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

arch/Kconfig

@@ -486,6 +486,9 @@ config HAVE_ARCH_SECCOMP_FILTER
 	  - secure_computing return value is checked and a return value of -1
 	    results in the system call being skipped immediately.
 	  - seccomp syscall wired up
+	  - if !HAVE_SPARSE_SYSCALL_NR, have SECCOMP_ARCH_NATIVE,
+	    SECCOMP_ARCH_NATIVE_NR, SECCOMP_ARCH_NATIVE_NAME defined. If
+	    COMPAT is supported, have the SECCOMP_ARCH_COMPAT* defines too.
 
 config SECCOMP
 	prompt "Enable seccomp to safely execute untrusted bytecode"
@@ -514,6 +517,20 @@ config SECCOMP_FILTER
 
 	  See Documentation/userspace-api/seccomp_filter.rst for details.
 
+config SECCOMP_CACHE_DEBUG
+	bool "Show seccomp filter cache status in /proc/pid/seccomp_cache"
+	depends on SECCOMP_FILTER && !HAVE_SPARSE_SYSCALL_NR
+	depends on PROC_FS
+	help
+	  This enables the /proc/pid/seccomp_cache interface to monitor
+	  seccomp cache data. The file format is subject to change. Reading
+	  the file requires CAP_SYS_ADMIN.
+
+	  This option is for debugging only. Enabling presents the risk that
+	  an adversary may be able to infer the seccomp filter logic.
+
+	  If unsure, say N.
+
 config HAVE_ARCH_STACKLEAK
 	bool
 	help

arch/arm/include/asm/Kbuild

@@ -4,7 +4,6 @@ generic-y += extable.h
 generic-y += flat.h
 generic-y += local64.h
 generic-y += parport.h
-generic-y += seccomp.h
 
 generated-y += mach-types.h
 generated-y += unistd-nr.h

arch/arm/include/asm/seccomp.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm-generic/seccomp.h>
+
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_ARM
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"arm"
+
+#endif /* _ASM_SECCOMP_H */

arch/arm64/include/asm/seccomp.h

@@ -19,4 +19,13 @@
 
 #include <asm-generic/seccomp.h>
 
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_AARCH64
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"aarch64"
+#ifdef CONFIG_COMPAT
+# define SECCOMP_ARCH_COMPAT		AUDIT_ARCH_ARM
+# define SECCOMP_ARCH_COMPAT_NR	__NR_compat_syscalls
+# define SECCOMP_ARCH_COMPAT_NAME	"arm"
+#endif
+
 #endif /* _ASM_SECCOMP_H */

arch/csky/include/asm/Kbuild

@@ -4,6 +4,5 @@ generic-y += gpio.h
 generic-y += kvm_para.h
 generic-y += local64.h
 generic-y += qrwlock.h
-generic-y += seccomp.h
 generic-y += user.h
 generic-y += vmlinux.lds.h

arch/csky/include/asm/seccomp.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm-generic/seccomp.h>
+
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_CSKY
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"csky"
+
+#endif /* _ASM_SECCOMP_H */

arch/parisc/include/asm/Kbuild

@@ -5,5 +5,4 @@ generated-y += syscall_table_c32.h
 generic-y += kvm_para.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
-generic-y += seccomp.h
 generic-y += user.h

arch/parisc/include/asm/seccomp.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm-generic/seccomp.h>
+
+#ifdef CONFIG_64BIT
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_PARISC64
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"parisc64"
+# ifdef CONFIG_COMPAT
+#  define SECCOMP_ARCH_COMPAT		AUDIT_ARCH_PARISC
+#  define SECCOMP_ARCH_COMPAT_NR	NR_syscalls
+#  define SECCOMP_ARCH_COMPAT_NAME	"parisc"
+# endif
+#else /* !CONFIG_64BIT */
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_PARISC
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"parisc"
+#endif
+
+#endif /* _ASM_SECCOMP_H */

arch/powerpc/include/asm/seccomp.h

@@ -8,4 +8,27 @@
 
 #include <asm-generic/seccomp.h>
 
+#ifdef __LITTLE_ENDIAN__
+#define __SECCOMP_ARCH_LE		__AUDIT_ARCH_LE
+#define __SECCOMP_ARCH_LE_NAME		"le"
+#else
+#define __SECCOMP_ARCH_LE		0
+#define __SECCOMP_ARCH_LE_NAME
+#endif
+
+#ifdef CONFIG_PPC64
+# define SECCOMP_ARCH_NATIVE		(AUDIT_ARCH_PPC64 | __SECCOMP_ARCH_LE)
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"ppc64" __SECCOMP_ARCH_LE_NAME
+# ifdef CONFIG_COMPAT
+#  define SECCOMP_ARCH_COMPAT		(AUDIT_ARCH_PPC | __SECCOMP_ARCH_LE)
+#  define SECCOMP_ARCH_COMPAT_NR	NR_syscalls
+#  define SECCOMP_ARCH_COMPAT_NAME	"ppc" __SECCOMP_ARCH_LE_NAME
+# endif
+#else /* !CONFIG_PPC64 */
+# define SECCOMP_ARCH_NATIVE		(AUDIT_ARCH_PPC | __SECCOMP_ARCH_LE)
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"ppc" __SECCOMP_ARCH_LE_NAME
+#endif
+
 #endif	/* _ASM_POWERPC_SECCOMP_H */

arch/riscv/include/asm/seccomp.h

@@ -7,4 +7,14 @@
 
 #include <asm-generic/seccomp.h>
 
+#ifdef CONFIG_64BIT
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_RISCV64
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"riscv64"
+#else /* !CONFIG_64BIT */
+# define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_RISCV32
+# define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+# define SECCOMP_ARCH_NATIVE_NAME	"riscv32"
+#endif
+
 #endif /* _ASM_SECCOMP_H */

arch/s390/include/asm/seccomp.h

@@ -16,4 +16,13 @@
 
 #include <asm-generic/seccomp.h>
 
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_S390X
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"s390x"
+#ifdef CONFIG_COMPAT
+# define SECCOMP_ARCH_COMPAT		AUDIT_ARCH_S390
+# define SECCOMP_ARCH_COMPAT_NR		NR_syscalls
+# define SECCOMP_ARCH_COMPAT_NAME	"s390"
+#endif
+
 #endif	/* _ASM_S390_SECCOMP_H */

arch/sh/include/asm/seccomp.h

@@ -8,4 +8,14 @@
 #define __NR_seccomp_exit __NR_exit
 #define __NR_seccomp_sigreturn __NR_rt_sigreturn
 
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define __SECCOMP_ARCH_LE		__AUDIT_ARCH_LE
+#else
+#define __SECCOMP_ARCH_LE		0
+#endif
+
+#define SECCOMP_ARCH_NATIVE		(AUDIT_ARCH_SH | __SECCOMP_ARCH_LE)
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"sh"
+
 #endif /* __ASM_SECCOMP_H */

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 */

arch/xtensa/include/asm/Kbuild

@@ -7,5 +7,4 @@ generic-y += mcs_spinlock.h
 generic-y += param.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
-generic-y += seccomp.h
 generic-y += user.h

arch/xtensa/include/asm/seccomp.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm-generic/seccomp.h>
+
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_XTENSA
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"xtensa"
+
+#endif /* _ASM_SECCOMP_H */

fs/proc/base.c

@@ -3263,6 +3263,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 	ONE("arch_status", S_IRUGO, proc_pid_arch_status),
 #endif
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3592,6 +3595,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 	ONE("arch_status", S_IRUGO, proc_pid_arch_status),
 #endif
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)

include/linux/seccomp.h

@@ -121,4 +121,11 @@ static inline long seccomp_get_metadata(struct task_struct *task,
 	return -EINVAL;
 }
 #endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */
+
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+struct seq_file;
+
+int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task);
+#endif
 #endif /* _LINUX_SECCOMP_H */

tools/testing/selftests/seccomp/config

+CONFIG_PID_NS=y
 CONFIG_SECCOMP=y
 CONFIG_SECCOMP_FILTER=y
 CONFIG_USER_NS=y

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;
 }

tools/testing/selftests/seccomp/settings

-timeout=90
+timeout=120