Merge tag 'seccomp-v5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:
 "The major change here is finally gaining seccomp constant-action
  bitmaps, which internally reduces the seccomp overhead for many
  real-world syscall filters to O(1), as discussed at Plumbers this
  year.

   - Improve seccomp performance via constant-action bitmaps (YiFei Zhu
     & Kees Cook)

   - Fix bogus __user annotations (Jann Horn)

   - Add missed CONFIG for improved selftest coverage (Mickaël Salaün)"

* tag 'seccomp-v5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  selftests/seccomp: Update kernel config
  seccomp: Remove bogus __user annotations
  seccomp/cache: Report cache data through /proc/pid/seccomp_cache
  xtensa: Enable seccomp architecture tracking
  sh: Enable seccomp architecture tracking
  s390: Enable seccomp architecture tracking
  riscv: Enable seccomp architecture tracking
  powerpc: Enable seccomp architecture tracking
  parisc: Enable seccomp architecture tracking
  csky: Enable seccomp architecture tracking
  arm: Enable seccomp architecture tracking
  arm64: Enable seccomp architecture tracking
  selftests/seccomp: Compare bitmap vs filter overhead
  x86: Enable seccomp architecture tracking
  seccomp/cache: Add "emulator" to check if filter is constant allow
  seccomp/cache: Lookup syscall allowlist bitmap for fast path

1 files changed, 293 insertions, 3 deletions

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 15f47fc11d13..952dc1c90229 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -143,6 +143,38 @@ struct notification {
 	struct list_head notifications;
 };
 
+#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
  *
@@ -159,6 +191,7 @@ struct notification {
  *	   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
@@ -180,6 +213,7 @@ struct seccomp_filter {
 	refcount_t refs;
 	refcount_t users;
 	bool log;
+	struct action_cache cache;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
 	struct notification *notif;
@@ -298,6 +332,52 @@ 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
@@ -320,6 +400,9 @@ 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).
@@ -470,6 +553,9 @@ void seccomp_filter_release(struct task_struct *tsk)
 {
 	struct seccomp_filter *orig = tsk->seccomp.filter;
 
+	/* We are effectively holding the siglock by not having any sighand. */
+	WARN_ON(tsk->sighand != NULL);
+
 	/* Detach task from its filter tree. */
 	tsk->seccomp.filter = NULL;
 	__seccomp_filter_release(orig);
@@ -544,7 +630,12 @@ 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);
@@ -609,6 +700,148 @@ 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
@@ -658,6 +891,7 @@ 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);
 
@@ -1967,7 +2201,7 @@ 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 __user *buffer,
+static int read_actions_logged(struct ctl_table *ro_table, void *buffer,
 			       size_t *lenp, loff_t *ppos)
 {
 	char names[sizeof(seccomp_actions_avail)];
@@ -1985,7 +2219,7 @@ static int read_actions_logged(struct ctl_table *ro_table, void __user *buffer,
 	return proc_dostring(&table, 0, buffer, lenp, ppos);
 }
 
-static int write_actions_logged(struct ctl_table *ro_table, void __user *buffer,
+static int write_actions_logged(struct ctl_table *ro_table, void *buffer,
 				size_t *lenp, loff_t *ppos, u32 *actions_logged)
 {
 	char names[sizeof(seccomp_actions_avail)];
@@ -2103,3 +2337,59 @@ static int __init seccomp_sysctl_init(void)
 device_initcall(seccomp_sysctl_init)
 
 #endif /* CONFIG_SYSCTL */
+
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+/* Currently CONFIG_SECCOMP_CACHE_DEBUG implies SECCOMP_ARCH_NATIVE */
+static void proc_pid_seccomp_cache_arch(struct seq_file *m, const char *name,
+					const void *bitmap, size_t bitmap_size)
+{
+	int nr;
+
+	for (nr = 0; nr < bitmap_size; nr++) {
+		bool cached = test_bit(nr, bitmap);
+		char *status = cached ? "ALLOW" : "FILTER";
+
+		seq_printf(m, "%s %d %s\n", name, nr, status);
+	}
+}
+
+int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task)
+{
+	struct seccomp_filter *f;
+	unsigned long flags;
+
+	/*
+	 * We don't want some sandboxed process to know what their seccomp
+	 * filters consist of.
+	 */
+	if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!lock_task_sighand(task, &flags))
+		return -ESRCH;
+
+	f = READ_ONCE(task->seccomp.filter);
+	if (!f) {
+		unlock_task_sighand(task, &flags);
+		return 0;
+	}
+
+	/* prevent filter from being freed while we are printing it */
+	__get_seccomp_filter(f);
+	unlock_task_sighand(task, &flags);
+
+	proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_NATIVE_NAME,
+				    f->cache.allow_native,
+				    SECCOMP_ARCH_NATIVE_NR);
+
+#ifdef SECCOMP_ARCH_COMPAT
+	proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME,
+				    f->cache.allow_compat,
+				    SECCOMP_ARCH_COMPAT_NR);
+#endif /* SECCOMP_ARCH_COMPAT */
+
+	__put_seccomp_filter(f);
+	return 0;
+}
+#endif /* CONFIG_SECCOMP_CACHE_DEBUG */