Merge branch 'akpm-current/current'

10 files changed, 112 insertions, 11 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 7f689728f16f..f13a72ad49a7 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1748,6 +1748,9 @@ static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
 		if (!strcmp(token, "nsdelegate")) {
 			*root_flags |= CGRP_ROOT_NS_DELEGATE;
 			continue;
+		} else if (!strcmp(token, "groupoom")) {
+			*root_flags |= CGRP_GROUP_OOM;
+			continue;
 		}
 
 		pr_err("cgroup2: unknown option \"%s\"\n", token);
@@ -1764,6 +1767,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
+
+		if (root_flags & CGRP_GROUP_OOM)
+			cgrp_dfl_root.flags |= CGRP_GROUP_OOM;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_GROUP_OOM;
 	}
 }
 
@@ -1771,6 +1779,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 {
 	if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
 		seq_puts(seq, ",nsdelegate");
+	if (cgrp_dfl_root.flags & CGRP_GROUP_OOM)
+		seq_puts(seq, ",groupoom");
 	return 0;
 }
 
@@ -5958,7 +5968,8 @@ static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
 static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			     char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "nsdelegate\n");
+	return snprintf(buf, PAGE_SIZE, "nsdelegate\n"
+					"groupoom\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 
diff --git a/kernel/cred.c b/kernel/cred.c
index ecf03657e71c..0192a94670e1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -448,6 +448,7 @@ int commit_creds(struct cred *new)
 		if (task->mm)
 			set_dumpable(task->mm, suid_dumpable);
 		task->pdeath_signal = 0;
+		task->signal->pdeath_signal_proc = 0;
 		smp_wmb();
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c3c7ac560114..63f7cea6456e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -635,6 +635,10 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (unlikely(p->exit_state == EXIT_DEAD))
 		return;
 
+	if (p->signal->pdeath_signal_proc)
+		group_send_sig_info(p->signal->pdeath_signal_proc,
+				    SEND_SIG_NOINFO, p);
+
 	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 08c6e5e217a0..03341e1854b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -440,6 +440,14 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			continue;
 		}
 		charge = 0;
+		/*
+		 * Don't duplicate many vmas if we've been oom-killed (for
+		 * example)
+		 */
+		if (fatal_signal_pending(current)) {
+			retval = -EINTR;
+			goto out;
+		}
 		if (mpnt->vm_flags & VM_ACCOUNT) {
 			unsigned long len = vma_pages(mpnt);
 
@@ -1471,6 +1479,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 	mutex_init(&sig->cred_guard_mutex);
 
+	sig->pdeath_signal_proc = current->signal->pdeath_signal_proc;
+
 	return 0;
 }
 
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 2c16f1ab5e10..3ebd09efe72a 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -58,7 +58,7 @@ struct kcov {
 
 static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
 {
-	enum kcov_mode mode;
+	unsigned int mode;
 
 	/*
 	 * We are interested in code coverage as a function of a syscall inputs,
@@ -241,7 +241,8 @@ static void kcov_put(struct kcov *kcov)
 
 void kcov_task_init(struct task_struct *t)
 {
-	t->kcov_mode = KCOV_MODE_DISABLED;
+	WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED);
+	barrier();
 	t->kcov_size = 0;
 	t->kcov_area = NULL;
 	t->kcov = NULL;
@@ -323,6 +324,21 @@ static int kcov_close(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+/*
+ * Fault in a lazily-faulted vmalloc area before it can be used by
+ * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the
+ * vmalloc fault handling path is instrumented.
+ */
+static void kcov_fault_in_area(struct kcov *kcov)
+{
+	unsigned long stride = PAGE_SIZE / sizeof(unsigned long);
+	unsigned long *area = kcov->area;
+	unsigned long offset;
+
+	for (offset = 0; offset < kcov->size; offset += stride)
+		READ_ONCE(area[offset]);
+}
+
 static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 			     unsigned long arg)
 {
@@ -371,6 +387,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 #endif
 		else
 			return -EINVAL;
+		kcov_fault_in_area(kcov);
 		/* Cache in task struct for performance. */
 		t->kcov_size = kcov->size;
 		t->kcov_area = kcov->area;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..fc698e8a21a2 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -124,7 +124,7 @@ static void devm_memremap_pages_release(void *data)
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
 
-	if (percpu_ref_tryget_live(pgmap->ref)) {
+	if (pgmap->registered && percpu_ref_tryget_live(pgmap->ref)) {
 		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
 		percpu_ref_put(pgmap->ref);
 	}
@@ -223,11 +223,32 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		goto err_pfn_remap;
 
 	mem_hotplug_begin();
-	error = arch_add_memory(nid, align_start, align_size, altmap, false);
-	if (!error)
-		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-					align_start >> PAGE_SHIFT,
+
+	/*
+	 * For device private memory we call add_pages() as we only need to
+	 * allocate and initialize struct page for the device memory. More-
+	 * over the device memory is un-accessible thus we do not want to
+	 * create a linear mapping for the memory like arch_add_memory()
+	 * would do.
+	 *
+	 * For all other device memory types, which are accessible by
+	 * the CPU, we do want the linear mapping and thus use
+	 * arch_add_memory().
+	 */
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+		error = add_pages(nid, align_start >> PAGE_SHIFT,
+				align_size >> PAGE_SHIFT, NULL, false);
+	} else {
+		struct zone *zone;
+
+		error = arch_add_memory(nid, align_start, align_size, altmap,
+				false);
+		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+		if (!error)
+			move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT,
 					align_size >> PAGE_SHIFT, altmap);
+	}
+
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
@@ -246,7 +267,11 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		percpu_ref_get(pgmap->ref);
 	}
 
-	devm_add_action(dev, devm_memremap_pages_release, pgmap);
+	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+			pgmap);
+	if (error)
+		return ERR_PTR(error);
+	pgmap->registered = true;
 
 	return __va(res->start);
 
@@ -257,7 +282,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	pgmap_radix_release(res, pgoff);
 	return ERR_PTR(error);
 }
-EXPORT_SYMBOL(devm_memremap_pages);
+EXPORT_SYMBOL_GPL(devm_memremap_pages);
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
 {
diff --git a/kernel/relay.c b/kernel/relay.c
index c955b10c973c..ae79846ced82 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -39,7 +39,7 @@ static void relay_file_mmap_close(struct vm_area_struct *vma)
 /*
  * fault() vm_op implementation for relay file mapping.
  */
-static int relay_buf_fault(struct vm_fault *vmf)
+static vm_fault_t relay_buf_fault(struct vm_fault *vmf)
 {
 	struct page *page;
 	struct rchan_buf *buf = vmf->vma->vm_private_data;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a98d54cd5535..78d8facba456 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10,6 +10,8 @@
 #include <linux/kthread.h>
 #include <linux/nospec.h>
 
+#include <linux/kcov.h>
+
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
@@ -2633,6 +2635,7 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
+	kcov_prepare_switch(prev);
 	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	rseq_preempt(prev);
@@ -2702,6 +2705,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	finish_task(prev);
 	finish_lock_switch(rq);
 	finish_arch_post_lock_switch();
+	kcov_finish_switch(current);
 
 	fire_sched_in_preempt_notifiers(current);
 	/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 38509dc1f77b..fcc370a2629d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2289,6 +2289,17 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_PDEATHSIG:
 		error = put_user(me->pdeath_signal, (int __user *)arg2);
 		break;
+	case PR_SET_PDEATHSIG_PROC:
+		if (!valid_signal(arg2)) {
+			error = -EINVAL;
+			break;
+		}
+		me->signal->pdeath_signal_proc = arg2;
+		break;
+	case PR_GET_PDEATHSIG_PROC:
+		error = put_user(me->signal->pdeath_signal_proc,
+				 (int __user *)arg2);
+		break;
 	case PR_GET_DUMPABLE:
 		error = get_dumpable(me->mm);
 		break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6a78cf70761d..f45ed9e696eb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1805,6 +1805,24 @@ static struct ctl_table fs_table[] = {
 		.extra2		= &one,
 	},
 	{
+		.procname	= "protected_fifos",
+		.data		= &sysctl_protected_fifos,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+	{
+		.procname	= "protected_regular",
+		.data		= &sysctl_protected_regular,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+	{
 		.procname	= "suid_dumpable",
 		.data		= &suid_dumpable,
 		.maxlen		= sizeof(int),