Merge tag 'stable/for-linus-3.16-rc0-tag' of...

Merge tag 'stable/for-linus-3.16-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip into next

Pull Xen updates from David Vrabel:
 "xen: features and fixes for 3.16-rc0
   - support foreign mappings in PVH domains (needed when dom0 is PVH)

   - fix mapping high MMIO regions in x86 PV guests (this is also the
     first half of removing the PAGE_IOMAP PTE flag).

   - ARM suspend/resume support.

   - ARM multicall support"

* tag 'stable/for-linus-3.16-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/xen: map foreign pfns for autotranslated guests
  xen-acpi-processor: Don't display errors when we get -ENOSYS
  xen/pciback: Document the entry points for 'pcistub_put_pci_dev'
  xen/pciback: Document when the 'unbind' and 'bind' functions are called.
  xen-pciback: Document when we FLR an PCI device.
  xen-pciback: First reset, then free.
  xen-pciback: Cleanup up pcistub_put_pci_dev
  x86/xen: do not use _PAGE_IOMAP in xen_remap_domain_mfn_range()
  x86/xen: set regions above the end of RAM as 1:1
  x86/xen: only warn once if bad MFNs are found during setup
  x86/xen: compactly store large identity ranges in the p2m
  x86/xen: fix set_phys_range_identity() if pfn_e > MAX_P2M_PFN
  x86/xen: rename early_p2m_alloc() and early_p2m_alloc_middle()
  xen/x86: set panic notifier priority to minimum
  arm,arm64/xen: introduce HYPERVISOR_suspend()
  xen: refactor suspend pre/post hooks
  arm: xen: export HYPERVISOR_multicall to modules.
  arm64: introduce virt_to_pfn
  arm/xen: Remove definiition of virt_to_pfn in asm/xen/page.h
  arm: xen: implement multicall hypercall support.

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

@@ -34,6 +34,7 @@
 #define _ASM_ARM_XEN_HYPERCALL_H
 
 #include <xen/interface/xen.h>
+#include <xen/interface/sched.h>
 
 long privcmd_call(unsigned call, unsigned long a1,
 		unsigned long a2, unsigned long a3,
@@ -48,6 +49,16 @@ int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
 int HYPERVISOR_physdev_op(int cmd, void *arg);
 int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
 int HYPERVISOR_tmem_op(void *arg);
+int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr);
+
+static inline int
+HYPERVISOR_suspend(unsigned long start_info_mfn)
+{
+	struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+	/* start_info_mfn is unused on ARM */
+	return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
+}
 
 static inline void
 MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
@@ -63,9 +74,4 @@ MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
 	BUG();
 }
 
-static inline int
-HYPERVISOR_multicall(void *call_list, int nr_calls)
-{
-	BUG();
-}
 #endif /* _ASM_ARM_XEN_HYPERCALL_H */

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

@@ -40,6 +40,8 @@ typedef uint64_t xen_pfn_t;
 #define PRI_xen_pfn "llx"
 typedef uint64_t xen_ulong_t;
 #define PRI_xen_ulong "llx"
+typedef int64_t xen_long_t;
+#define PRI_xen_long "llx"
 /* Guest handles for primitive C types. */
 __DEFINE_GUEST_HANDLE(uchar, unsigned char);
 __DEFINE_GUEST_HANDLE(uint,  unsigned int);

arch/arm/xen/enlighten.c

@@ -339,6 +339,14 @@ static int __init xen_pm_init(void)
 }
 late_initcall(xen_pm_init);
 
+
+/* empty stubs */
+void xen_arch_pre_suspend(void) { }
+void xen_arch_post_suspend(int suspend_cancelled) { }
+void xen_timer_resume(void) { }
+void xen_arch_resume(void) { }
+
+
 /* In the hypervisor.S file. */
 EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
@@ -350,4 +358,5 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
 EXPORT_SYMBOL_GPL(privcmd_call);

arch/arm/xen/hypercall.S

@@ -89,6 +89,7 @@ HYPERCALL2(memory_op);
 HYPERCALL2(physdev_op);
 HYPERCALL3(vcpu_op);
 HYPERCALL1(tmem_op);
+HYPERCALL2(multicall);
 
 ENTRY(privcmd_call)
 	stmdb sp!, {r4}

arch/arm64/xen/hypercall.S

@@ -80,6 +80,7 @@ HYPERCALL2(memory_op);
 HYPERCALL2(physdev_op);
 HYPERCALL3(vcpu_op);
 HYPERCALL1(tmem_op);
+HYPERCALL2(multicall);
 
 ENTRY(privcmd_call)
 	mov x16, x0

arch/x86/include/asm/xen/hypercall.h

@@ -343,7 +343,7 @@ HYPERVISOR_memory_op(unsigned int cmd, void *arg)
 }
 
 static inline int
-HYPERVISOR_multicall(void *call_list, int nr_calls)
+HYPERVISOR_multicall(void *call_list, uint32_t nr_calls)
 {
 	return _hypercall2(int, multicall, call_list, nr_calls);
 }

arch/x86/include/asm/xen/interface.h

@@ -54,6 +54,9 @@ typedef unsigned long xen_pfn_t;
 #define PRI_xen_pfn "lx"
 typedef unsigned long xen_ulong_t;
 #define PRI_xen_ulong "lx"
+typedef long xen_long_t;
+#define PRI_xen_long "lx"
+
 /* Guest handles for primitive C types. */
 __DEFINE_GUEST_HANDLE(uchar, unsigned char);
 __DEFINE_GUEST_HANDLE(uint,  unsigned int);

arch/x86/xen/enlighten.c

@@ -1339,6 +1339,7 @@ xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
 
 static struct notifier_block xen_panic_block = {
 	.notifier_call= xen_panic_event,
+	.priority = INT_MIN
 };
 
 int xen_panic_handler_init(void)

arch/x86/xen/mmu.c

@@ -2510,6 +2510,95 @@ void __init xen_hvm_init_mmu_ops(void)
 }
 #endif
 
+#ifdef CONFIG_XEN_PVH
+/*
+ * Map foreign gfn (fgfn), to local pfn (lpfn). This for the user
+ * space creating new guest on pvh dom0 and needing to map domU pages.
+ */
+static int xlate_add_to_p2m(unsigned long lpfn, unsigned long fgfn,
+			    unsigned int domid)
+{
+	int rc, err = 0;
+	xen_pfn_t gpfn = lpfn;
+	xen_ulong_t idx = fgfn;
+
+	struct xen_add_to_physmap_range xatp = {
+		.domid = DOMID_SELF,
+		.foreign_domid = domid,
+		.size = 1,
+		.space = XENMAPSPACE_gmfn_foreign,
+	};
+	set_xen_guest_handle(xatp.idxs, &idx);
+	set_xen_guest_handle(xatp.gpfns, &gpfn);
+	set_xen_guest_handle(xatp.errs, &err);
+
+	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
+	if (rc < 0)
+		return rc;
+	return err;
+}
+
+static int xlate_remove_from_p2m(unsigned long spfn, int count)
+{
+	struct xen_remove_from_physmap xrp;
+	int i, rc;
+
+	for (i = 0; i < count; i++) {
+		xrp.domid = DOMID_SELF;
+		xrp.gpfn = spfn+i;
+		rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
+		if (rc)
+			break;
+	}
+	return rc;
+}
+
+struct xlate_remap_data {
+	unsigned long fgfn; /* foreign domain's gfn */
+	pgprot_t prot;
+	domid_t  domid;
+	int index;
+	struct page **pages;
+};
+
+static int xlate_map_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
+			    void *data)
+{
+	int rc;
+	struct xlate_remap_data *remap = data;
+	unsigned long pfn = page_to_pfn(remap->pages[remap->index++]);
+	pte_t pteval = pte_mkspecial(pfn_pte(pfn, remap->prot));
+
+	rc = xlate_add_to_p2m(pfn, remap->fgfn, remap->domid);
+	if (rc)
+		return rc;
+	native_set_pte(ptep, pteval);
+
+	return 0;
+}
+
+static int xlate_remap_gfn_range(struct vm_area_struct *vma,
+				 unsigned long addr, unsigned long mfn,
+				 int nr, pgprot_t prot, unsigned domid,
+				 struct page **pages)
+{
+	int err;
+	struct xlate_remap_data pvhdata;
+
+	BUG_ON(!pages);
+
+	pvhdata.fgfn = mfn;
+	pvhdata.prot = prot;
+	pvhdata.domid = domid;
+	pvhdata.index = 0;
+	pvhdata.pages = pages;
+	err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT,
+				  xlate_map_pte_fn, &pvhdata);
+	flush_tlb_all();
+	return err;
+}
+#endif
+
 #define REMAP_BATCH_SIZE 16
 
 struct remap_data {
@@ -2522,7 +2611,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token,
 				 unsigned long addr, void *data)
 {
 	struct remap_data *rmd = data;
-	pte_t pte = pte_mkspecial(pfn_pte(rmd->mfn++, rmd->prot));
+	pte_t pte = pte_mkspecial(mfn_pte(rmd->mfn++, rmd->prot));
 
 	rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
 	rmd->mmu_update->val = pte_val_ma(pte);
@@ -2544,13 +2633,18 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	unsigned long range;
 	int err = 0;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return -EINVAL;
-
-	prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
-
 	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
 
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+#ifdef CONFIG_XEN_PVH
+		/* We need to update the local page tables and the xen HAP */
+		return xlate_remap_gfn_range(vma, addr, mfn, nr, prot,
+					     domid, pages);
+#else
+		return -EINVAL;
+#endif
+        }
+
 	rmd.mfn = mfn;
 	rmd.prot = prot;
 
@@ -2588,6 +2682,25 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
 	if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
 		return 0;
 
+#ifdef CONFIG_XEN_PVH
+	while (numpgs--) {
+		/*
+		 * The mmu has already cleaned up the process mmu
+		 * resources at this point (lookup_address will return
+		 * NULL).
+		 */
+		unsigned long pfn = page_to_pfn(pages[numpgs]);
+
+		xlate_remove_from_p2m(pfn, 1);
+	}
+	/*
+	 * We don't need to flush tlbs because as part of
+	 * xlate_remove_from_p2m, the hypervisor will do tlb flushes
+	 * after removing the p2m entries from the EPT/NPT
+	 */
+	return 0;
+#else
 	return -EINVAL;
+#endif
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);

arch/x86/xen/p2m.c

@@ -36,7 +36,7 @@
  *  pfn_to_mfn(0xc0000)=0xc0000
  *
  * The benefit of this is, that we can assume for non-RAM regions (think
- * PCI BARs, or ACPI spaces), we can create mappings easily b/c we
+ * PCI BARs, or ACPI spaces), we can create mappings easily because we
  * get the PFN value to match the MFN.
  *
  * For this to work efficiently we have one new page p2m_identity and
@@ -60,7 +60,7 @@
  * There is also a digram of the P2M at the end that can help.
  * Imagine your E820 looking as so:
  *
- *                    1GB                                           2GB
+ *                    1GB                                           2GB    4GB
  * /-------------------+---------\/----\         /----------\    /---+-----\
  * | System RAM        | Sys RAM ||ACPI|         | reserved |    | Sys RAM |
  * \-------------------+---------/\----/         \----------/    \---+-----/
@@ -77,9 +77,8 @@
  * of the PFN and the end PFN (263424 and 512256 respectively). The first step
  * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page
  * covers 512^2 of page estate (1GB) and in case the start or end PFN is not
- * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn
- * to end pfn.  We reserve_brk top leaf pages if they are missing (means they
- * point to p2m_mid_missing).
+ * aligned on 512^2*PAGE_SIZE (1GB) we reserve_brk new middle and leaf pages as
+ * required to split any existing p2m_mid_missing middle pages.
  *
  * With the E820 example above, 263424 is not 1GB aligned so we allocate a
  * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000.
@@ -88,7 +87,7 @@
  * Next stage is to determine if we need to do a more granular boundary check
  * on the 4MB (or 2MB depending on architecture) off the start and end pfn's.
  * We check if the start pfn and end pfn violate that boundary check, and if
- * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer
+ * so reserve_brk a (p2m[x][y]) leaf page. This way we have a much finer
  * granularity of setting which PFNs are missing and which ones are identity.
  * In our example 263424 and 512256 both fail the check so we reserve_brk two
  * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing"
@@ -102,9 +101,10 @@
  *
  * The next step is to walk from the start pfn to the end pfn setting
  * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity.
- * If we find that the middle leaf is pointing to p2m_missing we can swap it
- * over to p2m_identity - this way covering 4MB (or 2MB) PFN space.  At this
- * point we do not need to worry about boundary aligment (so no need to
+ * If we find that the middle entry is pointing to p2m_missing we can swap it
+ * over to p2m_identity - this way covering 4MB (or 2MB) PFN space (and
+ * similarly swapping p2m_mid_missing for p2m_mid_identity for larger regions).
+ * At this point we do not need to worry about boundary aligment (so no need to
  * reserve_brk a middle page, figure out which PFNs are "missing" and which
  * ones are identity), as that has been done earlier.  If we find that the
  * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference
@@ -118,6 +118,9 @@
  * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511]
  * contain the INVALID_P2M_ENTRY value and are considered "missing."
  *
+ * Finally, the region beyond the end of of the E820 (4 GB in this example)
+ * is set to be identity (in case there are MMIO regions placed here).
+ *
  * This is what the p2m ends up looking (for the E820 above) with this
  * fabulous drawing:
  *
@@ -129,21 +132,27 @@
  *  |-----|    \                      | [p2m_identity]+\\    | ....            |
  *  |  2  |--\  \-------------------->|  ...          | \\   \----------------/
  *  |-----|   \                       \---------------/  \\
- *  |  3  |\   \                                          \\  p2m_identity
- *  |-----| \   \-------------------->/---------------\   /-----------------\
- *  | ..  +->+                        | [p2m_identity]+-->| ~0, ~0, ~0, ... |
- *  \-----/ /                         | [p2m_identity]+-->| ..., ~0         |
- *         / /---------------\        | ....          |   \-----------------/
- *        /  | IDENTITY[@0]  |      /-+-[x], ~0, ~0.. |
- *       /   | IDENTITY[@256]|<----/  \---------------/
- *      /    | ~0, ~0, ....  |
- *     |     \---------------/
- *     |
- *   p2m_mid_missing           p2m_missing
- * /-----------------\     /------------\
- * | [p2m_missing]   +---->| ~0, ~0, ~0 |
- * | [p2m_missing]   +---->| ..., ~0    |
- * \-----------------/     \------------/
+ *  |  3  |-\  \                                          \\  p2m_identity [1]
+ *  |-----|  \  \-------------------->/---------------\   /-----------------\
+ *  | ..  |\  |                       | [p2m_identity]+-->| ~0, ~0, ~0, ... |
+ *  \-----/ | |                       | [p2m_identity]+-->| ..., ~0         |
+ *          | |                       | ....          |   \-----------------/
+ *          | |                       +-[x], ~0, ~0.. +\
+ *          | |                       \---------------/ \
+ *          | |                                          \-> /---------------\
+ *          | V  p2m_mid_missing       p2m_missing           | IDENTITY[@0]  |
+ *          | /-----------------\     /------------\         | IDENTITY[@256]|
+ *          | | [p2m_missing]   +---->| ~0, ~0, ...|         | ~0, ~0, ....  |
+ *          | | [p2m_missing]   +---->| ..., ~0    |         \---------------/
+ *          | | ...             |     \------------/
+ *          | \-----------------/
+ *          |
+ *          |     p2m_mid_identity
+ *          |   /-----------------\
+ *          \-->| [p2m_identity]  +---->[1]
+ *              | [p2m_identity]  +---->[1]
+ *              | ...             |
+ *              \-----------------/
  *
  * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
  */
@@ -187,13 +196,15 @@ static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
 static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
 
 static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_identity, P2M_MID_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE);
 
 RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
 RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
 
 /* We might hit two boundary violations at the start and end, at max each
  * boundary violation will require three middle nodes. */
-RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
+RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3);
 
 /* When we populate back during bootup, the amount of pages can vary. The
  * max we have is seen is 395979, but that does not mean it can't be more.
@@ -242,20 +253,20 @@ static void p2m_top_mfn_p_init(unsigned long **top)
 		top[i] = p2m_mid_missing_mfn;
 }
 
-static void p2m_mid_init(unsigned long **mid)
+static void p2m_mid_init(unsigned long **mid, unsigned long *leaf)
 {
 	unsigned i;
 
 	for (i = 0; i < P2M_MID_PER_PAGE; i++)
-		mid[i] = p2m_missing;
+		mid[i] = leaf;
 }
 
-static void p2m_mid_mfn_init(unsigned long *mid)
+static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf)
 {
 	unsigned i;
 
 	for (i = 0; i < P2M_MID_PER_PAGE; i++)
-		mid[i] = virt_to_mfn(p2m_missing);
+		mid[i] = virt_to_mfn(leaf);
 }
 
 static void p2m_init(unsigned long *p2m)
@@ -286,7 +297,9 @@ void __ref xen_build_mfn_list_list(void)
 	/* Pre-initialize p2m_top_mfn to be completely missing */
 	if (p2m_top_mfn == NULL) {
 		p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		p2m_mid_mfn_init(p2m_mid_missing_mfn);
+		p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing);
+		p2m_mid_identity_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
+		p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity);
 
 		p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
 		p2m_top_mfn_p_init(p2m_top_mfn_p);
@@ -295,7 +308,8 @@ void __ref xen_build_mfn_list_list(void)
 		p2m_top_mfn_init(p2m_top_mfn);
 	} else {
 		/* Reinitialise, mfn's all change after migration */
-		p2m_mid_mfn_init(p2m_mid_missing_mfn);
+		p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing);
+		p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity);
 	}
 
 	for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
@@ -327,7 +341,7 @@ void __ref xen_build_mfn_list_list(void)
 			 * it too late.
 			 */
 			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_mid_mfn_init(mid_mfn_p);
+			p2m_mid_mfn_init(mid_mfn_p, p2m_missing);
 
 			p2m_top_mfn_p[topidx] = mid_mfn_p;
 		}
@@ -365,16 +379,17 @@ void __init xen_build_dynamic_phys_to_machine(void)
 
 	p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
 	p2m_init(p2m_missing);
+	p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
+	p2m_init(p2m_identity);
 
 	p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	p2m_mid_init(p2m_mid_missing);
+	p2m_mid_init(p2m_mid_missing, p2m_missing);
+	p2m_mid_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
+	p2m_mid_init(p2m_mid_identity, p2m_identity);
 
 	p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
 	p2m_top_init(p2m_top);
 
-	p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
-	p2m_init(p2m_identity);
-
 	/*
 	 * The domain builder gives us a pre-constructed p2m array in
 	 * mfn_list for all the pages initially given to us, so we just
@@ -386,7 +401,7 @@ void __init xen_build_dynamic_phys_to_machine(void)
 
 		if (p2m_top[topidx] == p2m_mid_missing) {
 			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
-			p2m_mid_init(mid);
+			p2m_mid_init(mid, p2m_missing);
 
 			p2m_top[topidx] = mid;
 		}
@@ -492,7 +507,7 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 	unsigned topidx, mididx, idx;
 
 	if (unlikely(pfn >= MAX_P2M_PFN))
-		return INVALID_P2M_ENTRY;
+		return IDENTITY_FRAME(pfn);
 
 	topidx = p2m_top_index(pfn);
 	mididx = p2m_mid_index(pfn);
@@ -545,7 +560,7 @@ static bool alloc_p2m(unsigned long pfn)
 		if (!mid)
 			return false;
 
-		p2m_mid_init(mid);
+		p2m_mid_init(mid, p2m_missing);
 
 		if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
 			free_p2m_page(mid);
@@ -565,7 +580,7 @@ static bool alloc_p2m(unsigned long pfn)
 		if (!mid_mfn)
 			return false;
 
-		p2m_mid_mfn_init(mid_mfn);
+		p2m_mid_mfn_init(mid_mfn, p2m_missing);
 
 		missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
 		mid_mfn_mfn = virt_to_mfn(mid_mfn);
@@ -596,7 +611,7 @@ static bool alloc_p2m(unsigned long pfn)
 	return true;
 }
 
-static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary)
+static bool __init early_alloc_p2m(unsigned long pfn, bool check_boundary)
 {
 	unsigned topidx, mididx, idx;
 	unsigned long *p2m;
@@ -638,7 +653,7 @@ static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary
 	return true;
 }
 
-static bool __init early_alloc_p2m(unsigned long pfn)
+static bool __init early_alloc_p2m_middle(unsigned long pfn)
 {
 	unsigned topidx = p2m_top_index(pfn);
 	unsigned long *mid_mfn_p;
@@ -649,7 +664,7 @@ static bool __init early_alloc_p2m(unsigned long pfn)
 	if (mid == p2m_mid_missing) {
 		mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
 
-		p2m_mid_init(mid);
+		p2m_mid_init(mid, p2m_missing);
 
 		p2m_top[topidx] = mid;
 
@@ -658,12 +673,12 @@ static bool __init early_alloc_p2m(unsigned long pfn)
 	/* And the save/restore P2M tables.. */
 	if (mid_mfn_p == p2m_mid_missing_mfn) {
 		mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		p2m_mid_mfn_init(mid_mfn_p);
+		p2m_mid_mfn_init(mid_mfn_p, p2m_missing);
 
 		p2m_top_mfn_p[topidx] = mid_mfn_p;
 		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
 		/* Note: we don't set mid_mfn_p[midix] here,
-		 * look in early_alloc_p2m_middle */
+		 * look in early_alloc_p2m() */
 	}
 	return true;
 }
@@ -739,7 +754,7 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_
 
 	/* This shouldn't happen */
 	if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
-		early_alloc_p2m(set_pfn);
+		early_alloc_p2m_middle(set_pfn);
 
 	if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
 		return false;
@@ -754,13 +769,13 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_
 bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
-		if (!early_alloc_p2m(pfn))
+		if (!early_alloc_p2m_middle(pfn))
 			return false;
 
 		if (early_can_reuse_p2m_middle(pfn, mfn))
 			return __set_phys_to_machine(pfn, mfn);
 
-		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
+		if (!early_alloc_p2m(pfn, false /* boundary crossover OK!*/))
 			return false;
 
 		if (!__set_phys_to_machine(pfn, mfn))
@@ -769,12 +784,30 @@ bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 	return true;
 }
+
+static void __init early_split_p2m(unsigned long pfn)
+{
+	unsigned long mididx, idx;
+
+	mididx = p2m_mid_index(pfn);
+	idx = p2m_index(pfn);
+
+	/*
+	 * Allocate new middle and leaf pages if this pfn lies in the
+	 * middle of one.
+	 */
+	if (mididx || idx)
+		early_alloc_p2m_middle(pfn);
+	if (idx)
+		early_alloc_p2m(pfn, false);
+}
+
 unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 				      unsigned long pfn_e)
 {
 	unsigned long pfn;
 
-	if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
+	if (unlikely(pfn_s >= MAX_P2M_PFN))
 		return 0;
 
 	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
@@ -783,19 +816,30 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 	if (pfn_s > pfn_e)
 		return 0;
 
-	for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
-		pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
-		pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
-	{
-		WARN_ON(!early_alloc_p2m(pfn));
-	}
+	if (pfn_e > MAX_P2M_PFN)
+		pfn_e = MAX_P2M_PFN;
 
-	early_alloc_p2m_middle(pfn_s, true);
-	early_alloc_p2m_middle(pfn_e, true);
+	early_split_p2m(pfn_s);
+	early_split_p2m(pfn_e);
+
+	for (pfn = pfn_s; pfn < pfn_e;) {
+		unsigned topidx = p2m_top_index(pfn);
+		unsigned mididx = p2m_mid_index(pfn);
 
-	for (pfn = pfn_s; pfn < pfn_e; pfn++)
 		if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
 			break;
+		pfn++;
+
+		/*
+		 * If the PFN was set to a middle or leaf identity
+		 * page the remainder must also be identity, so skip
+		 * ahead to the next middle or leaf entry.
+		 */
+		if (p2m_top[topidx] == p2m_mid_identity)
+			pfn = ALIGN(pfn, P2M_MID_PER_PAGE * P2M_PER_PAGE);
+		else if (p2m_top[topidx][mididx] == p2m_identity)
+			pfn = ALIGN(pfn, P2M_PER_PAGE);
+	}
 
 	if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
 		"Identity mapping failed. We are %ld short of 1-1 mappings!\n",
@@ -825,8 +869,22 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 	/* For sparse holes were the p2m leaf has real PFN along with
 	 * PCI holes, stick in the PFN as the MFN value.
+	 *
+	 * set_phys_range_identity() will have allocated new middle
+	 * and leaf pages as required so an existing p2m_mid_missing
+	 * or p2m_missing mean that whole range will be identity so
+	 * these can be switched to p2m_mid_identity or p2m_identity.
 	 */
 	if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
+		if (p2m_top[topidx] == p2m_mid_identity)
+			return true;
+
+		if (p2m_top[topidx] == p2m_mid_missing) {
+			WARN_ON(cmpxchg(&p2m_top[topidx], p2m_mid_missing,
+					p2m_mid_identity) != p2m_mid_missing);
+			return true;
+		}
+
 		if (p2m_top[topidx][mididx] == p2m_identity)
 			return true;
 

arch/x86/xen/setup.c

@@ -89,10 +89,10 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
 
-		if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+		if (WARN_ONCE(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
 			continue;
-		WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
-			pfn, mfn);
+		WARN_ONCE(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
+			  pfn, mfn);
 
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 	}
@@ -468,6 +468,15 @@ char * __init xen_memory_setup(void)
 			i++;
 	}
 
+	/*
+	 * Set the rest as identity mapped, in case PCI BARs are
+	 * located here.
+	 *
+	 * PFNs above MAX_P2M_PFN are considered identity mapped as
+	 * well.
+	 */
+	set_phys_range_identity(map[i-1].addr / PAGE_SIZE, ~0ul);
+
 	/*
 	 * In domU, the ISA region is normal, usable memory, but we
 	 * reserve ISA memory anyway because too many things poke

arch/x86/xen/suspend.c

@@ -12,8 +12,10 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-void xen_arch_pre_suspend(void)
+static void xen_pv_pre_suspend(void)
 {
+	xen_mm_pin_all();
+
 	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
 	xen_start_info->console.domU.mfn =
 		mfn_to_pfn(xen_start_info->console.domU.mfn);
@@ -26,7 +28,7 @@ void xen_arch_pre_suspend(void)
 		BUG();
 }
 
-void xen_arch_hvm_post_suspend(int suspend_cancelled)
+static void xen_hvm_post_suspend(int suspend_cancelled)
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
@@ -41,7 +43,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled)
 #endif
 }
 
-void xen_arch_post_suspend(int suspend_cancelled)
+static void xen_pv_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
 
@@ -60,6 +62,21 @@ void xen_arch_post_suspend(int suspend_cancelled)
 		xen_vcpu_restore();
 	}
 
+	xen_mm_unpin_all();
+}
+
+void xen_arch_pre_suspend(void)
+{
+    if (xen_pv_domain())
+        xen_pv_pre_suspend();
+}
+
+void xen_arch_post_suspend(int cancelled)
+{
+    if (xen_pv_domain())
+        xen_pv_post_suspend(cancelled);
+    else
+        xen_hvm_post_suspend(cancelled);
 }
 
 static void xen_vcpu_notify_restore(void *data)

arch/x86/xen/xen-ops.h

@@ -31,6 +31,8 @@ void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_reserve_top(void);
 extern unsigned long xen_max_p2m_pfn;
 
+void xen_mm_pin_all(void);
+void xen_mm_unpin_all(void);
 void xen_set_pat(u64);
 
 char * __init xen_memory_setup(void);

drivers/xen/manage.c

@@ -41,9 +41,6 @@ static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
 
 struct suspend_info {
 	int cancelled;
-	unsigned long arg; /* extra hypercall argument */
-	void (*pre)(void);
-	void (*post)(int cancelled);
 };
 
 static RAW_NOTIFIER_HEAD(xen_resume_notifier);
@@ -61,26 +58,6 @@ void xen_resume_notifier_unregister(struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(xen_resume_notifier_unregister);
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
-static void xen_hvm_post_suspend(int cancelled)
-{
-	xen_arch_hvm_post_suspend(cancelled);
-	gnttab_resume();
-}
-
-static void xen_pre_suspend(void)
-{
-	xen_mm_pin_all();
-	gnttab_suspend();
-	xen_arch_pre_suspend();
-}
-
-static void xen_post_suspend(int cancelled)
-{
-	xen_arch_post_suspend(cancelled);
-	gnttab_resume();
-	xen_mm_unpin_all();
-}
-
 static int xen_suspend(void *data)
 {
 	struct suspend_info *si = data;
@@ -94,18 +71,20 @@ static int xen_suspend(void *data)
 		return err;
 	}
 
-	if (si->pre)
-		si->pre();
+	gnttab_suspend();
+	xen_arch_pre_suspend();
 
 	/*
 	 * This hypercall returns 1 if suspend was cancelled
 	 * or the domain was merely checkpointed, and 0 if it
 	 * is resuming in a new domain.
 	 */
-	si->cancelled = HYPERVISOR_suspend(si->arg);
+	si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
+                                           ? virt_to_mfn(xen_start_info)
+                                           : 0);
 
-	if (si->post)
-		si->post(si->cancelled);
+	xen_arch_post_suspend(si->cancelled);
+	gnttab_resume();
 
 	if (!si->cancelled) {
 		xen_irq_resume();
@@ -154,16 +133,6 @@ static void do_suspend(void)
 
 	si.cancelled = 1;
 
-	if (xen_hvm_domain()) {
-		si.arg = 0UL;
-		si.pre = NULL;
-		si.post = &xen_hvm_post_suspend;
-	} else {
-		si.arg = virt_to_mfn(xen_start_info);
-		si.pre = &xen_pre_suspend;
-		si.post = &xen_post_suspend;
-	}
-
 	err = stop_machine(xen_suspend, &si, cpumask_of(0));
 
 	raw_notifier_call_chain(&xen_resume_notifier, 0, NULL);

drivers/xen/xen-acpi-processor.c

@@ -127,7 +127,7 @@ static int push_cxx_to_hypervisor(struct acpi_processor *_pr)
 			pr_debug("     C%d: %s %d uS\n",
 				 cx->type, cx->desc, (u32)cx->latency);
 		}
-	} else if (ret != -EINVAL)
+	} else if ((ret != -EINVAL) && (ret != -ENOSYS))
 		/* EINVAL means the ACPI ID is incorrect - meaning the ACPI
 		 * table is referencing a non-existing CPU - which can happen
 		 * with broken ACPI tables. */
@@ -259,7 +259,7 @@ static int push_pxx_to_hypervisor(struct acpi_processor *_pr)
 			(u32) perf->states[i].power,
 			(u32) perf->states[i].transition_latency);
 		}
-	} else if (ret != -EINVAL)
+	} else if ((ret != -EINVAL) && (ret != -ENOSYS))
 		/* EINVAL means the ACPI ID is incorrect - meaning the ACPI
 		 * table is referencing a non-existing CPU - which can happen
 		 * with broken ACPI tables. */

drivers/xen/xen-pciback/pci_stub.c

@@ -242,6 +242,15 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
 	return found_dev;
 }
 
+/*
+ * Called when:
+ *  - XenBus state has been reconfigure (pci unplug). See xen_pcibk_remove_device
+ *  - XenBus state has been disconnected (guest shutdown). See xen_pcibk_xenbus_remove
+ *  - 'echo BDF > unbind' on pciback module with no guest attached. See pcistub_remove
+ *  - 'echo BDF > unbind' with a guest still using it. See pcistub_remove
+ *
+ *  As such we have to be careful.
+ */
 void pcistub_put_pci_dev(struct pci_dev *dev)
 {
 	struct pcistub_device *psdev, *found_psdev = NULL;
@@ -272,16 +281,16 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	 * and want to inhibit the user from fiddling with 'reset'
 	 */
 	pci_reset_function(dev);
-	pci_restore_state(psdev->dev);
+	pci_restore_state(dev);
 
 	/* This disables the device. */
-	xen_pcibk_reset_device(found_psdev->dev);
+	xen_pcibk_reset_device(dev);
 
 	/* And cleanup up our emulated fields. */
-	xen_pcibk_config_free_dyn_fields(found_psdev->dev);
-	xen_pcibk_config_reset_dev(found_psdev->dev);
+	xen_pcibk_config_reset_dev(dev);
+	xen_pcibk_config_free_dyn_fields(dev);
 
-	xen_unregister_device_domain_owner(found_psdev->dev);
+	xen_unregister_device_domain_owner(dev);
 
 	spin_lock_irqsave(&found_psdev->lock, flags);
 	found_psdev->pdev = NULL;
@@ -493,6 +502,8 @@ static int pcistub_seize(struct pci_dev *dev)
 	return err;
 }
 
+/* Called when 'bind'. This means we must _NOT_ call pci_reset_function or
+ * other functions that take the sysfs lock. */
 static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	int err = 0;
@@ -520,6 +531,8 @@ static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return err;
 }
 
+/* Called when 'unbind'. This means we must _NOT_ call pci_reset_function or
+ * other functions that take the sysfs lock. */
 static void pcistub_remove(struct pci_dev *dev)
 {
 	struct pcistub_device *psdev, *found_psdev = NULL;
@@ -551,6 +564,8 @@ static void pcistub_remove(struct pci_dev *dev)
 			pr_warn("****** shutdown driver domain before binding device\n");
 			pr_warn("****** to other drivers or domains\n");
 
+			/* N.B. This ends up calling pcistub_put_pci_dev which ends up
+			 * doing the FLR. */
 			xen_pcibk_release_pci_dev(found_psdev->pdev,
 						found_psdev->dev);
 		}

drivers/xen/xen-pciback/xenbus.c

@@ -93,6 +93,8 @@ static void free_pdev(struct xen_pcibk_device *pdev)
 
 	xen_pcibk_disconnect(pdev);
 
+	/* N.B. This calls pcistub_put_pci_dev which does the FLR on all
+	 * of the PCIe devices. */
 	xen_pcibk_release_devices(pdev);
 
 	dev_set_drvdata(&pdev->xdev->dev, NULL);
@@ -286,6 +288,8 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
 	dev_dbg(&dev->dev, "unregistering for %d\n", pdev->xdev->otherend_id);
 	xen_unregister_device_domain_owner(dev);
 
+	/* N.B. This ends up calling pcistub_put_pci_dev which ends up
+	 * doing the FLR. */
 	xen_pcibk_release_pci_dev(pdev, dev);
 
 out:

include/xen/interface/xen.h

@@ -275,9 +275,9 @@ DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
  * NB. The fields are natural register size for this architecture.
  */
 struct multicall_entry {
-    unsigned long op;
-    long result;
-    unsigned long args[6];
+    xen_ulong_t op;
+    xen_long_t result;
+    xen_ulong_t args[6];
 };
 DEFINE_GUEST_HANDLE_STRUCT(multicall_entry);
 

include/xen/xen-ops.h

@@ -9,10 +9,6 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 
 void xen_arch_pre_suspend(void);
 void xen_arch_post_suspend(int suspend_cancelled);
-void xen_arch_hvm_post_suspend(int suspend_cancelled);
-
-void xen_mm_pin_all(void);
-void xen_mm_unpin_all(void);
 
 void xen_timer_resume(void);
 void xen_arch_resume(void);