Merge commit 'v3.4' into x86/urgent

3 files changed, 25 insertions, 12 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d086a09c087d..11c9166c3337 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -945,9 +945,10 @@ struct mce_info {
 	atomic_t		inuse;
 	struct task_struct	*t;
 	__u64			paddr;
+	int			restartable;
 } mce_info[MCE_INFO_MAX];
 
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
 {
 	struct mce_info *mi;
 
@@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr)
 		if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
 			mi->t = current;
 			mi->paddr = addr;
+			mi->restartable = c;
 			return;
 		}
 	}
@@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 			mce_panic("Fatal machine check on current CPU", &m, msg);
 		if (worst == MCE_AR_SEVERITY) {
 			/* schedule action before return to userland */
-			mce_save_info(m.addr);
+			mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
 			set_thread_flag(TIF_MCE_NOTIFY);
 		} else if (kill_it) {
 			force_sig(SIGBUS, current);
@@ -1179,7 +1181,13 @@ void mce_notify_process(void)
 
 	pr_err("Uncorrected hardware memory error in user-access at %llx",
 		 mi->paddr);
-	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+	/*
+	 * We must call memory_failure() here even if the current process is
+	 * doomed. We still need to mark the page as poisoned and alert any
+	 * other users of the page.
+	 */
+	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+			   mi->restartable == 0) {
 		pr_err("Memory error not recovered");
 		force_sig(SIGBUS, current);
 	}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b8ba6e4a27e4..e554e5ad2fe8 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -79,7 +79,6 @@ struct kvm_task_sleep_node {
 	u32 token;
 	int cpu;
 	bool halted;
-	struct mm_struct *mm;
 };
 
 static struct kvm_task_sleep_head {
@@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.mm = current->active_mm;
 	n.halted = idle || preempt_count() > 1;
-	atomic_inc(&n.mm->mm_count);
 	init_waitqueue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	spin_unlock(&b->lock);
@@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
 static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 {
 	hlist_del_init(&n->link);
-	if (!n->mm)
-		return;
-	mmdrop(n->mm);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (waitqueue_active(&n->wq))
@@ -207,7 +201,7 @@ again:
 		 * async PF was not yet handled.
 		 * Add dummy entry for the token.
 		 */
-		n = kmalloc(sizeof(*n), GFP_ATOMIC);
+		n = kzalloc(sizeof(*n), GFP_ATOMIC);
 		if (!n) {
 			/*
 			 * Allocation failed! Busy wait while other cpu
@@ -219,7 +213,6 @@ again:
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
-		n->mm = NULL;
 		init_waitqueue_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da373..5a98aa272184 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
 #endif
 	rc = -EINVAL;
 	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
-		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
 		const size_t dyn_size = PERCPU_MODULE_RESERVE +
 			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+		size_t atom_size;
 
+		/*
+		 * On 64bit, use PMD_SIZE for atom_size so that embedded
+		 * percpu areas are aligned to PMD.  This, in the future,
+		 * can also allow using PMD mappings in vmalloc area.  Use
+		 * PAGE_SIZE on 32bit as vmalloc space is highly contended
+		 * and large vmalloc area allocs can easily fail.
+		 */
+#ifdef CONFIG_X86_64
+		atom_size = PMD_SIZE;
+#else
+		atom_size = PAGE_SIZE;
+#endif
 		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
 					    dyn_size, atom_size,
 					    pcpu_cpu_distance,