc(&viodev->cmo.allocs_failed);
-	}
-
+	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))))
+		goto out_fail;
+	ret = iommu_map_page(dev, tbl, page, offset, size, device_to_mask(dev),
+			direction, attrs);
+	if (unlikely(ret == DMA_MAPPING_ERROR))
+		goto out_deallocate;
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return DMA_MAPPING_ERROR;
 }
 
 static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
@@ -542,11 +543,9 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				     unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
-
-	tbl = get_iommu_table_base(dev);
-	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 
+	iommu_unmap_page(tbl, dma_handle, size, direction, attrs);
 	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
@@ -555,34 +554,32 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
                                 unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	int ret, count;
 	size_t alloc_size = 0;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
-	if (vio_cmo_alloc(viodev, alloc_size)) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return 0;
-	}
-
-	ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs);
-
-	if (unlikely(!ret)) {
-		vio_cmo_dealloc(viodev, alloc_size);
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
+	if (vio_cmo_alloc(viodev, alloc_size))
+		goto out_fail;
+	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, device_to_mask(dev),
+			direction, attrs);
+	if (unlikely(!ret))
+		goto out_deallocate;
 
 	for_each_sg(sglist, sgl, ret, count)
 		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
-
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, alloc_size);
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return 0;
 }
 
 static void vio_dma_iommu_unmap_sg(struct device *dev,
@@ -591,40 +588,27 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 		unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
 	int count;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
-	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
-
+	ppc_iommu_unmap_sg(tbl, sglist, nelems, direction, attrs);
 	vio_cmo_dealloc(viodev, alloc_size);
 }
 
-static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
-{
-        return dma_iommu_ops.dma_supported(dev, mask);
-}
-
-static u64 vio_dma_get_required_mask(struct device *dev)
-{
-        return dma_iommu_ops.get_required_mask(dev);
-}
-
 static const struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc             = vio_dma_iommu_alloc_coherent,
 	.free              = vio_dma_iommu_free_coherent,
-	.mmap		   = dma_nommu_mmap_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
 	.map_page          = vio_dma_iommu_map_page,
 	.unmap_page        = vio_dma_iommu_unmap_page,
-	.dma_supported     = vio_dma_iommu_dma_supported,
-	.get_required_mask = vio_dma_get_required_mask,
+	.dma_supported     = dma_iommu_dma_supported,
+	.get_required_mask = dma_iommu_get_required_mask,
 };
 
 /**
@@ -1715,3 +1699,10 @@ int vio_disable_interrupts(struct vio_dev *dev)
 }
 EXPORT_SYMBOL(vio_disable_interrupts);
 #endif /* CONFIG_PPC_PSERIES */
+
+static int __init vio_init(void)
+{
+	dma_debug_add_bus(&vio_bus_type);
+	return 0;
+}
+fs_initcall(vio_init);