Merge commit 'v3.3-rc6' into next

9 files changed, 103 insertions, 38 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 26c731a106a..fdce49c7aff 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -29,7 +29,8 @@ config XEN_PVHVM
 
 config XEN_MAX_DOMAIN_MEMORY
        int
-       default 128
+       default 500 if X86_64
+       default 64 if X86_32
        depends on XEN
        help
          This only affects the sizing of some bss arrays, the unused
@@ -48,3 +49,4 @@ config XEN_DEBUG_FS
 	help
 	  Enable statistics output and various tuning options in debugfs.
 	  Enabling this option may incur a significant performance overhead.
+
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index 7c0fedd98ea..ef1db1900d8 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -109,7 +109,7 @@ static const struct file_operations u32_array_fops = {
 	.llseek = no_llseek,
 };
 
-struct dentry *xen_debugfs_create_u32_array(const char *name, mode_t mode,
+struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
 					    struct dentry *parent,
 					    u32 *array, unsigned elements)
 {
diff --git a/arch/x86/xen/debugfs.h b/arch/x86/xen/debugfs.h
index e2813208483..78d25499be5 100644
--- a/arch/x86/xen/debugfs.h
+++ b/arch/x86/xen/debugfs.h
@@ -3,7 +3,7 @@
 
 struct dentry * __init xen_init_debugfs(void);
 
-struct dentry *xen_debugfs_create_u32_array(const char *name, mode_t mode,
+struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
 					    struct dentry *parent,
 					    u32 *array, unsigned elements);
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1f928659c33..4172af8ceeb 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1141,7 +1141,9 @@ asmlinkage void __init xen_start_kernel(void)
 
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
+#if 0
 	if (!xen_initial_domain())
+#endif
 		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
 	__supported_pte_mask |= _PAGE_IOMAP;
@@ -1204,10 +1206,6 @@ asmlinkage void __init xen_start_kernel(void)
 
 	pgd = (pgd_t *)xen_start_info->pt_base;
 
-	if (!xen_initial_domain())
-		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
-	__supported_pte_mask |= _PAGE_IOMAP;
 	/* Don't do the full vcpu_info placement stuff until we have a
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
@@ -1215,8 +1213,6 @@ asmlinkage void __init xen_start_kernel(void)
 	local_irq_disable();
 	early_boot_irqs_disabled = true;
 
-	memblock_init();
-
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
 	xen_ident_map_ISA();
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 5a40d24ba33..3a5f55d5190 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -54,6 +54,20 @@ static int map_pte_fn(pte_t *pte, struct page *pmd_page,
 	return 0;
 }
 
+/*
+ * This function is used to map shared frames to store grant status. It is
+ * different from map_pte_fn above, the frames type here is uint64_t.
+ */
+static int map_pte_fn_status(pte_t *pte, struct page *pmd_page,
+			     unsigned long addr, void *data)
+{
+	uint64_t **frames = (uint64_t **)data;
+
+	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
+	(*frames)++;
+	return 0;
+}
+
 static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
 			unsigned long addr, void *data)
 {
@@ -64,10 +78,10 @@ static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
 
 int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 			   unsigned long max_nr_gframes,
-			   struct grant_entry **__shared)
+			   void **__shared)
 {
 	int rc;
-	struct grant_entry *shared = *__shared;
+	void *shared = *__shared;
 
 	if (shared == NULL) {
 		struct vm_struct *area =
@@ -83,8 +97,30 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 	return rc;
 }
 
-void arch_gnttab_unmap_shared(struct grant_entry *shared,
-			      unsigned long nr_gframes)
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
+{
+	int rc;
+	grant_status_t *shared = *__shared;
+
+	if (shared == NULL) {
+		/* No need to pass in PTE as we are going to do it
+		 * in apply_to_page_range anyhow. */
+		struct vm_struct *area =
+			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
+		BUG_ON(area == NULL);
+		shared = area->addr;
+		*__shared = shared;
+	}
+
+	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
+				 PAGE_SIZE * nr_gframes,
+				 map_pte_fn_status, &frames);
+	return rc;
+}
+
+void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 {
 	apply_to_page_range(&init_mm, (unsigned long)shared,
 			    PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 87f6673b120..95c1cf60c66 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -415,13 +415,13 @@ static pteval_t iomap_pte(pteval_t val)
 static pteval_t xen_pte_val(pte_t pte)
 {
 	pteval_t pteval = pte.pte;
-
+#if 0
 	/* If this is a WC pte, convert back from Xen WC to Linux WC */
 	if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
 		WARN_ON(!pat_enabled);
 		pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
 	}
-
+#endif
 	if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
 		return pteval;
 
@@ -463,7 +463,7 @@ void xen_set_pat(u64 pat)
 static pte_t xen_make_pte(pteval_t pte)
 {
 	phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
 	/* If Linux is trying to set a WC pte, then map to the Xen WC.
 	 * If _PAGE_PAT is set, then it probably means it is really
 	 * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
@@ -476,7 +476,7 @@ static pte_t xen_make_pte(pteval_t pte)
 		if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
 			pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
 	}
-
+#endif
 	/*
 	 * Unprivileged domains are allowed to do IOMAPpings for
 	 * PCI passthrough, but not map ISA space.  The ISA
@@ -1774,10 +1774,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 	__xen_write_cr3(true, __pa(pgd));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
-	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
-		      __pa(xen_start_info->pt_base +
-			   xen_start_info->nr_pt_frames * PAGE_SIZE),
-		      "XEN PAGETABLES");
+	memblock_reserve(__pa(xen_start_info->pt_base),
+			 xen_start_info->nr_pt_frames * PAGE_SIZE);
 
 	return pgd;
 }
@@ -1853,10 +1851,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 			  PFN_DOWN(__pa(initial_page_table)));
 	xen_write_cr3(__pa(initial_page_table));
 
-	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
-		      __pa(xen_start_info->pt_base +
-			   xen_start_info->nr_pt_frames * PAGE_SIZE),
-		      "XEN PAGETABLES");
+	memblock_reserve(__pa(xen_start_info->pt_base),
+			 xen_start_info->nr_pt_frames * PAGE_SIZE);
 
 	return initial_page_table;
 }
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 38d0af4fefe..e03c6369217 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -75,7 +75,7 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
 		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
 
-	memblock_x86_reserve_range(start, start + size, "XEN EXTRA");
+	memblock_reserve(start, size);
 
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
 
@@ -173,9 +173,21 @@ static unsigned long __init xen_get_max_pages(void)
 	domid_t domid = DOMID_SELF;
 	int ret;
 
-	ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
-	if (ret > 0)
-		max_pages = ret;
+	/*
+	 * For the initial domain we use the maximum reservation as
+	 * the maximum page.
+	 *
+	 * For guest domains the current maximum reservation reflects
+	 * the current maximum rather than the static maximum. In this
+	 * case the e820 map provided to us will cover the static
+	 * maximum region.
+	 */
+	if (xen_initial_domain()) {
+		ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+		if (ret > 0)
+			max_pages = ret;
+	}
+
 	return min(max_pages, MAX_DOMAIN_PAGES);
 }
 
@@ -299,9 +311,8 @@ char * __init xen_memory_setup(void)
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	memblock_x86_reserve_range(__pa(xen_start_info->mfn_list),
-		      __pa(xen_start_info->pt_base),
-			"XEN START INFO");
+	memblock_reserve(__pa(xen_start_info->mfn_list),
+			 xen_start_info->pt_base - xen_start_info->mfn_list);
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
@@ -410,6 +421,6 @@ void __init xen_arch_setup(void)
 #endif
 	disable_cpuidle();
 	boot_option_idle_override = IDLE_HALT;
-
+	WARN_ON(set_pm_idle_to_default());
 	fiddle_vdso();
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 041d4fe9dfe..501d4e0244b 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -409,6 +409,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
+	/*
+	 * Balance out the preempt calls - as we are running in cpu_idle
+	 * loop which has been called at bootup from cpu_bringup_and_idle.
+	 * The cpucpu_bringup_and_idle called cpu_bringup which made a
+	 * preempt_disable() So this preempt_enable will balance it out.
+	 */
+	preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cc9b1e182fc..d69cc6c3f80 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -116,9 +116,26 @@ static inline void spin_time_accum_blocked(u64 start)
 }
 #endif  /* CONFIG_XEN_DEBUG_FS */
 
+/*
+ * Size struct xen_spinlock so it's the same as arch_spinlock_t.
+ */
+#if NR_CPUS < 256
+typedef u8 xen_spinners_t;
+# define inc_spinners(xl) \
+	asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+	asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
+#else
+typedef u16 xen_spinners_t;
+# define inc_spinners(xl) \
+	asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+	asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
+#endif
+
 struct xen_spinlock {
 	unsigned char lock;		/* 0 -> free; 1 -> locked */
-	unsigned short spinners;	/* count of waiting cpus */
+	xen_spinners_t spinners;	/* count of waiting cpus */
 };
 
 static int xen_spin_is_locked(struct arch_spinlock *lock)
@@ -164,8 +181,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
 
 	wmb();			/* set lock of interest before count */
 
-	asm(LOCK_PREFIX " incw %0"
-	    : "+m" (xl->spinners) : : "memory");
+	inc_spinners(xl);
 
 	return prev;
 }
@@ -176,8 +192,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
  */
 static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
 {
-	asm(LOCK_PREFIX " decw %0"
-	    : "+m" (xl->spinners) : : "memory");
+	dec_spinners(xl);
 	wmb();			/* decrement count before restoring lock */
 	__this_cpu_write(lock_spinners, prev);
 }
@@ -373,6 +388,8 @@ void xen_uninit_lock_cpu(int cpu)
 
 void __init xen_init_spinlocks(void)
 {
+	BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+
 	pv_lock_ops.spin_is_locked = xen_spin_is_locked;
 	pv_lock_ops.spin_is_contended = xen_spin_is_contended;
 	pv_lock_ops.spin_lock = xen_spin_lock;