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
  ...

8 files changed, 63 insertions, 17 deletions

diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
new file mode 100644
index 00000000000..7f02fe4e2c7
--- /dev/null
+++ b/arch/x86/include/asm/xen/page-coherent.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
+#define _ASM_X86_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)
+{
+	void *vstart = (void*)__get_free_pages(flags, get_order(size));
+	*dma_handle = virt_to_phys(vstart);
+	return vstart;
+}
+
+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)
+{
+	free_pages((unsigned long) cpu_addr, get_order(size));
+}
+
+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) { }
+
+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) { }
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction 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) { }
+
+#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 49c962fe7e6..ce563be09cc 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -468,8 +468,8 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
  * 3        PCD PWT      UC       UC     UC
  * 4    PAT              WB       WC     WB
  * 5    PAT     PWT      WC       WP     WT
- * 6    PAT PCD          UC-      UC     UC-
- * 7    PAT PCD PWT      UC       UC     UC
+ * 6    PAT PCD          UC-      rsv    UC-
+ * 7    PAT PCD PWT      UC       rsv    UC
  */
 
 void xen_set_pat(u64 pat)
@@ -2328,12 +2328,14 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
 	return success;
 }
 
-int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
-				 unsigned int address_bits)
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
+				 unsigned int address_bits,
+				 dma_addr_t *dma_handle)
 {
 	unsigned long *in_frames = discontig_frames, out_frame;
 	unsigned long  flags;
 	int            success;
+	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
 
 	/*
 	 * Currently an auto-translated guest will not perform I/O, nor will
@@ -2368,15 +2370,17 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 
 	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
+	*dma_handle = virt_to_machine(vstart).maddr;
 	return success ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
 
-void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
 	unsigned long *out_frames = discontig_frames, in_frame;
 	unsigned long  flags;
 	int success;
+	unsigned long vstart;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return;
@@ -2384,6 +2388,7 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return;
 
+	vstart = (unsigned long)phys_to_virt(pstart);
 	memset((void *) vstart, 0, PAGE_SIZE << order);
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index a61c7d5811b..2ae8699e876 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -799,10 +799,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	unsigned topidx, mididx, idx;
 
-	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
-		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+	/* don't track P2M changes in autotranslate guests */
+	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
 		return true;
-	}
+
 	if (unlikely(pfn >= MAX_P2M_PFN)) {
 		BUG_ON(mfn != INVALID_P2M_ENTRY);
 		return true;
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 969570491c3..0e98e5d241d 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -75,8 +75,10 @@ void __init pci_xen_swiotlb_init(void)
 		xen_swiotlb_init(1, true /* early */);
 		dma_ops = &xen_swiotlb_dma_ops;
 
+#ifdef CONFIG_PCI
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
+#endif
 	}
 }
 
@@ -92,8 +94,10 @@ int pci_xen_swiotlb_init_late(void)
 		return rc;
 
 	dma_ops = &xen_swiotlb_dma_ops;
+#ifdef CONFIG_PCI
 	/* Make sure ACS will be enabled */
 	pci_request_acs();
+#endif
 
 	return 0;
 }
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 09f3059cb00..68c054f59de 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -556,7 +556,7 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-void __cpuinit xen_enable_nmi(void)
+void xen_enable_nmi(void)
 {
 #ifdef CONFIG_X86_64
 	if (register_callback(CALLBACKTYPE_nmi, nmi))
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 31d04758b76..c36b325abd8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -149,7 +149,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
 				    cpu,
 				    xen_reschedule_interrupt,
-				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				    IRQF_PERCPU|IRQF_NOBALANCING,
 				    resched_name,
 				    NULL);
 	if (rc < 0)
@@ -161,7 +161,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
 				    cpu,
 				    xen_call_function_interrupt,
-				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				    IRQF_PERCPU|IRQF_NOBALANCING,
 				    callfunc_name,
 				    NULL);
 	if (rc < 0)
@@ -171,7 +171,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 
 	debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
 	rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
-				     IRQF_DISABLED | IRQF_PERCPU | IRQF_NOBALANCING,
+				     IRQF_PERCPU | IRQF_NOBALANCING,
 				     debug_name, NULL);
 	if (rc < 0)
 		goto fail;
@@ -182,7 +182,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
 				    cpu,
 				    xen_call_function_single_interrupt,
-				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				    IRQF_PERCPU|IRQF_NOBALANCING,
 				    callfunc_name,
 				    NULL);
 	if (rc < 0)
@@ -201,7 +201,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
 				    cpu,
 				    xen_irq_work_interrupt,
-				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				    IRQF_PERCPU|IRQF_NOBALANCING,
 				    callfunc_name,
 				    NULL);
 	if (rc < 0)
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index be6b8607895..0e36cde12f7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -234,7 +234,7 @@ void xen_init_lock_cpu(int cpu)
 	irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
 				     cpu,
 				     dummy_handler,
-				     IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				     IRQF_PERCPU|IRQF_NOBALANCING,
 				     name,
 				     NULL);
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index ee365895b06..12a1ca707b9 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -443,8 +443,7 @@ void xen_setup_timer(int cpu)
 		name = "<timer kasprintf failed>";
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
-				      IRQF_DISABLED|IRQF_PERCPU|
-				      IRQF_NOBALANCING|IRQF_TIMER|
+				      IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
 				      IRQF_FORCE_RESUME,
 				      name, NULL);