3 files changed, 47 insertions, 24 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 8cb7816d03b4..193204aee880 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 
 static void kill_me_now(struct callback_head *ch)
 {
+	struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me);
+
+	p->mce_count = 0;
 	force_sig(SIGBUS);
 }
 
@@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb)
 	int flags = MF_ACTION_REQUIRED;
 	int ret;
 
+	p->mce_count = 0;
 	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
 
 	if (!p->mce_ripv)
@@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb)
 	}
 }
 
-static void queue_task_work(struct mce *m, int kill_current_task)
+static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 {
-	current->mce_addr = m->addr;
-	current->mce_kflags = m->kflags;
-	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
-	current->mce_whole_page = whole_page(m);
+	int count = ++current->mce_count;
 
-	if (kill_current_task)
-		current->mce_kill_me.func = kill_me_now;
-	else
-		current->mce_kill_me.func = kill_me_maybe;
+	/* First call, save all the details */
+	if (count == 1) {
+		current->mce_addr = m->addr;
+		current->mce_kflags = m->kflags;
+		current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+		current->mce_whole_page = whole_page(m);
+
+		if (kill_current_task)
+			current->mce_kill_me.func = kill_me_now;
+		else
+			current->mce_kill_me.func = kill_me_maybe;
+	}
+
+	/* Ten is likely overkill. Don't expect more than two faults before task_work() */
+	if (count > 10)
+		mce_panic("Too many consecutive machine checks while accessing user data", m, msg);
+
+	/* Second or later call, make sure page address matches the one from first call */
+	if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
+		mce_panic("Consecutive machine checks to different user pages", m, msg);
+
+	/* Do not call task_work_add() more than once */
+	if (count > 1)
+		return;
 
 	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
@@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		queue_task_work(&m, kill_current_task);
+		queue_task_work(&m, msg, kill_current_task);
 
 	} else {
 		/*
@@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
-			queue_task_work(&m, kill_current_task);
+			queue_task_work(&m, msg, kill_current_task);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 79f164141116..40ed44ead063 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -830,6 +830,20 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
+	/*
+	 * Do some memory reservations *before* memory is added to memblock, so
+	 * memblock allocations won't overwrite it.
+	 *
+	 * After this point, everything still needed from the boot loader or
+	 * firmware or kernel text should be early reserved or marked not RAM in
+	 * e820. All other memory is free game.
+	 *
+	 * This call needs to happen before e820__memory_setup() which calls the
+	 * xen_memory_setup() on Xen dom0 which relies on the fact that those
+	 * early reservations have happened already.
+	 */
+	early_reserve_memory();
+
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	e820__memory_setup();
 	parse_setup_data();
@@ -876,18 +890,6 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-	/*
-	 * Do some memory reservations *before* memory is added to
-	 * memblock, so memblock allocations won't overwrite it.
-	 * Do it after early param, so we could get (unlikely) panic from
-	 * serial.
-	 *
-	 * After this point everything still needed from the boot loader or
-	 * firmware or kernel text should be early reserved or marked not
-	 * RAM in e820. All other memory is free game.
-	 */
-	early_reserve_memory();
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 78a32b956e81..5afd98559193 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free(__pa(ptr), size);
+	memblock_free_ptr(ptr, size);
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)