Merge remote-tracking branch 'sm8350/lineage-20' into lineage-23.2

* sm8350/lineage-20: (306 commits) ANDROID: gki_defconfig: reduce KFENCE pool size ANDROID: GKI: enable KFENCE by setting the sample interval to 500ms ANDROID: GKI: Enable KFENCE UPSTREAM: random: split initialization into early step and later step UPSTREAM: kfence: avoid passing -g for test UPSTREAM: net: add and use skb_unclone_keeptruesize() helper UPSTREAM: kfence: fix memory leak when cat kfence objects UPSTREAM: kfence: unconditionally use unbound work queue UPSTREAM: kfence: use TASK_IDLE when awaiting allocation UPSTREAM: kfence: fix is_kfence_address() for addresses below KFENCE_POOL_SIZE FROMLIST: kfence: skip all GFP_ZONEMASK allocations FROMLIST: kfence: move the size check to the beginning of __kfence_alloc() ANDROID: kasan: fix interoperability with KFENCE UPSTREAM: arm64: mm: don't use CON and BLK mapping if KFENCE is enabled ANDROID: kfence: clean up unused variables FROMGIT: kfence: use power-efficient work queue to run delayed work FROMGIT: kfence: maximize allocation wait timeout duration FROMGIT: kfence: await for allocation using wait_event FROMGIT: kfence: zero guard page after out-of-bounds access UPSTREAM: kfence: make compatible with kmemleak ... Change-Id: Id1436b77692839dc2394f500bba42487fac1b2b4
2026-10-05 19:31:57 -04:00 · 2026-05-07 18:19:43 +03:00 · 2026-05-07 18:19:43 +03:00 · 376925d57f
commit 376925d57f
parent ee679763c2 a8ef4f11e4
209 changed files with 10117 additions and 1291 deletions
--- a/kernel/exit.c
+++ b/kernel/exit.c
@ -274,6 +274,7 @@ repeat:
 	}

 	write_unlock_irq(&tasklist_lock);
+	seccomp_filter_release(p);
 	release_thread(p);
 	put_task_struct_rcu_user(p);

--- a/kernel/fork.c
+++ b/kernel/fork.c
@ -474,7 +474,6 @@ void free_task(struct task_struct *tsk)
 #endif
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
-	put_seccomp_filter(tsk);
 	arch_release_task_struct(tsk);
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@ -13,6 +13,7 @@
 * Mode 2 allows user-defined system call filters in the form
 *        of Berkeley Packet Filters/Linux Socket Filters.
 */
+#define pr_fmt(fmt) "seccomp: " fmt

 #include <linux/refcount.h>
 #include <linux/audit.h>
@ -44,6 +45,7 @@
 #include <linux/tracehook.h>
 #include <linux/uaccess.h>
 #include <linux/anon_inodes.h>
+#include <linux/lockdep.h>

 /*
 * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the
@ -86,6 +88,7 @@ struct seccomp_knotif {
 	/* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */
 	int error;
 	long val;
+	u32 flags;

 	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
 	struct completion ready;
@ -104,27 +107,68 @@ struct seccomp_knotif {
 *           filter->notify_lock.
 * @next_id: The id of the next request.
 * @notifications: A list of struct seccomp_knotif elements.
- * @wqh: A wait queue for poll.
 */
 struct notification {
 	struct semaphore request;
 	u64 next_id;
 	struct list_head notifications;
-	wait_queue_head_t wqh;
 };

+#ifdef SECCOMP_ARCH_NATIVE
+/**
+ * struct action_cache - per-filter cache of seccomp actions per
+ * arch/syscall pair
+ *
+ * @allow_native: A bitmap where each bit represents whether the
+ *		  filter will always allow the syscall, for the
+ *		  native architecture.
+ * @allow_compat: A bitmap where each bit represents whether the
+ *		  filter will always allow the syscall, for the
+ *		  compat architecture.
+ */
+struct action_cache {
+	DECLARE_BITMAP(allow_native, SECCOMP_ARCH_NATIVE_NR);
+#ifdef SECCOMP_ARCH_COMPAT
+	DECLARE_BITMAP(allow_compat, SECCOMP_ARCH_COMPAT_NR);
+#endif
+};
+#else
+struct action_cache { };
+
+static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter,
+					     const struct seccomp_data *sd)
+{
+	return false;
+}
+
+static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter)
+{
+}
+#endif /* SECCOMP_ARCH_NATIVE */
+
 /**
 * struct seccomp_filter - container for seccomp BPF programs
 *
- * @usage: reference count to manage the object lifetime.
- *         get/put helpers should be used when accessing an instance
- *         outside of a lifetime-guarded section.  In general, this
- *         is only needed for handling filters shared across tasks.
+ * @refs: Reference count to manage the object lifetime.
+ *	  A filter's reference count is incremented for each directly
+ *	  attached task, once for the dependent filter, and if
+ *	  requested for the user notifier. When @refs reaches zero,
+ *	  the filter can be freed.
+ * @users: A filter's @users count is incremented for each directly
+ *         attached task (filter installation, fork(), thread_sync),
+ *	   and once for the dependent filter (tracked in filter->prev).
+ *	   When it reaches zero it indicates that no direct or indirect
+ *	   users of that filter exist. No new tasks can get associated with
+ *	   this filter after reaching 0. The @users count is always smaller
+ *	   or equal to @refs. Hence, reaching 0 for @users does not mean
+ *	   the filter can be freed.
+ * @cache: cache of arch/syscall mappings to actions
 * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
 * @prev: points to a previously installed, or inherited, filter
 * @prog: the BPF program to evaluate
 * @notif: the struct that holds all notification related information
 * @notify_lock: A lock for all notification-related accesses.
+ * @wqh: A wait queue for poll if a notifier is in use.
 *
 * seccomp_filter objects are organized in a tree linked via the @prev
 * pointer.  For any task, it appears to be a singly-linked list starting
@ -134,15 +178,18 @@ struct notification {
 * how namespaces work.
 *
 * seccomp_filter objects should never be modified after being attached
- * to a task_struct (other than @usage).
+ * to a task_struct (other than @refs).
 */
 struct seccomp_filter {
-	refcount_t usage;
+	refcount_t refs;
+	refcount_t users;
 	bool log;
+	struct action_cache cache;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
 	struct notification *notif;
 	struct mutex notify_lock;
+	wait_queue_head_t wqh;
 };

 /* Limit any path through the tree to 256KB worth of instructions. */
@ -154,6 +201,10 @@ struct seccomp_filter {
 */
 static void populate_seccomp_data(struct seccomp_data *sd)
 {
+	/*
+	 * Instead of using current_pt_reg(), we're already doing the work
+	 * to safely fetch "current", so just use "task" everywhere below.
+	 */
 	struct task_struct *task = current;
 	struct pt_regs *regs = task_pt_regs(task);
 	unsigned long args[6];
@ -252,6 +303,52 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 	return 0;
 }

+#ifdef SECCOMP_ARCH_NATIVE
+static inline bool seccomp_cache_check_allow_bitmap(const void *bitmap,
+						    size_t bitmap_size,
+						    int syscall_nr)
+{
+	if (unlikely(syscall_nr < 0 || syscall_nr >= bitmap_size))
+		return false;
+	syscall_nr = array_index_nospec(syscall_nr, bitmap_size);
+
+	return test_bit(syscall_nr, bitmap);
+}
+
+/**
+ * seccomp_cache_check_allow - lookup seccomp cache
+ * @sfilter: The seccomp filter
+ * @sd: The seccomp data to lookup the cache with
+ *
+ * Returns true if the seccomp_data is cached and allowed.
+ */
+static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter,
+					     const struct seccomp_data *sd)
+{
+	int syscall_nr = sd->nr;
+	const struct action_cache *cache = &sfilter->cache;
+
+#ifndef SECCOMP_ARCH_COMPAT
+	/* A native-only architecture doesn't need to check sd->arch. */
+	return seccomp_cache_check_allow_bitmap(cache->allow_native,
+						SECCOMP_ARCH_NATIVE_NR,
+						syscall_nr);
+#else
+	if (likely(sd->arch == SECCOMP_ARCH_NATIVE))
+		return seccomp_cache_check_allow_bitmap(cache->allow_native,
+							SECCOMP_ARCH_NATIVE_NR,
+							syscall_nr);
+	if (likely(sd->arch == SECCOMP_ARCH_COMPAT))
+		return seccomp_cache_check_allow_bitmap(cache->allow_compat,
+							SECCOMP_ARCH_COMPAT_NR,
+							syscall_nr);
+#endif /* SECCOMP_ARCH_COMPAT */
+
+	WARN_ON_ONCE(true);
+	return false;
+}
+#endif /* SECCOMP_ARCH_NATIVE */
+
 /**
 * seccomp_run_filters - evaluates all seccomp filters against @sd
 * @sd: optional seccomp data to be passed to filters
@ -274,6 +371,9 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
 	if (WARN_ON(f == NULL))
 		return SECCOMP_RET_KILL_PROCESS;

+	if (seccomp_cache_check_allow(f, sd))
+		return SECCOMP_RET_ALLOW;
+
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
@ -378,6 +478,59 @@ static inline pid_t seccomp_can_sync_threads(void)
 	return 0;
 }

+static inline void seccomp_filter_free(struct seccomp_filter *filter)
+{
+	if (filter) {
+		bpf_prog_destroy(filter->prog);
+		kfree(filter);
+	}
+}
+
+static void __seccomp_filter_orphan(struct seccomp_filter *orig)
+{
+	while (orig && refcount_dec_and_test(&orig->users)) {
+		if (waitqueue_active(&orig->wqh))
+			wake_up_poll(&orig->wqh, EPOLLHUP);
+		orig = orig->prev;
+	}
+}
+
+static void __put_seccomp_filter(struct seccomp_filter *orig)
+{
+	/* Clean up single-reference branches iteratively. */
+	while (orig && refcount_dec_and_test(&orig->refs)) {
+		struct seccomp_filter *freeme = orig;
+		orig = orig->prev;
+		seccomp_filter_free(freeme);
+	}
+}
+
+static void __seccomp_filter_release(struct seccomp_filter *orig)
+{
+	/* Notify about any unused filters in the task's former filter tree. */
+	__seccomp_filter_orphan(orig);
+	/* Finally drop all references to the task's former tree. */
+	__put_seccomp_filter(orig);
+}
+
+/**
+ * seccomp_filter_release - Detach the task from its filter tree,
+ *			    drop its reference count, and notify
+ *			    about unused filters
+ *
+ * This function should only be called when the task is exiting as
+ * it detaches it from its filter tree. As such, READ_ONCE() and
+ * barriers are not needed here, as would normally be needed.
+ */
+void seccomp_filter_release(struct task_struct *tsk)
+{
+	struct seccomp_filter *orig = tsk->seccomp.filter;
+
+	/* Detach task from its filter tree. */
+	tsk->seccomp.filter = NULL;
+	__seccomp_filter_release(orig);
+}
+
 /**
 * seccomp_sync_threads: sets all threads to use current's filter
 *
@ -402,14 +555,19 @@ static inline void seccomp_sync_threads(unsigned long flags)

 		/* Get a task reference for the new leaf node. */
 		get_seccomp_filter(caller);
+
 		/*
 		 * Drop the task reference to the shared ancestor since
 		 * current's path will hold a reference.  (This also
 		 * allows a put before the assignment.)
 		 */
-		put_seccomp_filter(thread);
+		__seccomp_filter_release(thread->seccomp.filter);
+
+		/* Make our new filter tree visible. */
 		smp_store_release(&thread->seccomp.filter,
 				  caller->seccomp.filter);
+		atomic_set(&thread->seccomp.filter_count,
+			   atomic_read(&caller->seccomp.filter_count));

 		/*
 		 * Don't let an unprivileged task work around
@ -442,7 +600,12 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 {
 	struct seccomp_filter *sfilter;
 	int ret;
-	const bool save_orig = IS_ENABLED(CONFIG_CHECKPOINT_RESTORE);
+	const bool save_orig =
+#if defined(CONFIG_CHECKPOINT_RESTORE) || defined(SECCOMP_ARCH_NATIVE)
+		true;
+#else
+		false;
+#endif

 	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
 		return ERR_PTR(-EINVAL);
@ -472,7 +635,9 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 		return ERR_PTR(ret);
 	}

-	refcount_set(&sfilter->usage, 1);
+	refcount_set(&sfilter->refs, 1);
+	refcount_set(&sfilter->users, 1);
+	init_waitqueue_head(&sfilter->wqh);

 	return sfilter;
 }
@ -505,6 +670,148 @@ out:
 	return filter;
 }

+#ifdef SECCOMP_ARCH_NATIVE
+/**
+ * seccomp_is_const_allow - check if filter is constant allow with given data
+ * @fprog: The BPF programs
+ * @sd: The seccomp data to check against, only syscall number and arch
+ *      number are considered constant.
+ */
+static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
+				   struct seccomp_data *sd)
+{
+	unsigned int reg_value = 0;
+	unsigned int pc;
+	bool op_res;
+
+	if (WARN_ON_ONCE(!fprog))
+		return false;
+
+	for (pc = 0; pc < fprog->len; pc++) {
+		struct sock_filter *insn = &fprog->filter[pc];
+		u16 code = insn->code;
+		u32 k = insn->k;
+
+		switch (code) {
+		case BPF_LD | BPF_W | BPF_ABS:
+			switch (k) {
+			case offsetof(struct seccomp_data, nr):
+				reg_value = sd->nr;
+				break;
+			case offsetof(struct seccomp_data, arch):
+				reg_value = sd->arch;
+				break;
+			default:
+				/* can't optimize (non-constant value load) */
+				return false;
+			}
+			break;
+		case BPF_RET | BPF_K:
+			/* reached return with constant values only, check allow */
+			return k == SECCOMP_RET_ALLOW;
+		case BPF_JMP | BPF_JA:
+			pc += insn->k;
+			break;
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_K:
+			switch (BPF_OP(code)) {
+			case BPF_JEQ:
+				op_res = reg_value == k;
+				break;
+			case BPF_JGE:
+				op_res = reg_value >= k;
+				break;
+			case BPF_JGT:
+				op_res = reg_value > k;
+				break;
+			case BPF_JSET:
+				op_res = !!(reg_value & k);
+				break;
+			default:
+				/* can't optimize (unknown jump) */
+				return false;
+			}
+
+			pc += op_res ? insn->jt : insn->jf;
+			break;
+		case BPF_ALU | BPF_AND | BPF_K:
+			reg_value &= k;
+			break;
+		default:
+			/* can't optimize (unknown insn) */
+			return false;
+		}
+	}
+
+	/* ran off the end of the filter?! */
+	WARN_ON(1);
+	return false;
+}
+
+static void seccomp_cache_prepare_bitmap(struct seccomp_filter *sfilter,
+					 void *bitmap, const void *bitmap_prev,
+					 size_t bitmap_size, int arch)
+{
+	struct sock_fprog_kern *fprog = sfilter->prog->orig_prog;
+	struct seccomp_data sd;
+	int nr;
+
+	if (bitmap_prev) {
+		/* The new filter must be as restrictive as the last. */
+		bitmap_copy(bitmap, bitmap_prev, bitmap_size);
+	} else {
+		/* Before any filters, all syscalls are always allowed. */
+		bitmap_fill(bitmap, bitmap_size);
+	}
+
+	for (nr = 0; nr < bitmap_size; nr++) {
+		/* No bitmap change: not a cacheable action. */
+		if (!test_bit(nr, bitmap))
+			continue;
+
+		sd.nr = nr;
+		sd.arch = arch;
+
+		/* No bitmap change: continue to always allow. */
+		if (seccomp_is_const_allow(fprog, &sd))
+			continue;
+
+		/*
+		 * Not a cacheable action: always run filters.
+		 * atomic clear_bit() not needed, filter not visible yet.
+		 */
+		__clear_bit(nr, bitmap);
+	}
+}
+
+/**
+ * seccomp_cache_prepare - emulate the filter to find cachable syscalls
+ * @sfilter: The seccomp filter
+ *
+ * Returns 0 if successful or -errno if error occurred.
+ */
+static void seccomp_cache_prepare(struct seccomp_filter *sfilter)
+{
+	struct action_cache *cache = &sfilter->cache;
+	const struct action_cache *cache_prev =
+		sfilter->prev ? &sfilter->prev->cache : NULL;
+
+	seccomp_cache_prepare_bitmap(sfilter, cache->allow_native,
+				     cache_prev ? cache_prev->allow_native : NULL,
+				     SECCOMP_ARCH_NATIVE_NR,
+				     SECCOMP_ARCH_NATIVE);
+
+#ifdef SECCOMP_ARCH_COMPAT
+	seccomp_cache_prepare_bitmap(sfilter, cache->allow_compat,
+				     cache_prev ? cache_prev->allow_compat : NULL,
+				     SECCOMP_ARCH_COMPAT_NR,
+				     SECCOMP_ARCH_COMPAT);
+#endif /* SECCOMP_ARCH_COMPAT */
+}
+#endif /* SECCOMP_ARCH_NATIVE */
+
 /**
 * seccomp_attach_filter: validate and attach filter
 * @flags:  flags to change filter behavior
@ -550,7 +857,9 @@ static long seccomp_attach_filter(unsigned int flags,
 	 * task reference.
 	 */
 	filter->prev = current->seccomp.filter;
+	seccomp_cache_prepare(filter);
 	current->seccomp.filter = filter;
+	atomic_inc(&current->seccomp.filter_count);

 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
@ -561,7 +870,7 @@ static long seccomp_attach_filter(unsigned int flags,

 static void __get_seccomp_filter(struct seccomp_filter *filter)
 {
-	refcount_inc(&filter->usage);
+	refcount_inc(&filter->refs);
 }

 /* get_seccomp_filter - increments the reference count of the filter on @tsk */
@ -571,30 +880,7 @@ void get_seccomp_filter(struct task_struct *tsk)
 	if (!orig)
 		return;
 	__get_seccomp_filter(orig);
-}
-
-static inline void seccomp_filter_free(struct seccomp_filter *filter)
-{
-	if (filter) {
-		bpf_prog_destroy(filter->prog);
-		kfree(filter);
-	}
-}
-
-static void __put_seccomp_filter(struct seccomp_filter *orig)
-{
-	/* Clean up single-reference branches iteratively. */
-	while (orig && refcount_dec_and_test(&orig->usage)) {
-		struct seccomp_filter *freeme = orig;
-		orig = orig->prev;
-		seccomp_filter_free(freeme);
-	}
-}
-
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
-{
-	__put_seccomp_filter(tsk->seccomp.filter);
+	refcount_inc(&orig->users);
 }

 static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason)
@ -691,20 +977,20 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
 */
 static const int mode1_syscalls[] = {
 	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
-	0, /* null terminated */
+	-1, /* negative terminated */
 };

 static void __secure_computing_strict(int this_syscall)
 {
-	const int *syscall_whitelist = mode1_syscalls;
+	const int *allowed_syscalls = mode1_syscalls;
 #ifdef CONFIG_COMPAT
 	if (in_compat_syscall())
-		syscall_whitelist = get_compat_mode1_syscalls();
+		allowed_syscalls = get_compat_mode1_syscalls();
 #endif
 	do {
-		if (*syscall_whitelist == this_syscall)
+		if (*allowed_syscalls == this_syscall)
 			return;
-	} while (*++syscall_whitelist);
+	} while (*++allowed_syscalls != -1);

 #ifdef SECCOMP_DEBUG
 	dump_stack();
@ -743,11 +1029,12 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
 	return filter->notif->next_id++;
 }

-static void seccomp_do_user_notification(int this_syscall,
-					 struct seccomp_filter *match,
-					 const struct seccomp_data *sd)
+static int seccomp_do_user_notification(int this_syscall,
+					struct seccomp_filter *match,
+					const struct seccomp_data *sd)
 {
 	int err;
+	u32 flags = 0;
 	long ret = 0;
 	struct seccomp_knotif n = {};

@ -764,7 +1051,7 @@ static void seccomp_do_user_notification(int this_syscall,
 	list_add(&n.list, &match->notif->notifications);

 	up(&match->notif->request);
-	wake_up_poll(&match->notif->wqh, EPOLLIN | EPOLLRDNORM);
+	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
 	mutex_unlock(&match->notify_lock);

 	/*
@ -775,6 +1062,7 @@ static void seccomp_do_user_notification(int this_syscall,
 	if (err == 0) {
 		ret = n.val;
 		err = n.error;
+		flags = n.flags;
 	}

 	/*
@ -791,8 +1079,14 @@ static void seccomp_do_user_notification(int this_syscall,
 		list_del(&n.list);
 out:
 	mutex_unlock(&match->notify_lock);
-	syscall_set_return_value(current, task_pt_regs(current),
+
+	/* Userspace requests to continue the syscall. */
+	if (flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE)
+		return 0;
+
+	syscall_set_return_value(current, current_pt_regs(),
 				 err, ret);
+	return -1;
 }

 static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
@ -823,13 +1117,13 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		/* Set low-order bits as an errno, capped at MAX_ERRNO. */
 		if (data > MAX_ERRNO)
 			data = MAX_ERRNO;
-		syscall_set_return_value(current, task_pt_regs(current),
+		syscall_set_return_value(current, current_pt_regs(),
 					 -data, 0);
 		goto skip;

 	case SECCOMP_RET_TRAP:
 		/* Show the handler the original registers. */
-		syscall_rollback(current, task_pt_regs(current));
+		syscall_rollback(current, current_pt_regs());
 		/* Let the filter pass back 16 bits of data. */
 		seccomp_send_sigsys(this_syscall, data);
 		goto skip;
@ -842,7 +1136,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		/* ENOSYS these calls if there is no tracer attached. */
 		if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
 			syscall_set_return_value(current,
-						 task_pt_regs(current),
+						 current_pt_regs(),
 						 -ENOSYS, 0);
 			goto skip;
 		}
@ -862,7 +1156,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		if (fatal_signal_pending(current))
 			goto skip;
 		/* Check if the tracer forced the syscall to be skipped. */
-		this_syscall = syscall_get_nr(current, task_pt_regs(current));
+		this_syscall = syscall_get_nr(current, current_pt_regs());
 		if (this_syscall < 0)
 			goto skip;

@ -878,8 +1172,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		return 0;

 	case SECCOMP_RET_USER_NOTIF:
-		seccomp_do_user_notification(this_syscall, match, sd);
-		goto skip;
+		if (seccomp_do_user_notification(this_syscall, match, sd))
+			goto skip;
+
+		return 0;

 	case SECCOMP_RET_LOG:
 		seccomp_log(this_syscall, 0, action, true);
@ -899,20 +1195,20 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		current->seccomp.mode = SECCOMP_MODE_DEAD;
 		seccomp_log(this_syscall, SIGSYS, action, true);
 		/* Dump core only if this is the last remaining thread. */
-		if (action == SECCOMP_RET_KILL_PROCESS ||
+		if (action != SECCOMP_RET_KILL_THREAD ||
 		    get_nr_threads(current) == 1) {
 			kernel_siginfo_t info;

 			/* Show the original registers in the dump. */
-			syscall_rollback(current, task_pt_regs(current));
+			syscall_rollback(current, current_pt_regs());
 			/* Trigger a manual coredump since do_exit skips it. */
 			seccomp_init_siginfo(&info, this_syscall, data);
 			do_coredump(&info);
 		}
-		if (action == SECCOMP_RET_KILL_PROCESS)
-			do_group_exit(SIGSYS);
-		else
+		if (action == SECCOMP_RET_KILL_THREAD)
 			do_exit(SIGSYS);
+		else
+			do_group_exit(SIGSYS);
 	}

 	unreachable();
@ -941,7 +1237,7 @@ int __secure_computing(const struct seccomp_data *sd)
 		return 0;

 	this_syscall = sd ? sd->nr :
-		syscall_get_nr(current, task_pt_regs(current));
+		syscall_get_nr(current, current_pt_regs());

 	switch (mode) {
 	case SECCOMP_MODE_STRICT:
@ -995,13 +1291,18 @@ out:
 }

 #ifdef CONFIG_SECCOMP_FILTER
-static int seccomp_notify_release(struct inode *inode, struct file *file)
+static void seccomp_notify_free(struct seccomp_filter *filter)
+{
+	kfree(filter->notif);
+	filter->notif = NULL;
+}
+
+static void seccomp_notify_detach(struct seccomp_filter *filter)
 {
-	struct seccomp_filter *filter = file->private_data;
 	struct seccomp_knotif *knotif;

 	if (!filter)
-		return 0;
+		return;

 	mutex_lock(&filter->notify_lock);

@ -1020,13 +1321,36 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		complete(&knotif->ready);
 	}

-	kfree(filter->notif);
-	filter->notif = NULL;
+	seccomp_notify_free(filter);
 	mutex_unlock(&filter->notify_lock);
+}
+
+static int seccomp_notify_release(struct inode *inode, struct file *file)
+{
+	struct seccomp_filter *filter = file->private_data;
+
+	seccomp_notify_detach(filter);
 	__put_seccomp_filter(filter);
 	return 0;
 }

+/* must be called with notif_lock held */
+static inline struct seccomp_knotif *
+find_notification(struct seccomp_filter *filter, u64 id)
+{
+	struct seccomp_knotif *cur;
+
+	lockdep_assert_held(&filter->notify_lock);
+
+	list_for_each_entry(cur, &filter->notif->notifications, list) {
+		if (cur->id == id)
+			return cur;
+	}
+
+	return NULL;
+}
+
+
 static long seccomp_notify_recv(struct seccomp_filter *filter,
 				void __user *buf)
 {
@ -1070,7 +1394,7 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 	unotif.data = *(knotif->data);

 	knotif->state = SECCOMP_NOTIFY_SENT;
-	wake_up_poll(&filter->notif->wqh, EPOLLOUT | EPOLLWRNORM);
+	wake_up_poll(&filter->wqh, EPOLLOUT | EPOLLWRNORM);
 	ret = 0;
 out:
 	mutex_unlock(&filter->notify_lock);
@ -1084,15 +1408,8 @@ out:
 		 * may have died when we released the lock, so we need to make
 		 * sure it's still around.
 		 */
-		knotif = NULL;
 		mutex_lock(&filter->notify_lock);
-		list_for_each_entry(cur, &filter->notif->notifications, list) {
-			if (cur->id == unotif.id) {
-				knotif = cur;
-				break;
-			}
-		}
-
+		knotif = find_notification(filter, unotif.id);
 		if (knotif) {
 			knotif->state = SECCOMP_NOTIFY_INIT;
 			up(&filter->notif->request);
@ -1107,26 +1424,24 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 				void __user *buf)
 {
 	struct seccomp_notif_resp resp = {};
-	struct seccomp_knotif *knotif = NULL, *cur;
+	struct seccomp_knotif *knotif;
 	long ret;

 	if (copy_from_user(&resp, buf, sizeof(resp)))
 		return -EFAULT;

-	if (resp.flags)
+	if (resp.flags & ~SECCOMP_USER_NOTIF_FLAG_CONTINUE)
+		return -EINVAL;
+
+	if ((resp.flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) &&
+	    (resp.error || resp.val))
 		return -EINVAL;

 	ret = mutex_lock_interruptible(&filter->notify_lock);
 	if (ret < 0)
 		return ret;

-	list_for_each_entry(cur, &filter->notif->notifications, list) {
-		if (cur->id == resp.id) {
-			knotif = cur;
-			break;
-		}
-	}
-
+	knotif = find_notification(filter, resp.id);
 	if (!knotif) {
 		ret = -ENOENT;
 		goto out;
@ -1142,6 +1457,7 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 	knotif->state = SECCOMP_NOTIFY_REPLIED;
 	knotif->error = resp.error;
 	knotif->val = resp.val;
+	knotif->flags = resp.flags;
 	complete(&knotif->ready);
 out:
 	mutex_unlock(&filter->notify_lock);
@ -1151,7 +1467,7 @@ out:
 static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 				    void __user *buf)
 {
-	struct seccomp_knotif *knotif = NULL;
+	struct seccomp_knotif *knotif;
 	u64 id;
 	long ret;

@ -1162,16 +1478,12 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 	if (ret < 0)
 		return ret;

-	ret = -ENOENT;
-	list_for_each_entry(knotif, &filter->notif->notifications, list) {
-		if (knotif->id == id) {
-			if (knotif->state == SECCOMP_NOTIFY_SENT)
-				ret = 0;
-			goto out;
-		}
-	}
+	knotif = find_notification(filter, id);
+	if (knotif && knotif->state == SECCOMP_NOTIFY_SENT)
+		ret = 0;
+	else
+		ret = -ENOENT;

-out:
 	mutex_unlock(&filter->notify_lock);
 	return ret;
 }
@ -1202,7 +1514,7 @@ static __poll_t seccomp_notify_poll(struct file *file,
 	__poll_t ret = 0;
 	struct seccomp_knotif *cur;

-	poll_wait(file, &filter->notif->wqh, poll_tab);
+	poll_wait(file, &filter->wqh, poll_tab);

 	if (mutex_lock_interruptible(&filter->notify_lock) < 0)
 		return EPOLLERR;
@ -1218,6 +1530,9 @@ static __poll_t seccomp_notify_poll(struct file *file,

 	mutex_unlock(&filter->notify_lock);

+	if (refcount_read(&filter->users) == 0)
+		ret |= EPOLLHUP;
+
 	return ret;
 }

@ -1240,7 +1555,6 @@ static struct file *init_listener(struct seccomp_filter *filter)
 	sema_init(&filter->notif->request, 0);
 	filter->notif->next_id = get_random_u64();
 	INIT_LIST_HEAD(&filter->notif->notifications);
-	init_waitqueue_head(&filter->notif->wqh);

 	ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops,
 				 filter, O_RDWR);
@ -1252,7 +1566,7 @@ static struct file *init_listener(struct seccomp_filter *filter)

 out_notif:
 	if (IS_ERR(ret))
-		kfree(filter->notif);
+		seccomp_notify_free(filter);
 out:
 	return ret;
 }
@ -1373,6 +1687,7 @@ out_put_fd:
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
+			seccomp_notify_detach(prepared);
 		} else {
 			fd_install(listener, listener_f);
 			ret = listener;
@ -1720,7 +2035,7 @@ static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names)
 	return true;
 }

-static int read_actions_logged(struct ctl_table *ro_table, void *buffer,
+static int read_actions_logged(struct ctl_table *ro_table, void __user *buffer,
 			       size_t *lenp, loff_t *ppos)
 {
 	char names[sizeof(seccomp_actions_avail)];
@ -1738,7 +2053,7 @@ static int read_actions_logged(struct ctl_table *ro_table, void *buffer,
 	return proc_dostring(&table, 0, buffer, lenp, ppos);
 }

-static int write_actions_logged(struct ctl_table *ro_table, void *buffer,
+static int write_actions_logged(struct ctl_table *ro_table, void __user *buffer,
 				size_t *lenp, loff_t *ppos, u32 *actions_logged)
 {
 	char names[sizeof(seccomp_actions_avail)];
@ -1846,7 +2161,7 @@ static int __init seccomp_sysctl_init(void)

 	hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
 	if (!hdr)
-		pr_warn("seccomp: sysctl registration failed\n");
+		pr_warn("sysctl registration failed\n");
 	else
 		kmemleak_not_leak(hdr);

--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@ -74,6 +74,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
+obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
--- a/kernel/trace/error_report-traces.c
+++ b/kernel/trace/error_report-traces.c
@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Error reporting trace points.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/error_report.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(error_report_end);
+