diff options
Diffstat (limited to 'tools')
78 files changed, 2582 insertions, 691 deletions
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index a59cb0ee609c..73409e27be01 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -83,6 +83,7 @@ struct btf_id { int cnt; }; int addr_cnt; + bool is_set; Elf64_Addr addr[ADDR_CNT]; }; @@ -451,8 +452,10 @@ static int symbols_collect(struct object *obj) * in symbol's size, together with 'cnt' field hence * that - 1. */ - if (id) + if (id) { id->cnt = sym.st_size / sizeof(int) - 1; + id->is_set = true; + } } else { pr_err("FAILED unsupported prefix %s\n", prefix); return -1; @@ -568,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id) int *ptr = data->d_buf; int i; - if (!id->id) { + if (!id->id && !id->is_set) pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); - } for (i = 0; i < id->addr_cnt; i++) { unsigned long addr = id->addr[i]; diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 45a9a59828c3..ae61f464043a 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -48,7 +48,6 @@ FEATURE_TESTS_BASIC := \ numa_num_possible_cpus \ libperl \ libpython \ - libpython-version \ libslang \ libslang-include-subdir \ libtraceevent \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 0a3244ad9673..1480910c792e 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -32,7 +32,6 @@ FILES= \ test-numa_num_possible_cpus.bin \ test-libperl.bin \ test-libpython.bin \ - test-libpython-version.bin \ test-libslang.bin \ test-libslang-include-subdir.bin \ test-libtraceevent.bin \ @@ -227,9 +226,6 @@ $(OUTPUT)test-libperl.bin: $(OUTPUT)test-libpython.bin: $(BUILD) $(FLAGS_PYTHON_EMBED) -$(OUTPUT)test-libpython-version.bin: - $(BUILD) - $(OUTPUT)test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 0b243ce842be..5ffafb967b6e 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -14,10 +14,6 @@ # include "test-libpython.c" #undef main -#define main main_test_libpython_version -# include "test-libpython-version.c" -#undef main - #define main main_test_libperl # include "test-libperl.c" #undef main @@ -177,7 +173,6 @@ int main(int argc, char *argv[]) { main_test_libpython(); - main_test_libpython_version(); main_test_libperl(); main_test_hello(); main_test_libelf(); diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c deleted file mode 100644 index 47714b942d4d..000000000000 --- a/tools/build/feature/test-libpython-version.c +++ /dev/null @@ -1,11 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <Python.h> - -#if PY_VERSION_HEX >= 0x03000000 - #error -#endif - -int main(void) -{ - return 0; -} diff --git a/tools/include/linux/debug_locks.h b/tools/include/linux/debug_locks.h deleted file mode 100644 index 72d595ce764a..000000000000 --- a/tools/include/linux/debug_locks.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_ -#define _LIBLOCKDEP_DEBUG_LOCKS_H_ - -#include <stddef.h> -#include <linux/compiler.h> -#include <asm/bug.h> - -#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x) - -extern bool debug_locks; -extern bool debug_locks_silent; - -#endif diff --git a/tools/include/linux/hardirq.h b/tools/include/linux/hardirq.h deleted file mode 100644 index b25580b6a9be..000000000000 --- a/tools/include/linux/hardirq.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_ -#define _LIBLOCKDEP_LINUX_HARDIRQ_H_ - -#define SOFTIRQ_BITS 0UL -#define HARDIRQ_BITS 0UL -#define SOFTIRQ_SHIFT 0UL -#define HARDIRQ_SHIFT 0UL -#define hardirq_count() 0UL -#define softirq_count() 0UL - -#endif diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h deleted file mode 100644 index 501262aee8ff..000000000000 --- a/tools/include/linux/irqflags.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ -#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ - -# define lockdep_hardirq_context() 0 -# define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled() 0 -# define lockdep_softirqs_enabled(p) 0 -# define lockdep_hardirq_enter() do { } while (0) -# define lockdep_hardirq_exit() do { } while (0) -# define lockdep_softirq_enter() do { } while (0) -# define lockdep_softirq_exit() do { } while (0) -# define INIT_TRACE_IRQFLAGS - -# define stop_critical_timings() do { } while (0) -# define start_critical_timings() do { } while (0) - -#define raw_local_irq_disable() do { } while (0) -#define raw_local_irq_enable() do { } while (0) -#define raw_local_irq_save(flags) ((flags) = 0) -#define raw_local_irq_restore(flags) ((void)(flags)) -#define raw_local_save_flags(flags) ((flags) = 0) -#define raw_irqs_disabled_flags(flags) ((void)(flags)) -#define raw_irqs_disabled() 0 -#define raw_safe_halt() - -#define local_irq_enable() do { } while (0) -#define local_irq_disable() do { } while (0) -#define local_irq_save(flags) ((flags) = 0) -#define local_irq_restore(flags) ((void)(flags)) -#define local_save_flags(flags) ((flags) = 0) -#define irqs_disabled() (1) -#define irqs_disabled_flags(flags) ((void)(flags), 0) -#define safe_halt() do { } while (0) - -#define trace_lock_release(x, y) -#define trace_lock_acquire(a, b, c, d, e, f, g) - -#endif diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index a7e54a08fb54..3e8df500cfbd 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -7,6 +7,7 @@ #include <assert.h> #include <linux/build_bug.h> #include <linux/compiler.h> +#include <linux/math.h> #include <endian.h> #include <byteswap.h> @@ -14,8 +15,6 @@ #define UINT_MAX (~0U) #endif -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) - #define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) #define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) @@ -52,15 +51,6 @@ _min1 < _min2 ? _min1 : _min2; }) #endif -#ifndef roundup -#define roundup(x, y) ( \ -{ \ - const typeof(y) __y = y; \ - (((x) + (__y - 1)) / __y) * __y; \ -} \ -) -#endif - #ifndef BUG_ON #ifdef NDEBUG #define BUG_ON(cond) do { if (cond) {} } while (0) @@ -104,16 +94,6 @@ int scnprintf_pad(char * buf, size_t size, const char * fmt, ...); #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x, y) ((__typeof__(x))((y)-1)) -#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) -#define round_down(x, y) ((x) & ~__round_mask(x, y)) - #define current_gfp_context(k) 0 #define synchronize_rcu() diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h deleted file mode 100644 index e56997288f2b..000000000000 --- a/tools/include/linux/lockdep.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LOCKDEP_H_ -#define _LIBLOCKDEP_LOCKDEP_H_ - -#include <sys/prctl.h> -#include <sys/syscall.h> -#include <string.h> -#include <limits.h> -#include <linux/utsname.h> -#include <linux/compiler.h> -#include <linux/export.h> -#include <linux/kern_levels.h> -#include <linux/err.h> -#include <linux/rcu.h> -#include <linux/list.h> -#include <linux/hardirq.h> -#include <unistd.h> - -#define MAX_LOCK_DEPTH 63UL - -#define asmlinkage -#define __visible - -#include "../../../include/linux/lockdep.h" - -struct task_struct { - u64 curr_chain_key; - int lockdep_depth; - unsigned int lockdep_recursion; - struct held_lock held_locks[MAX_LOCK_DEPTH]; - gfp_t lockdep_reclaim_gfp; - int pid; - int state; - char comm[17]; -}; - -#define TASK_RUNNING 0 - -extern struct task_struct *__curr(void); - -#define current (__curr()) - -static inline int debug_locks_off(void) -{ - return 1; -} - -#define task_pid_nr(tsk) ((tsk)->pid) - -#define KSYM_NAME_LEN 128 -#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) -#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) -#define pr_warn pr_err -#define pr_cont pr_err - -#define list_del_rcu list_del - -#define atomic_t unsigned long -#define atomic_inc(x) ((*(x))++) - -#define print_tainted() "" -#define static_obj(x) 1 - -#define debug_show_all_locks() -extern void debug_check_no_locks_held(void); - -static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr) -{ - return false; -} - -#endif diff --git a/tools/include/linux/math.h b/tools/include/linux/math.h new file mode 100644 index 000000000000..4e7af99ec9eb --- /dev/null +++ b/tools/include/linux/math.h @@ -0,0 +1,25 @@ +#ifndef _TOOLS_MATH_H +#define _TOOLS_MATH_H + +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + +#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) + +#ifndef roundup +#define roundup(x, y) ( \ +{ \ + const typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#endif + +#endif diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h deleted file mode 100644 index 8b3b03b64fda..000000000000 --- a/tools/include/linux/proc_fs.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H -#define _TOOLS_INCLUDE_LINUX_PROC_FS_H - -#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index c934572d935c..622266b197d0 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) return true; } -#include <linux/lockdep.h> - #endif diff --git a/tools/include/linux/stacktrace.h b/tools/include/linux/stacktrace.h deleted file mode 100644 index ae343ac35bfa..000000000000 --- a/tools/include/linux/stacktrace.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_ -#define _LIBLOCKDEP_LINUX_STACKTRACE_H_ - -#include <execinfo.h> - -struct stack_trace { - unsigned int nr_entries, max_entries; - unsigned long *entries; - int skip; -}; - -static inline void print_stack_trace(struct stack_trace *trace, int spaces) -{ - backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1); -} - -#define save_stack_trace(trace) \ - ((trace)->nr_entries = \ - backtrace((void **)(trace)->entries, (trace)->max_entries)) - -static inline int dump_stack(void) -{ - void *array[64]; - size_t size; - - size = backtrace(array, 64); - backtrace_symbols_fd(array, size, 1); - - return 0; -} - -#endif diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1fee..eebd3894fe89 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,201 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ @@ -170,12 +340,29 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -293,6 +480,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -346,6 +534,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -433,6 +623,7 @@ enum macvlan_macaddr_mode { }; #define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ /* VRF section */ enum { @@ -597,6 +788,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -899,7 +1102,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -909,6 +1119,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; @@ -1033,6 +1246,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, @@ -1048,4 +1263,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 81a4c543ff7e..4b384c907027 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf) return -1; } memset(sym, 0, sizeof(*sym)); + INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; sym->idx = i; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index c90c7084e45a..bdf699f6552b 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -153,6 +153,10 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) !strcmp(func->name, "_paravirt_ident_64")) return; + /* already added this function */ + if (!list_empty(&func->pv_target)) + return; + list_add(&func->pv_target, &f->pv_ops[idx].targets); f->pv_ops[idx].clean = false; } diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index afd144725a0b..3df74cf5651a 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -271,8 +271,6 @@ endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) -FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) -FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 7bef917cc84e..15109af9d075 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -528,3 +528,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index df5261e5cfe1..ed9c5c2eafad 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv sys_futex_waitv diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index fa0ff4ce2b74..488f6e6ba1a5 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -223,8 +223,6 @@ static unsigned int group(pthread_t *pth, snd_ctx->out_fds[i] = fds[1]; if (!thread_mode) close(fds[0]); - - free(ctx); } /* Now we have all the fds, fork the senders */ @@ -241,8 +239,6 @@ static unsigned int group(pthread_t *pth, for (i = 0; i < num_fds; i++) close(snd_ctx->out_fds[i]); - free(snd_ctx); - /* Return number of children to reap */ return num_fds * 2; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index bc5259db5fd9..b9d6306cc14e 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -820,7 +820,7 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.ordered_events = true; inject->tool.ordering_requires_timestamps = true; /* Allow space in the header for new attributes */ - output_data_offset = 4096; + output_data_offset = roundup(8192 + session->header.data_offset, 4096); if (inject->strip) strip_init(inject); } diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index c895de481fe1..d54c5371c6a6 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -169,7 +169,9 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0); TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies); TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0); - TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); + + if (num_dies) // Some platforms do not have CPU die support, for example s390 + TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); /* * Source count returns the number of events aggregating in a leader diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 574b7e4efd3a..07b6f4ec024f 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, struct evsel *evsel; u64 count; + perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); perf_stat__update_shadow_stats(evsel, count, 0, st); diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h deleted file mode 100644 index 186a5551ddb9..000000000000 --- a/tools/perf/util/bpf_skel/bperf.h +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -// Copyright (c) 2021 Facebook - -#ifndef __BPERF_STAT_H -#define __BPERF_STAT_H - -typedef struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); - __uint(max_entries, 1); -} reading_map; - -#endif /* __BPERF_STAT_H */ diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c index b8fa3cb2da23..f193998530d4 100644 --- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c @@ -1,14 +1,23 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" #include "bperf_u.h" -reading_map diff_readings SEC(".maps"); -reading_map accum_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} accum_readings SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH); diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c index 4f70d1459e86..e2a2d4cd7779 100644 --- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c @@ -1,10 +1,8 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -13,8 +11,19 @@ struct { __uint(map_flags, BPF_F_PRESERVE_ELEMS); } events SEC(".maps"); -reading_map prev_readings SEC(".maps"); -reading_map diff_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} prev_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); SEC("raw_tp/sched_switch") int BPF_PROG(on_switch) diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c index ab12b4c4ece2..97037d3b3d9f 100644 --- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 95ffed66369c..c59331eea1d9 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -44,13 +44,16 @@ struct perf_event_attr; /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) +/* number of register is bound by the number of bits in regs_dump::mask (64) */ +#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64)) + struct regs_dump { u64 abi; u64 mask; u64 *regs; /* Cached values/mask filled by first register access. */ - u64 cache_regs[PERF_REGS_MAX]; + u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE]; u64 cache_mask; }; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 79cce216727e..e3c1a532d059 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2321,6 +2321,7 @@ out: #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ {\ + free(ff->ph->env.__feat_env); \ ff->ph->env.__feat_env = do_read_string(ff); \ return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } @@ -4124,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session, struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; int type = fe->header.type; u64 feat = fe->feat_id; + int ret = 0; if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { pr_warning("invalid record type %d in pipe-mode\n", type); @@ -4141,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session, ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; - if (feat_ops[feat].process(&ff, NULL)) - return -1; + if (feat_ops[feat].process(&ff, NULL)) { + ret = -1; + goto out; + } if (!feat_ops[feat].print || !tool->show_feat_hdr) - return 0; + goto out; if (!feat_ops[feat].full_only || tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { @@ -4154,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session, fprintf(stdout, "# %s info available, use -I to display\n", feat_ops[feat].name); } - - return 0; +out: + free_event_desc(ff.events); + return ret; } size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 5f83937bf8f3..0e013c2d9eb4 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1205,61 +1205,69 @@ out_no_progress: static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) { + enum intel_pt_sample_type type = decoder->state.type; bool ret = false; + decoder->state.type &= ~INTEL_PT_BRANCH; + if (decoder->set_fup_tx_flags) { decoder->set_fup_tx_flags = false; decoder->tx_flags = decoder->fup_tx_flags; - decoder->state.type = INTEL_PT_TRANSACTION; + decoder->state.type |= INTEL_PT_TRANSACTION; if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX) decoder->state.type |= INTEL_PT_BRANCH; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.flags = decoder->fup_tx_flags; - return true; + ret = true; } if (decoder->set_fup_ptw) { decoder->set_fup_ptw = false; - decoder->state.type = INTEL_PT_PTW; + decoder->state.type |= INTEL_PT_PTW; decoder->state.flags |= INTEL_PT_FUP_IP; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.ptw_payload = decoder->fup_ptw_payload; - return true; + ret = true; } if (decoder->set_fup_mwait) { decoder->set_fup_mwait = false; - decoder->state.type = INTEL_PT_MWAIT_OP; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; + decoder->state.type |= INTEL_PT_MWAIT_OP; decoder->state.mwait_payload = decoder->fup_mwait_payload; ret = true; } if (decoder->set_fup_pwre) { decoder->set_fup_pwre = false; decoder->state.type |= INTEL_PT_PWR_ENTRY; - decoder->state.type &= ~INTEL_PT_BRANCH; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.pwre_payload = decoder->fup_pwre_payload; ret = true; } if (decoder->set_fup_exstop) { decoder->set_fup_exstop = false; decoder->state.type |= INTEL_PT_EX_STOP; - decoder->state.type &= ~INTEL_PT_BRANCH; decoder->state.flags |= INTEL_PT_FUP_IP; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; ret = true; } if (decoder->set_fup_bep) { decoder->set_fup_bep = false; decoder->state.type |= INTEL_PT_BLK_ITEMS; - decoder->state.type &= ~INTEL_PT_BRANCH; + ret = true; + } + if (decoder->overflow) { + decoder->overflow = false; + if (!ret && !decoder->pge) { + if (decoder->hop) { + decoder->state.type = 0; + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; + } + decoder->pge = true; + decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN; + decoder->state.from_ip = 0; + decoder->state.to_ip = decoder->ip; + return true; + } + } + if (ret) { decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; - ret = true; + } else { + decoder->state.type = type; } return ret; } @@ -1608,7 +1616,16 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) intel_pt_clear_tx_flags(decoder); intel_pt_set_nr(decoder); decoder->timestamp_insn_cnt = 0; - decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->state.from_ip = decoder->ip; + decoder->ip = 0; + decoder->pge = false; + decoder->set_fup_tx_flags = false; + decoder->set_fup_ptw = false; + decoder->set_fup_mwait = false; + decoder->set_fup_pwre = false; + decoder->set_fup_exstop = false; + decoder->set_fup_bep = false; decoder->overflow = true; return -EOVERFLOW; } @@ -2666,6 +2683,8 @@ static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder); /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err) { + *err = 0; + /* Leap from PSB to PSB, getting ip from FUP within PSB+ */ if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) { *err = intel_pt_scan_for_psb(decoder); @@ -2678,6 +2697,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in return HOP_IGNORE; case INTEL_PT_TIP_PGD: + decoder->pge = false; if (!decoder->packet.count) { intel_pt_set_nr(decoder); return HOP_IGNORE; @@ -2705,18 +2725,21 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in if (!decoder->packet.count) return HOP_IGNORE; intel_pt_set_ip(decoder); - if (intel_pt_fup_event(decoder)) - return HOP_RETURN; - if (!decoder->branch_enable) + if (decoder->set_fup_mwait || decoder->set_fup_pwre) + *no_tip = true; + if (!decoder->branch_enable || !decoder->pge) *no_tip = true; if (*no_tip) { decoder->state.type = INTEL_PT_INSTRUCTION; decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; + intel_pt_fup_event(decoder); return HOP_RETURN; } + intel_pt_fup_event(decoder); + decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH; *err = intel_pt_walk_fup_tip(decoder); - if (!*err) + if (!*err && decoder->state.to_ip) decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; return HOP_RETURN; @@ -2897,7 +2920,7 @@ static bool intel_pt_psb_with_fup(struct intel_pt_decoder *decoder, int *err) { struct intel_pt_psb_info data = { .fup = false }; - if (!decoder->branch_enable || !decoder->pge) + if (!decoder->branch_enable) return false; intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data); @@ -2924,6 +2947,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder) if (err) return err; next: + err = 0; if (decoder->cyc_threshold) { if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC) decoder->sample_cyc = false; @@ -2962,6 +2986,7 @@ next: case INTEL_PT_TIP_PGE: { decoder->pge = true; + decoder->overflow = false; intel_pt_mtc_cyc_cnt_pge(decoder); intel_pt_set_nr(decoder); if (decoder->packet.count == 0) { @@ -2999,7 +3024,7 @@ next: break; } intel_pt_set_last_ip(decoder); - if (!decoder->branch_enable) { + if (!decoder->branch_enable || !decoder->pge) { decoder->ip = decoder->last_ip; if (intel_pt_fup_event(decoder)) return 0; @@ -3467,10 +3492,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) decoder->set_fup_pwre = false; decoder->set_fup_exstop = false; decoder->set_fup_bep = false; + decoder->overflow = false; if (!decoder->branch_enable) { decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - decoder->overflow = false; decoder->state.type = 0; /* Do not have a sample */ return 0; } @@ -3485,7 +3510,6 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - decoder->overflow = false; decoder->state.from_ip = 0; decoder->state.to_ip = decoder->ip; @@ -3607,7 +3631,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) } decoder->have_last_ip = true; - decoder->pkt_state = INTEL_PT_STATE_NO_IP; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_psb(decoder); if (err) @@ -3704,7 +3728,8 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) if (err) { decoder->state.err = intel_pt_ext_err(err); - decoder->state.from_ip = decoder->ip; + if (err != -EOVERFLOW) + decoder->state.from_ip = decoder->ip; intel_pt_update_sample_time(decoder); decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt; intel_pt_set_nr(decoder); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 556a893508da..10c3187e4c5a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2565,6 +2565,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) ptq->sync_switch = false; intel_pt_next_tid(pt, ptq); } + ptq->timestamp = state->est_timestamp; if (pt->synth_opts.errors) { err = intel_ptq_synth_error(ptq, state); if (err) diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 5ee47ae1509c..06a7461ba864 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -25,6 +25,9 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) int i, idx = 0; u64 mask = regs->mask; + if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE) + return -EINVAL; + if (regs->cache_mask & (1ULL << id)) goto out; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 563a9ba8954f..7f782a31bda3 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -461,7 +461,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) struct tep_event *tp_format; tp_format = trace_event__tp_format_id(evsel->core.attr.config); - if (!tp_format) + if (IS_ERR_OR_NULL(tp_format)) return NULL; evsel->tp_format = tp_format; diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 20bacd5972ad..34f1b1b1176c 100644 --- a/tools/perf/util/smt.c +++ b/tools/perf/util/smt.c @@ -15,7 +15,7 @@ int smt_on(void) if (cached) return cached_result; - if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0) + if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) goto done; ncpu = sysconf(_SC_NPROCESSORS_CONF); diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index 331f6d30f472..cd7106876a5f 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -69,6 +69,7 @@ KERNEL_INCLUDE := $(OUTPUT)include ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE) CFLAGS += $(WARNINGS) +MKDIR = mkdir ifeq ($(strip $(V)),false) QUIET=@ diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules index 2a6c170b57cd..1d7616f5d0ae 100644 --- a/tools/power/acpi/Makefile.rules +++ b/tools/power/acpi/Makefile.rules @@ -21,6 +21,7 @@ $(KERNEL_INCLUDE): $(objdir)%.o: %.c $(KERNEL_INCLUDE) $(ECHO) " CC " $(subst $(OUTPUT),,$@) + $(QUIET) $(MKDIR) -p $(objdir) 2>/dev/null $(QUIET) $(CC) -c $(CFLAGS) -o $@ $< all: $(OUTPUT)$(TOOL) diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h index 565fccdfe6e9..016cff473cfc 100644 --- a/tools/testing/radix-tree/linux/lockdep.h +++ b/tools/testing/radix-tree/linux/lockdep.h @@ -1,5 +1,8 @@ #ifndef _LINUX_LOCKDEP_H #define _LINUX_LOCKDEP_H + +#include <linux/spinlock.h> + struct lock_class_key { unsigned int a; }; diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c index bfb97383e6b5..b4ec228eb95d 100644 --- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c @@ -35,7 +35,7 @@ .prog_type = BPF_PROG_TYPE_XDP, }, { - "XDP pkt read, pkt_data' > pkt_end, good access", + "XDP pkt read, pkt_data' > pkt_end, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -88,6 +88,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data' > pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_end > pkt_data', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -106,16 +141,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end > pkt_data', bad access 1", + "XDP pkt read, pkt_end > pkt_data', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -143,6 +178,42 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_end > pkt_data', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end > pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data' < pkt_end, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -161,16 +232,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' < pkt_end, bad access 1", + "XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -198,7 +269,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end < pkt_data', good access", + "XDP pkt read, pkt_data' < pkt_end, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' < pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end < pkt_data', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -251,6 +358,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_end < pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end < pkt_data', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data' >= pkt_end, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -268,15 +410,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' >= pkt_end, bad access 1", + "XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -304,7 +446,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end >= pkt_data', good access", + "XDP pkt read, pkt_data' >= pkt_end, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end >= pkt_data', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -359,7 +535,44 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' <= pkt_end, good access", + "XDP pkt read, pkt_end >= pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' <= pkt_end, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -414,6 +627,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_end <= pkt_data', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -431,15 +681,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end <= pkt_data', bad access 1", + "XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -467,7 +717,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' > pkt_data, good access", + "XDP pkt read, pkt_end <= pkt_data', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end <= pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' > pkt_data, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -520,6 +804,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data > pkt_meta', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -538,16 +857,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data > pkt_meta', bad access 1", + "XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -575,6 +894,42 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data > pkt_meta', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data > pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_meta' < pkt_data, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -593,16 +948,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' < pkt_data, bad access 1", + "XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -630,7 +985,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data < pkt_meta', good access", + "XDP pkt read, pkt_meta' < pkt_data, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data < pkt_meta', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -683,6 +1074,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data < pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_meta' >= pkt_data, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -700,15 +1126,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' >= pkt_data, bad access 1", + "XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -736,7 +1162,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data >= pkt_meta', good access", + "XDP pkt read, pkt_meta' >= pkt_data, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data >= pkt_meta', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -791,7 +1251,44 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' <= pkt_data, good access", + "XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' <= pkt_data, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -846,6 +1343,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data <= pkt_meta', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -863,15 +1397,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data <= pkt_meta', bad access 1", + "XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -898,3 +1432,37 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "XDP pkt read, pkt_data <= pkt_meta', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore new file mode 100644 index 000000000000..c6c2965a6607 --- /dev/null +++ b/tools/testing/selftests/damon/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +huge_count_read_write diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 8a3f2cd9fec0..937d36ae9a69 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -1,7 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for damon selftests -TEST_FILES = _chk_dependency.sh -TEST_PROGS = debugfs_attrs.sh +TEST_GEN_FILES += huge_count_read_write + +TEST_FILES = _chk_dependency.sh _debugfs_common.sh +TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh +TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh new file mode 100644 index 000000000000..48989d4813ae --- /dev/null +++ b/tools/testing/selftests/damon/_debugfs_common.sh @@ -0,0 +1,52 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +test_write_result() { + file=$1 + content=$2 + orig_content=$3 + expect_reason=$4 + expected=$5 + + echo "$content" > "$file" + if [ $? -ne "$expected" ] + then + echo "writing $content to $file doesn't return $expected" + echo "expected because: $expect_reason" + echo "$orig_content" > "$file" + exit 1 + fi +} + +test_write_succ() { + test_write_result "$1" "$2" "$3" "$4" 0 +} + +test_write_fail() { + test_write_result "$1" "$2" "$3" "$4" 1 +} + +test_content() { + file=$1 + orig_content=$2 + expected=$3 + expect_reason=$4 + + content=$(cat "$file") + if [ "$content" != "$expected" ] + then + echo "reading $file expected $expected but $content" + echo "expected because: $expect_reason" + echo "$orig_content" > "$file" + exit 1 + fi +} + +source ./_chk_dependency.sh + +damon_onoff="$DBGFS/monitor_on" +if [ $(cat "$damon_onoff") = "on" ] +then + echo "monitoring is on" + exit $ksft_skip +fi diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index 196b6640bf37..902e312bca89 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -1,48 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -test_write_result() { - file=$1 - content=$2 - orig_content=$3 - expect_reason=$4 - expected=$5 - - echo "$content" > "$file" - if [ $? -ne "$expected" ] - then - echo "writing $content to $file doesn't return $expected" - echo "expected because: $expect_reason" - echo "$orig_content" > "$file" - exit 1 - fi -} - -test_write_succ() { - test_write_result "$1" "$2" "$3" "$4" 0 -} - -test_write_fail() { - test_write_result "$1" "$2" "$3" "$4" 1 -} - -test_content() { - file=$1 - orig_content=$2 - expected=$3 - expect_reason=$4 - - content=$(cat "$file") - if [ "$content" != "$expected" ] - then - echo "reading $file expected $expected but $content" - echo "expected because: $expect_reason" - echo "$orig_content" > "$file" - exit 1 - fi -} - -source ./_chk_dependency.sh +source _debugfs_common.sh # Test attrs file # =============== @@ -56,33 +15,3 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ "min_nr_regions > max_nr_regions" test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" echo "$orig_content" > "$file" - -# Test schemes file -# ================= - -file="$DBGFS/schemes" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ - "$orig_content" "valid input" -test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" -test_write_succ "$file" "" "$orig_content" "disabling" -echo "$orig_content" > "$file" - -# Test target_ids file -# ==================== - -file="$DBGFS/target_ids" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" -test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" -test_content "$file" "$orig_content" "1 2" "non-integer was there" -test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" -test_content "$file" "$orig_content" "" "wrong input written" -test_write_succ "$file" "" "$orig_content" "empty input" -test_content "$file" "$orig_content" "" "empty input written" -echo "$orig_content" > "$file" - -echo "PASS" diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh new file mode 100644 index 000000000000..87aff8083822 --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_empty_targets.sh @@ -0,0 +1,13 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test empty targets case +# ======================= + +orig_target_ids=$(cat "$DBGFS/target_ids") +echo "" > "$DBGFS/target_ids" +orig_monitor_on=$(cat "$DBGFS/monitor_on") +test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids" +echo "$orig_target_ids" > "$DBGFS/target_ids" diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh new file mode 100644 index 000000000000..922cadac2950 --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh @@ -0,0 +1,22 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test huge count read write +# ========================== + +dmesg -C + +for file in "$DBGFS/"* +do + ./huge_count_read_write "$file" +done + +if dmesg | grep -q WARNING +then + dmesg + exit 1 +else + exit 0 +fi diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh new file mode 100644 index 000000000000..5b39ab44731c --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_schemes.sh @@ -0,0 +1,19 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test schemes file +# ================= + +file="$DBGFS/schemes" +orig_content=$(cat "$file") + +test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ + "$orig_content" "valid input" +test_write_fail "$file" "1 2 +3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" +test_write_succ "$file" "" "$orig_content" "disabling" +test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \ + "$orig_content" "wrong condition ranges" +echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh new file mode 100644 index 000000000000..49aeabdb0aae --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_target_ids.sh @@ -0,0 +1,19 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test target_ids file +# ==================== + +file="$DBGFS/target_ids" +orig_content=$(cat "$file") + +test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" +test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" +test_content "$file" "$orig_content" "1 2" "non-integer was there" +test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" +test_content "$file" "$orig_content" "" "wrong input written" +test_write_succ "$file" "" "$orig_content" "empty input" +test_content "$file" "$orig_content" "" "empty input written" +echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c new file mode 100644 index 000000000000..ad7a6b4cf338 --- /dev/null +++ b/tools/testing/selftests/damon/huge_count_read_write.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: SeongJae Park <sj@kernel.org> + */ + +#include <fcntl.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdio.h> + +void write_read_with_huge_count(char *file) +{ + int filedesc = open(file, O_RDWR); + char buf[25]; + int ret; + + printf("%s %s\n", __func__, file); + if (filedesc < 0) { + fprintf(stderr, "failed opening %s\n", file); + exit(1); + } + + write(filedesc, "", 0xfffffffful); + perror("after write: "); + ret = read(filedesc, buf, 0xfffffffful); + perror("after read: "); + close(filedesc); +} + +int main(int argc, char *argv[]) +{ + if (argc != 2) { + fprintf(stderr, "Usage: %s <file>\n", argv[0]); + exit(1); + } + write_read_with_huge_count(argv[1]); + + return 0; +} diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 3763105029fb..00814c0f87a6 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -30,6 +30,7 @@ /x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test +/x86_64/userspace_io_test /x86_64/userspace_msr_exit_test /x86_64/vmx_apic_access_test /x86_64/vmx_close_while_nested_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index c4e34717826a..f307c9f61981 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -59,6 +59,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 6a1a37f30494..da2b702da71a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -71,6 +71,15 @@ enum vm_guest_mode { #endif +#if defined(__x86_64__) +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); +#else +static inline unsigned long vm_compute_max_gfn(struct kvm_vm *vm) +{ + return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; +} +#endif + #define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) #define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index f968dfd4ee88..aed9dc3ca1e9 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -12,6 +12,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/resource.h> #include "test_util.h" @@ -40,11 +41,40 @@ int main(int argc, char *argv[]) { int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID); int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); + /* + * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds + + * an arbitrary number for everything else. + */ + int nr_fds_wanted = kvm_max_vcpus + 100; + struct rlimit rl; pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id); pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus); /* + * Check that we're allowed to open nr_fds_wanted file descriptors and + * try raising the limits if needed. + */ + TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!"); + + if (rl.rlim_cur < nr_fds_wanted) { + rl.rlim_cur = nr_fds_wanted; + if (rl.rlim_max < nr_fds_wanted) { + int old_rlim_max = rl.rlim_max; + rl.rlim_max = nr_fds_wanted; + + int r = setrlimit(RLIMIT_NOFILE, &rl); + if (r < 0) { + printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n", + old_rlim_max, nr_fds_wanted); + exit(KSFT_SKIP); + } + } else { + TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!"); + } + } + + /* * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID. * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID * in this case. diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 3836322add00..ba1fdc3dcf4a 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) #ifdef __s390x__ alignment = max(0x100000, alignment); #endif - guest_test_phys_mem = align_down(guest_test_virt_mem, alignment); + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); /* Set up the shared data structure test_args */ test_args.vm = vm; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8f2e0bb1ef96..daf6fdb217a7 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -302,7 +302,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) (1ULL << (vm->va_bits - 1)) >> vm->page_shift); /* Limit physical addresses to PA-bits. */ - vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; + vm->max_gfn = vm_compute_max_gfn(vm); /* Allocate and setup memory for guest. */ vm->vpages_mapped = sparsebit_alloc(); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 82c39db91369..eef7b34756d5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1431,3 +1431,71 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui return cpuid; } + +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 + +static inline unsigned x86_family(unsigned int eax) +{ + unsigned int x86; + + x86 = (eax >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (eax >> 20) & 0xff; + + return x86; +} + +unsigned long vm_compute_max_gfn(struct kvm_vm *vm) +{ + const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ + unsigned long ht_gfn, max_gfn, max_pfn; + uint32_t eax, ebx, ecx, edx, max_ext_leaf; + + max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; + + /* Avoid reserved HyperTransport region on AMD processors. */ + eax = ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx || + ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx || + edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return max_gfn; + + /* On parts with <40 physical address bits, the area is fully hidden */ + if (vm->pa_bits < 40) + return max_gfn; + + /* Before family 17h, the HyperTransport area is just below 1T. */ + ht_gfn = (1 << 28) - num_ht_pages; + eax = 1; + cpuid(&eax, &ebx, &ecx, &edx); + if (x86_family(eax) < 0x17) + goto done; + + /* + * Otherwise it's at the top of the physical address space, possibly + * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use + * the old conservative value if MAXPHYADDR is not enumerated. + */ + eax = 0x80000000; + cpuid(&eax, &ebx, &ecx, &edx); + max_ext_leaf = eax; + if (max_ext_leaf < 0x80000008) + goto done; + + eax = 0x80000008; + cpuid(&eax, &ebx, &ecx, &edx); + max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1; + if (max_ext_leaf >= 0x8000001f) { + eax = 0x8000001f; + cpuid(&eax, &ebx, &ecx, &edx); + max_pfn >>= (ebx >> 6) & 0x3f; + } + + ht_gfn = max_pfn - num_ht_pages; +done: + return min(max_gfn, ht_gfn - 1); +} diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 91d88aaa9899..672915ce73d8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, vcpu_set_cpuid(vm, VCPU_ID, cpuid); } -static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, - struct kvm_cpuid2 *best) +static void guest_test_msrs_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - struct kvm_enable_cap cap = {0}; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_cpuid2 *best; + vm_vaddr_t msr_gva; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + struct msr_data *msr; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_msr); + + msr_gva = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); + msr = addr_gva2hva(vm, msr_gva); + + vcpu_args_set(vm, VCPU_ID, 1, msr_gva); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: /* @@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, * capability enabled and guest visible CPUID bit unset. */ cap.cap = KVM_CAP_HYPERV_SYNIC2; + cap.args[0] = 0; vcpu_enable_cap(vm, VCPU_ID, &cap); break; case 22: @@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, } stage++; + kvm_vm_free(vm); } } -static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall, - void *input, void *output, struct kvm_cpuid2 *best) +static void guest_test_hcalls_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + vm_vaddr_t hcall_page, hcall_params; + struct hcall_data *hcall; + struct kvm_cpuid2 *best; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_hcall); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall = addr_gva2hva(vm, hcall_page); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + hcall_params = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + + vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: hcall->control = 0xdeadbeef; @@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall } stage++; + kvm_vm_free(vm); } } int main(void) { - struct kvm_cpuid2 *best; - struct kvm_vm *vm; - vm_vaddr_t msr_gva, hcall_page, hcall_params; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; - - /* Test MSRs */ - vm = vm_create_default(VCPU_ID, 0, guest_msr); - - msr_gva = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); - vcpu_args_set(vm, VCPU_ID, 1, msr_gva); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); - pr_info("Testing access to Hyper-V specific MSRs\n"); - guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), - best); - kvm_vm_free(vm); - - /* Test hypercalls */ - vm = vm_create_default(VCPU_ID, 0, guest_hcall); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); - - /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); - memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - - hcall_params = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); - - vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); + guest_test_msrs_access(); pr_info("Testing access to Hyper-V hypercalls\n"); - guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params), - addr_gva2hva(vm, hcall_page), - addr_gva2hva(vm, hcall_page) + getpagesize(), - best); - - kvm_vm_free(vm); + guest_test_hcalls_access(); } diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c index 5ba325cd64bf..29b18d565cf4 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -54,12 +54,15 @@ static struct kvm_vm *sev_vm_create(bool es) return vm; } -static struct kvm_vm *__vm_create(void) +static struct kvm_vm *aux_vm_create(bool with_vcpus) { struct kvm_vm *vm; int i; vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + if (!with_vcpus) + return vm; + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) vm_vcpu_add(vm, i); @@ -89,11 +92,11 @@ static void test_sev_migrate_from(bool es) { struct kvm_vm *src_vm; struct kvm_vm *dst_vms[NR_MIGRATE_TEST_VMS]; - int i; + int i, ret; src_vm = sev_vm_create(es); for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) - dst_vms[i] = __vm_create(); + dst_vms[i] = aux_vm_create(true); /* Initial migration from the src to the first dst. */ sev_migrate_from(dst_vms[0]->fd, src_vm->fd); @@ -102,7 +105,10 @@ static void test_sev_migrate_from(bool es) sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd); /* Migrate the guest back to the original VM. */ - sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + TEST_ASSERT(ret == -1 && errno == EIO, + "VM that was migrated from should be dead. ret %d, errno: %d\n", ret, + errno); kvm_vm_free(src_vm); for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) @@ -146,6 +152,8 @@ static void test_sev_migrate_locking(void) for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) pthread_join(pt[i], NULL); + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + kvm_vm_free(input[i].vm); } static void test_sev_migrate_parameters(void) @@ -157,12 +165,11 @@ static void test_sev_migrate_parameters(void) sev_vm = sev_vm_create(/* es= */ false); sev_es_vm = sev_vm_create(/* es= */ true); vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); - vm_no_sev = __vm_create(); + vm_no_sev = aux_vm_create(true); sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); vm_vcpu_add(sev_es_vm_no_vmsa, 1); - ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd); TEST_ASSERT( ret == -1 && errno == EINVAL, @@ -191,13 +198,151 @@ static void test_sev_migrate_parameters(void) TEST_ASSERT(ret == -1 && errno == EINVAL, "Migrations require SEV enabled. ret %d, errno: %d\n", ret, errno); + + kvm_vm_free(sev_vm); + kvm_vm_free(sev_es_vm); + kvm_vm_free(sev_es_vm_no_vmsa); + kvm_vm_free(vm_no_vcpu); + kvm_vm_free(vm_no_sev); +} + +static int __sev_mirror_create(int dst_fd, int src_fd) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, + .args = { src_fd } + }; + + return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); +} + + +static void sev_mirror_create(int dst_fd, int src_fd) +{ + int ret; + + ret = __sev_mirror_create(dst_fd, src_fd); + TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); +} + +static void test_sev_mirror(bool es) +{ + struct kvm_vm *src_vm, *dst_vm; + struct kvm_sev_launch_start start = { + .policy = es ? SEV_POLICY_ES : 0 + }; + int i; + + src_vm = sev_vm_create(es); + dst_vm = aux_vm_create(false); + + sev_mirror_create(dst_vm->fd, src_vm->fd); + + /* Check that we can complete creation of the mirror VM. */ + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(dst_vm, i); + sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) + sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + +static void test_sev_mirror_parameters(void) +{ + struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_with_vcpu; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); + vm_with_vcpu = aux_vm_create(true); + vm_no_vcpu = aux_vm_create(false); + + ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to self. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, + errno); + + ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", + ret, errno); + + kvm_vm_free(sev_vm); + kvm_vm_free(sev_es_vm); + kvm_vm_free(vm_with_vcpu); + kvm_vm_free(vm_no_vcpu); +} + +static void test_sev_move_copy(void) +{ + struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + dst_vm = aux_vm_create(true); + mirror_vm = aux_vm_create(false); + dst_mirror_vm = aux_vm_create(false); + + sev_mirror_create(mirror_vm->fd, sev_vm->fd); + ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); + TEST_ASSERT(ret == -1 && errno == EBUSY, + "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, + errno); + + /* The mirror itself can be migrated. */ + sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); + ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); + TEST_ASSERT(ret == -1 && errno == EBUSY, + "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, + errno); + + /* + * mirror_vm is not a mirror anymore, dst_mirror_vm is. Thus, + * the owner can be copied as soon as dst_mirror_vm is gone. + */ + kvm_vm_free(dst_mirror_vm); + sev_migrate_from(dst_vm->fd, sev_vm->fd); + + kvm_vm_free(mirror_vm); + kvm_vm_free(dst_vm); + kvm_vm_free(sev_vm); } int main(int argc, char *argv[]) { - test_sev_migrate_from(/* es= */ false); - test_sev_migrate_from(/* es= */ true); - test_sev_migrate_locking(); - test_sev_migrate_parameters(); + if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { + test_sev_migrate_from(/* es= */ false); + test_sev_migrate_from(/* es= */ true); + test_sev_migrate_locking(); + test_sev_migrate_parameters(); + if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) + test_sev_move_copy(); + } + if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + test_sev_mirror(/* es= */ false); + test_sev_mirror(/* es= */ true); + test_sev_mirror_parameters(); + } return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index df04f56ce859..30a81038df46 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -75,7 +75,7 @@ static void l1_guest_code(struct svm_test_data *svm) vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; /* No intercepts for real and virtual interrupts */ - vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR)); /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c new file mode 100644 index 000000000000..e4bef2e05686 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 1 + +static void guest_ins_port80(uint8_t *buffer, unsigned int count) +{ + unsigned long end; + + if (count == 2) + end = (unsigned long)buffer + 1; + else + end = (unsigned long)buffer + 8192; + + asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory"); + GUEST_ASSERT_1(count == 0, count); + GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end); +} + +static void guest_code(void) +{ + uint8_t buffer[8192]; + int i; + + /* + * Special case tests. main() will adjust RCX 2 => 1 and 3 => 8192 to + * test that KVM doesn't explode when userspace modifies the "count" on + * a userspace I/O exit. KVM isn't required to play nice with the I/O + * itself as KVM doesn't support manipulating the count, it just needs + * to not explode or overflow a buffer. + */ + guest_ins_port80(buffer, 2); + guest_ins_port80(buffer, 3); + + /* Verify KVM fills the buffer correctly when not stuffing RCX. */ + memset(buffer, 0, sizeof(buffer)); + guest_ins_port80(buffer, 8192); + for (i = 0; i < 8192; i++) + GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_regs regs; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + int rc; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + run = vcpu_state(vm, VCPU_ID); + + memset(®s, 0, sizeof(regs)); + + while (1) { + rc = _vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + if (get_ucall(vm, VCPU_ID, &uc)) + break; + + TEST_ASSERT(run->io.port == 0x80, + "Expected I/O at port 0x80, got port 0x%x\n", run->io.port); + + /* + * Modify the rep string count in RCX: 2 => 1 and 3 => 8192. + * Note, this abuses KVM's batching of rep string I/O to avoid + * getting stuck in an infinite loop. That behavior isn't in + * scope from a testing perspective as it's not ABI in any way, + * i.e. it really is abusing internal KVM knowledge. + */ + vcpu_regs_get(vm, VCPU_ID, ®s); + if (regs.rcx == 2) + regs.rcx = 1; + if (regs.rcx == 3) + regs.rcx = 8192; + memset((void *)run + run->io.data_offset, 0xaa, 4096); + vcpu_regs_set(vm, VCPU_ID, ®s); + } + + switch (uc.cmd) { + case UCALL_DONE: + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3]); + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7615f29831eb..9897fa9ab953 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 3313566ce906..a1da013d847b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4002,8 +4002,8 @@ EOF ################################################################################ # main -TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter" -TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter" +TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter" +TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter" TESTS_OTHER="use_cases" PAUSE_ON_FAIL=no @@ -4077,3 +4077,11 @@ cleanup 2>/dev/null printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} + +if [ $nfail -ne 0 ]; then + exit 1 # KSFT_FAIL +elif [ $nsuccess -eq 0 ]; then + exit $ksft_skip +fi + +exit 0 # KSFT_PASS diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index b5a69ad191b0..d444ee6aa3cb 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -629,6 +629,66 @@ ipv6_fcnal() log_test $? 0 "Nexthops removed on admin down" } +ipv6_grp_refs() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test; need mausezahn tool" + return + fi + + run_cmd "$IP link set dev veth1 up" + run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10" + run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20" + run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10" + run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20" + run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10" + run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20" + run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10" + run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20" + run_cmd "$IP nexthop add id 102 group 100" + run_cmd "$IP route add 2001:db8:101::1/128 nhid 102" + + # create per-cpu dsts through nh 100 + run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1" + + # remove nh 100 from the group to delete the route potentially leaving + # a stale per-cpu dst which holds a reference to the nexthop's net + # device and to the IPv6 route + run_cmd "$IP nexthop replace id 102 group 101" + run_cmd "$IP route del 2001:db8:101::1/128" + + # add both nexthops to the group so a reference is taken on them + run_cmd "$IP nexthop replace id 102 group 100/101" + + # if the bug described in commit "net: nexthop: release IPv6 per-cpu + # dsts when replacing a nexthop group" exists at this point we have + # an unlinked IPv6 route (but not freed due to stale dst) with a + # reference over the group so we delete the group which will again + # only unlink it due to the route reference + run_cmd "$IP nexthop del id 102" + + # delete the nexthop with stale dst, since we have an unlinked + # group with a ref to it and an unlinked IPv6 route with ref to the + # group, the nh will only be unlinked and not freed so the stale dst + # remains forever and we get a net device refcount imbalance + run_cmd "$IP nexthop del id 100" + + # if a reference was lost this command will hang because the net device + # cannot be removed + timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1 + + # we can't cleanup if the command is hung trying to delete the netdev + if [ $? -eq 137 ]; then + return 1 + fi + + # cleanup + run_cmd "$IP link del veth1.20" + run_cmd "$IP nexthop flush" + + return 0 +} + ipv6_grp_fcnal() { local rc @@ -734,6 +794,9 @@ ipv6_grp_fcnal() run_cmd "$IP nexthop add id 108 group 31/24" log_test $? 2 "Nexthop group can not have a blackhole and another nexthop" + + ipv6_grp_refs + log_test $? 0 "Nexthop group replace refcounts" } ipv6_res_grp_fcnal() diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5abe92d55b69..996af1ae3d3d 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -444,24 +444,63 @@ fib_rp_filter_test() setup set -e + ip netns add ns2 + ip netns set ns2 auto + + ip -netns ns2 link set dev lo up + + $IP link add name veth1 type veth peer name veth2 + $IP link set dev veth2 netns ns2 + $IP address add 192.0.2.1/24 dev veth1 + ip -netns ns2 address add 192.0.2.1/24 dev veth2 + $IP link set dev veth1 up + ip -netns ns2 link set dev veth2 up + $IP link set dev lo address 52:54:00:6a:c7:5e - $IP link set dummy0 address 52:54:00:6a:c7:5e - $IP link add dummy1 type dummy - $IP link set dummy1 address 52:54:00:6a:c7:5e - $IP link set dev dummy1 up + $IP link set dev veth1 address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e + + # 1. (ns2) redirect lo's egress to veth2's egress + ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel + ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth2 + ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth2 + + # 2. (ns1) redirect veth1's ingress to lo's ingress + $NS_EXEC tc qdisc add dev veth1 ingress + $NS_EXEC tc filter add dev veth1 ingress protocol arp basic \ + action mirred ingress redirect dev lo + $NS_EXEC tc filter add dev veth1 ingress protocol ip basic \ + action mirred ingress redirect dev lo + + # 3. (ns1) redirect lo's egress to veth1's egress + $NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel + $NS_EXEC tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth1 + $NS_EXEC tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth1 + + # 4. (ns2) redirect veth2's ingress to lo's ingress + ip netns exec ns2 tc qdisc add dev veth2 ingress + ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \ + action mirred ingress redirect dev lo + ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \ + action mirred ingress redirect dev lo + $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1 $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1 $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1 - - $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel - $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo - $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1 set +e - run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1" + run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1" log_test $? 0 "rp_filter passes local packets" - run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1" + run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1" log_test $? 0 "rp_filter passes loopback packets" cleanup diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e61fc4c32ba2..6e468e0f42f7 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -31,6 +31,8 @@ struct tls_crypto_info_keys { struct tls12_crypto_info_chacha20_poly1305 chacha20; struct tls12_crypto_info_sm4_gcm sm4gcm; struct tls12_crypto_info_sm4_ccm sm4ccm; + struct tls12_crypto_info_aes_ccm_128 aesccm128; + struct tls12_crypto_info_aes_gcm_256 aesgcm256; }; size_t len; }; @@ -61,6 +63,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->sm4ccm.info.version = tls_version; tls12->sm4ccm.info.cipher_type = cipher_type; break; + case TLS_CIPHER_AES_CCM_128: + tls12->len = sizeof(struct tls12_crypto_info_aes_ccm_128); + tls12->aesccm128.info.version = tls_version; + tls12->aesccm128.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_AES_GCM_256: + tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_256); + tls12->aesgcm256.info.version = tls_version; + tls12->aesgcm256.info.cipher_type = cipher_type; + break; default: break; } @@ -78,26 +90,21 @@ static void memrnd(void *s, size_t n) *byte++ = rand(); } -FIXTURE(tls_basic) -{ - int fd, cfd; - bool notls; -}; - -FIXTURE_SETUP(tls_basic) +static void ulp_sock_pair(struct __test_metadata *_metadata, + int *fd, int *cfd, bool *notls) { struct sockaddr_in addr; socklen_t len; int sfd, ret; - self->notls = false; + *notls = false; len = sizeof(addr); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); addr.sin_port = 0; - self->fd = socket(AF_INET, SOCK_STREAM, 0); + *fd = socket(AF_INET, SOCK_STREAM, 0); sfd = socket(AF_INET, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); @@ -108,26 +115,96 @@ FIXTURE_SETUP(tls_basic) ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = connect(*fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); + *cfd = accept(sfd, &addr, &len); + ASSERT_GE(*cfd, 0); close(sfd); - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); if (ret != 0) { ASSERT_EQ(errno, ENOENT); - self->notls = true; + *notls = true; printf("Failure setting TCP_ULP, testing without tls\n"); return; } - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); ASSERT_EQ(ret, 0); } +/* Produce a basic cmsg */ +static int tls_send_cmsg(int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + int cmsg_len = sizeof(char); + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec vec; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + /* test sending non-record types. */ + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(cmsg_len); + *CMSG_DATA(cmsg) = record_type; + msg.msg_controllen = cmsg->cmsg_len; + + return sendmsg(fd, &msg, flags); +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + struct cmsghdr *cmsg; + unsigned char ctype; + struct msghdr msg; + struct iovec vec; + int n; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + n = recvmsg(fd, &msg, flags); + + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + ctype = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(ctype, record_type); + + return n; +} + +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); +} + FIXTURE_TEARDOWN(tls_basic) { close(self->fd); @@ -196,63 +273,48 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) .cipher_type = TLS_CIPHER_SM4_CCM, }; +FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_AES_CCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 13_aes_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_AES_CCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm_256) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_AES_GCM_256, +}; + +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm_256) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_AES_GCM_256, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; - struct sockaddr_in addr; - socklen_t len; - int sfd, ret; - - self->notls = false; - len = sizeof(addr); + int ret; tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; - - self->fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); + if (self->notls) + return; - ret = getsockname(sfd, &addr, &len); + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - self->notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } - - if (!self->notls) { - ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); - - if (!self->notls) { - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - ASSERT_EQ(ret, 0); - - ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - close(sfd); } FIXTURE_TEARDOWN(tls) @@ -613,6 +675,95 @@ TEST_F(tls, splice_to_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, splice_dec_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, recv_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int half = send_len / 2; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + /* Recv hald of the record, splice the other half */ + EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK), + half); + EXPECT_EQ(read(p[0], &mem_recv[half], half), half); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, peek_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int chunk = TLS_PAYLOAD_MAX_LEN / 4; + int n, i, p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + for (i = 0; i < 4; i++) + EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0), + chunk); + + EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2, + MSG_WAITALL | MSG_PEEK), + chunk * 5 / 2); + EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0); + + n = 0; + while (n < send_len) { + i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0); + EXPECT_GT(i, 0); + n += i; + } + EXPECT_EQ(n, send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; @@ -1193,60 +1344,30 @@ TEST_F(tls, mutliproc_sendpage_writers) TEST_F(tls, control_msg) { - if (self->notls) - return; - - char cbuf[CMSG_SPACE(sizeof(char))]; - char const *test_str = "test_read"; - int cmsg_len = sizeof(char); + char *test_str = "test_read"; char record_type = 100; - struct cmsghdr *cmsg; - struct msghdr msg; int send_len = 10; - struct iovec vec; char buf[10]; - vec.iov_base = (char *)test_str; - vec.iov_len = 10; - memset(&msg, 0, sizeof(struct msghdr)); - msg.msg_iov = &vec; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_TLS; - /* test sending non-record types. */ - cmsg->cmsg_type = TLS_SET_RECORD_TYPE; - cmsg->cmsg_len = CMSG_LEN(cmsg_len); - *CMSG_DATA(cmsg) = record_type; - msg.msg_controllen = cmsg->cmsg_len; + if (self->notls) + SKIP(return, "no TLS support"); - EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0), + send_len); /* Should fail because we didn't provide a control message */ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); - vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len); - - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL | MSG_PEEK), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); /* Recv the message again without MSG_PEEK */ - record_type = 0; memset(buf, 0, sizeof(buf)); - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -1301,6 +1422,160 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +FIXTURE(tls_err) +{ + int fd, cfd; + int fd2, cfd2; + bool notls; +}; + +FIXTURE_VARIANT(tls_err) +{ + uint16_t tls_version; +}; + +FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm) +{ + .tls_version = TLS_1_2_VERSION, +}; + +FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm) +{ + .tls_version = TLS_1_3_VERSION, +}; + +FIXTURE_SETUP(tls_err) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, + &tls12); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); + if (self->notls) + return; + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_err) +{ + close(self->fd); + close(self->cfd); + close(self->fd2); + close(self->cfd2); +} + +TEST_F(tls_err, bad_rec) +{ + char buf[64]; + + if (self->notls) + SKIP(return, "no TLS support"); + + memset(buf, 0x55, sizeof(buf)); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EMSGSIZE); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EAGAIN); +} + +TEST_F(tls_err, bad_auth) +{ + char buf[128]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + memrnd(buf, sizeof(buf) / 2); + EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + n = recv(self->cfd, buf, sizeof(buf), 0); + EXPECT_GT(n, sizeof(buf) / 2); + + buf[n - 1]++; + + EXPECT_EQ(send(self->fd2, buf, n, 0), n); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_in_large_read) +{ + char txt[3][64]; + char cip[3][128]; + char buf[3 * 128]; + int i, n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Put 3 records in the sockets */ + for (i = 0; i < 3; i++) { + memrnd(txt[i], sizeof(txt[i])); + EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0), + sizeof(txt[i])); + n = recv(self->cfd, cip[i], sizeof(cip[i]), 0); + EXPECT_GT(n, sizeof(txt[i])); + /* Break the third message */ + if (i == 2) + cip[2][n - 1]++; + EXPECT_EQ(send(self->fd2, cip[i], n, 0), n); + } + + /* We should be able to receive the first two messages */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2); + EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0); + EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0); + /* Third mesasge is bad */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_cmsg) +{ + char *test_str = "test_read"; + int send_len = 10; + char cip[128]; + char buf[128]; + char txt[64]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Queue up one data record */ + memrnd(txt, sizeof(txt)); + EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt)); + n = recv(self->cfd, cip, sizeof(cip), 0); + EXPECT_GT(n, sizeof(txt)); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + n = recv(self->cfd, cip, sizeof(cip), 0); + cip[n - 1]++; /* Break it */ + EXPECT_GT(n, send_len); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt)); + EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; @@ -1355,64 +1630,82 @@ TEST(non_established) { TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; - struct sockaddr_in addr; - int sfd, ret, fd, cfd; - socklen_t len; + int ret, fd, cfd; bool notls; - notls = false; - len = sizeof(addr); - memset(&tls12, 0, sizeof(tls12)); tls12.info.version = TLS_1_2_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); - fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + close(fd); + close(cfd); +} + +TEST(tls_v6ops) { + struct tls_crypto_info_keys tls12; + struct sockaddr_in6 addr, addr2; + int sfd, ret, fd; + socklen_t len, len2; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + + addr.sin6_family = AF_INET6; + addr.sin6_addr = in6addr_any; + addr.sin6_port = 0; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + sfd = socket(AF_INET6, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); ret = listen(sfd, 10); ASSERT_EQ(ret, 0); + len = sizeof(addr); ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); ret = connect(fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); + len = sizeof(addr); + ret = getsockname(fd, &addr, &len); + ASSERT_EQ(ret, 0); + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); } + ASSERT_EQ(ret, 0); - if (!notls) { - ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, - sizeof(tls12)); - EXPECT_EQ(ret, 0); - } + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); - cfd = accept(sfd, &addr, &len); - ASSERT_GE(cfd, 0); + ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); - if (!notls) { - ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - EXPECT_EQ(ret, 0); + len2 = sizeof(addr2); + ret = getsockname(fd, &addr2, &len2); + ASSERT_EQ(ret, 0); - ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, - sizeof(tls12)); - EXPECT_EQ(ret, 0); - } + EXPECT_EQ(len2, len); + EXPECT_EQ(memcmp(&addr, &addr2, len), 0); - close(sfd); close(fd); - close(cfd); + close(sfd); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 8748199ac109..ffca314897c4 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ + conntrack_vrf.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh new file mode 100755 index 000000000000..8b5ea9234588 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh @@ -0,0 +1,241 @@ +#!/bin/sh + +# This script demonstrates interaction of conntrack and vrf. +# The vrf driver calls the netfilter hooks again, with oif/iif +# pointing at the VRF device. +# +# For ingress, this means first iteration has iifname of lower/real +# device. In this script, thats veth0. +# Second iteration is iifname set to vrf device, tvrf in this script. +# +# For egress, this is reversed: first iteration has the vrf device, +# second iteration is done with the lower/real/veth0 device. +# +# test_ct_zone_in demonstrates unexpected change of nftables +# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack +# connection on VRF rcv" +# +# It was possible to assign conntrack zone to a packet (or mark it for +# `notracking`) in the prerouting chain before conntrack, based on real iif. +# +# After the change, the zone assignment is lost and the zone is assigned based +# on the VRF master interface (in case such a rule exists). +# assignment is lost. Instead, assignment based on the `iif` matching +# Thus it is impossible to distinguish packets based on the original +# interface. +# +# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem +# that was supposed to be fixed by the commit mentioned above to make sure +# that any fix to test case 1 won't break masquerade again. + +ksft_skip=4 + +IP0=172.30.30.1 +IP1=172.30.30.2 +PFXL=30 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" + +cleanup() +{ + ip netns pids $ns0 | xargs kill 2>/dev/null + ip netns pids $ns1 | xargs kill 2>/dev/null + + ip netns del $ns0 $ns1 +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add "$ns0" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns0" + exit $ksft_skip +fi +ip netns add "$ns1" + +trap cleanup EXIT + +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + +ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not add veth device" + exit $ksft_skip +fi + +ip -net $ns0 li add tvrf type vrf table 9876 +if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + exit $ksft_skip +fi + +ip -net $ns0 li set lo up + +ip -net $ns0 li set veth0 master tvrf +ip -net $ns0 li set tvrf up +ip -net $ns0 li set veth0 up +ip -net $ns1 li set veth0 up + +ip -net $ns0 addr add $IP0/$PFXL dev veth0 +ip -net $ns1 addr add $IP1/$PFXL dev veth0 + +ip netns exec $ns1 iperf3 -s > /dev/null 2>&1& +if [ $? -ne 0 ];then + echo "SKIP: Could not start iperf3" + exit $ksft_skip +fi + +# test vrf ingress handling. +# The incoming connection should be placed in conntrack zone 1, +# as decided by the first iteration of the ruleset. +test_ct_zone_in() +{ +ip netns exec $ns0 nft -f - <<EOF +table testct { + chain rawpre { + type filter hook prerouting priority raw; + + iif { veth0, tvrf } counter meta nftrace set 1 + iif veth0 counter ct zone set 1 counter return + iif tvrf counter ct zone set 2 counter return + ip protocol icmp counter + notrack counter + } + + chain rawout { + type filter hook output priority raw; + + oif veth0 counter ct zone set 1 counter return + oif tvrf counter ct zone set 2 counter return + notrack counter + } +} +EOF + ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null + + # should be in zone 1, not zone 2 + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "PASS: entry found in conntrack zone 1" + else + echo "FAIL: entry not found in conntrack zone 1" + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "FAIL: entry found in zone 2 instead" + else + echo "FAIL: entry not in zone 1 or 2, dumping table" + ip netns exec $ns0 conntrack -L + ip netns exec $ns0 nft list ruleset + fi + fi +} + +# add masq rule that gets evaluated w. outif set to vrf device. +# This tests the first iteration of the packet through conntrack, +# oifname is the vrf device. +test_masquerade_vrf() +{ + local qdisc=$1 + + if [ "$qdisc" != "default" ]; then + tc -net $ns0 qdisc add dev tvrf root $qdisc + fi + + ip netns exec $ns0 conntrack -F 2>/dev/null + +ip netns exec $ns0 nft -f - <<EOF +flush ruleset +table ip nat { + chain rawout { + type filter hook output priority raw; + + oif tvrf ct state untracked counter + } + chain postrouting2 { + type filter hook postrouting priority mangle; + + oif tvrf ct state untracked counter + } + chain postrouting { + type nat hook postrouting priority 0; + # NB: masquerade should always be combined with 'oif(name) bla', + # lack of this is intentional here, we want to exercise double-snat. + ip saddr 172.30.30.0/30 counter masquerade random + } +} +EOF + ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' && + ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)" + else + echo "FAIL: vrf rules have unexpected counter value" + ret=1 + fi + + if [ "$qdisc" != "default" ]; then + tc -net $ns0 qdisc del dev tvrf root + fi +} + +# add masq rule that gets evaluated w. outif set to veth device. +# This tests the 2nd iteration of the packet through conntrack, +# oifname is the lower device (veth0 in this case). +test_masquerade_veth() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null +ip netns exec $ns0 nft -f - <<EOF +flush ruleset +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; + meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random + } +} +EOF + ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +test_ct_zone_in +test_masquerade_vrf "default" +test_masquerade_vrf "pfifo" +test_masquerade_veth + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index 5a4938d6dcf2..ed61f6cab60f 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -23,8 +23,8 @@ TESTS="reported_issues correctness concurrency timeout" # Set types, defined by TYPE_ variables below TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto - net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port - net_port_mac_proto_net" + net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp + net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below BUGS="flush_remove_add" @@ -277,6 +277,23 @@ perf_entries 1000 perf_proto ipv4 " +TYPE_mac_net=" +display mac,net +type_spec ether_addr . ipv4_addr +chain_spec ether saddr . ip saddr +dst +src mac addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + TYPE_net_mac_icmp=" display net,mac - ICMP type_spec ipv4_addr . ether_addr @@ -984,7 +1001,8 @@ format() { fi done for f in ${src}; do - __expr="${__expr} . " + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + __start="$(eval format_"${f}" "${srcstart}")" __end="$(eval format_"${f}" "${srcend}")" diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index da1c1e4b6c86..d88867d2fed7 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -759,19 +759,21 @@ test_port_shadow() local result="" local logmsg="" - echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_r=$! + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405 - echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_c=$! + echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 & + sc_r=$! - # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport & + sc_c=$! + + sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. - result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404) if [ "$result" = "$expect" ] ;then echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" @@ -780,7 +782,7 @@ test_port_shadow() ret=1 fi - kill $nc_r $nc_c 2>/dev/null + kill $sc_r $sc_c 2>/dev/null # flush udp entries for next test round, if any ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 @@ -816,11 +818,10 @@ table $family raw { chain prerouting { type filter hook prerouting priority -300; policy accept; meta iif veth0 udp dport 1405 notrack - udp dport 1405 notrack } chain output { type filter hook output priority -300; policy accept; - udp sport 1405 notrack + meta oif veth0 udp sport 1405 notrack } } EOF @@ -851,6 +852,18 @@ test_port_shadowing() { local family="ip" + conntrack -h >/dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without conntrack tool" + return + fi + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without socat tool" + return + fi + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 3d202b90b33d..7d27f1f3bc01 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -16,6 +16,10 @@ timeout=4 cleanup() { + ip netns pids ${ns1} | xargs kill 2>/dev/null + ip netns pids ${ns2} | xargs kill 2>/dev/null + ip netns pids ${nsrouter} | xargs kill 2>/dev/null + ip netns del ${ns1} ip netns del ${ns2} ip netns del ${nsrouter} @@ -332,6 +336,55 @@ EOF echo "PASS: tcp via loopback and re-queueing" } +test_icmp_vrf() { + ip -net $ns1 link add tvrf type vrf table 9876 + if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + return + fi + + ip -net $ns1 li set eth0 master tvrf + ip -net $ns1 li set tvrf up + + ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876 +ip netns exec ${ns1} nft -f /dev/stdin <<EOF +flush ruleset +table inet filter { + chain output { + type filter hook output priority 0; policy accept; + meta oifname "tvrf" icmp type echo-request counter queue num 1 + meta oifname "eth0" icmp type echo-request counter queue num 1 + } + chain post { + type filter hook postrouting priority 0; policy accept; + meta oifname "tvrf" icmp type echo-request counter queue num 1 + meta oifname "eth0" icmp type echo-request counter queue num 1 + } +} +EOF + ip netns exec ${ns1} ./nf-queue -q 1 -t $timeout & + local nfqpid=$! + + sleep 1 + ip netns exec ${ns1} ip vrf exec tvrf ping -c 1 10.0.2.99 > /dev/null + + for n in output post; do + for d in tvrf eth0; do + ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1" + if [ $? -ne 0 ] ; then + echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2 + ip netns exec ${ns1} nft list ruleset + ret=1 + return + fi + done + done + + wait $nfqpid + [ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf" + wait 2>/dev/null +} + ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null @@ -372,5 +425,6 @@ test_queue 20 test_tcp_forward test_tcp_localhost test_tcp_localhost_requeue +test_icmp_vrf exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index ac646376eb01..04633119b29a 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -18,11 +18,17 @@ cleanup() ip netns del $ns } -ip netns add $ns -if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace $gw" - exit $ksft_skip -fi +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "socat -V" "run test without socat tool" +checktool "ip netns add $ns" "create net namespace" trap cleanup EXIT @@ -71,7 +77,8 @@ EOF local start=$(date +%s%3N) i=$((i + 10000)) j=$((j + 1)) - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + # nft rule in output places each packet in a different zone. + dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index b71828df5a6d..a3239d5e40c7 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -60,6 +60,8 @@ CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_FQ_PIE=m +CONFIG_NETDEVSIM=m # ## Network testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 503982b8f295..91832400ddbd 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -68,7 +68,7 @@ "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 88a20c781e49..c6046096d9db 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -15,7 +15,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -37,7 +37,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}", "matchCount": "256", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -60,7 +60,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -82,7 +82,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -106,7 +106,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -128,7 +128,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index a3e43189d940..ee22e3447ec7 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -716,6 +716,7 @@ def set_operation_mode(pm, parser, args, remaining): list_test_cases(alltests) exit(0) + exit_code = 0 # KSFT_PASS if len(alltests): req_plugins = pm.get_required_plugins(alltests) try: @@ -724,6 +725,8 @@ def set_operation_mode(pm, parser, args, remaining): print('The following plugins were not found:') print('{}'.format(pde.missing_pg)) catresults = test_runner(pm, args, alltests) + if catresults.count_failures() != 0: + exit_code = 1 # KSFT_FAIL if args.format == 'none': print('Test results output suppression requested\n') else: @@ -748,6 +751,8 @@ def set_operation_mode(pm, parser, args, remaining): gid=int(os.getenv('SUDO_GID'))) else: print('No tests found\n') + exit_code = 4 # KSFT_SKIP + exit(exit_code) def main(): """ @@ -767,8 +772,5 @@ def main(): set_operation_mode(pm, parser, args, remaining) - exit(0) - - if __name__ == "__main__": main() diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 7fe38c76db44..afb0cd86fa3d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -1,5 +1,6 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +modprobe netdevsim ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index ebc4ee0fe179..8a9461aa0878 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -276,7 +276,11 @@ n0 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 ip2 link del wg0 ip2 link del wg1 -! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel +read _ _ tx_bytes_before < <(n0 wg show wg1 transfer) +! n0 ping -W 1 -c 10 -f 192.168.241.2 || false +sleep 1 +read _ _ tx_bytes_after < <(n0 wg show wg1 transfer) +(( tx_bytes_after - tx_bytes_before < 70000 )) ip0 link del wg1 ip1 link del wg0 @@ -609,6 +613,28 @@ ip0 link set wg0 up kill $ncat_pid ip0 link del wg0 +# Ensure that dst_cache references don't outlive netns lifetime +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers +ip1 link add veth1 type veth peer name veth2 +ip1 link set veth2 netns $netns2 +ip1 addr add fd00:aa::1/64 dev veth1 +ip2 addr add fd00:aa::2/64 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +ip1 -6 route add default dev veth1 via fd00:aa::2 +ip2 -6 route add default dev veth2 via fd00:aa::1 +n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 +n1 ping6 -c 1 fd00::2 +pp ip netns delete $netns1 +pp ip netns delete $netns2 +pp ip netns add $netns1 +pp ip netns add $netns2 + # Ensure there aren't circular reference loops ip1 link add wg1 type wireguard ip2 link add wg2 type wireguard @@ -627,7 +653,7 @@ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do done < /dev/kmsg alldeleted=1 for object in "${!objects[@]}"; do - if [[ ${objects["$object"]} != *createddestroyed ]]; then + if [[ ${objects["$object"]} != *createddestroyed && ${objects["$object"]} != *createdcreateddestroyeddestroyed ]]; then echo "Error: $object: merely ${objects["$object"]}" >&3 alldeleted=0 fi diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index fe07d97df9fa..2b321b8a96cf 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -47,7 +47,7 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_TRACE_IRQFLAGS=y CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_PI_LIST=y +CONFIG_DEBUG_PLIST=y CONFIG_PROVE_RCU=y CONFIG_SPARSE_RCU_POINTER=y CONFIG_RCU_CPU_STALL_TIMEOUT=21 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 74db83a0aedd..a9b5a520a1d2 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -66,6 +66,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 +CONFIG_LOG_BUF_SHIFT=18 CONFIG_PRINTK_TIME=y CONFIG_BLK_DEV_INITRD=y CONFIG_LEGACY_VSYSCALL_NONE=y |