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, 179 insertions, 36 deletions

diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index c193af6a628..636c9baad7a 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -183,7 +183,7 @@ static int dom0_write_console(uint32_t vtermno, const char *str, int len)
 {
 	int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str);
 	if (rc < 0)
-		return 0;
+		return rc;
 
 	return len;
 }
@@ -642,7 +642,22 @@ struct console xenboot_console = {
 
 void xen_raw_console_write(const char *str)
 {
-	dom0_write_console(0, str, strlen(str));
+	ssize_t len = strlen(str);
+	int rc = 0;
+
+	if (xen_domain()) {
+		rc = dom0_write_console(0, str, len);
+#ifdef CONFIG_X86
+		if (rc == -ENOSYS && xen_hvm_domain())
+			goto outb_print;
+
+	} else if (xen_cpuid_base()) {
+		int i;
+outb_print:
+		for (i = 0; i < len; i++)
+			outb(str[i], 0xe9);
+#endif
+	}
 }
 
 void xen_raw_printk(const char *fmt, ...)
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 23eae5cb69c..c794ea18214 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -140,7 +140,6 @@ config XEN_GRANT_DEV_ALLOC
 
 config SWIOTLB_XEN
 	def_bool y
-	depends on PCI && X86
 	select SWIOTLB
 
 config XEN_TMEM
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index b232908a619..55ea73f7c70 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -596,7 +596,7 @@ static void __init balloon_add_region(unsigned long start_pfn,
 	}
 }
 
-static int __cpuinit balloon_cpu_notify(struct notifier_block *self,
+static int balloon_cpu_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
 	int cpu = (long)hcpu;
@@ -616,7 +616,7 @@ static int __cpuinit balloon_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block balloon_cpu_notifier __cpuinitdata = {
+static struct notifier_block balloon_cpu_notifier = {
 	.notifier_call	= balloon_cpu_notify,
 };
 
@@ -641,7 +641,7 @@ static int __init balloon_init(void)
 
 	balloon_stats.current_pages = xen_pv_domain()
 		? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
-		: max_pfn;
+		: get_num_physpages();
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 8b3a69a06c3..5de2063e16d 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -305,7 +305,7 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port)
 	if (rc < 0)
 		goto err;
 
-	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
+	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, 0,
 				       u->name, evtchn);
 	if (rc < 0)
 		goto err;
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index c4d2298893b..62ccf5424ba 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -49,6 +49,7 @@
 #include <xen/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
+#include <xen/swiotlb-xen.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -898,8 +899,16 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 			gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
 						&map_ops[i].status, __func__);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
+	/* this is basically a nop on x86 */
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+		for (i = 0; i < count; i++) {
+			if (map_ops[i].status)
+				continue;
+			set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT,
+					map_ops[i].dev_bus_addr >> PAGE_SHIFT);
+		}
 		return ret;
+	}
 
 	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();
@@ -942,8 +951,14 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 	if (ret)
 		return ret;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
+	/* this is basically a nop on x86 */
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+		for (i = 0; i < count; i++) {
+			set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT,
+					INVALID_P2M_ENTRY);
+		}
 		return ret;
+	}
 
 	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index 18fff88254e..d15f6e80479 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -26,6 +26,7 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include "../pci/pci.h"
+#include <asm/pci_x86.h>
 
 static bool __read_mostly pci_seg_supported = true;
 
@@ -192,3 +193,49 @@ static int __init register_xen_pci_notifier(void)
 }
 
 arch_initcall(register_xen_pci_notifier);
+
+#ifdef CONFIG_PCI_MMCONFIG
+static int __init xen_mcfg_late(void)
+{
+	struct pci_mmcfg_region *cfg;
+	int rc;
+
+	if (!xen_initial_domain())
+		return 0;
+
+	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+		return 0;
+
+	if (list_empty(&pci_mmcfg_list))
+		return 0;
+
+	/* Check whether they are in the right area. */
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		struct physdev_pci_mmcfg_reserved r;
+
+		r.address = cfg->address;
+		r.segment = cfg->segment;
+		r.start_bus = cfg->start_bus;
+		r.end_bus = cfg->end_bus;
+		r.flags = XEN_PCI_MMCFG_RESERVED;
+
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pci_mmcfg_reserved, &r);
+		switch (rc) {
+		case 0:
+		case -ENOSYS:
+			continue;
+
+		default:
+			pr_warn("Failed to report MMCONFIG reservation"
+				" state for %s to hypervisor"
+				" (%d)\n",
+				cfg->name, rc);
+		}
+	}
+	return 0;
+}
+/*
+ * Needs to be done after acpi_init which are subsys_initcall.
+ */
+subsys_initcall_sync(xen_mcfg_late);
+#endif
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index 99db9e1eb8b..2f3528e93cb 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -84,7 +84,7 @@ static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id)
 static int xen_allocate_irq(struct pci_dev *pdev)
 {
 	return request_irq(pdev->irq, do_hvm_evtchn_intr,
-			IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TRIGGER_RISING,
+			IRQF_NOBALANCING | IRQF_TRIGGER_RISING,
 			"xen-platform-pci", pdev);
 }
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1b2277c311d..a224bc74b6b 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -42,12 +42,31 @@
 #include <xen/page.h>
 #include <xen/xen-ops.h>
 #include <xen/hvc-console.h>
+
+#include <asm/dma-mapping.h>
+#include <asm/xen/page-coherent.h>
+
+#include <trace/events/swiotlb.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.
  */
 
+#ifndef CONFIG_X86
+static unsigned long dma_alloc_coherent_mask(struct device *dev,
+					    gfp_t gfp)
+{
+	unsigned long dma_mask = 0;
+
+	dma_mask = dev->coherent_dma_mask;
+	if (!dma_mask)
+		dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
+
+	return dma_mask;
+}
+#endif
+
 static char *xen_io_tlb_start, *xen_io_tlb_end;
 static unsigned long xen_io_tlb_nslabs;
 /*
@@ -56,17 +75,17 @@ static unsigned long xen_io_tlb_nslabs;
 
 static u64 start_dma_addr;
 
-static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
+static inline 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)
+static inline 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)
+static inline dma_addr_t xen_virt_to_bus(void *address)
 {
 	return xen_phys_to_bus(virt_to_phys(address));
 }
@@ -89,7 +108,7 @@ static int check_pages_physically_contiguous(unsigned long pfn,
 	return 1;
 }
 
-static int range_straddles_page_boundary(phys_addr_t p, size_t size)
+static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 {
 	unsigned long pfn = PFN_DOWN(p);
 	unsigned int offset = p & ~PAGE_MASK;
@@ -126,6 +145,8 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 {
 	int i, rc;
 	int dma_bits;
+	dma_addr_t dma_handle;
+	phys_addr_t p = virt_to_phys(buf);
 
 	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
 
@@ -135,9 +156,9 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 
 		do {
 			rc = xen_create_contiguous_region(
-				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				p + (i << IO_TLB_SHIFT),
 				get_order(slabs << IO_TLB_SHIFT),
-				dma_bits);
+				dma_bits, &dma_handle);
 		} while (rc && dma_bits++ < max_dma_bits);
 		if (rc)
 			return rc;
@@ -263,7 +284,6 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	void *ret;
 	int order = get_order(size);
 	u64 dma_mask = DMA_BIT_MASK(32);
-	unsigned long vstart;
 	phys_addr_t phys;
 	dma_addr_t dev_addr;
 
@@ -278,8 +298,12 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
 		return ret;
 
-	vstart = __get_free_pages(flags, order);
-	ret = (void *)vstart;
+	/* On ARM this function returns an ioremap'ped virtual address for
+	 * which virt_to_phys doesn't return the corresponding physical
+	 * address. In fact on ARM virt_to_phys only works for kernel direct
+	 * mapped RAM memory. Also see comment below.
+	 */
+	ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);
 
 	if (!ret)
 		return ret;
@@ -287,18 +311,21 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (hwdev && hwdev->coherent_dma_mask)
 		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
 
-	phys = virt_to_phys(ret);
+	/* At this point dma_handle is the physical address, next we are
+	 * going to set it to the machine address.
+	 * Do not use virt_to_phys(ret) because on ARM it doesn't correspond
+	 * to *dma_handle. */
+	phys = *dma_handle;
 	dev_addr = xen_phys_to_bus(phys);
 	if (((dev_addr + size - 1 <= dma_mask)) &&
 	    !range_straddles_page_boundary(phys, size))
 		*dma_handle = dev_addr;
 	else {
-		if (xen_create_contiguous_region(vstart, order,
-						 fls64(dma_mask)) != 0) {
-			free_pages(vstart, order);
+		if (xen_create_contiguous_region(phys, order,
+						 fls64(dma_mask), dma_handle) != 0) {
+			xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
 			return NULL;
 		}
-		*dma_handle = virt_to_machine(ret).maddr;
 	}
 	memset(ret, 0, size);
 	return ret;
@@ -319,13 +346,15 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	if (hwdev && hwdev->coherent_dma_mask)
 		dma_mask = hwdev->coherent_dma_mask;
 
-	phys = virt_to_phys(vaddr);
+	/* do not use virt_to_phys because on ARM it doesn't return you the
+	 * physical address */
+	phys = xen_bus_to_phys(dev_addr);
 
 	if (((dev_addr + size - 1 > dma_mask)) ||
 	    range_straddles_page_boundary(phys, size))
-		xen_destroy_contiguous_region((unsigned long)vaddr, order);
+		xen_destroy_contiguous_region(phys, order);
 
-	free_pages((unsigned long)vaddr, order);
+	xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
 
@@ -352,16 +381,25 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size) &&
-	    !range_straddles_page_boundary(phys, size) && !swiotlb_force)
+	    !range_straddles_page_boundary(phys, size) && !swiotlb_force) {
+		/* we are not interested in the dma_addr returned by
+		 * xen_dma_map_page, only in the potential cache flushes executed
+		 * by the function. */
+		xen_dma_map_page(dev, page, offset, size, dir, attrs);
 		return dev_addr;
+	}
 
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
+	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+
 	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
+	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
+					map & ~PAGE_MASK, size, dir, attrs);
 	dev_addr = xen_phys_to_bus(map);
 
 	/*
@@ -384,12 +422,15 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
  * 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)
+			     size_t size, enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
 {
 	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 
+	xen_dma_unmap_page(hwdev, paddr, size, dir, attrs);
+
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
 		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
@@ -412,7 +453,7 @@ 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);
+	xen_unmap_single(hwdev, dev_addr, size, dir, attrs);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
 
@@ -435,11 +476,15 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	BUG_ON(dir == DMA_NONE);
 
+	if (target == SYNC_FOR_CPU)
+		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+
 	/* NOTE: We use dev_addr here, not paddr! */
-	if (is_xen_swiotlb_buffer(dev_addr)) {
+	if (is_xen_swiotlb_buffer(dev_addr))
 		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
-		return;
-	}
+
+	if (target == SYNC_FOR_DEVICE)
+		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
@@ -502,16 +547,26 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 								 sg->length,
 								 dir);
 			if (map == SWIOTLB_MAP_ERROR) {
+				dev_warn(hwdev, "swiotlb buffer is full\n");
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
 				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
 							   attrs);
 				sg_dma_len(sgl) = 0;
-				return DMA_ERROR_CODE;
+				return 0;
 			}
 			sg->dma_address = xen_phys_to_bus(map);
-		} else
+		} else {
+			/* we are not interested in the dma_addr returned by
+			 * xen_dma_map_page, only in the potential cache flushes executed
+			 * by the function. */
+			xen_dma_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT),
+						paddr & ~PAGE_MASK,
+						sg->length,
+						dir,
+						attrs);
 			sg->dma_address = dev_addr;
+		}
 		sg_dma_len(sg) = sg->length;
 	}
 	return nelems;
@@ -533,7 +588,7 @@ xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i)
-		xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir);
+		xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
 
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
@@ -593,3 +648,15 @@ 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);
+
+int
+xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
+{
+	if (!dev->dma_mask || !xen_swiotlb_dma_supported(dev, dma_mask))
+		return -EIO;
+
+	*dev->dma_mask = dma_mask;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);