Merge tag 'stable/for-linus-3.17-b-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull Xen bug fixes from David Vrabel:
 - fix for PVHVM suspend/resume and migration
 - don't pointlessly retry certain ballooning ops
 - fix gntalloc when grefs have run out.
 - fix PV boot if KSALR is enable or very large modules are used.

* tag 'stable/for-linus-3.17-b-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/xen: don't copy bogus duplicate entries into kernel page tables
  xen/gntalloc: safely delete grefs in add_grefs() undo path
  xen/gntalloc: fix oops after runnning out of grant refs
  xen/balloon: cancel ballooning if adding new memory failed
  xen/manage: Always freeze/thaw processes when suspend/resuming

arch/x86/include/asm/pgtable_64.h

@@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
+extern pte_t level1_fixmap_pgt[512];
 extern pgd_t init_level4_pgt[];
 
 #define swapper_pg_dir init_level4_pgt

arch/x86/xen/mmu.c

@@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
- * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt.  This
- * means that only the kernel has a physical mapping to start with -
- * but that's enough to get __va working.  We need to fill in the rest
- * of the physical mapping once some sort of allocator has been set
- * up.
- * NOTE: for PVH, the page tables are native.
+ * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
+ * kernel has a physical mapping to start with - but that's enough to
+ * get __va working.  We need to fill in the rest of the physical
+ * mapping once some sort of allocator has been set up.  NOTE: for
+ * PVH, the page tables are native.
  */
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
@@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		/* L3_i[0] -> level2_ident_pgt */
 		convert_pfn_mfn(level3_ident_pgt);
 		/* L3_k[510] -> level2_kernel_pgt
-		 * L3_i[511] -> level2_fixmap_pgt */
+		 * L3_k[511] -> level2_fixmap_pgt */
 		convert_pfn_mfn(level3_kernel_pgt);
+
+		/* L3_k[511][506] -> level1_fixmap_pgt */
+		convert_pfn_mfn(level2_fixmap_pgt);
 	}
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
@@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
 	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][511] have entries that point to the same
+	 * Both L4[272][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you
 	 * are OK - which is what cleanup_highmap does) */
 	copy_page(level2_ident_pgt, l2);
-	/* Graft it onto L4[511][511] */
+	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
-	/* Get [511][510] and graft that in level2_fixmap_pgt */
-	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
-	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
-	copy_page(level2_fixmap_pgt, l2);
-	/* Note that we don't do anything with level1_fixmap_pgt which
-	 * we don't need. */
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/* Make pagetable pieces RO */
 		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
@@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
 
 		/* Pin down new L4 */
 		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,

drivers/xen/balloon.c

@@ -230,8 +230,8 @@ static enum bp_state reserve_additional_memory(long credit)
 	rc = add_memory(nid, hotplug_start_paddr, balloon_hotplug << PAGE_SHIFT);
 
 	if (rc) {
-		pr_info("%s: add_memory() failed: %i\n", __func__, rc);
-		return BP_EAGAIN;
+		pr_warn("Cannot add additional memory (%i)\n", rc);
+		return BP_ECANCELED;
 	}
 
 	balloon_hotplug -= credit;

drivers/xen/gntalloc.c

@@ -124,7 +124,7 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op,
 	int i, rc, readonly;
 	LIST_HEAD(queue_gref);
 	LIST_HEAD(queue_file);
-	struct gntalloc_gref *gref;
+	struct gntalloc_gref *gref, *next;
 
 	readonly = !(op->flags & GNTALLOC_FLAG_WRITABLE);
 	rc = -ENOMEM;
@@ -141,13 +141,11 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op,
 			goto undo;
 
 		/* Grant foreign access to the page. */
-		gref->gref_id = gnttab_grant_foreign_access(op->domid,
+		rc = gnttab_grant_foreign_access(op->domid,
 			pfn_to_mfn(page_to_pfn(gref->page)), readonly);
-		if ((int)gref->gref_id < 0) {
-			rc = gref->gref_id;
+		if (rc < 0)
 			goto undo;
-		}
-		gref_ids[i] = gref->gref_id;
+		gref_ids[i] = gref->gref_id = rc;
 	}
 
 	/* Add to gref lists. */
@@ -162,8 +160,8 @@ undo:
 	mutex_lock(&gref_mutex);
 	gref_size -= (op->count - i);
 
-	list_for_each_entry(gref, &queue_file, next_file) {
-		/* __del_gref does not remove from queue_file */
+	list_for_each_entry_safe(gref, next, &queue_file, next_file) {
+		list_del(&gref->next_file);
 		__del_gref(gref);
 	}
 
@@ -193,7 +191,7 @@ static void __del_gref(struct gntalloc_gref *gref)
 
 	gref->notify.flags = 0;
 
-	if (gref->gref_id > 0) {
+	if (gref->gref_id) {
 		if (gnttab_query_foreign_access(gref->gref_id))
 			return;
 

drivers/xen/manage.c

@@ -103,16 +103,11 @@ static void do_suspend(void)
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
-#ifdef CONFIG_PREEMPT
-	/* If the kernel is preemptible, we need to freeze all the processes
-	   to prevent them from being in the middle of a pagetable update
-	   during suspend. */
 	err = freeze_processes();
 	if (err) {
 		pr_err("%s: freeze failed %d\n", __func__, err);
 		goto out;
 	}
-#endif
 
 	err = dpm_suspend_start(PMSG_FREEZE);
 	if (err) {
@@ -157,10 +152,8 @@ out_resume:
 	dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
 
 out_thaw:
-#ifdef CONFIG_PREEMPT
 	thaw_processes();
 out:
-#endif
 	shutting_down = SHUTDOWN_INVALID;
 }
 #endif	/* CONFIG_HIBERNATE_CALLBACKS */