Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

5 files changed, 527 insertions, 0 deletions

diff --git a/tools/testing/selftests/syscall_user_dispatch/.gitignore b/tools/testing/selftests/syscall_user_dispatch/.gitignore
new file mode 100644
index 000000000..f539615ad
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+sud_test
+sud_benchmark
diff --git a/tools/testing/selftests/syscall_user_dispatch/Makefile b/tools/testing/selftests/syscall_user_dispatch/Makefile
new file mode 100644
index 000000000..03c120270
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+top_srcdir = ../../../..
+INSTALL_HDR_PATH = $(top_srcdir)/usr
+LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
+
+CFLAGS += -Wall -I$(LINUX_HDR_PATH)
+
+TEST_GEN_PROGS := sud_test sud_benchmark
+include ../lib.mk
diff --git a/tools/testing/selftests/syscall_user_dispatch/config b/tools/testing/selftests/syscall_user_dispatch/config
new file mode 100644
index 000000000..039e303e5
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/config
@@ -0,0 +1 @@
+CONFIG_GENERIC_ENTRY=y
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
new file mode 100644
index 000000000..073a03702
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ *
+ * Benchmark and test syscall user dispatch
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <sys/sysinfo.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+
+#ifndef PR_SET_SYSCALL_USER_DISPATCH
+# define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF	0
+# define PR_SYS_DISPATCH_ON	1
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
+#endif
+
+#ifdef __NR_syscalls
+# define MAGIC_SYSCALL_1 (__NR_syscalls + 1) /* Bad Linux syscall number */
+#else
+# define MAGIC_SYSCALL_1 (0xff00)  /* Bad Linux syscall number */
+#endif
+
+/*
+ * To test returning from a sigsys with selector blocked, the test
+ * requires some per-architecture support (i.e. knowledge about the
+ * signal trampoline address).  On i386, we know it is on the vdso, and
+ * a small trampoline is open-coded for x86_64.  Other architectures
+ * that have a trampoline in the vdso will support TEST_BLOCKED_RETURN
+ * out of the box, but don't enable them until they support syscall user
+ * dispatch.
+ */
+#if defined(__x86_64__) || defined(__i386__)
+#define TEST_BLOCKED_RETURN
+#endif
+
+#ifdef __x86_64__
+void* (syscall_dispatcher_start)(void);
+void* (syscall_dispatcher_end)(void);
+#else
+unsigned long syscall_dispatcher_start = 0;
+unsigned long syscall_dispatcher_end = 0;
+#endif
+
+unsigned long trapped_call_count = 0;
+unsigned long native_call_count = 0;
+
+char selector;
+#define SYSCALL_BLOCK   (selector = SYSCALL_DISPATCH_FILTER_BLOCK)
+#define SYSCALL_UNBLOCK (selector = SYSCALL_DISPATCH_FILTER_ALLOW)
+
+#define CALIBRATION_STEP 100000
+#define CALIBRATE_TO_SECS 5
+int factor;
+
+static double one_sysinfo_step(void)
+{
+	struct timespec t1, t2;
+	int i;
+	struct sysinfo info;
+
+	clock_gettime(CLOCK_MONOTONIC, &t1);
+	for (i = 0; i < CALIBRATION_STEP; i++)
+		sysinfo(&info);
+	clock_gettime(CLOCK_MONOTONIC, &t2);
+	return (t2.tv_sec - t1.tv_sec) + 1.0e-9 * (t2.tv_nsec - t1.tv_nsec);
+}
+
+static void calibrate_set(void)
+{
+	double elapsed = 0;
+
+	printf("Calibrating test set to last ~%d seconds...\n", CALIBRATE_TO_SECS);
+
+	while (elapsed < 1) {
+		elapsed += one_sysinfo_step();
+		factor += CALIBRATE_TO_SECS;
+	}
+
+	printf("test iterations = %d\n", CALIBRATION_STEP * factor);
+}
+
+static double perf_syscall(void)
+{
+	unsigned int i;
+	double partial = 0;
+
+	for (i = 0; i < factor; ++i)
+		partial += one_sysinfo_step()/(CALIBRATION_STEP*factor);
+	return partial;
+}
+
+static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
+{
+	char buf[1024];
+	int len;
+
+	SYSCALL_UNBLOCK;
+
+	/* printf and friends are not signal-safe. */
+	len = snprintf(buf, 1024, "Caught sys_%x\n", info->si_syscall);
+	write(1, buf, len);
+
+	if (info->si_syscall == MAGIC_SYSCALL_1)
+		trapped_call_count++;
+	else
+		native_call_count++;
+
+#ifdef TEST_BLOCKED_RETURN
+	SYSCALL_BLOCK;
+#endif
+
+#ifdef __x86_64__
+	__asm__ volatile("movq $0xf, %rax");
+	__asm__ volatile("leaveq");
+	__asm__ volatile("add $0x8, %rsp");
+	__asm__ volatile("syscall_dispatcher_start:");
+	__asm__ volatile("syscall");
+	__asm__ volatile("nop"); /* Landing pad within dispatcher area */
+	__asm__ volatile("syscall_dispatcher_end:");
+#endif
+
+}
+
+int main(void)
+{
+	struct sigaction act;
+	double time1, time2;
+	int ret;
+	sigset_t mask;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&mask);
+
+	act.sa_sigaction = handle_sigsys;
+	act.sa_flags = SA_SIGINFO;
+	act.sa_mask = mask;
+
+	calibrate_set();
+
+	time1 = perf_syscall();
+	printf("Avg syscall time %.0lfns.\n", time1 * 1.0e9);
+
+	ret = sigaction(SIGSYS, &act, NULL);
+	if (ret) {
+		perror("Error sigaction:");
+		exit(-1);
+	}
+
+	fprintf(stderr, "Enabling syscall trapping.\n");
+
+	if (prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON,
+		  syscall_dispatcher_start,
+		  (syscall_dispatcher_end - syscall_dispatcher_start + 1),
+		  &selector)) {
+		perror("prctl failed\n");
+		exit(-1);
+	}
+
+	SYSCALL_BLOCK;
+	syscall(MAGIC_SYSCALL_1);
+
+#ifdef TEST_BLOCKED_RETURN
+	if (selector == SYSCALL_DISPATCH_FILTER_ALLOW) {
+		fprintf(stderr, "Failed to return with selector blocked.\n");
+		exit(-1);
+	}
+#endif
+
+	SYSCALL_UNBLOCK;
+
+	if (!trapped_call_count) {
+		fprintf(stderr, "syscall trapping does not work.\n");
+		exit(-1);
+	}
+
+	time2 = perf_syscall();
+
+	if (native_call_count) {
+		perror("syscall trapping intercepted more syscalls than expected\n");
+		exit(-1);
+	}
+
+	printf("trapped_call_count %lu, native_call_count %lu.\n",
+	       trapped_call_count, native_call_count);
+	printf("Avg syscall time %.0lfns.\n", time2 * 1.0e9);
+	printf("Interception overhead: %.1lf%% (+%.0lfns).\n",
+	       100.0 * (time2 / time1 - 1.0), 1.0e9 * (time2 - time1));
+	return 0;
+
+}
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
new file mode 100644
index 000000000..b5d592d40
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ *
+ * Test code for syscall user dispatch
+ */
+
+#define _GNU_SOURCE
+#include <sys/prctl.h>
+#include <sys/sysinfo.h>
+#include <sys/syscall.h>
+#include <signal.h>
+
+#include <asm/unistd.h>
+#include "../kselftest_harness.h"
+
+#ifndef PR_SET_SYSCALL_USER_DISPATCH
+# define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF	0
+# define PR_SYS_DISPATCH_ON	1
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
+#endif
+
+#ifndef SYS_USER_DISPATCH
+# define SYS_USER_DISPATCH	2
+#endif
+
+#ifdef __NR_syscalls
+# define MAGIC_SYSCALL_1 (__NR_syscalls + 1) /* Bad Linux syscall number */
+#else
+# define MAGIC_SYSCALL_1 (0xff00)  /* Bad Linux syscall number */
+#endif
+
+#define SYSCALL_DISPATCH_ON(x) ((x) = SYSCALL_DISPATCH_FILTER_BLOCK)
+#define SYSCALL_DISPATCH_OFF(x) ((x) = SYSCALL_DISPATCH_FILTER_ALLOW)
+
+/* Test Summary:
+ *
+ * - dispatch_trigger_sigsys: Verify if PR_SET_SYSCALL_USER_DISPATCH is
+ *   able to trigger SIGSYS on a syscall.
+ *
+ * - bad_selector: Test that a bad selector value triggers SIGSYS with
+ *   si_errno EINVAL.
+ *
+ * - bad_prctl_param: Test that the API correctly rejects invalid
+ *   parameters on prctl
+ *
+ * - dispatch_and_return: Test that a syscall is selectively dispatched
+ *   to userspace depending on the value of selector.
+ *
+ * - disable_dispatch: Test that the PR_SYS_DISPATCH_OFF correctly
+ *   disables the dispatcher
+ *
+ * - direct_dispatch_range: Test that a syscall within the allowed range
+ *   can bypass the dispatcher.
+ */
+
+TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS)
+{
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+	struct sysinfo info;
+	int ret;
+
+	ret = sysinfo(&info);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	SYSCALL_DISPATCH_ON(sel);
+
+	sysinfo(&info);
+
+	EXPECT_FALSE(true) {
+		TH_LOG("Unreachable!");
+	}
+}
+
+TEST(bad_prctl_param)
+{
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+	int op;
+
+	/* Invalid op */
+	op = -1;
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0, 0, &sel);
+	ASSERT_EQ(EINVAL, errno);
+
+	/* PR_SYS_DISPATCH_OFF */
+	op = PR_SYS_DISPATCH_OFF;
+
+	/* offset != 0 */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x1, 0x0, 0);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* len != 0 */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0xff, 0);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* sel != NULL */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x0, &sel);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* Valid parameter */
+	errno = 0;
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x0, 0x0);
+	EXPECT_EQ(0, errno);
+
+	/* PR_SYS_DISPATCH_ON */
+	op = PR_SYS_DISPATCH_ON;
+
+	/* Dispatcher region is bad (offset > 0 && len == 0) */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x1, 0x0, &sel);
+	EXPECT_EQ(EINVAL, errno);
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, -1L, 0x0, &sel);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* Invalid selector */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x1, (void *) -1);
+	ASSERT_EQ(EFAULT, errno);
+
+	/*
+	 * Dispatcher range overflows unsigned long
+	 */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 1, -1L, &sel);
+	ASSERT_EQ(EINVAL, errno) {
+		TH_LOG("Should reject bad syscall range");
+	}
+
+	/*
+	 * Allowed range overflows usigned long
+	 */
+	prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, -1L, 0x1, &sel);
+	ASSERT_EQ(EINVAL, errno) {
+		TH_LOG("Should reject bad syscall range");
+	}
+}
+
+/*
+ * Use global selector for handle_sigsys tests, to avoid passing
+ * selector to signal handler
+ */
+char glob_sel;
+int nr_syscalls_emulated;
+int si_code;
+int si_errno;
+
+static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
+{
+	si_code = info->si_code;
+	si_errno = info->si_errno;
+
+	if (info->si_syscall == MAGIC_SYSCALL_1)
+		nr_syscalls_emulated++;
+
+	/* In preparation for sigreturn. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+}
+
+TEST(dispatch_and_return)
+{
+	long ret;
+	struct sigaction act;
+	sigset_t mask;
+
+	glob_sel = 0;
+	nr_syscalls_emulated = 0;
+	si_code = 0;
+	si_errno = 0;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&mask);
+
+	act.sa_sigaction = handle_sigsys;
+	act.sa_flags = SA_SIGINFO;
+	act.sa_mask = mask;
+
+	ret = sigaction(SIGSYS, &act, NULL);
+	ASSERT_EQ(0, ret);
+
+	/* Make sure selector is good prior to prctl. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &glob_sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	/* MAGIC_SYSCALL_1 doesn't exist. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+	ret = syscall(MAGIC_SYSCALL_1);
+	EXPECT_EQ(-1, ret) {
+		TH_LOG("Dispatch triggered unexpectedly");
+	}
+
+	/* MAGIC_SYSCALL_1 should be emulated. */
+	nr_syscalls_emulated = 0;
+	SYSCALL_DISPATCH_ON(glob_sel);
+
+	ret = syscall(MAGIC_SYSCALL_1);
+	EXPECT_EQ(MAGIC_SYSCALL_1, ret) {
+		TH_LOG("Failed to intercept syscall");
+	}
+	EXPECT_EQ(1, nr_syscalls_emulated) {
+		TH_LOG("Failed to emulate syscall");
+	}
+	ASSERT_EQ(SYS_USER_DISPATCH, si_code) {
+		TH_LOG("Bad si_code in SIGSYS");
+	}
+	ASSERT_EQ(0, si_errno) {
+		TH_LOG("Bad si_errno in SIGSYS");
+	}
+}
+
+TEST_SIGNAL(bad_selector, SIGSYS)
+{
+	long ret;
+	struct sigaction act;
+	sigset_t mask;
+	struct sysinfo info;
+
+	glob_sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+	nr_syscalls_emulated = 0;
+	si_code = 0;
+	si_errno = 0;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&mask);
+
+	act.sa_sigaction = handle_sigsys;
+	act.sa_flags = SA_SIGINFO;
+	act.sa_mask = mask;
+
+	ret = sigaction(SIGSYS, &act, NULL);
+	ASSERT_EQ(0, ret);
+
+	/* Make sure selector is good prior to prctl. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &glob_sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	glob_sel = -1;
+
+	sysinfo(&info);
+
+	/* Even though it is ready to catch SIGSYS, the signal is
+	 * supposed to be uncatchable.
+	 */
+
+	EXPECT_FALSE(true) {
+		TH_LOG("Unreachable!");
+	}
+}
+
+TEST(disable_dispatch)
+{
+	int ret;
+	struct sysinfo info;
+	char sel = 0;
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	/* MAGIC_SYSCALL_1 doesn't exist. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_OFF, 0, 0, 0);
+	EXPECT_EQ(0, ret) {
+		TH_LOG("Failed to unset syscall user dispatch");
+	}
+
+	/* Shouldn't have any effect... */
+	SYSCALL_DISPATCH_ON(glob_sel);
+
+	ret = syscall(__NR_sysinfo, &info);
+	EXPECT_EQ(0, ret) {
+		TH_LOG("Dispatch triggered unexpectedly");
+	}
+}
+
+TEST(direct_dispatch_range)
+{
+	int ret = 0;
+	struct sysinfo info;
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+
+	/*
+	 * Instead of calculating libc addresses; allow the entire
+	 * memory map and lock the selector.
+	 */
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, -1L, &sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	SYSCALL_DISPATCH_ON(sel);
+
+	ret = sysinfo(&info);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Dispatch triggered unexpectedly");
+	}
+}
+
+TEST_HARNESS_MAIN