Merge remote-tracking branch 'seccomp/for-next/seccomp' into master

4 files changed, 382 insertions, 24 deletions

diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h
index 2bd1338de236..fef16e398161 100644
--- a/arch/x86/include/asm/seccomp.h
+++ b/arch/x86/include/asm/seccomp.h
@@ -16,6 +16,26 @@
 #define __NR_seccomp_sigreturn_32	__NR_ia32_sigreturn
 #endif
 
+#ifdef CONFIG_X86_64
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_X86_64
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"x86_64"
+# ifdef CONFIG_COMPAT
+#  define SECCOMP_ARCH_COMPAT		AUDIT_ARCH_I386
+#  define SECCOMP_ARCH_COMPAT_NR	IA32_NR_syscalls
+#  define SECCOMP_ARCH_COMPAT_NAME	"ia32"
+# endif
+/*
+ * x32 will have __X32_SYSCALL_BIT set in syscall number. We don't support
+ * caching them and they are treated as out of range syscalls, which will
+ * always pass through the BPF filter.
+ */
+#else /* !CONFIG_X86_64 */
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_I386
+# define SECCOMP_ARCH_NATIVE_NR	        NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"ia32"
+#endif
+
 #include <asm-generic/seccomp.h>
 
 #endif /* _ASM_X86_SECCOMP_H */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 8ad7a293255a..d8cf468dbe1e 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).
@@ -544,7 +627,12 @@ 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);
@@ -610,6 +698,148 @@ 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
@@ -659,6 +889,7 @@ 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);
 
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 91f5a89cadac..fcc806585266 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -4,12 +4,16 @@
  */
 #define _GNU_SOURCE
 #include <assert.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stddef.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
 #include <unistd.h>
 #include <linux/filter.h>
 #include <linux/seccomp.h>
+#include <sys/param.h>
 #include <sys/prctl.h>
 #include <sys/syscall.h>
 #include <sys/types.h>
@@ -70,18 +74,74 @@ unsigned long long calibrate(void)
 	return samples * seconds;
 }
 
+bool approx(int i_one, int i_two)
+{
+	double one = i_one, one_bump = one * 0.01;
+	double two = i_two, two_bump = two * 0.01;
+
+	one_bump = one + MAX(one_bump, 2.0);
+	two_bump = two + MAX(two_bump, 2.0);
+
+	/* Equal to, or within 1% or 2 digits */
+	if (one == two ||
+	    (one > two && one <= two_bump) ||
+	    (two > one && two <= one_bump))
+		return true;
+	return false;
+}
+
+bool le(int i_one, int i_two)
+{
+	if (i_one <= i_two)
+		return true;
+	return false;
+}
+
+long compare(const char *name_one, const char *name_eval, const char *name_two,
+	     unsigned long long one, bool (*eval)(int, int), unsigned long long two)
+{
+	bool good;
+
+	printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
+	       (long long)one, name_eval, (long long)two);
+	if (one > INT_MAX) {
+		printf("Miscalculation! Measurement went negative: %lld\n", (long long)one);
+		return 1;
+	}
+	if (two > INT_MAX) {
+		printf("Miscalculation! Measurement went negative: %lld\n", (long long)two);
+		return 1;
+	}
+
+	good = eval(one, two);
+	printf("%s\n", good ? "✔️" : "❌");
+
+	return good ? 0 : 1;
+}
+
 int main(int argc, char *argv[])
 {
+	struct sock_filter bitmap_filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog bitmap_prog = {
+		.len = (unsigned short)ARRAY_SIZE(bitmap_filter),
+		.filter = bitmap_filter,
+	};
 	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, args[0])),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
 	struct sock_fprog prog = {
 		.len = (unsigned short)ARRAY_SIZE(filter),
 		.filter = filter,
 	};
-	long ret;
-	unsigned long long samples;
-	unsigned long long native, filter1, filter2;
+
+	long ret, bits;
+	unsigned long long samples, calc;
+	unsigned long long native, filter1, filter2, bitmap1, bitmap2;
+	unsigned long long entry, per_filter1, per_filter2;
 
 	printf("Current BPF sysctl settings:\n");
 	system("sysctl net.core.bpf_jit_enable");
@@ -101,35 +161,82 @@ int main(int argc, char *argv[])
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	assert(ret == 0);
 
-	/* One filter */
-	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+	/* One filter resulting in a bitmap */
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
-	filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1);
+	bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
+
+	/* Second filter resulting in a bitmap */
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
+	assert(ret == 0);
 
-	if (filter1 == native)
-		printf("No overhead measured!? Try running again with more samples.\n");
+	bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
 
-	/* Two filters */
+	/* Third filter, can no longer be converted to bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
 	assert(ret == 0);
 
-	filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2);
-
-	/* Calculations */
-	printf("Estimated total seccomp overhead for 1 filter: %llu ns\n",
-		filter1 - native);
+	filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
 
-	printf("Estimated total seccomp overhead for 2 filters: %llu ns\n",
-		filter2 - native);
+	/* Fourth filter, can not be converted to bitmap because of filter 3 */
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
+	assert(ret == 0);
 
-	printf("Estimated seccomp per-filter overhead: %llu ns\n",
-		filter2 - filter1);
+	filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+	printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
+
+	/* Estimations */
+#define ESTIMATE(fmt, var, what)	do {			\
+		var = (what);					\
+		printf("Estimated " fmt ": %llu ns\n", var);	\
+		if (var > INT_MAX)				\
+			goto more_samples;			\
+	} while (0)
+
+	ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc,
+		 bitmap1 - native);
+	ESTIMATE("total seccomp overhead for 2 bitmapped filters", calc,
+		 bitmap2 - native);
+	ESTIMATE("total seccomp overhead for 3 full filters", calc,
+		 filter1 - native);
+	ESTIMATE("total seccomp overhead for 4 full filters", calc,
+		 filter2 - native);
+	ESTIMATE("seccomp entry overhead", entry,
+		 bitmap1 - native - (bitmap2 - bitmap1));
+	ESTIMATE("seccomp per-filter overhead (last 2 diff)", per_filter1,
+		 filter2 - filter1);
+	ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2,
+		 (filter2 - native - entry) / 4);
+
+	printf("Expectations:\n");
+	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1);
+	bits = compare("native", "≤", "1 filter", native, le, filter1);
+	if (bits)
+		goto more_samples;
+
+	ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)",
+			per_filter1, approx, per_filter2);
+
+	bits = compare("1 bitmapped", "≈", "2 bitmapped",
+			bitmap1 - native, approx, bitmap2 - native);
+	if (bits) {
+		printf("Skipping constant action bitmap expectations: they appear unsupported.\n");
+		goto out;
+	}
 
-	printf("Estimated seccomp entry overhead: %llu ns\n",
-		filter1 - native - (filter2 - filter1));
+	ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native);
+	ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native);
+	ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total",
+			entry + (per_filter1 * 4) + native, approx, filter2);
+	if (ret == 0)
+		goto out;
 
+more_samples:
+	printf("Saw unexpected benchmark result. Try running again with more samples?\n");
+out:
 	return 0;
 }
diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings
index ba4d85f74cd6..6091b45d226b 100644
--- a/tools/testing/selftests/seccomp/settings
+++ b/tools/testing/selftests/seccomp/settings
@@ -1 +1 @@
-timeout=90
+timeout=120