Merge tag 'stable/for-linus-3.7-x86-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull Xen update from Konrad Rzeszutek Wilk:
 "Features:
   - When hotplugging PCI devices in a PV guest we can allocate
     Xen-SWIOTLB later.
   - Cleanup Xen SWIOTLB.
   - Support pages out grants from HVM domains in the backends.
   - Support wild cards in xen-pciback.hide=(BDF) arguments.
   - Update grant status updates with upstream hypervisor.
   - Boot PV guests with more than 128GB.
   - Cleanup Xen MMU code/add comments.
   - Obtain XENVERS using a preferred method.
   - Lay out generic changes to support Xen ARM.
   - Allow privcmd ioctl for HVM (used to do only PV).
   - Do v2 of mmap_batch for privcmd ioctls.
   - If hypervisor saves the LED keyboard light - we will now instruct
     the kernel about its state.
  Fixes:
   - More fixes to Xen PCI backend for various calls/FLR/etc.
   - With more than 4GB in a 64-bit PV guest disable native SWIOTLB.
   - Fix up smatch warnings.
   - Fix up various return values in privmcmd and mm."

* tag 'stable/for-linus-3.7-x86-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen: (48 commits)
  xen/pciback: Restore the PCI config space after an FLR.
  xen-pciback: properly clean up after calling pcistub_device_find()
  xen/vga: add the xen EFI video mode support
  xen/x86: retrieve keyboard shift status flags from hypervisor.
  xen/gndev: Xen backend support for paged out grant targets V4.
  xen-pciback: support wild cards in slot specifications
  xen/swiotlb: Fix compile warnings when using plain integer instead of NULL pointer.
  xen/swiotlb: Remove functions not needed anymore.
  xen/pcifront: Use Xen-SWIOTLB when initting if required.
  xen/swiotlb: For early initialization, return zero on success.
  xen/swiotlb: Use the swiotlb_late_init_with_tbl to init Xen-SWIOTLB late when PV PCI is used.
  xen/swiotlb: Move the error strings to its own function.
  xen/swiotlb: Move the nr_tbl determination in its own function.
  xen/arm: compile and run xenbus
  xen: resynchronise grant table status codes with upstream
  xen/privcmd: return -EFAULT on error
  xen/privcmd: Fix mmap batch ioctl error status copy back.
  xen/privcmd: add PRIVCMD_MMAPBATCH_V2 ioctl
  xen/mm: return more precise error from xen_remap_domain_range()
  xen/mmu: If the revector fails, don't attempt to revector anything else.
  ...

drivers/xen/events.c

@@ -373,11 +373,22 @@ static void unmask_evtchn(int port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	unsigned int cpu = get_cpu();
+	int do_hypercall = 0, evtchn_pending = 0;
 
 	BUG_ON(!irqs_disabled());
 
-	/* Slow path (hypercall) if this is a non-local port. */
-	if (unlikely(cpu != cpu_from_evtchn(port))) {
+	if (unlikely((cpu != cpu_from_evtchn(port))))
+		do_hypercall = 1;
+	else
+		evtchn_pending = sync_test_bit(port, &s->evtchn_pending[0]);
+
+	if (unlikely(evtchn_pending && xen_hvm_domain()))
+		do_hypercall = 1;
+
+	/* Slow path (hypercall) if this is a non-local port or if this is
+	 * an hvm domain and an event is pending (hvm domains don't have
+	 * their own implementation of irq_enable). */
+	if (do_hypercall) {
 		struct evtchn_unmask unmask = { .port = port };
 		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
 	} else {
@@ -390,7 +401,7 @@ static void unmask_evtchn(int port)
 		 * 'hw_resend_irq'. Just like a real IO-APIC we 'lose
 		 * the interrupt edge' if the channel is masked.
 		 */
-		if (sync_test_bit(port, &s->evtchn_pending[0]) &&
+		if (evtchn_pending &&
 		    !sync_test_and_set_bit(port / BITS_PER_LONG,
 					   &vcpu_info->evtchn_pending_sel))
 			vcpu_info->evtchn_upcall_pending = 1;
@@ -831,6 +842,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
 	}
+	irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
 
 out:
 	mutex_unlock(&irq_mapping_update_lock);

drivers/xen/gntdev.c

@@ -446,7 +446,7 @@ static void mn_release(struct mmu_notifier *mn,
 	spin_unlock(&priv->lock);
 }
 
-struct mmu_notifier_ops gntdev_mmu_ops = {
+static struct mmu_notifier_ops gntdev_mmu_ops = {
 	.release                = mn_release,
 	.invalidate_page        = mn_invl_page,
 	.invalidate_range_start = mn_invl_range_start,

drivers/xen/grant-table.c

@@ -38,6 +38,7 @@
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/delay.h>
 #include <linux/hardirq.h>
 
 #include <xen/xen.h>
@@ -47,6 +48,7 @@
 #include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
 #include <asm/xen/hypercall.h>
+#include <asm/xen/interface.h>
 
 #include <asm/pgtable.h>
 #include <asm/sync_bitops.h>
@@ -285,10 +287,9 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
 }
 EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
 
-void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid,
-				    unsigned long frame, int flags,
-				    unsigned page_off,
-				    unsigned length)
+static void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid,
+					   unsigned long frame, int flags,
+					   unsigned page_off, unsigned length)
 {
 	gnttab_shared.v2[ref].sub_page.frame = frame;
 	gnttab_shared.v2[ref].sub_page.page_off = page_off;
@@ -345,9 +346,9 @@ bool gnttab_subpage_grants_available(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_subpage_grants_available);
 
-void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid,
-				  int flags, domid_t trans_domid,
-				  grant_ref_t trans_gref)
+static void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid,
+					 int flags, domid_t trans_domid,
+					 grant_ref_t trans_gref)
 {
 	gnttab_shared.v2[ref].transitive.trans_domid = trans_domid;
 	gnttab_shared.v2[ref].transitive.gref = trans_gref;
@@ -823,6 +824,52 @@ unsigned int gnttab_max_grant_frames(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_max_grant_frames);
 
+/* Handling of paged out grant targets (GNTST_eagain) */
+#define MAX_DELAY 256
+static inline void
+gnttab_retry_eagain_gop(unsigned int cmd, void *gop, int16_t *status,
+						const char *func)
+{
+	unsigned delay = 1;
+
+	do {
+		BUG_ON(HYPERVISOR_grant_table_op(cmd, gop, 1));
+		if (*status == GNTST_eagain)
+			msleep(delay++);
+	} while ((*status == GNTST_eagain) && (delay < MAX_DELAY));
+
+	if (delay >= MAX_DELAY) {
+		printk(KERN_ERR "%s: %s eagain grant\n", func, current->comm);
+		*status = GNTST_bad_page;
+	}
+}
+
+void gnttab_batch_map(struct gnttab_map_grant_ref *batch, unsigned count)
+{
+	struct gnttab_map_grant_ref *op;
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, batch, count))
+		BUG();
+	for (op = batch; op < batch + count; op++)
+		if (op->status == GNTST_eagain)
+			gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, op,
+						&op->status, __func__);
+}
+EXPORT_SYMBOL_GPL(gnttab_batch_map);
+
+void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count)
+{
+	struct gnttab_copy *op;
+
+	if (HYPERVISOR_grant_table_op(GNTTABOP_copy, batch, count))
+		BUG();
+	for (op = batch; op < batch + count; op++)
+		if (op->status == GNTST_eagain)
+			gnttab_retry_eagain_gop(GNTTABOP_copy, op,
+						&op->status, __func__);
+}
+EXPORT_SYMBOL_GPL(gnttab_batch_copy);
+
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count)
@@ -836,6 +883,12 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 	if (ret)
 		return ret;
 
+	/* Retry eagain maps */
+	for (i = 0; i < count; i++)
+		if (map_ops[i].status == GNTST_eagain)
+			gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
+						&map_ops[i].status, __func__);
+
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return ret;
 

drivers/xen/privcmd.c

@@ -76,7 +76,7 @@ static void free_page_list(struct list_head *pages)
  */
 static int gather_array(struct list_head *pagelist,
 			unsigned nelem, size_t size,
-			void __user *data)
+			const void __user *data)
 {
 	unsigned pageidx;
 	void *pagedata;
@@ -246,61 +246,117 @@ struct mmap_batch_state {
 	domid_t domain;
 	unsigned long va;
 	struct vm_area_struct *vma;
-	int err;
+	/* A tristate:
+	 *      0 for no errors
+	 *      1 if at least one error has happened (and no
+	 *          -ENOENT errors have happened)
+	 *      -ENOENT if at least 1 -ENOENT has happened.
+	 */
+	int global_error;
+	/* An array for individual errors */
+	int *err;
 
-	xen_pfn_t __user *user;
+	/* User-space mfn array to store errors in the second pass for V1. */
+	xen_pfn_t __user *user_mfn;
 };
 
 static int mmap_batch_fn(void *data, void *state)
 {
 	xen_pfn_t *mfnp = data;
 	struct mmap_batch_state *st = state;
+	int ret;
 
-	if (xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
-				       st->vma->vm_page_prot, st->domain) < 0) {
-		*mfnp |= 0xf0000000U;
-		st->err++;
+	ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
+					 st->vma->vm_page_prot, st->domain);
+
+	/* Store error code for second pass. */
+	*(st->err++) = ret;
+
+	/* And see if it affects the global_error. */
+	if (ret < 0) {
+		if (ret == -ENOENT)
+			st->global_error = -ENOENT;
+		else {
+			/* Record that at least one error has happened. */
+			if (st->global_error == 0)
+				st->global_error = 1;
+		}
 	}
 	st->va += PAGE_SIZE;
 
 	return 0;
 }
 
-static int mmap_return_errors(void *data, void *state)
+static int mmap_return_errors_v1(void *data, void *state)
 {
 	xen_pfn_t *mfnp = data;
 	struct mmap_batch_state *st = state;
+	int err = *(st->err++);
 
-	return put_user(*mfnp, st->user++);
+	/*
+	 * V1 encodes the error codes in the 32bit top nibble of the
+	 * mfn (with its known limitations vis-a-vis 64 bit callers).
+	 */
+	*mfnp |= (err == -ENOENT) ?
+				PRIVCMD_MMAPBATCH_PAGED_ERROR :
+				PRIVCMD_MMAPBATCH_MFN_ERROR;
+	return __put_user(*mfnp, st->user_mfn++);
 }
 
 static struct vm_operations_struct privcmd_vm_ops;
 
-static long privcmd_ioctl_mmap_batch(void __user *udata)
+static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 {
 	int ret;
-	struct privcmd_mmapbatch m;
+	struct privcmd_mmapbatch_v2 m;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long nr_pages;
 	LIST_HEAD(pagelist);
+	int *err_array = NULL;
 	struct mmap_batch_state state;
 
 	if (!xen_initial_domain())
 		return -EPERM;
 
-	if (copy_from_user(&m, udata, sizeof(m)))
-		return -EFAULT;
+	switch (version) {
+	case 1:
+		if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch)))
+			return -EFAULT;
+		/* Returns per-frame error in m.arr. */
+		m.err = NULL;
+		if (!access_ok(VERIFY_WRITE, m.arr, m.num * sizeof(*m.arr)))
+			return -EFAULT;
+		break;
+	case 2:
+		if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch_v2)))
+			return -EFAULT;
+		/* Returns per-frame error code in m.err. */
+		if (!access_ok(VERIFY_WRITE, m.err, m.num * (sizeof(*m.err))))
+			return -EFAULT;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	nr_pages = m.num;
 	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
 		return -EINVAL;
 
-	ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t),
-			   m.arr);
+	ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t), m.arr);
 
-	if (ret || list_empty(&pagelist))
+	if (ret)
 		goto out;
+	if (list_empty(&pagelist)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	err_array = kcalloc(m.num, sizeof(int), GFP_KERNEL);
+	if (err_array == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	down_write(&mm->mmap_sem);
 
@@ -315,24 +371,37 @@ static long privcmd_ioctl_mmap_batch(void __user *udata)
 		goto out;
 	}
 
-	state.domain = m.dom;
-	state.vma = vma;
-	state.va = m.addr;
-	state.err = 0;
+	state.domain        = m.dom;
+	state.vma           = vma;
+	state.va            = m.addr;
+	state.global_error  = 0;
+	state.err           = err_array;
 
-	ret = traverse_pages(m.num, sizeof(xen_pfn_t),
-			     &pagelist, mmap_batch_fn, &state);
+	/* mmap_batch_fn guarantees ret == 0 */
+	BUG_ON(traverse_pages(m.num, sizeof(xen_pfn_t),
+			     &pagelist, mmap_batch_fn, &state));
 
 	up_write(&mm->mmap_sem);
 
-	if (state.err > 0) {
-		state.user = m.arr;
+	if (state.global_error && (version == 1)) {
+		/* Write back errors in second pass. */
+		state.user_mfn = (xen_pfn_t *)m.arr;
+		state.err      = err_array;
 		ret = traverse_pages(m.num, sizeof(xen_pfn_t),
-			       &pagelist,
-			       mmap_return_errors, &state);
+				     &pagelist, mmap_return_errors_v1, &state);
+	} else if (version == 2) {
+		ret = __copy_to_user(m.err, err_array, m.num * sizeof(int));
+		if (ret)
+			ret = -EFAULT;
 	}
 
+	/* If we have not had any EFAULT-like global errors then set the global
+	 * error to -ENOENT if necessary. */
+	if ((ret == 0) && (state.global_error == -ENOENT))
+		ret = -ENOENT;
+
 out:
+	kfree(err_array);
 	free_page_list(&pagelist);
 
 	return ret;
@@ -354,7 +423,11 @@ static long privcmd_ioctl(struct file *file,
 		break;
 
 	case IOCTL_PRIVCMD_MMAPBATCH:
-		ret = privcmd_ioctl_mmap_batch(udata);
+		ret = privcmd_ioctl_mmap_batch(udata, 1);
+		break;
+
+	case IOCTL_PRIVCMD_MMAPBATCH_V2:
+		ret = privcmd_ioctl_mmap_batch(udata, 2);
 		break;
 
 	default:
@@ -380,10 +453,6 @@ static struct vm_operations_struct privcmd_vm_ops = {
 
 static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	/* Unsupported for auto-translate guests. */
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return -ENOSYS;
-
 	/* DONTCOPY is essential for Xen because copy_page_range doesn't know
 	 * how to recreate these mappings */
 	vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY | VM_PFNMAP;

drivers/xen/swiotlb-xen.c

@@ -52,7 +52,7 @@ static unsigned long xen_io_tlb_nslabs;
  * Quick lookup value of the bus address of the IOTLB.
  */
 
-u64 start_dma_addr;
+static u64 start_dma_addr;
 
 static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
 {
@@ -144,31 +144,72 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 	} while (i < nslabs);
 	return 0;
 }
-
-void __init xen_swiotlb_init(int verbose)
+static unsigned long xen_set_nslabs(unsigned long nr_tbl)
 {
-	unsigned long bytes;
-	int rc = -ENOMEM;
-	unsigned long nr_tbl;
-	char *m = NULL;
-	unsigned int repeat = 3;
-
-	nr_tbl = swiotlb_nr_tbl();
-	if (nr_tbl)
-		xen_io_tlb_nslabs = nr_tbl;
-	else {
+	if (!nr_tbl) {
 		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
 		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
-	}
-retry:
-	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+	} else
+		xen_io_tlb_nslabs = nr_tbl;
 
+	return xen_io_tlb_nslabs << IO_TLB_SHIFT;
+}
+
+enum xen_swiotlb_err {
+	XEN_SWIOTLB_UNKNOWN = 0,
+	XEN_SWIOTLB_ENOMEM,
+	XEN_SWIOTLB_EFIXUP
+};
+
+static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
+{
+	switch (err) {
+	case XEN_SWIOTLB_ENOMEM:
+		return "Cannot allocate Xen-SWIOTLB buffer\n";
+	case XEN_SWIOTLB_EFIXUP:
+		return "Failed to get contiguous memory for DMA from Xen!\n"\
+		    "You either: don't have the permissions, do not have"\
+		    " enough free memory under 4GB, or the hypervisor memory"\
+		    " is too fragmented!";
+	default:
+		break;
+	}
+	return "";
+}
+int __ref xen_swiotlb_init(int verbose, bool early)
+{
+	unsigned long bytes, order;
+	int rc = -ENOMEM;
+	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
+	unsigned int repeat = 3;
+
+	xen_io_tlb_nslabs = swiotlb_nr_tbl();
+retry:
+	bytes = xen_set_nslabs(xen_io_tlb_nslabs);
+	order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
 	/*
 	 * Get IO TLB memory from any location.
 	 */
-	xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	if (early)
+		xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	else {
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+		while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+			xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
+			if (xen_io_tlb_start)
+				break;
+			order--;
+		}
+		if (order != get_order(bytes)) {
+			pr_warn("Warning: only able to allocate %ld MB "
+				"for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+			xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
+			bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+		}
+	}
 	if (!xen_io_tlb_start) {
-		m = "Cannot allocate Xen-SWIOTLB buffer!\n";
+		m_ret = XEN_SWIOTLB_ENOMEM;
 		goto error;
 	}
 	xen_io_tlb_end = xen_io_tlb_start + bytes;
@@ -179,17 +220,22 @@ retry:
 			       bytes,
 			       xen_io_tlb_nslabs);
 	if (rc) {
-		free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
-		m = "Failed to get contiguous memory for DMA from Xen!\n"\
-		    "You either: don't have the permissions, do not have"\
-		    " enough free memory under 4GB, or the hypervisor memory"\
-		    "is too fragmented!";
+		if (early)
+			free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+		else {
+			free_pages((unsigned long)xen_io_tlb_start, order);
+			xen_io_tlb_start = NULL;
+		}
+		m_ret = XEN_SWIOTLB_EFIXUP;
 		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;
+	if (early) {
+		swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+		rc = 0;
+	} else
+		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
+	return rc;
 error:
 	if (repeat--) {
 		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
@@ -198,10 +244,13 @@ error:
 		      (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
 		goto retry;
 	}
-	xen_raw_printk("%s (rc:%d)", m, rc);
-	panic("%s (rc:%d)", m, rc);
+	pr_err("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	if (early)
+		panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	else
+		free_pages((unsigned long)xen_io_tlb_start, order);
+	return rc;
 }
-
 void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,
@@ -466,14 +515,6 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 }
 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.
@@ -494,14 +535,6 @@ xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 }
 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.

drivers/xen/sys-hypervisor.c

@@ -114,7 +114,7 @@ static void xen_sysfs_version_destroy(void)
 
 /* UUID */
 
-static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+static ssize_t uuid_show_fallback(struct hyp_sysfs_attr *attr, char *buffer)
 {
 	char *vm, *val;
 	int ret;
@@ -135,6 +135,17 @@ static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
 	return ret;
 }
 
+static ssize_t uuid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	xen_domain_handle_t uuid;
+	int ret;
+	ret = HYPERVISOR_xen_version(XENVER_guest_handle, uuid);
+	if (ret)
+		return uuid_show_fallback(attr, buffer);
+	ret = sprintf(buffer, "%pU\n", uuid);
+	return ret;
+}
+
 HYPERVISOR_ATTR_RO(uuid);
 
 static int __init xen_sysfs_uuid_init(void)

drivers/xen/tmem.c

@@ -21,6 +21,7 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/tmem.h>
 
 #define TMEM_CONTROL               0
 #define TMEM_NEW_POOL              1

drivers/xen/xen-pciback/pci_stub.c

@@ -362,6 +362,7 @@ static int __devinit pcistub_init_device(struct pci_dev *dev)
 	else {
 		dev_dbg(&dev->dev, "reseting (FLR, D3, etc) the device\n");
 		__pci_reset_function_locked(dev);
+		pci_restore_state(dev);
 	}
 	/* Now disable the device (this also ensures some private device
 	 * data is setup before we export)
@@ -681,14 +682,14 @@ static pci_ers_result_t xen_pcibk_slot_reset(struct pci_dev *dev)
 		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
 			" by HVM, kill it\n");
 		kill_domain_by_device(psdev);
-		goto release;
+		goto end;
 	}
 
 	if (!test_bit(_XEN_PCIB_AERHANDLER,
 		(unsigned long *)&psdev->pdev->sh_info->flags)) {
 		dev_err(&dev->dev,
 			"guest with no AER driver should have been killed\n");
-		goto release;
+		goto end;
 	}
 	result = common_process(psdev, 1, XEN_PCI_OP_aer_slotreset, result);
 
@@ -698,9 +699,9 @@ static pci_ers_result_t xen_pcibk_slot_reset(struct pci_dev *dev)
 			"No AER slot_reset service or disconnected!\n");
 		kill_domain_by_device(psdev);
 	}
-release:
-	pcistub_device_put(psdev);
 end:
+	if (psdev)
+		pcistub_device_put(psdev);
 	up_write(&pcistub_sem);
 	return result;
 
@@ -739,14 +740,14 @@ static pci_ers_result_t xen_pcibk_mmio_enabled(struct pci_dev *dev)
 		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
 			" by HVM, kill it\n");
 		kill_domain_by_device(psdev);
-		goto release;
+		goto end;
 	}
 
 	if (!test_bit(_XEN_PCIB_AERHANDLER,
 		(unsigned long *)&psdev->pdev->sh_info->flags)) {
 		dev_err(&dev->dev,
 			"guest with no AER driver should have been killed\n");
-		goto release;
+		goto end;
 	}
 	result = common_process(psdev, 1, XEN_PCI_OP_aer_mmio, result);
 
@@ -756,9 +757,9 @@ static pci_ers_result_t xen_pcibk_mmio_enabled(struct pci_dev *dev)
 			"No AER mmio_enabled service or disconnected!\n");
 		kill_domain_by_device(psdev);
 	}
-release:
-	pcistub_device_put(psdev);
 end:
+	if (psdev)
+		pcistub_device_put(psdev);
 	up_write(&pcistub_sem);
 	return result;
 }
@@ -797,7 +798,7 @@ static pci_ers_result_t xen_pcibk_error_detected(struct pci_dev *dev,
 		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
 			" by HVM, kill it\n");
 		kill_domain_by_device(psdev);
-		goto release;
+		goto end;
 	}
 
 	/*Guest owns the device yet no aer handler regiested, kill guest*/
@@ -805,7 +806,7 @@ static pci_ers_result_t xen_pcibk_error_detected(struct pci_dev *dev,
 		(unsigned long *)&psdev->pdev->sh_info->flags)) {
 		dev_dbg(&dev->dev, "guest may have no aer driver, kill it\n");
 		kill_domain_by_device(psdev);
-		goto release;
+		goto end;
 	}
 	result = common_process(psdev, error, XEN_PCI_OP_aer_detected, result);
 
@@ -815,9 +816,9 @@ static pci_ers_result_t xen_pcibk_error_detected(struct pci_dev *dev,
 			"No AER error_detected service or disconnected!\n");
 		kill_domain_by_device(psdev);
 	}
-release:
-	pcistub_device_put(psdev);
 end:
+	if (psdev)
+		pcistub_device_put(psdev);
 	up_write(&pcistub_sem);
 	return result;
 }
@@ -851,7 +852,7 @@ static void xen_pcibk_error_resume(struct pci_dev *dev)
 		dev_err(&dev->dev, DRV_NAME " device is not connected or owned"
 			" by HVM, kill it\n");
 		kill_domain_by_device(psdev);
-		goto release;
+		goto end;
 	}
 
 	if (!test_bit(_XEN_PCIB_AERHANDLER,
@@ -859,13 +860,13 @@ static void xen_pcibk_error_resume(struct pci_dev *dev)
 		dev_err(&dev->dev,
 			"guest with no AER driver should have been killed\n");
 		kill_domain_by_device(psdev);
-		goto release;
+		goto end;
 	}
 	common_process(psdev, 1, XEN_PCI_OP_aer_resume,
 		       PCI_ERS_RESULT_RECOVERED);
-release:
-	pcistub_device_put(psdev);
 end:
+	if (psdev)
+		pcistub_device_put(psdev);
 	up_write(&pcistub_sem);
 	return;
 }
@@ -897,17 +898,41 @@ static inline int str_to_slot(const char *buf, int *domain, int *bus,
 			      int *slot, int *func)
 {
 	int err;
+	char wc = '*';
 
 	err = sscanf(buf, " %x:%x:%x.%x", domain, bus, slot, func);
-	if (err == 4)
+	switch (err) {
+	case 3:
+		*func = -1;
+		err = sscanf(buf, " %x:%x:%x.%c", domain, bus, slot, &wc);
+		break;
+	case 2:
+		*slot = *func = -1;
+		err = sscanf(buf, " %x:%x:*.%c", domain, bus, &wc);
+		if (err >= 2)
+			++err;
+		break;
+	}
+	if (err == 4 && wc == '*')
 		return 0;
 	else if (err < 0)
 		return -EINVAL;
 
 	/* try again without domain */
 	*domain = 0;
+	wc = '*';
 	err = sscanf(buf, " %x:%x.%x", bus, slot, func);
-	if (err == 3)
+	switch (err) {
+	case 2:
+		*func = -1;
+		err = sscanf(buf, " %x:%x.%c", bus, slot, &wc);
+		break;
+	case 1:
+		*slot = *func = -1;
+		err = sscanf(buf, " %x:*.%c", bus, &wc) + 1;
+		break;
+	}
+	if (err == 3 && wc == '*')
 		return 0;
 
 	return -EINVAL;
@@ -930,6 +955,19 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func)
 {
 	struct pcistub_device_id *pci_dev_id;
 	unsigned long flags;
+	int rc = 0;
+
+	if (slot < 0) {
+		for (slot = 0; !rc && slot < 32; ++slot)
+			rc = pcistub_device_id_add(domain, bus, slot, func);
+		return rc;
+	}
+
+	if (func < 0) {
+		for (func = 0; !rc && func < 8; ++func)
+			rc = pcistub_device_id_add(domain, bus, slot, func);
+		return rc;
+	}
 
 	pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL);
 	if (!pci_dev_id)
@@ -952,15 +990,15 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func)
 static int pcistub_device_id_remove(int domain, int bus, int slot, int func)
 {
 	struct pcistub_device_id *pci_dev_id, *t;
-	int devfn = PCI_DEVFN(slot, func);
 	int err = -ENOENT;
 	unsigned long flags;
 
 	spin_lock_irqsave(&device_ids_lock, flags);
 	list_for_each_entry_safe(pci_dev_id, t, &pcistub_device_ids,
 				 slot_list) {
-		if (pci_dev_id->domain == domain
-		    && pci_dev_id->bus == bus && pci_dev_id->devfn == devfn) {
+		if (pci_dev_id->domain == domain && pci_dev_id->bus == bus
+		    && (slot < 0 || PCI_SLOT(pci_dev_id->devfn) == slot)
+		    && (func < 0 || PCI_FUNC(pci_dev_id->devfn) == func)) {
 			/* Don't break; here because it's possible the same
 			 * slot could be in the list more than once
 			 */
@@ -987,7 +1025,7 @@ static int pcistub_reg_add(int domain, int bus, int slot, int func, int reg,
 	struct config_field *field;
 
 	psdev = pcistub_device_find(domain, bus, slot, func);
-	if (!psdev || !psdev->dev) {
+	if (!psdev) {
 		err = -ENODEV;
 		goto out;
 	}
@@ -1011,6 +1049,8 @@ static int pcistub_reg_add(int domain, int bus, int slot, int func, int reg,
 	if (err)
 		kfree(field);
 out:
+	if (psdev)
+		pcistub_device_put(psdev);
 	return err;
 }
 
@@ -1115,10 +1155,9 @@ static ssize_t pcistub_irq_handler_switch(struct device_driver *drv,
 
 	err = str_to_slot(buf, &domain, &bus, &slot, &func);
 	if (err)
-		goto out;
+		return err;
 
 	psdev = pcistub_device_find(domain, bus, slot, func);
-
 	if (!psdev)
 		goto out;
 
@@ -1134,6 +1173,8 @@ static ssize_t pcistub_irq_handler_switch(struct device_driver *drv,
 	if (dev_data->isr_on)
 		dev_data->ack_intr = 1;
 out:
+	if (psdev)
+		pcistub_device_put(psdev);
 	if (!err)
 		err = count;
 	return err;
@@ -1216,15 +1257,16 @@ static ssize_t permissive_add(struct device_driver *drv, const char *buf,
 	err = str_to_slot(buf, &domain, &bus, &slot, &func);
 	if (err)
 		goto out;
+	if (slot < 0 || func < 0) {
+		err = -EINVAL;
+		goto out;
+	}
 	psdev = pcistub_device_find(domain, bus, slot, func);
 	if (!psdev) {
 		err = -ENODEV;
 		goto out;
 	}
-	if (!psdev->dev) {
-		err = -ENODEV;
-		goto release;
-	}
+
 	dev_data = pci_get_drvdata(psdev->dev);
 	/* the driver data for a device should never be null at this point */
 	if (!dev_data) {
@@ -1297,17 +1339,51 @@ static int __init pcistub_init(void)
 
 	if (pci_devs_to_hide && *pci_devs_to_hide) {
 		do {
+			char wc = '*';
+
 			parsed = 0;
 
 			err = sscanf(pci_devs_to_hide + pos,
 				     " (%x:%x:%x.%x) %n",
 				     &domain, &bus, &slot, &func, &parsed);
-			if (err != 4) {
+			switch (err) {
+			case 3:
+				func = -1;
+				err = sscanf(pci_devs_to_hide + pos,
+					     " (%x:%x:%x.%c) %n",
+					     &domain, &bus, &slot, &wc,
+					     &parsed);
+				break;
+			case 2:
+				slot = func = -1;
+				err = sscanf(pci_devs_to_hide + pos,
+					     " (%x:%x:*.%c) %n",
+					     &domain, &bus, &wc, &parsed) + 1;
+				break;
+			}
+
+			if (err != 4 || wc != '*') {
 				domain = 0;
+				wc = '*';
 				err = sscanf(pci_devs_to_hide + pos,
 					     " (%x:%x.%x) %n",
 					     &bus, &slot, &func, &parsed);
-				if (err != 3)
+				switch (err) {
+				case 2:
+					func = -1;
+					err = sscanf(pci_devs_to_hide + pos,
+						     " (%x:%x.%c) %n",
+						     &bus, &slot, &wc,
+						     &parsed);
+					break;
+				case 1:
+					slot = func = -1;
+					err = sscanf(pci_devs_to_hide + pos,
+						     " (%x:*.%c) %n",
+						     &bus, &wc, &parsed) + 1;
+					break;
+				}
+				if (err != 3 || wc != '*')
 					goto parse_error;
 			}
 

drivers/xen/xenbus/xenbus_client.c

@@ -490,8 +490,7 @@ static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
 
 	op.host_addr = arbitrary_virt_to_machine(pte).maddr;
 
-	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
-		BUG();
+	gnttab_batch_map(&op, 1);
 
 	if (op.status != GNTST_okay) {
 		free_vm_area(area);
@@ -572,8 +571,7 @@ int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref,
 	gnttab_set_map_op(&op, (unsigned long)vaddr, GNTMAP_host_map, gnt_ref,
 			  dev->otherend_id);
 
-	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
-		BUG();
+	gnttab_batch_map(&op, 1);
 
 	if (op.status != GNTST_okay) {
 		xenbus_dev_fatal(dev, op.status,

drivers/xen/xenbus/xenbus_comms.c

@@ -224,7 +224,7 @@ int xb_init_comms(void)
 		int err;
 		err = bind_evtchn_to_irqhandler(xen_store_evtchn, wake_waiting,
 						0, "xenbus", &xb_waitq);
-		if (err <= 0) {
+		if (err < 0) {
 			printk(KERN_ERR "XENBUS request irq failed %i\n", err);
 			return err;
 		}

drivers/xen/xenbus/xenbus_dev_backend.c

@@ -107,7 +107,7 @@ static int xenbus_backend_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-const struct file_operations xenbus_backend_fops = {
+static const struct file_operations xenbus_backend_fops = {
 	.open = xenbus_backend_open,
 	.mmap = xenbus_backend_mmap,
 	.unlocked_ioctl = xenbus_backend_ioctl,

drivers/xen/xenbus/xenbus_probe.c

@@ -324,8 +324,8 @@ static int cmp_dev(struct device *dev, void *data)
 	return 0;
 }
 
-struct xenbus_device *xenbus_device_find(const char *nodename,
-					 struct bus_type *bus)
+static struct xenbus_device *xenbus_device_find(const char *nodename,
+						struct bus_type *bus)
 {
 	struct xb_find_info info = { .dev = NULL, .nodename = nodename };
 
@@ -719,17 +719,47 @@ static int __init xenstored_local_init(void)
 	return err;
 }
 
+enum xenstore_init {
+	UNKNOWN,
+	PV,
+	HVM,
+	LOCAL,
+};
 static int __init xenbus_init(void)
 {
 	int err = 0;
+	enum xenstore_init usage = UNKNOWN;
+	uint64_t v = 0;
 
 	if (!xen_domain())
 		return -ENODEV;
 
 	xenbus_ring_ops_init();
 
-	if (xen_hvm_domain()) {
-		uint64_t v = 0;
+	if (xen_pv_domain())
+		usage = PV;
+	if (xen_hvm_domain())
+		usage = HVM;
+	if (xen_hvm_domain() && xen_initial_domain())
+		usage = LOCAL;
+	if (xen_pv_domain() && !xen_start_info->store_evtchn)
+		usage = LOCAL;
+	if (xen_pv_domain() && xen_start_info->store_evtchn)
+		xenstored_ready = 1;
+
+	switch (usage) {
+	case LOCAL:
+		err = xenstored_local_init();
+		if (err)
+			goto out_error;
+		xen_store_interface = mfn_to_virt(xen_store_mfn);
+		break;
+	case PV:
+		xen_store_evtchn = xen_start_info->store_evtchn;
+		xen_store_mfn = xen_start_info->store_mfn;
+		xen_store_interface = mfn_to_virt(xen_store_mfn);
+		break;
+	case HVM:
 		err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v);
 		if (err)
 			goto out_error;
@@ -738,18 +768,12 @@ static int __init xenbus_init(void)
 		if (err)
 			goto out_error;
 		xen_store_mfn = (unsigned long)v;
-		xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
-	} else {
-		xen_store_evtchn = xen_start_info->store_evtchn;
-		xen_store_mfn = xen_start_info->store_mfn;
-		if (xen_store_evtchn)
-			xenstored_ready = 1;
-		else {
-			err = xenstored_local_init();
-			if (err)
-				goto out_error;
-		}
-		xen_store_interface = mfn_to_virt(xen_store_mfn);
+		xen_store_interface =
+			ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE);
+		break;
+	default:
+		pr_warn("Xenstore state unknown\n");
+		break;
 	}
 
 	/* Initialize the interface to xenstore. */

drivers/xen/xenbus/xenbus_probe_frontend.c

@@ -21,6 +21,7 @@
 #include <xen/xenbus.h>
 #include <xen/events.h>
 #include <xen/page.h>
+#include <xen/xen.h>
 
 #include <xen/platform_pci.h>
 

drivers/xen/xenbus/xenbus_xs.c

@@ -44,6 +44,7 @@
 #include <linux/rwsem.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <asm/xen/hypervisor.h>
 #include <xen/xenbus.h>
 #include <xen/xen.h>
 #include "xenbus_comms.h"
@@ -622,7 +623,7 @@ static void xs_reset_watches(void)
 {
 	int err, supported = 0;
 
-	if (!xen_hvm_domain())
+	if (!xen_hvm_domain() || xen_initial_domain())
 		return;
 
 	err = xenbus_scanf(XBT_NIL, "control",