Merge branch 'stable/xen-swiotlb-0.8.6' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/xen-swiotlb-0.8.6' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  x86: Detect whether we should use Xen SWIOTLB.
  pci-swiotlb-xen: Add glue code to setup dma_ops utilizing xen_swiotlb_* functions.
  swiotlb-xen: SWIOTLB library for Xen PV guest with PCI passthrough.
  xen/mmu: inhibit vmap aliases rather than trying to clear them out
  vmap: add flag to allow lazy unmap to be disabled at runtime
  xen: Add xen_create_contiguous_region
  xen: Rename the balloon lock
  xen: Allow unprivileged Xen domains to create iomap pages
  xen: use _PAGE_IOMAP in ioremap to do machine mappings

Fix up trivial conflicts (adding both xen swiotlb and xen pci platform
driver setup close to each other) in drivers/xen/{Kconfig,Makefile} and
include/xen/xen-ops.h

4 files changed, 525 insertions, 11 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 0a8826936639..60d71e9abe9f 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -71,4 +71,9 @@ config XEN_PLATFORM_PCI
 	  initializing xenbus and grant_table when running in a Xen HVM
 	  domain. As a consequence this driver is required to run any Xen PV
 	  frontend on Xen HVM.
+
+config SWIOTLB_XEN
+	def_bool y
+	depends on SWIOTLB
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index e392fb776af3..fcaf838f54be 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -11,3 +11,4 @@ obj-$(CONFIG_XEN_DEV_EVTCHN)	+= evtchn.o
 obj-$(CONFIG_XENFS)		+= xenfs/
 obj-$(CONFIG_XEN_SYS_HYPERVISOR)	+= sys-hypervisor.o
 obj-$(CONFIG_XEN_PLATFORM_PCI)	+= platform-pci.o
+obj-$(CONFIG_SWIOTLB_XEN)	+= swiotlb-xen.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 1a0d8c2a0354..500290b150bb 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -85,13 +85,6 @@ static struct sys_device balloon_sysdev;
 
 static int register_balloon(struct sys_device *sysdev);
 
-/*
- * Protects atomic reservation decrease/increase against concurrent increases.
- * Also protects non-atomic updates of current_pages and driver_pages, and
- * balloon lists.
- */
-static DEFINE_SPINLOCK(balloon_lock);
-
 static struct balloon_stats balloon_stats;
 
 /* We increase/decrease in batches which fit in a page */
@@ -210,7 +203,7 @@ static int increase_reservation(unsigned long nr_pages)
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
-	spin_lock_irqsave(&balloon_lock, flags);
+	spin_lock_irqsave(&xen_reservation_lock, flags);
 
 	page = balloon_first_page();
 	for (i = 0; i < nr_pages; i++) {
@@ -254,7 +247,7 @@ static int increase_reservation(unsigned long nr_pages)
 	balloon_stats.current_pages += rc;
 
  out:
-	spin_unlock_irqrestore(&balloon_lock, flags);
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
 	return rc < 0 ? rc : rc != nr_pages;
 }
@@ -299,7 +292,7 @@ static int decrease_reservation(unsigned long nr_pages)
 	kmap_flush_unused();
 	flush_tlb_all();
 
-	spin_lock_irqsave(&balloon_lock, flags);
+	spin_lock_irqsave(&xen_reservation_lock, flags);
 
 	/* No more mappings: invalidate P2M and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
@@ -315,7 +308,7 @@ static int decrease_reservation(unsigned long nr_pages)
 
 	balloon_stats.current_pages -= nr_pages;
 
-	spin_unlock_irqrestore(&balloon_lock, flags);
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
 	return need_sleep;
 }
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
new file mode 100644
index 000000000000..54469c3eeacd
--- /dev/null
+++ b/drivers/xen/swiotlb-xen.c
@@ -0,0 +1,515 @@
+/*
+ *  Copyright 2010
+ *  by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ *
+ * This code provides a IOMMU for Xen PV guests with PCI passthrough.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License v2.0 as published by
+ * the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * PV guests under Xen are running in an non-contiguous memory architecture.
+ *
+ * When PCI pass-through is utilized, this necessitates an IOMMU for
+ * translating bus (DMA) to virtual and vice-versa and also providing a
+ * mechanism to have contiguous pages for device drivers operations (say DMA
+ * operations).
+ *
+ * Specifically, under Xen the Linux idea of pages is an illusion. It
+ * assumes that pages start at zero and go up to the available memory. To
+ * help with that, the Linux Xen MMU provides a lookup mechanism to
+ * translate the page frame numbers (PFN) to machine frame numbers (MFN)
+ * and vice-versa. The MFN are the "real" frame numbers. Furthermore
+ * memory is not contiguous. Xen hypervisor stitches memory for guests
+ * from different pools, which means there is no guarantee that PFN==MFN
+ * and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
+ * allocated in descending order (high to low), meaning the guest might
+ * never get any MFN's under the 4GB mark.
+ *
+ */
+
+#include <linux/bootmem.h>
+#include <linux/dma-mapping.h>
+#include <xen/swiotlb-xen.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+/*
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+
+static char *xen_io_tlb_start, *xen_io_tlb_end;
+static unsigned long xen_io_tlb_nslabs;
+/*
+ * Quick lookup value of the bus address of the IOTLB.
+ */
+
+u64 start_dma_addr;
+
+static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
+{
+	return phys_to_machine(XPADDR(paddr)).maddr;;
+}
+
+static phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
+{
+	return machine_to_phys(XMADDR(baddr)).paddr;
+}
+
+static dma_addr_t xen_virt_to_bus(void *address)
+{
+	return xen_phys_to_bus(virt_to_phys(address));
+}
+
+static int check_pages_physically_contiguous(unsigned long pfn,
+					     unsigned int offset,
+					     size_t length)
+{
+	unsigned long next_mfn;
+	int i;
+	int nr_pages;
+
+	next_mfn = pfn_to_mfn(pfn);
+	nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
+
+	for (i = 1; i < nr_pages; i++) {
+		if (pfn_to_mfn(++pfn) != ++next_mfn)
+			return 0;
+	}
+	return 1;
+}
+
+static int range_straddles_page_boundary(phys_addr_t p, size_t size)
+{
+	unsigned long pfn = PFN_DOWN(p);
+	unsigned int offset = p & ~PAGE_MASK;
+
+	if (offset + size <= PAGE_SIZE)
+		return 0;
+	if (check_pages_physically_contiguous(pfn, offset, size))
+		return 0;
+	return 1;
+}
+
+static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
+{
+	unsigned long mfn = PFN_DOWN(dma_addr);
+	unsigned long pfn = mfn_to_local_pfn(mfn);
+	phys_addr_t paddr;
+
+	/* If the address is outside our domain, it CAN
+	 * have the same virtual address as another address
+	 * in our domain. Therefore _only_ check address within our domain.
+	 */
+	if (pfn_valid(pfn)) {
+		paddr = PFN_PHYS(pfn);
+		return paddr >= virt_to_phys(xen_io_tlb_start) &&
+		       paddr < virt_to_phys(xen_io_tlb_end);
+	}
+	return 0;
+}
+
+static int max_dma_bits = 32;
+
+static int
+xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
+{
+	int i, rc;
+	int dma_bits;
+
+	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+
+	i = 0;
+	do {
+		int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
+
+		do {
+			rc = xen_create_contiguous_region(
+				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				get_order(slabs << IO_TLB_SHIFT),
+				dma_bits);
+		} while (rc && dma_bits++ < max_dma_bits);
+		if (rc)
+			return rc;
+
+		i += slabs;
+	} while (i < nslabs);
+	return 0;
+}
+
+void __init xen_swiotlb_init(int verbose)
+{
+	unsigned long bytes;
+	int rc;
+
+	xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+	xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+
+	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+
+	/*
+	 * Get IO TLB memory from any location.
+	 */
+	xen_io_tlb_start = alloc_bootmem(bytes);
+	if (!xen_io_tlb_start)
+		panic("Cannot allocate SWIOTLB buffer");
+
+	xen_io_tlb_end = xen_io_tlb_start + bytes;
+	/*
+	 * And replace that memory with pages under 4GB.
+	 */
+	rc = xen_swiotlb_fixup(xen_io_tlb_start,
+			       bytes,
+			       xen_io_tlb_nslabs);
+	if (rc)
+		goto error;
+
+	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
+	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+
+	return;
+error:
+	panic("DMA(%d): Failed to exchange pages allocated for DMA with Xen! "\
+	      "We either don't have the permission or you do not have enough"\
+	      "free memory under 4GB!\n", rc);
+}
+
+void *
+xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flags)
+{
+	void *ret;
+	int order = get_order(size);
+	u64 dma_mask = DMA_BIT_MASK(32);
+	unsigned long vstart;
+
+	/*
+	* Ignore region specifiers - the kernel's ideas of
+	* pseudo-phys memory layout has nothing to do with the
+	* machine physical layout.  We can't allocate highmem
+	* because we can't return a pointer to it.
+	*/
+	flags &= ~(__GFP_DMA | __GFP_HIGHMEM);
+
+	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
+		return ret;
+
+	vstart = __get_free_pages(flags, order);
+	ret = (void *)vstart;
+
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
+
+	if (ret) {
+		if (xen_create_contiguous_region(vstart, order,
+						 fls64(dma_mask)) != 0) {
+			free_pages(vstart, order);
+			return NULL;
+		}
+		memset(ret, 0, size);
+		*dma_handle = virt_to_machine(ret).maddr;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
+
+void
+xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+			  dma_addr_t dev_addr)
+{
+	int order = get_order(size);
+
+	if (dma_release_from_coherent(hwdev, order, vaddr))
+		return;
+
+	xen_destroy_contiguous_region((unsigned long)vaddr, order);
+	free_pages((unsigned long)vaddr, order);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
+
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode.  The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+				unsigned long offset, size_t size,
+				enum dma_data_direction dir,
+				struct dma_attrs *attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dev_addr = xen_phys_to_bus(phys);
+	void *map;
+
+	BUG_ON(dir == DMA_NONE);
+	/*
+	 * If the address happens to be in the device's DMA window,
+	 * we can safely return the device addr and not worry about bounce
+	 * buffering it.
+	 */
+	if (dma_capable(dev, dev_addr, size) &&
+	    !range_straddles_page_boundary(phys, size) && !swiotlb_force)
+		return dev_addr;
+
+	/*
+	 * Oh well, have to allocate and map a bounce buffer.
+	 */
+	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
+	if (!map)
+		return DMA_ERROR_CODE;
+
+	dev_addr = xen_virt_to_bus(map);
+
+	/*
+	 * Ensure that the address returned is DMA'ble
+	 */
+	if (!dma_capable(dev, dev_addr, size))
+		panic("map_single: bounce buffer is not DMA'ble");
+
+	return dev_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
+
+/*
+ * Unmap a single streaming mode DMA translation.  The dma_addr and size must
+ * match what was provided for in a previous xen_swiotlb_map_page call.  All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			     size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	/*
+	 * phys_to_virt doesn't work with hihgmem page but we could
+	 * call dma_mark_clean() with hihgmem page here. However, we
+	 * are fine since dma_mark_clean() is null on POWERPC. We can
+	 * make dma_mark_clean() take a physical address if necessary.
+	 */
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+			    size_t size, enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
+{
+	xen_unmap_single(hwdev, dev_addr, size, dir);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a xen_swiotlb_map_page() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so.  At the next point you give the dma
+ * address back to the card, you must first perform a
+ * xen_swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+			size_t size, enum dma_data_direction dir,
+			enum dma_sync_target target)
+{
+	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+
+	/* NOTE: We use dev_addr here, not paddr! */
+	if (is_xen_swiotlb_buffer(dev_addr)) {
+		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
+				       target);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void
+xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+				size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);
+
+void
+xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+				   size_t size, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above xen_swiotlb_map_page
+ * interface.  Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length.  They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ *       DMA address/length pairs than there are SG table elements.
+ *       (for example via virtual mapping capabilities)
+ *       The routine returns the number of addr/length pairs actually
+ *       used, at most nents.
+ *
+ * Device ownership issues as mentioned above for xen_swiotlb_map_page are the
+ * same here.
+ */
+int
+xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			 int nelems, enum dma_data_direction dir,
+			 struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i) {
+		phys_addr_t paddr = sg_phys(sg);
+		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
+
+		if (swiotlb_force ||
+		    !dma_capable(hwdev, dev_addr, sg->length) ||
+		    range_straddles_page_boundary(paddr, sg->length)) {
+			void *map = swiotlb_tbl_map_single(hwdev,
+							   start_dma_addr,
+							   sg_phys(sg),
+							   sg->length, dir);
+			if (!map) {
+				/* Don't panic here, we expect map_sg users
+				   to do proper error handling. */
+				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+							   attrs);
+				sgl[0].dma_length = 0;
+				return DMA_ERROR_CODE;
+			}
+			sg->dma_address = xen_virt_to_bus(map);
+		} else
+			sg->dma_address = dev_addr;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
+
+int
+xen_swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		   enum dma_data_direction dir)
+{
+	return xen_swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg);
+
+/*
+ * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+void
+xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+			   int nelems, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
+
+void
+xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		     enum dma_data_direction dir)
+{
+	return xen_swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg);
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
+		    int nelems, enum dma_data_direction dir,
+		    enum dma_sync_target target)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		xen_swiotlb_sync_single(hwdev, sg->dma_address,
+					sg->dma_length, dir, target);
+}
+
+void
+xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			    int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);
+
+void
+xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+			       int nelems, enum dma_data_direction dir)
+{
+	xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
+
+int
+xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+	return !dma_addr;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);