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
  ...

1 files changed, 66 insertions, 9 deletions

diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 9c9bcaae2f75..09231ef06d01 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -6,12 +6,31 @@
  * busses using the iommu infrastructure
  */
 
+#include <linux/dma-direct.h>
+#include <linux/pci.h>
 #include <asm/iommu.h>
 
 /*
  * Generic iommu implementation
  */
 
+/*
+ * The coherent mask may be smaller than the real mask, check if we can
+ * really use a direct window.
+ */
+static inline bool dma_iommu_alloc_bypass(struct device *dev)
+{
+	return dev->archdata.iommu_bypass && !iommu_fixed_is_weak &&
+		dma_direct_supported(dev, dev->coherent_dma_mask);
+}
+
+static inline bool dma_iommu_map_bypass(struct device *dev,
+		unsigned long attrs)
+{
+	return dev->archdata.iommu_bypass &&
+		(!iommu_fixed_is_weak || (attrs & DMA_ATTR_WEAK_ORDERING));
+}
+
 /* Allocates a contiguous real buffer and creates mappings over it.
  * Returns the virtual address of the buffer and sets dma_handle
  * to the dma address (mapping) of the first page.
@@ -20,6 +39,8 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 				      dma_addr_t *dma_handle, gfp_t flag,
 				      unsigned long attrs)
 {
+	if (dma_iommu_alloc_bypass(dev))
+		return dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
 				    dma_handle, dev->coherent_dma_mask, flag,
 				    dev_to_node(dev));
@@ -29,7 +50,11 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size,
 				    void *vaddr, dma_addr_t dma_handle,
 				    unsigned long attrs)
 {
-	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
+	if (dma_iommu_alloc_bypass(dev))
+		dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+	else
+		iommu_free_coherent(get_iommu_table_base(dev), size, vaddr,
+				dma_handle);
 }
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
@@ -42,6 +67,9 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
 {
+	if (dma_iommu_map_bypass(dev, attrs))
+		return dma_direct_map_page(dev, page, offset, size, direction,
+				attrs);
 	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
 			      size, device_to_mask(dev), direction, attrs);
 }
@@ -51,8 +79,9 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				 size_t size, enum dma_data_direction direction,
 				 unsigned long attrs)
 {
-	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
-			 attrs);
+	if (!dma_iommu_map_bypass(dev, attrs))
+		iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size,
+				direction,  attrs);
 }
 
 
@@ -60,6 +89,8 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction,
 			    unsigned long attrs)
 {
+	if (dma_iommu_map_bypass(dev, attrs))
+		return dma_direct_map_sg(dev, sglist, nelems, direction, attrs);
 	return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
 				device_to_mask(dev), direction, attrs);
 }
@@ -68,10 +99,20 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+	if (!dma_iommu_map_bypass(dev, attrs))
+		ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
 			   direction, attrs);
 }
 
+static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+
+	return phb->controller_ops.iommu_bypass_supported &&
+		phb->controller_ops.iommu_bypass_supported(pdev, mask);
+}
+
 /* We support DMA to/from any memory page via the iommu */
 int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
@@ -83,32 +124,48 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 0;
 	}
 
+	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
+		dev->archdata.iommu_bypass = true;
+		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+		return 1;
+	}
+
 	if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
 		dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
 		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
 				mask, tbl->it_offset << tbl->it_page_shift);
 		return 0;
-	} else
-		return 1;
+	}
+
+	dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
+	dev->archdata.iommu_bypass = false;
+	return 1;
 }
 
-static u64 dma_iommu_get_required_mask(struct device *dev)
+u64 dma_iommu_get_required_mask(struct device *dev)
 {
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 	u64 mask;
+
 	if (!tbl)
 		return 0;
 
+	if (dev_is_pci(dev)) {
+		u64 bypass_mask = dma_direct_get_required_mask(dev);
+
+		if (dma_iommu_bypass_supported(dev, bypass_mask))
+			return bypass_mask;
+	}
+
 	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
 	mask += mask - 1;
 
 	return mask;
 }
 
-struct dma_map_ops dma_iommu_ops = {
+const struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
-	.mmap			= dma_nommu_mmap_coherent,
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,