Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/sys.c b/kernel/sys.c
index 3459a5c..24a3a28 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -47,6 +47,7 @@
 #include <linux/syscalls.h>
 #include <linux/kprobes.h>
 #include <linux/user_namespace.h>
+#include <linux/time_namespace.h>
 #include <linux/binfmts.h>
 
 #include <linux/sched.h>
@@ -372,7 +373,7 @@
 	if (rgid != (gid_t) -1) {
 		if (gid_eq(old->gid, krgid) ||
 		    gid_eq(old->egid, krgid) ||
-		    ns_capable(old->user_ns, CAP_SETGID))
+		    ns_capable_setid(old->user_ns, CAP_SETGID))
 			new->gid = krgid;
 		else
 			goto error;
@@ -381,7 +382,7 @@
 		if (gid_eq(old->gid, kegid) ||
 		    gid_eq(old->egid, kegid) ||
 		    gid_eq(old->sgid, kegid) ||
-		    ns_capable(old->user_ns, CAP_SETGID))
+		    ns_capable_setid(old->user_ns, CAP_SETGID))
 			new->egid = kegid;
 		else
 			goto error;
@@ -392,6 +393,10 @@
 		new->sgid = new->egid;
 	new->fsgid = new->egid;
 
+	retval = security_task_fix_setgid(new, old, LSM_SETID_RE);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -427,13 +432,17 @@
 	old = current_cred();
 
 	retval = -EPERM;
-	if (ns_capable(old->user_ns, CAP_SETGID))
+	if (ns_capable_setid(old->user_ns, CAP_SETGID))
 		new->gid = new->egid = new->sgid = new->fsgid = kgid;
 	else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
 		new->egid = new->fsgid = kgid;
 	else
 		goto error;
 
+	retval = security_task_fix_setgid(new, old, LSM_SETID_ID);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -735,7 +744,7 @@
 	old = current_cred();
 
 	retval = -EPERM;
-	if (!ns_capable(old->user_ns, CAP_SETGID)) {
+	if (!ns_capable_setid(old->user_ns, CAP_SETGID)) {
 		if (rgid != (gid_t) -1        && !gid_eq(krgid, old->gid) &&
 		    !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
 			goto error;
@@ -755,6 +764,10 @@
 		new->sgid = ksgid;
 	new->fsgid = new->egid;
 
+	retval = security_task_fix_setgid(new, old, LSM_SETID_RES);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -858,10 +871,11 @@
 
 	if (gid_eq(kgid, old->gid)  || gid_eq(kgid, old->egid)  ||
 	    gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
-	    ns_capable(old->user_ns, CAP_SETGID)) {
+	    ns_capable_setid(old->user_ns, CAP_SETGID)) {
 		if (!gid_eq(kgid, old->fsgid)) {
 			new->fsgid = kgid;
-			goto change_okay;
+			if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0)
+				goto change_okay;
 		}
 	}
 
@@ -1739,7 +1753,7 @@
 
 		if (who == RUSAGE_CHILDREN)
 			break;
-		/* fall through */
+		fallthrough;
 
 	case RUSAGE_SELF:
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
@@ -1765,8 +1779,8 @@
 	unlock_task_sighand(p, &flags);
 
 out:
-	r->ru_utime = ns_to_timeval(utime);
-	r->ru_stime = ns_to_timeval(stime);
+	r->ru_utime = ns_to_kernel_old_timeval(utime);
+	r->ru_stime = ns_to_kernel_old_timeval(stime);
 
 	if (who != RUSAGE_CHILDREN) {
 		struct mm_struct *mm = get_task_mm(p);
@@ -1845,7 +1859,7 @@
 	if (exe_file) {
 		struct vm_area_struct *vma;
 
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			if (!vma->vm_file)
 				continue;
@@ -1854,7 +1868,7 @@
 				goto exit_err;
 		}
 
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		fput(exe_file);
 	}
 
@@ -1868,7 +1882,7 @@
 	fdput(exe);
 	return err;
 exit_err:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	fput(exe_file);
 	goto exit;
 }
@@ -1928,13 +1942,6 @@
 	error = -EINVAL;
 
 	/*
-	 * @brk should be after @end_data in traditional maps.
-	 */
-	if (prctl_map->start_brk <= prctl_map->end_data ||
-	    prctl_map->brk <= prctl_map->end_data)
-		goto out;
-
-	/*
 	 * Neither we should allow to override limits if they set.
 	 */
 	if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk,
@@ -1993,12 +2000,15 @@
 
 	if (prctl_map.exe_fd != (u32)-1) {
 		/*
-		 * Make sure the caller has the rights to
-		 * change /proc/pid/exe link: only local sys admin should
-		 * be allowed to.
+		 * Check if the current user is checkpoint/restore capable.
+		 * At the time of this writing, it checks for CAP_SYS_ADMIN
+		 * or CAP_CHECKPOINT_RESTORE.
+		 * Note that a user with access to ptrace can masquerade an
+		 * arbitrary program as any executable, even setuid ones.
+		 * This may have implications in the tomoyo subsystem.
 		 */
-		if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
-			return -EINVAL;
+		if (!checkpoint_restore_ns_capable(current_user_ns()))
+			return -EPERM;
 
 		error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
 		if (error)
@@ -2006,10 +2016,10 @@
 	}
 
 	/*
-	 * arg_lock protects concurent updates but we still need mmap_sem for
+	 * arg_lock protects concurent updates but we still need mmap_lock for
 	 * read to exclude races with sys_brk.
 	 */
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	/*
 	 * We don't validate if these members are pointing to
@@ -2017,7 +2027,7 @@
 	 * VMAs already unmapped and kernel uses these members for statistics
 	 * output in procfs mostly, except
 	 *
-	 *  - @start_brk/@brk which are used in do_brk but kernel lookups
+	 *  - @start_brk/@brk which are used in do_brk_flags but kernel lookups
 	 *    for VMAs when updating these memvers so anything wrong written
 	 *    here cause kernel to swear at userspace program but won't lead
 	 *    to any problem in kernel itself
@@ -2048,7 +2058,7 @@
 	if (prctl_map.auxv_size)
 		memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return 0;
 }
 #endif /* CONFIG_CHECKPOINT_RESTORE */
@@ -2121,10 +2131,10 @@
 
 	/*
 	 * arg_lock protects concurent updates of arg boundaries, we need
-	 * mmap_sem for a) concurrent sys_brk, b) finding VMA for addr
+	 * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr
 	 * validation.
 	 */
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_vma(mm, addr);
 
 	spin_lock(&mm->arg_lock);
@@ -2216,17 +2226,17 @@
 	error = 0;
 out:
 	spin_unlock(&mm->arg_lock);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return error;
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
-static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr)
 {
 	return put_user(me->clear_child_tid, tid_addr);
 }
 #else
-static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr)
 {
 	return -EINVAL;
 }
@@ -2261,6 +2271,8 @@
 	return -EINVAL;
 }
 
+#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2408,7 +2420,7 @@
 		error = prctl_set_mm(arg2, arg3, arg4, arg5);
 		break;
 	case PR_GET_TID_ADDRESS:
-		error = prctl_get_tid_address(me, (int __user **)arg2);
+		error = prctl_get_tid_address(me, (int __user * __user *)arg2);
 		break;
 	case PR_SET_CHILD_SUBREAPER:
 		me->signal->is_child_subreaper = !!arg2;
@@ -2439,13 +2451,13 @@
 	case PR_SET_THP_DISABLE:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;
-		if (down_write_killable(&me->mm->mmap_sem))
+		if (mmap_write_lock_killable(me->mm))
 			return -EINTR;
 		if (arg2)
 			set_bit(MMF_DISABLE_THP, &me->mm->flags);
 		else
 			clear_bit(MMF_DISABLE_THP, &me->mm->flags);
-		up_write(&me->mm->mmap_sem);
+		mmap_write_unlock(me->mm);
 		break;
 	case PR_MPX_ENABLE_MANAGEMENT:
 	case PR_MPX_DISABLE_MANAGEMENT:
@@ -2488,6 +2500,29 @@
 			return -EINVAL;
 		error = GET_TAGGED_ADDR_CTRL();
 		break;
+	case PR_SET_IO_FLUSHER:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		if (arg2 == 1)
+			current->flags |= PR_IO_FLUSHER;
+		else if (!arg2)
+			current->flags &= ~PR_IO_FLUSHER;
+		else
+			return -EINVAL;
+		break;
+	case PR_GET_IO_FLUSHER:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
+		break;
 	default:
 		error = -EINVAL;
 		break;
@@ -2521,6 +2556,7 @@
 	memset(info, 0, sizeof(struct sysinfo));
 
 	ktime_get_boottime_ts64(&tp);
+	timens_add_boottime(&tp);
 	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
 	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
@@ -2607,6 +2643,7 @@
 COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 {
 	struct sysinfo s;
+	struct compat_sysinfo s_32;
 
 	do_sysinfo(&s);
 
@@ -2631,23 +2668,23 @@
 		s.freehigh >>= bitcount;
 	}
 
-	if (!access_ok(info, sizeof(struct compat_sysinfo)) ||
-	    __put_user(s.uptime, &info->uptime) ||
-	    __put_user(s.loads[0], &info->loads[0]) ||
-	    __put_user(s.loads[1], &info->loads[1]) ||
-	    __put_user(s.loads[2], &info->loads[2]) ||
-	    __put_user(s.totalram, &info->totalram) ||
-	    __put_user(s.freeram, &info->freeram) ||
-	    __put_user(s.sharedram, &info->sharedram) ||
-	    __put_user(s.bufferram, &info->bufferram) ||
-	    __put_user(s.totalswap, &info->totalswap) ||
-	    __put_user(s.freeswap, &info->freeswap) ||
-	    __put_user(s.procs, &info->procs) ||
-	    __put_user(s.totalhigh, &info->totalhigh) ||
-	    __put_user(s.freehigh, &info->freehigh) ||
-	    __put_user(s.mem_unit, &info->mem_unit))
+	memset(&s_32, 0, sizeof(s_32));
+	s_32.uptime = s.uptime;
+	s_32.loads[0] = s.loads[0];
+	s_32.loads[1] = s.loads[1];
+	s_32.loads[2] = s.loads[2];
+	s_32.totalram = s.totalram;
+	s_32.freeram = s.freeram;
+	s_32.sharedram = s.sharedram;
+	s_32.bufferram = s.bufferram;
+	s_32.totalswap = s.totalswap;
+	s_32.freeswap = s.freeswap;
+	s_32.procs = s.procs;
+	s_32.totalhigh = s.totalhigh;
+	s_32.freehigh = s.freehigh;
+	s_32.mem_unit = s.mem_unit;
+	if (copy_to_user(info, &s_32, sizeof(s_32)))
 		return -EFAULT;
-
 	return 0;
 }
 #endif /* CONFIG_COMPAT */