Merge branch 'linus' into perf/kprobes

Conflicts:
	include/asm-generic/atomic-instrumented.h
	kernel/kprobes.c

Use the upstream atomic-instrumented.h checksum, and pick
the kprobes version of kernel/kprobes.c, which effectively
reverts this upstream workaround:

  645f224e7ba2: ("kprobes: Tell lockdep about kprobe nesting")

Since the new code *should* be fine without nesting.

Knock on wood ...

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 40 insertions, 12 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 53a1f508a097..b9c289d0f4ef 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -95,6 +95,7 @@
 #include <linux/stackleak.h>
 #include <linux/kasan.h>
 #include <linux/scs.h>
+#include <linux/io_uring.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -555,10 +556,10 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 			get_file(file);
 			if (tmp->vm_flags & VM_DENYWRITE)
-				atomic_dec(&inode->i_writecount);
+				put_write_access(inode);
 			i_mmap_lock_write(mapping);
 			if (tmp->vm_flags & VM_SHARED)
-				atomic_inc(&mapping->i_mmap_writable);
+				mapping_allow_writable(mapping);
 			flush_dcache_mmap_lock(mapping);
 			/* insert tmp into the share list, just after mpnt */
 			vma_interval_tree_insert_after(tmp, mpnt,
@@ -589,7 +590,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(mm, oldmm, mpnt);
+			retval = copy_page_range(tmp, mpnt);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
@@ -728,6 +729,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
@@ -1011,6 +1013,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
+	atomic_set(&mm->has_pinned, 0);
 	atomic64_set(&mm->pinned_vm, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
@@ -1809,6 +1812,25 @@ static __always_inline void delayed_free_task(struct task_struct *tsk)
 		free_task(tsk);
 }
 
+static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk)
+{
+	/* Skip if kernel thread */
+	if (!tsk->mm)
+		return;
+
+	/* Skip if spawning a thread or using vfork */
+	if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM)
+		return;
+
+	/* We need to synchronize with __set_oom_adj */
+	mutex_lock(&oom_adj_mutex);
+	set_bit(MMF_MULTIPROCESS, &tsk->mm->flags);
+	/* Update the values in case they were changed after copy_signal */
+	tsk->signal->oom_score_adj = current->signal->oom_score_adj;
+	tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min;
+	mutex_unlock(&oom_adj_mutex);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1982,6 +2004,10 @@ static __latent_entropy struct task_struct *copy_process(
 	p->vtime.state = VTIME_INACTIVE;
 #endif
 
+#ifdef CONFIG_IO_URING
+	p->io_uring = NULL;
+#endif
+
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
@@ -2167,7 +2193,7 @@ static __latent_entropy struct task_struct *copy_process(
 
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
-	 * forked. It should be noted the the new process's css_set can be changed
+	 * forked. It should be noted that the new process's css_set can be changed
 	 * between here and cgroup_post_fork() if an organisation operation is in
 	 * progress.
 	 */
@@ -2285,6 +2311,8 @@ static __latent_entropy struct task_struct *copy_process(
 	trace_task_newtask(p, clone_flags);
 	uprobe_copy_process(p, clone_flags);
 
+	copy_oom_score_adj(clone_flags, p);
+
 	return p;
 
 bad_fork_cancel_cgroup:
@@ -2388,14 +2416,14 @@ struct mm_struct *copy_init_mm(void)
  *
  * args->exit_signal is expected to be checked for sanity by the caller.
  */
-long _do_fork(struct kernel_clone_args *args)
+pid_t kernel_clone(struct kernel_clone_args *args)
 {
 	u64 clone_flags = args->flags;
 	struct completion vfork;
 	struct pid *pid;
 	struct task_struct *p;
 	int trace = 0;
-	long nr;
+	pid_t nr;
 
 	/*
 	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
@@ -2481,7 +2509,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.stack_size	= (unsigned long)arg,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 
 #ifdef __ARCH_WANT_SYS_FORK
@@ -2492,7 +2520,7 @@ SYSCALL_DEFINE0(fork)
 		.exit_signal = SIGCHLD,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 #else
 	/* can not support in nommu mode */
 	return -EINVAL;
@@ -2508,7 +2536,7 @@ SYSCALL_DEFINE0(vfork)
 		.exit_signal	= SIGCHLD,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif
 
@@ -2546,7 +2574,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		.tls		= tls,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif
 
@@ -2704,7 +2732,7 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 	if (!clone3_args_valid(&kargs))
 		return -EINVAL;
 
-	return _do_fork(&kargs);
+	return kernel_clone(&kargs);
 }
 #endif
 
@@ -2867,7 +2895,7 @@ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
- * functions used by _do_fork() cannot be used here directly
+ * functions used by kernel_clone() cannot be used here directly
  * because they modify an inactive task_struct that is being
  * constructed. Here we are modifying the current, active,
  * task_struct.