Merge tag 'stable/for-linus-3.13-rc0-tag' of git://git.kernel.org/pub…

…/scm/linux/kernel/git/xen/tip

Pull Xen updates from Konrad Rzeszutek Wilk:
 "This has tons of fixes and two major features which are concentrated
  around the Xen SWIOTLB library.

  The short <blurb> is that the tracing facility (just one function) has
  been added to SWIOTLB to make it easier to track I/O progress.
  Additionally under Xen and ARM (32 & 64) the Xen-SWIOTLB driver
  "is used to translate physical to machine and machine to physical
  addresses of foreign[guest] pages for DMA operations" (Stefano) when
  booting under hardware without proper IOMMU.

  There are also bug-fixes, cleanups, compile warning fixes, etc.

  The commit times for some of the commits is a bit fresh - that is b/c
  we wanted to make sure we have the Ack's from the ARM folks - which
  with the string of back-to-back conferences took a bit of time.  Rest
  assured - the code has been stewing in #linux-next for some time.

  Features:
   - SWIOTLB has tracing added when doing bounce buffer.
   - Xen ARM/ARM64 can use Xen-SWIOTLB.  This work allows Linux to
     safely program real devices for DMA operations when running as a
     guest on Xen on ARM, without IOMMU support. [*1]
   - xen_raw_printk works with PVHVM guests if needed.

  Bug-fixes:
   - Make memory ballooning work under HVM with large MMIO region.
   - Inform hypervisor of MCFG regions found in ACPI DSDT.
   - Remove deprecated IRQF_DISABLED.
   - Remove deprecated __cpuinit.

  [*1]:
  "On arm and arm64 all Xen guests, including dom0, run with second
   stage translation enabled.  As a consequence when dom0 programs a
   device for a DMA operation is going to use (pseudo) physical
   addresses instead machine addresses.  This work introduces two trees
   to track physical to machine and machine to physical mappings of
   foreign pages.  Local pages are assumed mapped 1:1 (physical address
   == machine address).  It enables the SWIOTLB-Xen driver on ARM and
   ARM64, so that Linux can translate physical addresses to machine
   addresses for dma operations when necessary.  " (Stefano)"

* tag 'stable/for-linus-3.13-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (32 commits)
  xen/arm: pfn_to_mfn and mfn_to_pfn return the argument if nothing is in the p2m
  arm,arm64/include/asm/io.h: define struct bio_vec
  swiotlb-xen: missing include dma-direction.h
  pci-swiotlb-xen: call pci_request_acs only ifdef CONFIG_PCI
  arm: make SWIOTLB available
  xen: delete new instances of added __cpuinit
  xen/balloon: Set balloon's initial state to number of existing RAM pages
  xen/mcfg: Call PHYSDEVOP_pci_mmcfg_reserved for MCFG areas.
  xen: remove deprecated IRQF_DISABLED
  x86/xen: remove deprecated IRQF_DISABLED
  swiotlb-xen: fix error code returned by xen_swiotlb_map_sg_attrs
  swiotlb-xen: static inline xen_phys_to_bus, xen_bus_to_phys, xen_virt_to_bus and range_straddles_page_boundary
  grant-table: call set_phys_to_machine after mapping grant refs
  arm,arm64: do not always merge biovec if we are running on Xen
  swiotlb: print a warning when the swiotlb is full
  swiotlb-xen: use xen_dma_map/unmap_page, xen_dma_sync_single_for_cpu/device
  xen: introduce xen_dma_map/unmap_page and xen_dma_sync_single_for_cpu/device
  tracing/events: Fix swiotlb tracepoint creation
  swiotlb-xen: use xen_alloc/free_coherent_pages
  xen: introduce xen_alloc/free_coherent_pages
  ...

arch/arm/Kconfig

@@ -1862,6 +1862,12 @@ config CC_STACKPROTECTOR
 	  neutralized via a kernel panic.
 	  This feature requires gcc version 4.2 or above.
 
+config SWIOTLB
+	def_bool y
+
+config IOMMU_HELPER
+	def_bool SWIOTLB
+
 config XEN_DOM0
 	def_bool y
 	depends on XEN
@@ -1872,6 +1878,7 @@ config XEN
 	depends on CPU_V7 && !CPU_V6
 	depends on !GENERIC_ATOMIC64
 	select ARM_PSCI
+	select SWIOTLB_XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 

arch/arm/include/asm/dma-mapping.h

@@ -11,17 +11,28 @@
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
 #define DMA_ERROR_CODE	(~0)
 extern struct dma_map_ops arm_dma_ops;
 extern struct dma_map_ops arm_coherent_dma_ops;
 
-static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
 	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
 	return &arm_dma_ops;
 }
 
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (xen_initial_domain())
+		return xen_dma_ops;
+	else
+		return __generic_dma_ops(dev);
+}
+
 static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 {
 	BUG_ON(!dev);
@@ -94,6 +105,39 @@ static inline unsigned long dma_max_pfn(struct device *dev)
 }
 #define dma_max_pfn(dev) dma_max_pfn(dev)
 
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	unsigned int offset = paddr & ~PAGE_MASK;
+	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+{
+	unsigned int offset = dev_addr & ~PAGE_MASK;
+	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
+}
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	u64 limit, mask;
+
+	if (!dev->dma_mask)
+		return 0;
+
+	mask = *dev->dma_mask;
+
+	limit = (mask + 1) & ~mask;
+	if (limit && size > limit)
+		return 0;
+
+	if ((addr | (addr + size - 1)) & ~mask)
+		return 0;
+
+	return 1;
+}
+
+static inline void dma_mark_clean(void *addr, size_t size) { }
+
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
  */

arch/arm/include/asm/io.h

@@ -24,9 +24,11 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 #include <asm/byteorder.h>
 #include <asm/memory.h>
 #include <asm-generic/pci_iomap.h>
+#include <xen/xen.h>
 
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
@@ -372,6 +374,13 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
 #define BIOVEC_MERGEABLE(vec1, vec2)	\
 	((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2)))
 
+struct bio_vec;
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+				      const struct bio_vec *vec2);
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
+	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
+	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+
 #ifdef CONFIG_MMU
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern int valid_phys_addr_range(phys_addr_t addr, size_t size);

arch/arm/include/asm/xen/hypervisor.h

@@ -16,4 +16,6 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return PARAVIRT_LAZY_NONE;
 }
 
+extern struct dma_map_ops *xen_dma_ops;
+
 #endif /* _ASM_ARM_XEN_HYPERVISOR_H */

arch/arm/include/asm/xen/page-coherent.h

@@ -0,0 +1,50 @@
+#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
+#define _ASM_ARM_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs)
+{
+	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	if (__generic_dma_ops(hwdev)->unmap_page)
+		__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
+		__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (__generic_dma_ops(hwdev)->sync_single_for_device)
+		__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+}
+#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */

arch/arm/include/asm/xen/page.h

@@ -6,12 +6,12 @@
 
 #include <linux/pfn.h>
 #include <linux/types.h>
+#include <linux/dma-mapping.h>
 
+#include <xen/xen.h>
 #include <xen/interface/grant_table.h>
 
-#define pfn_to_mfn(pfn)			(pfn)
 #define phys_to_machine_mapping_valid(pfn) (1)
-#define mfn_to_pfn(mfn)			(mfn)
 #define mfn_to_virt(m)			(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
 #define pte_mfn	    pte_pfn
@@ -32,6 +32,38 @@ typedef struct xpaddr {
 
 #define INVALID_P2M_ENTRY      (~0UL)
 
+unsigned long __pfn_to_mfn(unsigned long pfn);
+unsigned long __mfn_to_pfn(unsigned long mfn);
+extern struct rb_root phys_to_mach;
+
+static inline unsigned long pfn_to_mfn(unsigned long pfn)
+{
+	unsigned long mfn;
+
+	if (phys_to_mach.rb_node != NULL) {
+		mfn = __pfn_to_mfn(pfn);
+		if (mfn != INVALID_P2M_ENTRY)
+			return mfn;
+	}
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (phys_to_mach.rb_node != NULL) {
+		pfn = __mfn_to_pfn(mfn);
+		if (pfn != INVALID_P2M_ENTRY)
+			return pfn;
+	}
+
+	return mfn;
+}
+
+#define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn)
+
 static inline xmaddr_t phys_to_machine(xpaddr_t phys)
 {
 	unsigned offset = phys.paddr & ~PAGE_MASK;
@@ -76,11 +108,9 @@ static inline int m2p_remove_override(struct page *page, bool clear_pte)
 	return 0;
 }
 
-static inline bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-	BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-	return true;
-}
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn,
+		unsigned long nr_pages);
 
 static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {

arch/arm/xen/Makefile

@@ -1 +1 @@
-obj-y		:= enlighten.o hypercall.o grant-table.o
+obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o

arch/arm/xen/mm.c

@@ -0,0 +1,65 @@
+#include <linux/bootmem.h>
+#include <linux/gfp.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+#include <linux/swiotlb.h>
+
+#include <xen/xen.h>
+#include <xen/interface/memory.h>
+#include <xen/swiotlb-xen.h>
+
+#include <asm/cacheflush.h>
+#include <asm/xen/page.h>
+#include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
+
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
+				 unsigned int address_bits,
+				 dma_addr_t *dma_handle)
+{
+	if (!xen_initial_domain())
+		return -EINVAL;
+
+	/* we assume that dom0 is mapped 1:1 for now */
+	*dma_handle = pstart;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
+
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
+{
+	return;
+}
+EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
+
+struct dma_map_ops *xen_dma_ops;
+EXPORT_SYMBOL_GPL(xen_dma_ops);
+
+static struct dma_map_ops xen_swiotlb_dma_ops = {
+	.mapping_error = xen_swiotlb_dma_mapping_error,
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
+	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
+	.map_sg = xen_swiotlb_map_sg_attrs,
+	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
+	.map_page = xen_swiotlb_map_page,
+	.unmap_page = xen_swiotlb_unmap_page,
+	.dma_supported = xen_swiotlb_dma_supported,
+	.set_dma_mask = xen_swiotlb_set_dma_mask,
+};
+
+int __init xen_mm_init(void)
+{
+	if (!xen_initial_domain())
+		return 0;
+	xen_swiotlb_init(1, false);
+	xen_dma_ops = &xen_swiotlb_dma_ops;
+	return 0;
+}
+arch_initcall(xen_mm_init);