diff options
Diffstat (limited to 'tools')
113 files changed, 2487 insertions, 903 deletions
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 17c5a038f42d..0780f97c1850 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data { }; struct kvm_vmx_nested_state_hdr { - __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; - __u64 preemption_timer_deadline; struct { __u16 flags; } smm; + + __u32 flags; + __u64 preemption_timer_deadline; }; struct kvm_svm_nested_state_data { diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index df767afc690f..45f8e1b02241 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include <asm/alternative-asm.h> #include <asm/export.h> +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 6df1850f8353..8a69258fd8aa 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -9,7 +9,8 @@ MAKE = make INSTALL ?= install CFLAGS += -Wall -O2 -CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/include # This will work when bpf is built in tools env. where srctree # isn't set and when invoked from selftests build, where srctree diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 3c21de88af9e..f4699f9b46ba 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -173,7 +173,7 @@ class IocgStat: self.usages = [] self.usage = 0 for i in range(NR_USAGE_SLOTS): - usage = iocg.usages[(usage_idx + i) % NR_USAGE_SLOTS].value_() + usage = iocg.usages[(usage_idx + 1 + i) % NR_USAGE_SLOTS].value_() upct = usage * 100 / HWEIGHT_WHOLE self.usages.append(upct) self.usage = max(self.usage, upct) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 4671fbf28842..7f475d59a097 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -18,8 +18,7 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#if !defined(__ASSEMBLY__) && \ - (!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000) +#if !defined(__ASSEMBLY__) #include <linux/build_bug.h> #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 9f9002734e19..2f2f4082225e 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -111,8 +111,6 @@ # define noinline #endif -#define uninitialized_var(x) x = *(&(x)) - #include <linux/types.h> /* diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h index 67e01bbadbfe..501262aee8ff 100644 --- a/tools/include/linux/irqflags.h +++ b/tools/include/linux/irqflags.h @@ -2,9 +2,9 @@ #ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ #define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ -# define lockdep_hardirq_context(p) 0 +# define lockdep_hardirq_context() 0 # define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled(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) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 974a71342aea..8bd33050b7bb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3171,13 +3171,12 @@ union bpf_attr { * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return - * 0, on success; - * < 0, on error. + * 0 on success, or a negative error in case of failure. * * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) * Description @@ -3189,20 +3188,20 @@ union bpf_attr { * void bpf_ringbuf_submit(void *data, u64 flags) * Description * Submit reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * * void bpf_ringbuf_discard(void *data, u64 flags) * Description * Discard reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * @@ -3210,16 +3209,18 @@ union bpf_attr { * Description * Query various characteristics of provided ring buffer. What * exactly is queries is determined by *flags*: - * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; - * - BPF_RB_RING_SIZE - the size of ring buffer; - * - BPF_RB_CONS_POS - consumer position (can wrap around); - * - BPF_RB_PROD_POS - producer(s) position (can wrap around); - * Data returned is just a momentary snapshots of actual values + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values * and could be inaccurate, so this facility should be used to * power heuristics and for reporting, not to make 100% correct * calculation. * Return - * Requested value, or 0, if flags are not recognized. + * Requested value, or 0, if *flags* are not recognized. * * int bpf_csum_level(struct sk_buff *skb, u64 level) * Description diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h new file mode 100644 index 000000000000..eaef459e7bd4 --- /dev/null +++ b/tools/include/uapi/linux/filter.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Linux Socket Filter Data Structures + */ + +#ifndef __LINUX_FILTER_H__ +#define __LINUX_FILTER_H__ + + +#include <linux/types.h> +#include <linux/bpf_common.h> + +/* + * Current version of the filter code architecture. + */ +#define BPF_MAJOR_VERSION 1 +#define BPF_MINOR_VERSION 1 + +/* + * Try and keep these values and structures similar to BSD, especially + * the BPF code definitions which need to match so you can share filters + */ + +struct sock_filter { /* Filter block */ + __u16 code; /* Actual filter code */ + __u8 jt; /* Jump true */ + __u8 jf; /* Jump false */ + __u32 k; /* Generic multiuse field */ +}; + +struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ + unsigned short len; /* Number of filter blocks */ + struct sock_filter *filter; +}; + +/* ret - BPF_K and BPF_X also apply */ +#define BPF_RVAL(code) ((code) & 0x18) +#define BPF_A 0x10 + +/* misc */ +#define BPF_MISCOP(code) ((code) & 0xf8) +#define BPF_TAX 0x00 +#define BPF_TXA 0x80 + +/* + * Macros for filter block array initializers. + */ +#ifndef BPF_STMT +#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } +#endif +#ifndef BPF_JUMP +#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k } +#endif + +/* + * Number of scratch memory words for: BPF_ST and BPF_STX + */ +#define BPF_MEMWORDS 16 + +/* RATIONALE. Negative offsets are invalid in BPF. + We use them to reference ancillary data. + Unlike introduction new instructions, it does not break + existing compilers/optimizers. + */ +#define SKF_AD_OFF (-0x1000) +#define SKF_AD_PROTOCOL 0 +#define SKF_AD_PKTTYPE 4 +#define SKF_AD_IFINDEX 8 +#define SKF_AD_NLATTR 12 +#define SKF_AD_NLATTR_NEST 16 +#define SKF_AD_MARK 20 +#define SKF_AD_QUEUE 24 +#define SKF_AD_HATYPE 28 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_ALU_XOR_X 40 +#define SKF_AD_VLAN_TAG 44 +#define SKF_AD_VLAN_TAG_PRESENT 48 +#define SKF_AD_PAY_OFFSET 52 +#define SKF_AD_RANDOM 56 +#define SKF_AD_VLAN_TPID 60 +#define SKF_AD_MAX 64 + +#define SKF_NET_OFF (-0x100000) +#define SKF_LL_OFF (-0x200000) + +#define BPF_NET_OFF SKF_NET_OFF +#define BPF_LL_OFF SKF_LL_OFF + +#endif /* __LINUX_FILTER_H__ */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..21a1edd08cbe 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -532,9 +532,10 @@ struct perf_event_mmap_page { cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ - cap_user_time : 1, /* The time_* fields are used */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - cap_____res : 59; + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; }; }; @@ -593,13 +594,29 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; /* * Hole for extension of the self monitor capabilities */ - __u8 __reserved[118*8+4]; /* align to 1k. */ + __u8 __reserved[116*8]; /* align to 1k. */ /* * Control data for the mmap() data buffer. diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h index 5f305c86b892..28a837b6069d 100644 --- a/tools/io_uring/liburing.h +++ b/tools/io_uring/liburing.h @@ -10,6 +10,7 @@ extern "C" { #include <string.h> #include "../../include/uapi/linux/io_uring.h" #include <inttypes.h> +#include <linux/swab.h> #include "barrier.h" /* @@ -145,11 +146,14 @@ static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd, } static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd, - short poll_mask) + unsigned poll_mask) { memset(sqe, 0, sizeof(*sqe)); sqe->opcode = IORING_OP_POLL_ADD; sqe->fd = fd; +#if __BYTE_ORDER == __BIG_ENDIAN + poll_mask = __swahw32(poll_mask); +#endif sqe->poll_events = poll_mask; } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 1b6015b21ba8..dbef24ebcfcb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -233,6 +233,8 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); + +enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */ LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); #ifdef __cplusplus diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index df59fd4fc95b..e0af36b0e5d8 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -11,14 +11,18 @@ #include <stdbool.h> #include <stddef.h> #include <limits.h> -#ifndef __WORDSIZE -#define __WORDSIZE (__SIZEOF_LONG__ * 8) -#endif static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ - return (h * 11400714819323198485llu) >> (__WORDSIZE - bits); +#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) + /* LP64 case */ + return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); +#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__) + return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits); +#else +# error "Unsupported size_t size" +#endif } typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 477c679ed945..11e4725b8b1c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4818,7 +4818,13 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) err = -EINVAL; goto out; } - prog = bpf_object__find_program_by_title(obj, sec_name); + prog = NULL; + for (i = 0; i < obj->nr_programs; i++) { + if (!strcmp(obj->programs[i].section_name, sec_name)) { + prog = &obj->programs[i]; + break; + } + } if (!prog) { pr_warn("failed to find program '%s' for CO-RE offset relocation\n", sec_name); @@ -6653,7 +6659,7 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, .attach_fn = attach_iter), - BPF_EAPROG_SEC("xdp_devmap", BPF_PROG_TYPE_XDP, + BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index dbb9efbf718a..39ebf6192016 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -237,6 +237,9 @@ static int get_value(struct parse_opt_ctx_t *p, return err; case OPTION_CALLBACK: + if (opt->set) + *(bool *)opt->set = true; + if (unset) return (*opt->callback)(opt, NULL, 1) ? (-1) : 0; if (opt->flags & PARSE_OPT_NOARG) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 5b36c589a029..ba4f33804af1 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2861,6 +2861,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg, if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; + free_token(token); type = read_token(&token); *tok = token; diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index 27f3b07fdae8..f1640d651c8a 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -361,6 +361,7 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, break; case KBUFFER_TYPE_TIME_EXTEND: + case KBUFFER_TYPE_TIME_STAMP: extend = read_4(kbuf, data); data += 4; extend <<= TS_SHIFT; @@ -369,10 +370,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, *length = 0; break; - case KBUFFER_TYPE_TIME_STAMP: - data += 12; - *length = 0; - break; case 0: *length = read_4(kbuf, data) - 4; *length = (*length + 3) & ~3; @@ -397,7 +394,11 @@ static unsigned int update_pointers(struct kbuffer *kbuf) type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); - kbuf->timestamp += delta; + if (type_len == KBUFFER_TYPE_TIME_STAMP) + kbuf->timestamp = delta; + else + kbuf->timestamp += delta; + kbuf->index = calc_index(kbuf, ptr); kbuf->next = kbuf->index + length; @@ -454,7 +455,9 @@ static int __next_event(struct kbuffer *kbuf) if (kbuf->next >= kbuf->size) return -1; type = update_pointers(kbuf); - } while (type == KBUFFER_TYPE_TIME_EXTEND || type == KBUFFER_TYPE_PADDING); + } while (type == KBUFFER_TYPE_TIME_EXTEND || + type == KBUFFER_TYPE_TIME_STAMP || + type == KBUFFER_TYPE_PADDING); return 0; } @@ -547,6 +550,34 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer) } /** + * kbuffer_subbuf_timestamp - read the timestamp from a sub buffer + * @kbuf: The kbuffer to load + * @subbuf: The subbuffer to read from. + * + * Return the timestamp from a subbuffer. + */ +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf) +{ + return kbuf->read_8(subbuf); +} + +/** + * kbuffer_ptr_delta - read the delta field from a record + * @kbuf: The kbuffer to load + * @ptr: The record in the buffe. + * + * Return the timestamp delta from a record + */ +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr) +{ + unsigned int type_len_ts; + + type_len_ts = read_4(kbuf, ptr); + return ts4host(kbuf, type_len_ts); +} + + +/** * kbuffer_read_event - read the next event in the kbuffer subbuffer * @kbuf: The kbuffer to read from * @ts: The address to store the timestamp of the event (may be NULL to ignore) diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h index ed4d697fc137..5fa8292e341b 100644 --- a/tools/lib/traceevent/kbuffer.h +++ b/tools/lib/traceevent/kbuffer.h @@ -49,6 +49,8 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer); void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts); void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts); unsigned long long kbuffer_timestamp(struct kbuffer *kbuf); +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf); +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr); void *kbuffer_translate_data(int swap, void *data, unsigned int *size); diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile index 349bb81482ab..680d883efe05 100644 --- a/tools/lib/traceevent/plugins/Makefile +++ b/tools/lib/traceevent/plugins/Makefile @@ -197,7 +197,7 @@ define do_generate_dynamic_list_file xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ if [ "$$symbol_type" = "U W" ];then \ (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + $(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\ echo '};'; \ ) > $2; \ else \ diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index e91a2eb19592..f9d610d5a1a4 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -1122,12 +1122,10 @@ maintain at least the appearance of FIFO order. In practice, this difficulty is solved by inserting a special fence between P1's two loads when the kernel is compiled for the Alpha architecture. In fact, as of version 4.15, the kernel automatically -adds this fence (called smp_read_barrier_depends() and defined as -nothing at all on non-Alpha builds) after every READ_ONCE() and atomic -load. The effect of the fence is to cause the CPU not to execute any -po-later instructions until after the local cache has finished -processing all the stores it has already received. Thus, if the code -was changed to: +adds this fence after every READ_ONCE() and atomic load on Alpha. The +effect of the fence is to cause the CPU not to execute any po-later +instructions until after the local cache has finished processing all +the stores it has already received. Thus, if the code was changed to: P1() { @@ -1146,14 +1144,14 @@ READ_ONCE() or another synchronization primitive rather than accessed directly. The LKMM requires that smp_rmb(), acquire fences, and strong fences -share this property with smp_read_barrier_depends(): They do not allow -the CPU to execute any po-later instructions (or po-later loads in the -case of smp_rmb()) until all outstanding stores have been processed by -the local cache. In the case of a strong fence, the CPU first has to -wait for all of its po-earlier stores to propagate to every other CPU -in the system; then it has to wait for the local cache to process all -the stores received as of that time -- not just the stores received -when the strong fence began. +share this property: They do not allow the CPU to execute any po-later +instructions (or po-later loads in the case of smp_rmb()) until all +outstanding stores have been processed by the local cache. In the +case of a strong fence, the CPU first has to wait for all of its +po-earlier stores to propagate to every other CPU in the system; then +it has to wait for the local cache to process all the stores received +as of that time -- not just the stores received when the strong fence +began. And of course, none of this matters for any architecture other than Alpha. @@ -1987,28 +1985,36 @@ outcome undefined. In technical terms, the compiler is allowed to assume that when the program executes, there will not be any data races. A "data race" -occurs when two conflicting memory accesses execute concurrently; -two memory accesses "conflict" if: +occurs when there are two memory accesses such that: - they access the same location, +1. they access the same location, - they occur on different CPUs (or in different threads on the - same CPU), +2. at least one of them is a store, - at least one of them is a plain access, +3. at least one of them is plain, - and at least one of them is a store. +4. they occur on different CPUs (or in different threads on the + same CPU), and -The LKMM tries to determine whether a program contains two conflicting -accesses which may execute concurrently; if it does then the LKMM says -there is a potential data race and makes no predictions about the -program's outcome. +5. they execute concurrently. -Determining whether two accesses conflict is easy; you can see that -all the concepts involved in the definition above are already part of -the memory model. The hard part is telling whether they may execute -concurrently. The LKMM takes a conservative attitude, assuming that -accesses may be concurrent unless it can prove they cannot. +In the literature, two accesses are said to "conflict" if they satisfy +1 and 2 above. We'll go a little farther and say that two accesses +are "race candidates" if they satisfy 1 - 4. Thus, whether or not two +race candidates actually do race in a given execution depends on +whether they are concurrent. + +The LKMM tries to determine whether a program contains race candidates +which may execute concurrently; if it does then the LKMM says there is +a potential data race and makes no predictions about the program's +outcome. + +Determining whether two accesses are race candidates is easy; you can +see that all the concepts involved in the definition above are already +part of the memory model. The hard part is telling whether they may +execute concurrently. The LKMM takes a conservative attitude, +assuming that accesses may be concurrent unless it can prove they +are not. If two memory accesses aren't concurrent then one must execute before the other. Therefore the LKMM decides two accesses aren't concurrent @@ -2171,8 +2177,8 @@ again, now using plain accesses for buf: } This program does not contain a data race. Although the U and V -accesses conflict, the LKMM can prove they are not concurrent as -follows: +accesses are race candidates, the LKMM can prove they are not +concurrent as follows: The smp_wmb() fence in P0 is both a compiler barrier and a cumul-fence. It guarantees that no matter what hash of @@ -2326,12 +2332,11 @@ could now perform the load of x before the load of ptr (there might be a control dependency but no address dependency at the machine level). Finally, it turns out there is a situation in which a plain write does -not need to be w-post-bounded: when it is separated from the -conflicting access by a fence. At first glance this may seem -impossible. After all, to be conflicting the second access has to be -on a different CPU from the first, and fences don't link events on -different CPUs. Well, normal fences don't -- but rcu-fence can! -Here's an example: +not need to be w-post-bounded: when it is separated from the other +race-candidate access by a fence. At first glance this may seem +impossible. After all, to be race candidates the two accesses must +be on different CPUs, and fences don't link events on different CPUs. +Well, normal fences don't -- but rcu-fence can! Here's an example: int x, y; @@ -2367,7 +2372,7 @@ concurrent and there is no race, even though P1's plain store to y isn't w-post-bounded by any marked accesses. Putting all this material together yields the following picture. For -two conflicting stores W and W', where W ->co W', the LKMM says the +race-candidate stores W and W', where W ->co W', the LKMM says the stores don't race if W can be linked to W' by a w-post-bounded ; vis ; w-pre-bounded @@ -2380,8 +2385,8 @@ sequence, and if W' is plain then they also have to be linked by a w-post-bounded ; vis ; r-pre-bounded -sequence. For a conflicting load R and store W, the LKMM says the two -accesses don't race if R can be linked to W by an +sequence. For race-candidate load R and store W, the LKMM says the +two accesses don't race if R can be linked to W by an r-post-bounded ; xb* ; w-pre-bounded @@ -2413,20 +2418,20 @@ is, the rules governing the memory subsystem's choice of a store to satisfy a load request and its determination of where a store will fall in the coherence order): - If R and W conflict and it is possible to link R to W by one - of the xb* sequences listed above, then W ->rfe R is not - allowed (i.e., a load cannot read from a store that it + If R and W are race candidates and it is possible to link R to + W by one of the xb* sequences listed above, then W ->rfe R is + not allowed (i.e., a load cannot read from a store that it executes before, even if one or both is plain). - If W and R conflict and it is possible to link W to R by one - of the vis sequences listed above, then R ->fre W is not - allowed (i.e., if a store is visible to a load then the load - must read from that store or one coherence-after it). + If W and R are race candidates and it is possible to link W to + R by one of the vis sequences listed above, then R ->fre W is + not allowed (i.e., if a store is visible to a load then the + load must read from that store or one coherence-after it). - If W and W' conflict and it is possible to link W to W' by one - of the vis sequences listed above, then W' ->co W is not - allowed (i.e., if one store is visible to a second then the - second must come after the first in the coherence order). + If W and W' are race candidates and it is possible to link W + to W' by one of the vis sequences listed above, then W' ->co W + is not allowed (i.e., if one store is visible to a second then + the second must come after the first in the coherence order). This is the extent to which the LKMM deals with plain accesses. Perhaps it could say more (for example, plain accesses might diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt index 7fe8d7aa3029..63c4adfed884 100644 --- a/tools/memory-model/Documentation/recipes.txt +++ b/tools/memory-model/Documentation/recipes.txt @@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by locking will be seen as ordered by CPUs not holding that lock. Consider this example: - /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */ + /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */ void CPU0(void) { spin_lock(&mylock); diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt index b177f3e4a614..ecbbaa5396d4 100644 --- a/tools/memory-model/Documentation/references.txt +++ b/tools/memory-model/Documentation/references.txt @@ -73,6 +73,18 @@ o Christopher Pulte, Shaked Flur, Will Deacon, Jon French, Linux-kernel memory model ========================= +o Jade Alglave, Will Deacon, Boqun Feng, David Howells, Daniel + Lustig, Luc Maranget, Paul E. McKenney, Andrea Parri, Nicholas + Piggin, Alan Stern, Akira Yokosawa, and Peter Zijlstra. + 2019. "Calibrating your fear of big bad optimizing compilers" + Linux Weekly News. https://lwn.net/Articles/799218/ + +o Jade Alglave, Will Deacon, Boqun Feng, David Howells, Daniel + Lustig, Luc Maranget, Paul E. McKenney, Andrea Parri, Nicholas + Piggin, Alan Stern, Akira Yokosawa, and Peter Zijlstra. + 2019. "Who's afraid of a big bad optimizing compiler?" + Linux Weekly News. https://lwn.net/Articles/793253/ + o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2018. "Frightening small children and disconcerting grown-ups: Concurrency in the Linux kernel". In Proceedings of @@ -88,6 +100,11 @@ o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2017. "A formal kernel memory-ordering model (part 2)" Linux Weekly News. https://lwn.net/Articles/720550/ +o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and + Alan Stern. 2017-2019. "A Formal Model of Linux-Kernel Memory + Ordering" (backup material for the LWN articles) + https://mirrors.edge.kernel.org/pub/linux/kernel/people/paulmck/LWNLinuxMM/ + Memory-model tooling ==================== @@ -110,5 +127,5 @@ Memory-model comparisons ======================== o Paul E. McKenney, Ulrich Weigand, Andrea Parri, and Boqun - Feng. 2016. "Linux-Kernel Memory Model". (6 June 2016). - http://open-std.org/JTC1/SC22/WG21/docs/papers/2016/p0124r2.html. + Feng. 2018. "Linux-Kernel Memory Model". (27 September 2018). + http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2018/p0124r6.html. diff --git a/tools/memory-model/README b/tools/memory-model/README index fc07b52f2028..ecb7385376bf 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -28,8 +28,34 @@ downloaded separately: See "herdtools7/INSTALL.md" for installation instructions. Note that although these tools usually provide backwards compatibility, -this is not absolutely guaranteed. Therefore, if a later version does -not work, please try using the exact version called out above. +this is not absolutely guaranteed. + +For example, a future version of herd7 might not work with the model +in this release. A compatible model will likely be made available in +a later release of Linux kernel. + +If you absolutely need to run the model in this particular release, +please try using the exact version called out above. + +klitmus7 is independent of the model provided here. It has its own +dependency on a target kernel release where converted code is built +and executed. Any change in kernel APIs essential to klitmus7 will +necessitate an upgrade of klitmus7. + +If you find any compatibility issues in klitmus7, please inform the +memory model maintainers. + +klitmus7 Compatibility Table +---------------------------- + + ============ ========== + target Linux herdtools7 + ------------ ---------- + -- 4.18 7.48 -- + 4.15 -- 4.19 7.49 -- + 4.20 -- 5.5 7.54 -- + 5.6 -- 7.56 -- + ============ ========== ================== @@ -207,11 +233,15 @@ The Linux-kernel memory model (LKMM) has the following limitations: case as a store release. b. The "unless" RMW operations are not currently modeled: - atomic_long_add_unless(), atomic_add_unless(), - atomic_inc_unless_negative(), and - atomic_dec_unless_positive(). These can be emulated + atomic_long_add_unless(), atomic_inc_unless_negative(), + and atomic_dec_unless_positive(). These can be emulated in litmus tests, for example, by using atomic_cmpxchg(). + One exception of this limitation is atomic_add_unless(), + which is provided directly by herd7 (so no corresponding + definition in linux-kernel.def). atomic_add_unless() is + modeled by herd7 therefore it can be used in litmus tests. + c. The call_rcu() function is not modeled. It can be emulated in litmus tests by adding another process that invokes synchronize_rcu() and the body of the callback diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 3c5967748abb..2e2ce089b0e9 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -82,7 +82,7 @@ bool arch_callee_saved_reg(unsigned char reg); unsigned long arch_jump_destination(struct instruction *insn); -unsigned long arch_dest_rela_offset(int addend); +unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 9872195f998b..1967370440b3 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -67,7 +67,7 @@ bool arch_callee_saved_reg(unsigned char reg) } } -unsigned long arch_dest_rela_offset(int addend) +unsigned long arch_dest_reloc_offset(int addend) { return addend + 4; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5e0d70a89fb8..e034a8f24f46 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -353,7 +353,7 @@ static struct instruction *find_last_insn(struct objtool_file *file, static int add_dead_ends(struct objtool_file *file) { struct section *sec; - struct rela *rela; + struct reloc *reloc; struct instruction *insn; /* @@ -371,24 +371,24 @@ static int add_dead_ends(struct objtool_file *file) if (!sec) goto reachable; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - insn = find_last_insn(file, rela->sym->sec); + else if (reloc->addend == reloc->sym->sec->len) { + insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } } else { WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } @@ -406,24 +406,24 @@ reachable: if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - insn = find_last_insn(file, rela->sym->sec); + else if (reloc->addend == reloc->sym->sec->len) { + insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } } else { WARN("can't find reachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } @@ -441,26 +441,26 @@ static void add_ignores(struct objtool_file *file) struct instruction *insn; struct section *sec; struct symbol *func; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); if (!sec) return; - list_for_each_entry(rela, &sec->rela_list, list) { - switch (rela->sym->type) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + switch (reloc->sym->type) { case STT_FUNC: - func = rela->sym; + func = reloc->sym; break; case STT_SECTION: - func = find_func_by_offset(rela->sym->sec, rela->addend); + func = find_func_by_offset(reloc->sym->sec, reloc->addend); if (!func) continue; break; default: - WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type); + WARN("unexpected relocation symbol type in %s: %d", sec->name, reloc->sym->type); continue; } @@ -580,20 +580,20 @@ static void add_uaccess_safe(struct objtool_file *file) static int add_ignore_alternatives(struct objtool_file *file) { struct section *sec; - struct rela *rela; + struct reloc *reloc; struct instruction *insn; sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.ignore_alts entry"); return -1; @@ -611,7 +611,7 @@ static int add_ignore_alternatives(struct objtool_file *file) static int add_jump_destinations(struct objtool_file *file) { struct instruction *insn; - struct rela *rela; + struct reloc *reloc; struct section *dest_sec; unsigned long dest_off; @@ -622,19 +622,19 @@ static int add_jump_destinations(struct objtool_file *file) if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET) continue; - rela = find_rela_by_dest_range(file->elf, insn->sec, + reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!rela) { + if (!reloc) { dest_sec = insn->sec; dest_off = arch_jump_destination(insn); - } else if (rela->sym->type == STT_SECTION) { - dest_sec = rela->sym->sec; - dest_off = arch_dest_rela_offset(rela->addend); - } else if (rela->sym->sec->idx) { - dest_sec = rela->sym->sec; - dest_off = rela->sym->sym.st_value + - arch_dest_rela_offset(rela->addend); - } else if (strstr(rela->sym->name, "_indirect_thunk_")) { + } else if (reloc->sym->type == STT_SECTION) { + dest_sec = reloc->sym->sec; + dest_off = arch_dest_reloc_offset(reloc->addend); + } else if (reloc->sym->sec->idx) { + dest_sec = reloc->sym->sec; + dest_off = reloc->sym->sym.st_value + + arch_dest_reloc_offset(reloc->addend); + } else if (strstr(reloc->sym->name, "_indirect_thunk_")) { /* * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly. @@ -648,7 +648,7 @@ static int add_jump_destinations(struct objtool_file *file) continue; } else { /* external sibling call */ - insn->call_dest = rela->sym; + insn->call_dest = reloc->sym; continue; } @@ -724,15 +724,15 @@ static int add_call_destinations(struct objtool_file *file) { struct instruction *insn; unsigned long dest_off; - struct rela *rela; + struct reloc *reloc; for_each_insn(file, insn) { if (insn->type != INSN_CALL) continue; - rela = find_rela_by_dest_range(file->elf, insn->sec, + reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!rela) { + if (!reloc) { dest_off = arch_jump_destination(insn); insn->call_dest = find_func_by_offset(insn->sec, dest_off); if (!insn->call_dest) @@ -752,19 +752,19 @@ static int add_call_destinations(struct objtool_file *file) return -1; } - } else if (rela->sym->type == STT_SECTION) { - dest_off = arch_dest_rela_offset(rela->addend); - insn->call_dest = find_func_by_offset(rela->sym->sec, + } else if (reloc->sym->type == STT_SECTION) { + dest_off = arch_dest_reloc_offset(reloc->addend); + insn->call_dest = find_func_by_offset(reloc->sym->sec, dest_off); if (!insn->call_dest) { WARN_FUNC("can't find call dest symbol at %s+0x%lx", insn->sec, insn->offset, - rela->sym->sec->name, + reloc->sym->sec->name, dest_off); return -1; } } else - insn->call_dest = rela->sym; + insn->call_dest = reloc->sym; /* * Many compilers cannot disable KCOV with a function attribute @@ -773,9 +773,9 @@ static int add_call_destinations(struct objtool_file *file) */ if (insn->sec->noinstr && !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { - if (rela) { - rela->type = R_NONE; - elf_write_rela(file->elf, rela); + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); } elf_write_insn(file->elf, insn->sec, @@ -890,7 +890,7 @@ static int handle_group_alt(struct objtool_file *file, */ if ((insn->offset != special_alt->new_off || (insn->type != INSN_CALL && !is_static_jump(insn))) && - find_rela_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) { + find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) { WARN_FUNC("unsupported relocation in alternatives section", insn->sec, insn->offset); @@ -1036,34 +1036,34 @@ out: } static int add_jump_table(struct objtool_file *file, struct instruction *insn, - struct rela *table) + struct reloc *table) { - struct rela *rela = table; + struct reloc *reloc = table; struct instruction *dest_insn; struct alternative *alt; struct symbol *pfunc = insn->func->pfunc; unsigned int prev_offset = 0; /* - * Each @rela is a switch table relocation which points to the target + * Each @reloc is a switch table relocation which points to the target * instruction. */ - list_for_each_entry_from(rela, &table->sec->rela_list, list) { + list_for_each_entry_from(reloc, &table->sec->reloc_list, list) { /* Check for the end of the table: */ - if (rela != table && rela->jump_table_start) + if (reloc != table && reloc->jump_table_start) break; /* Make sure the table entries are consecutive: */ - if (prev_offset && rela->offset != prev_offset + 8) + if (prev_offset && reloc->offset != prev_offset + 8) break; /* Detect function pointers from contiguous objects: */ - if (rela->sym->sec == pfunc->sec && - rela->addend == pfunc->offset) + if (reloc->sym->sec == pfunc->sec && + reloc->addend == pfunc->offset) break; - dest_insn = find_insn(file, rela->sym->sec, rela->addend); + dest_insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!dest_insn) break; @@ -1079,7 +1079,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; list_add_tail(&alt->list, &insn->alts); - prev_offset = rela->offset; + prev_offset = reloc->offset; } if (!prev_offset) { @@ -1134,11 +1134,11 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, * * NOTE: RETPOLINE made it harder still to decode dynamic jumps. */ -static struct rela *find_jump_table(struct objtool_file *file, +static struct reloc *find_jump_table(struct objtool_file *file, struct symbol *func, struct instruction *insn) { - struct rela *text_rela, *table_rela; + struct reloc *text_reloc, *table_reloc; struct instruction *dest_insn, *orig_insn = insn; struct section *table_sec; unsigned long table_offset; @@ -1163,16 +1163,16 @@ static struct rela *find_jump_table(struct objtool_file *file, break; /* look for a relocation which references .rodata */ - text_rela = find_rela_by_dest_range(file->elf, insn->sec, + text_reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!text_rela || text_rela->sym->type != STT_SECTION || - !text_rela->sym->sec->rodata) + if (!text_reloc || text_reloc->sym->type != STT_SECTION || + !text_reloc->sym->sec->rodata) continue; - table_offset = text_rela->addend; - table_sec = text_rela->sym->sec; + table_offset = text_reloc->addend; + table_sec = text_reloc->sym->sec; - if (text_rela->type == R_X86_64_PC32) + if (text_reloc->type == R_X86_64_PC32) table_offset += 4; /* @@ -1189,14 +1189,14 @@ static struct rela *find_jump_table(struct objtool_file *file, continue; /* - * Each table entry has a rela associated with it. The rela + * Each table entry has a reloc associated with it. The reloc * should reference text in the same function as the original * instruction. */ - table_rela = find_rela_by_dest(file->elf, table_sec, table_offset); - if (!table_rela) + table_reloc = find_reloc_by_dest(file->elf, table_sec, table_offset); + if (!table_reloc) continue; - dest_insn = find_insn(file, table_rela->sym->sec, table_rela->addend); + dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend); if (!dest_insn || !dest_insn->func || dest_insn->func->pfunc != func) continue; @@ -1205,10 +1205,10 @@ static struct rela *find_jump_table(struct objtool_file *file, * indicates a rare GCC quirk/bug which can leave dead code * behind. */ - if (text_rela->type == R_X86_64_PC32) + if (text_reloc->type == R_X86_64_PC32) file->ignore_unreachables = true; - return table_rela; + return table_reloc; } return NULL; @@ -1222,7 +1222,7 @@ static void mark_func_jump_tables(struct objtool_file *file, struct symbol *func) { struct instruction *insn, *last = NULL; - struct rela *rela; + struct reloc *reloc; func_for_each_insn(file, func, insn) { if (!last) @@ -1245,10 +1245,10 @@ static void mark_func_jump_tables(struct objtool_file *file, if (insn->type != INSN_JUMP_DYNAMIC) continue; - rela = find_jump_table(file, func, insn); - if (rela) { - rela->jump_table_start = true; - insn->jump_table = rela; + reloc = find_jump_table(file, func, insn); + if (reloc) { + reloc->jump_table_start = true; + insn->jump_table = reloc; } } } @@ -1302,8 +1302,8 @@ static int add_jump_table_alts(struct objtool_file *file) static int read_unwind_hints(struct objtool_file *file) { - struct section *sec, *relasec; - struct rela *rela; + struct section *sec, *relocsec; + struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; struct cfi_reg *cfa; @@ -1313,8 +1313,8 @@ static int read_unwind_hints(struct objtool_file *file) if (!sec) return 0; - relasec = sec->rela; - if (!relasec) { + relocsec = sec->reloc; + if (!relocsec) { WARN("missing .rela.discard.unwind_hints section"); return -1; } @@ -1329,13 +1329,13 @@ static int read_unwind_hints(struct objtool_file *file) for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; - rela = find_rela_by_dest(file->elf, sec, i * sizeof(*hint)); - if (!rela) { - WARN("can't find rela for unwind_hints[%d]", i); + reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); + if (!reloc) { + WARN("can't find reloc for unwind_hints[%d]", i); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("can't find insn for unwind_hints[%d]", i); return -1; @@ -1393,19 +1393,19 @@ static int read_retpoline_hints(struct objtool_file *file) { struct section *sec; struct instruction *insn; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.retpoline_safe entry"); return -1; @@ -1428,19 +1428,19 @@ static int read_instr_hints(struct objtool_file *file) { struct section *sec; struct instruction *insn; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.instr_end"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -1453,13 +1453,13 @@ static int read_instr_hints(struct objtool_file *file) if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.instr_begin entry"); return -1; @@ -1475,22 +1475,22 @@ static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; struct section *sec; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { + list_for_each_entry(reloc, &sec->reloc_list, list) { unsigned long dest_off; - if (rela->sym->type != STT_SECTION) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.intra_function_call entry"); return -1; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 906b5210f7ca..061aa96e15d3 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -37,7 +37,7 @@ struct instruction { struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; - struct rela *jump_table; + struct reloc *jump_table; struct list_head alts; struct symbol *func; struct list_head stack_ops; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 26d11d821941..3ddbd66f1a37 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -228,26 +228,26 @@ struct symbol *find_symbol_by_name(const struct elf *elf, const char *name) return NULL; } -struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len) { - struct rela *rela, *r = NULL; + struct reloc *reloc, *r = NULL; unsigned long o; - if (!sec->rela) + if (!sec->reloc) return NULL; - sec = sec->rela; + sec = sec->reloc; for_offset_range(o, offset, offset + len) { - elf_hash_for_each_possible(elf->rela_hash, rela, hash, + elf_hash_for_each_possible(elf->reloc_hash, reloc, hash, sec_offset_hash(sec, o)) { - if (rela->sec != sec) + if (reloc->sec != sec) continue; - if (rela->offset >= offset && rela->offset < offset + len) { - if (!r || rela->offset < r->offset) - r = rela; + if (reloc->offset >= offset && reloc->offset < offset + len) { + if (!r || reloc->offset < r->offset) + r = reloc; } } if (r) @@ -257,9 +257,9 @@ struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, return NULL; } -struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset) +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset) { - return find_rela_by_dest_range(elf, sec, offset, 1); + return find_reloc_by_dest_range(elf, sec, offset, 1); } static int read_sections(struct elf *elf) @@ -288,7 +288,7 @@ static int read_sections(struct elf *elf) memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->rela_list); + INIT_LIST_HEAD(&sec->reloc_list); s = elf_getscn(elf->elf, i); if (!s) { @@ -434,7 +434,13 @@ static int read_symbols(struct elf *elf) size_t pnamelen; if (sym->type != STT_FUNC) continue; - sym->pfunc = sym->cfunc = sym; + + if (sym->pfunc == NULL) + sym->pfunc = sym; + + if (sym->cfunc == NULL) + sym->cfunc = sym; + coldstr = strstr(sym->name, ".cold"); if (!coldstr) continue; @@ -482,72 +488,101 @@ err: return -1; } -void elf_add_rela(struct elf *elf, struct rela *rela) +void elf_add_reloc(struct elf *elf, struct reloc *reloc) +{ + struct section *sec = reloc->sec; + + list_add_tail(&reloc->list, &sec->reloc_list); + elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc)); +} + +static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) { - struct section *sec = rela->sec; + if (!gelf_getrel(sec->data, i, &reloc->rel)) { + WARN_ELF("gelf_getrel"); + return -1; + } + reloc->type = GELF_R_TYPE(reloc->rel.r_info); + reloc->addend = 0; + reloc->offset = reloc->rel.r_offset; + *symndx = GELF_R_SYM(reloc->rel.r_info); + return 0; +} - list_add_tail(&rela->list, &sec->rela_list); - elf_hash_add(elf->rela_hash, &rela->hash, rela_hash(rela)); +static int read_rela_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) +{ + if (!gelf_getrela(sec->data, i, &reloc->rela)) { + WARN_ELF("gelf_getrela"); + return -1; + } + reloc->type = GELF_R_TYPE(reloc->rela.r_info); + reloc->addend = reloc->rela.r_addend; + reloc->offset = reloc->rela.r_offset; + *symndx = GELF_R_SYM(reloc->rela.r_info); + return 0; } -static int read_relas(struct elf *elf) +static int read_relocs(struct elf *elf) { struct section *sec; - struct rela *rela; + struct reloc *reloc; int i; unsigned int symndx; - unsigned long nr_rela, max_rela = 0, tot_rela = 0; + unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0; list_for_each_entry(sec, &elf->sections, list) { - if (sec->sh.sh_type != SHT_RELA) + if ((sec->sh.sh_type != SHT_RELA) && + (sec->sh.sh_type != SHT_REL)) continue; - sec->base = find_section_by_name(elf, sec->name + 5); + sec->base = find_section_by_index(elf, sec->sh.sh_info); if (!sec->base) { - WARN("can't find base section for rela section %s", + WARN("can't find base section for reloc section %s", sec->name); return -1; } - sec->base->rela = sec; + sec->base->reloc = sec; - nr_rela = 0; + nr_reloc = 0; for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) { - rela = malloc(sizeof(*rela)); - if (!rela) { + reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } - memset(rela, 0, sizeof(*rela)); - - if (!gelf_getrela(sec->data, i, &rela->rela)) { - WARN_ELF("gelf_getrela"); - return -1; + memset(reloc, 0, sizeof(*reloc)); + switch (sec->sh.sh_type) { + case SHT_REL: + if (read_rel_reloc(sec, i, reloc, &symndx)) + return -1; + break; + case SHT_RELA: + if (read_rela_reloc(sec, i, reloc, &symndx)) + return -1; + break; + default: return -1; } - rela->type = GELF_R_TYPE(rela->rela.r_info); - rela->addend = rela->rela.r_addend; - rela->offset = rela->rela.r_offset; - symndx = GELF_R_SYM(rela->rela.r_info); - rela->sec = sec; - rela->idx = i; - rela->sym = find_symbol_by_index(elf, symndx); - if (!rela->sym) { - WARN("can't find rela entry symbol %d for %s", + reloc->sec = sec; + reloc->idx = i; + reloc->sym = find_symbol_by_index(elf, symndx); + if (!reloc->sym) { + WARN("can't find reloc entry symbol %d for %s", symndx, sec->name); return -1; } - elf_add_rela(elf, rela); - nr_rela++; + elf_add_reloc(elf, reloc); + nr_reloc++; } - max_rela = max(max_rela, nr_rela); - tot_rela += nr_rela; + max_reloc = max(max_reloc, nr_reloc); + tot_reloc += nr_reloc; } if (stats) { - printf("max_rela: %lu\n", max_rela); - printf("tot_rela: %lu\n", tot_rela); + printf("max_reloc: %lu\n", max_reloc); + printf("tot_reloc: %lu\n", tot_reloc); } return 0; @@ -573,7 +608,7 @@ struct elf *elf_open_read(const char *name, int flags) elf_hash_init(elf->symbol_name_hash); elf_hash_init(elf->section_hash); elf_hash_init(elf->section_name_hash); - elf_hash_init(elf->rela_hash); + elf_hash_init(elf->reloc_hash); elf->fd = open(name, flags); if (elf->fd == -1) { @@ -606,7 +641,7 @@ struct elf *elf_open_read(const char *name, int flags) if (read_symbols(elf)) goto err; - if (read_relas(elf)) + if (read_relocs(elf)) goto err; return elf; @@ -632,7 +667,7 @@ struct section *elf_create_section(struct elf *elf, const char *name, memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->rela_list); + INIT_LIST_HEAD(&sec->reloc_list); s = elf_newscn(elf->elf); if (!s) { @@ -719,28 +754,28 @@ struct section *elf_create_section(struct elf *elf, const char *name, return sec; } -struct section *elf_create_rela_section(struct elf *elf, struct section *base) +static struct section *elf_create_rel_reloc_section(struct elf *elf, struct section *base) { - char *relaname; + char *relocname; struct section *sec; - relaname = malloc(strlen(base->name) + strlen(".rela") + 1); - if (!relaname) { + relocname = malloc(strlen(base->name) + strlen(".rel") + 1); + if (!relocname) { perror("malloc"); return NULL; } - strcpy(relaname, ".rela"); - strcat(relaname, base->name); + strcpy(relocname, ".rel"); + strcat(relocname, base->name); - sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0); - free(relaname); + sec = elf_create_section(elf, relocname, sizeof(GElf_Rel), 0); + free(relocname); if (!sec) return NULL; - base->rela = sec; + base->reloc = sec; sec->base = base; - sec->sh.sh_type = SHT_RELA; + sec->sh.sh_type = SHT_REL; sec->sh.sh_addralign = 8; sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; sec->sh.sh_info = base->idx; @@ -749,42 +784,125 @@ struct section *elf_create_rela_section(struct elf *elf, struct section *base) return sec; } -int elf_rebuild_rela_section(struct elf *elf, struct section *sec) +static struct section *elf_create_rela_reloc_section(struct elf *elf, struct section *base) { - struct rela *rela; - int nr, idx = 0, size; - GElf_Rela *relas; + char *relocname; + struct section *sec; - nr = 0; - list_for_each_entry(rela, &sec->rela_list, list) - nr++; + relocname = malloc(strlen(base->name) + strlen(".rela") + 1); + if (!relocname) { + perror("malloc"); + return NULL; + } + strcpy(relocname, ".rela"); + strcat(relocname, base->name); + + sec = elf_create_section(elf, relocname, sizeof(GElf_Rela), 0); + free(relocname); + if (!sec) + return NULL; - size = nr * sizeof(*relas); - relas = malloc(size); - if (!relas) { + base->reloc = sec; + sec->base = base; + + sec->sh.sh_type = SHT_RELA; + sec->sh.sh_addralign = 8; + sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; + sec->sh.sh_info = base->idx; + sec->sh.sh_flags = SHF_INFO_LINK; + + return sec; +} + +struct section *elf_create_reloc_section(struct elf *elf, + struct section *base, + int reltype) +{ + switch (reltype) { + case SHT_REL: return elf_create_rel_reloc_section(elf, base); + case SHT_RELA: return elf_create_rela_reloc_section(elf, base); + default: return NULL; + } +} + +static int elf_rebuild_rel_reloc_section(struct section *sec, int nr) +{ + struct reloc *reloc; + int idx = 0, size; + GElf_Rel *relocs; + + /* Allocate a buffer for relocations */ + size = nr * sizeof(*relocs); + relocs = malloc(size); + if (!relocs) { perror("malloc"); return -1; } - sec->changed = true; - elf->changed = true; + sec->data->d_buf = relocs; + sec->data->d_size = size; + + sec->sh.sh_size = size; + + idx = 0; + list_for_each_entry(reloc, &sec->reloc_list, list) { + relocs[idx].r_offset = reloc->offset; + relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + idx++; + } + + return 0; +} + +static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) +{ + struct reloc *reloc; + int idx = 0, size; + GElf_Rela *relocs; + + /* Allocate a buffer for relocations with addends */ + size = nr * sizeof(*relocs); + relocs = malloc(size); + if (!relocs) { + perror("malloc"); + return -1; + } - sec->data->d_buf = relas; + sec->data->d_buf = relocs; sec->data->d_size = size; sec->sh.sh_size = size; idx = 0; - list_for_each_entry(rela, &sec->rela_list, list) { - relas[idx].r_offset = rela->offset; - relas[idx].r_addend = rela->addend; - relas[idx].r_info = GELF_R_INFO(rela->sym->idx, rela->type); + list_for_each_entry(reloc, &sec->reloc_list, list) { + relocs[idx].r_offset = reloc->offset; + relocs[idx].r_addend = reloc->addend; + relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); idx++; } return 0; } +int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) +{ + struct reloc *reloc; + int nr; + + sec->changed = true; + elf->changed = true; + + nr = 0; + list_for_each_entry(reloc, &sec->reloc_list, list) + nr++; + + switch (sec->sh.sh_type) { + case SHT_REL: return elf_rebuild_rel_reloc_section(sec, nr); + case SHT_RELA: return elf_rebuild_rela_reloc_section(sec, nr); + default: return -1; + } +} + int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn) @@ -804,17 +922,27 @@ int elf_write_insn(struct elf *elf, struct section *sec, return 0; } -int elf_write_rela(struct elf *elf, struct rela *rela) +int elf_write_reloc(struct elf *elf, struct reloc *reloc) { - struct section *sec = rela->sec; + struct section *sec = reloc->sec; - rela->rela.r_info = GELF_R_INFO(rela->sym->idx, rela->type); - rela->rela.r_addend = rela->addend; - rela->rela.r_offset = rela->offset; + if (sec->sh.sh_type == SHT_REL) { + reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + reloc->rel.r_offset = reloc->offset; - if (!gelf_update_rela(sec->data, rela->idx, &rela->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; + if (!gelf_update_rel(sec->data, reloc->idx, &reloc->rel)) { + WARN_ELF("gelf_update_rel"); + return -1; + } + } else { + reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + reloc->rela.r_addend = reloc->addend; + reloc->rela.r_offset = reloc->offset; + + if (!gelf_update_rela(sec->data, reloc->idx, &reloc->rela)) { + WARN_ELF("gelf_update_rela"); + return -1; + } } elf->changed = true; @@ -862,7 +990,7 @@ void elf_close(struct elf *elf) { struct section *sec, *tmpsec; struct symbol *sym, *tmpsym; - struct rela *rela, *tmprela; + struct reloc *reloc, *tmpreloc; if (elf->elf) elf_end(elf->elf); @@ -876,10 +1004,10 @@ void elf_close(struct elf *elf) hash_del(&sym->hash); free(sym); } - list_for_each_entry_safe(rela, tmprela, &sec->rela_list, list) { - list_del(&rela->list); - hash_del(&rela->hash); - free(rela); + list_for_each_entry_safe(reloc, tmpreloc, &sec->reloc_list, list) { + list_del(&reloc->list); + hash_del(&reloc->hash); + free(reloc); } list_del(&sec->list); free(sec); diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 7324e772583e..6cc80a075166 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -32,8 +32,8 @@ struct section { GElf_Shdr sh; struct rb_root symbol_tree; struct list_head symbol_list; - struct list_head rela_list; - struct section *base, *rela; + struct list_head reloc_list; + struct section *base, *reloc; struct symbol *sym; Elf_Data *data; char *name; @@ -58,10 +58,13 @@ struct symbol { bool uaccess_safe; }; -struct rela { +struct reloc { struct list_head list; struct hlist_node hash; - GElf_Rela rela; + union { + GElf_Rela rela; + GElf_Rel rel; + }; struct section *sec; struct symbol *sym; unsigned long offset; @@ -84,7 +87,7 @@ struct elf { DECLARE_HASHTABLE(symbol_name_hash, ELF_HASH_BITS); DECLARE_HASHTABLE(section_hash, ELF_HASH_BITS); DECLARE_HASHTABLE(section_name_hash, ELF_HASH_BITS); - DECLARE_HASHTABLE(rela_hash, ELF_HASH_BITS); + DECLARE_HASHTABLE(reloc_hash, ELF_HASH_BITS); }; #define OFFSET_STRIDE_BITS 4 @@ -111,19 +114,19 @@ static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) return ol; } -static inline u32 rela_hash(struct rela *rela) +static inline u32 reloc_hash(struct reloc *reloc) { - return sec_offset_hash(rela->sec, rela->offset); + return sec_offset_hash(reloc->sec, reloc->offset); } struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, size_t entsize, int nr); -struct section *elf_create_rela_section(struct elf *elf, struct section *base); -void elf_add_rela(struct elf *elf, struct rela *rela); +struct section *elf_create_reloc_section(struct elf *elf, struct section *base, int reltype); +void elf_add_reloc(struct elf *elf, struct reloc *reloc); int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); -int elf_write_rela(struct elf *elf, struct rela *rela); +int elf_write_reloc(struct elf *elf, struct reloc *reloc); int elf_write(struct elf *elf); void elf_close(struct elf *elf); @@ -132,11 +135,11 @@ struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); -struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); -struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_func_containing(struct section *sec, unsigned long offset); -int elf_rebuild_rela_section(struct elf *elf, struct section *sec); +int elf_rebuild_reloc_section(struct elf *elf, struct section *sec); #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 4c37f80eb987..968f55e6dd94 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -80,56 +80,56 @@ int create_orc(struct objtool_file *file) return 0; } -static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relasec, +static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relocsec, unsigned int idx, struct section *insn_sec, unsigned long insn_off, struct orc_entry *o) { struct orc_entry *orc; - struct rela *rela; + struct reloc *reloc; /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc)); - /* populate rela for ip */ - rela = malloc(sizeof(*rela)); - if (!rela) { + /* populate reloc for ip */ + reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } - memset(rela, 0, sizeof(*rela)); + memset(reloc, 0, sizeof(*reloc)); if (insn_sec->sym) { - rela->sym = insn_sec->sym; - rela->addend = insn_off; + reloc->sym = insn_sec->sym; + reloc->addend = insn_off; } else { /* * The Clang assembler doesn't produce section symbols, so we * have to reference the function symbol instead: */ - rela->sym = find_symbol_containing(insn_sec, insn_off); - if (!rela->sym) { + reloc->sym = find_symbol_containing(insn_sec, insn_off); + if (!reloc->sym) { /* * Hack alert. This happens when we need to reference * the NOP pad insn immediately after the function. */ - rela->sym = find_symbol_containing(insn_sec, + reloc->sym = find_symbol_containing(insn_sec, insn_off - 1); } - if (!rela->sym) { + if (!reloc->sym) { WARN("missing symbol for insn at offset 0x%lx\n", insn_off); return -1; } - rela->addend = insn_off - rela->sym->offset; + reloc->addend = insn_off - reloc->sym->offset; } - rela->type = R_X86_64_PC32; - rela->offset = idx * sizeof(int); - rela->sec = ip_relasec; + reloc->type = R_X86_64_PC32; + reloc->offset = idx * sizeof(int); + reloc->sec = ip_relocsec; - elf_add_rela(elf, rela); + elf_add_reloc(elf, reloc); return 0; } @@ -137,7 +137,7 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti int create_orc_sections(struct objtool_file *file) { struct instruction *insn, *prev_insn; - struct section *sec, *u_sec, *ip_relasec; + struct section *sec, *u_sec, *ip_relocsec; unsigned int idx; struct orc_entry empty = { @@ -181,8 +181,8 @@ int create_orc_sections(struct objtool_file *file) if (!sec) return -1; - ip_relasec = elf_create_rela_section(file->elf, sec); - if (!ip_relasec) + ip_relocsec = elf_create_reloc_section(file->elf, sec, SHT_RELA); + if (!ip_relocsec) return -1; /* create .orc_unwind section */ @@ -200,7 +200,7 @@ int create_orc_sections(struct objtool_file *file) if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc, sizeof(struct orc_entry))) { - if (create_orc_entry(file->elf, u_sec, ip_relasec, idx, + if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, insn->sec, insn->offset, &insn->orc)) return -1; @@ -212,7 +212,7 @@ int create_orc_sections(struct objtool_file *file) /* section terminator */ if (prev_insn) { - if (create_orc_entry(file->elf, u_sec, ip_relasec, idx, + if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, prev_insn->sec, prev_insn->offset + prev_insn->len, &empty)) @@ -222,7 +222,7 @@ int create_orc_sections(struct objtool_file *file) } } - if (elf_rebuild_rela_section(file->elf, ip_relasec)) + if (elf_rebuild_reloc_section(file->elf, ip_relocsec)) return -1; return 0; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index e74e0189de22..e893f1e48e44 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -72,7 +72,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) { - struct rela *orig_rela, *new_rela; + struct reloc *orig_reloc, *new_reloc; unsigned long offset; offset = idx * entry->size; @@ -118,30 +118,30 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, } } - orig_rela = find_rela_by_dest(elf, sec, offset + entry->orig); - if (!orig_rela) { - WARN_FUNC("can't find orig rela", sec, offset + entry->orig); + orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); + if (!orig_reloc) { + WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_rela->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section rela symbol %s", - sec, offset + entry->orig, orig_rela->sym->name); + if (orig_reloc->sym->type != STT_SECTION) { + WARN_FUNC("don't know how to handle non-section reloc symbol %s", + sec, offset + entry->orig, orig_reloc->sym->name); return -1; } - alt->orig_sec = orig_rela->sym->sec; - alt->orig_off = orig_rela->addend; + alt->orig_sec = orig_reloc->sym->sec; + alt->orig_off = orig_reloc->addend; if (!entry->group || alt->new_len) { - new_rela = find_rela_by_dest(elf, sec, offset + entry->new); - if (!new_rela) { - WARN_FUNC("can't find new rela", + new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); + if (!new_reloc) { + WARN_FUNC("can't find new reloc", sec, offset + entry->new); return -1; } - alt->new_sec = new_rela->sym->sec; - alt->new_off = (unsigned int)new_rela->addend; + alt->new_sec = new_reloc->sym->sec; + alt->new_off = (unsigned int)new_reloc->addend; /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 0a6e75b8777a..28a5d0c18b1d 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -56,7 +56,7 @@ struct auxtrace_record struct perf_pmu *cs_etm_pmu; struct evsel *evsel; bool found_etm = false; - bool found_spe = false; + struct perf_pmu *found_spe = NULL; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; int i = 0; @@ -74,12 +74,12 @@ struct auxtrace_record evsel->core.attr.type == cs_etm_pmu->type) found_etm = true; - if (!nr_spes) + if (!nr_spes || found_spe) continue; for (i = 0; i < nr_spes; i++) { if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = true; + found_spe = arm_spe_pmus[i]; break; } } @@ -96,7 +96,7 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); #endif /* diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 839ef52c1ac2..6ce451293634 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -641,6 +641,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq = 0; evsel->core.attr.sample_period = 1; + evsel->no_aux_samples = true; intel_pt_evsel = evsel; opts->full_auxtrace = true; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e108d90ae2ed..a37e7910e9e9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -852,20 +852,20 @@ static int record__open(struct record *rec) * event synthesis. */ if (opts->initial_delay || target__has_cpu(&opts->target)) { - if (perf_evlist__add_dummy(evlist)) - return -ENOMEM; + pos = perf_evlist__get_tracking_event(evlist); + if (!evsel__is_dummy_event(pos)) { + /* Set up dummy event. */ + if (perf_evlist__add_dummy(evlist)) + return -ENOMEM; + pos = evlist__last(evlist); + perf_evlist__set_tracking_event(evlist, pos); + } - /* Disable tracking of mmaps on lead event. */ - pos = evlist__first(evlist); - pos->tracking = 0; - /* Set up dummy event. */ - pos = evlist__last(evlist); - pos->tracking = 1; /* * Enable the dummy event when the process is forked for * initial_delay, immediately for system wide. */ - if (opts->initial_delay) + if (opts->initial_delay && !pos->immediate) pos->core.attr.enable_on_exec = 1; else pos->immediate = 1; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 181d65e5a450..447457786362 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -462,7 +462,7 @@ static int perf_evsel__check_attr(struct evsel *evsel, struct perf_session *sess return -EINVAL; if (PRINT_FIELD(IREGS) && - evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS)) + evsel__do_check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS, allow_user_set)) return -EINVAL; if (PRINT_FIELD(UREGS) && diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json index 2df2e231e9ee..24c4ba2a9ae5 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json @@ -380,7 +380,7 @@ { "Unit": "CPU-M-CF", "EventCode": "265", - "EventName": "DFLT_CCERROR", + "EventName": "DFLT_CCFINISH", "BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2", "PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2" }, diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 7bd73a904b4e..d187e46c2683 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -1055,7 +1055,7 @@ def cbr(id, raw_buf): cbr = data[0] MHz = (data[4] + 500) / 1000 percent = ((cbr * 1000 / data[2]) + 5) / 10 - value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent) + value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, int(MHz), 4, int(percent)) cbr_file.write(value) def mwait(id, raw_buf): diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 26d7be785288..7daa8bb70a5a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -768,7 +768,8 @@ class CallGraphModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " GROUP BY comm_id, thread_id, call_path_id" " ORDER BY comm_id, thread_id, call_path_id") @@ -963,7 +964,8 @@ class CallTreeModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " ORDER BY comm_id, thread_id, call_time, calls.id") def FindPath(self, query): @@ -1050,6 +1052,7 @@ class TreeWindowBase(QMdiSubWindow): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break @@ -1127,6 +1130,7 @@ class CallTreeWindow(TreeWindowBase): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break @@ -1139,6 +1143,7 @@ class CallTreeWindow(TreeWindowBase): return last_child = None for row in xrange(n): + self.view.setExpanded(parent, True) child = self.model.index(row, 0, parent) child_call_time = child.internalPointer().call_time if child_call_time < time: @@ -1151,9 +1156,11 @@ class CallTreeWindow(TreeWindowBase): if not last_child: if not found: child = self.model.index(0, 0, parent) + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) return found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(last_child) parent = last_child diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py index 61f3be9add6b..65780013f745 100755 --- a/tools/perf/scripts/python/flamegraph.py +++ b/tools/perf/scripts/python/flamegraph.py @@ -17,6 +17,7 @@ from __future__ import print_function import sys import os +import io import argparse import json @@ -81,7 +82,7 @@ class FlameGraphCLI: if self.args.format == "html": try: - with open(self.args.template) as f: + with io.open(self.args.template, encoding="utf-8") as f: output_str = f.read().replace("/** @flamegraph_json **/", json_str) except IOError as e: @@ -93,11 +94,12 @@ class FlameGraphCLI: output_fn = self.args.output or "stacks.json" if output_fn == "-": - sys.stdout.write(output_str) + with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out: + out.write(output_str) else: print("dumping data to {}".format(output_fn)) try: - with open(output_fn, "w") as out: + with io.open(output_fn, "w", encoding="utf-8") as out: out.write(output_str) except IOError as e: print("Error writing output file: {}".format(e), file=sys.stderr) diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 63a91ec473bb..045723b3d992 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,8 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - $perf_tool record -o $trace_file -g -z -F 5000 -- \ + [[ "$(uname -m)" != s390x ]] && gflag='-g' + $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index f98a118dfc49..be9c4c0549bc 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2288,6 +2288,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser return browser->he_selection->thread; } +static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser) +{ + return browser->he_selection ? browser->he_selection->res_samples : NULL; +} + /* Check whether the browser is for 'top' or 'report' */ static inline bool is_report_browser(void *timer) { @@ -3357,16 +3362,16 @@ skip_annotation: &options[nr_options], NULL, NULL, evsel); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_NORMAL); + hist_browser__selected_res_sample(browser), + evsel, A_NORMAL); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_ASM); + hist_browser__selected_res_sample(browser), + evsel, A_ASM); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_SOURCE); + hist_browser__selected_res_sample(browser), + evsel, A_SOURCE); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: @@ -3598,6 +3603,23 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist, hbt, warn_lost_event); } +static bool perf_evlist__single_entry(struct evlist *evlist) +{ + int nr_entries = evlist->core.nr_entries; + + if (nr_entries == 1) + return true; + + if (nr_entries == 2) { + struct evsel *last = evlist__last(evlist); + + if (evsel__is_dummy_event(last)) + return true; + } + + return false; +} + int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, @@ -3608,7 +3630,7 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, int nr_entries = evlist->core.nr_entries; single_entry: - if (nr_entries == 1) { + if (perf_evlist__single_entry(evlist)) { struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 173b4f0e0e6e..ab48be4cf258 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1566,6 +1566,18 @@ void perf_evlist__to_front(struct evlist *evlist, list_splice(&move, &evlist->core.entries); } +struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->tracking) + return evsel; + } + + return evlist__first(evlist); +} + void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b6f325dfb4d2..a8081dfc19cf 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -335,6 +335,7 @@ void perf_evlist__to_front(struct evlist *evlist, evlist__cpu_iter_start(evlist); \ perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) +struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist); void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 96e5171dce41..ef802f6d40c1 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -898,12 +898,6 @@ static void evsel__apply_config_terms(struct evsel *evsel, } } -static bool is_dummy_event(struct evsel *evsel) -{ - return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && - (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); -} - struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type) { struct evsel_config_term *term, *found_term = NULL; @@ -1020,12 +1014,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (callchain && callchain->enabled && !evsel->no_aux_samples) evsel__config_callchain(evsel, opts, callchain); - if (opts->sample_intr_regs) { + if (opts->sample_intr_regs && !evsel->no_aux_samples) { attr->sample_regs_intr = opts->sample_intr_regs; evsel__set_sample_bit(evsel, REGS_INTR); } - if (opts->sample_user_regs) { + if (opts->sample_user_regs && !evsel->no_aux_samples) { attr->sample_regs_user |= opts->sample_user_regs; evsel__set_sample_bit(evsel, REGS_USER); } @@ -1161,7 +1155,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, * The software event will trigger -EOPNOTSUPP error out, * if BRANCH_STACK bit is set. */ - if (is_dummy_event(evsel)) + if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0f963c2a88a5..35e3f6d66085 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -399,6 +399,12 @@ static inline bool evsel__has_br_stack(const struct evsel *evsel) evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK; } +static inline bool evsel__is_dummy_event(struct evsel *evsel) +{ + return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && + (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); +} + struct perf_env *evsel__env(struct evsel *evsel); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index df59fd4fc95b..e0af36b0e5d8 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -11,14 +11,18 @@ #include <stdbool.h> #include <stddef.h> #include <limits.h> -#ifndef __WORDSIZE -#define __WORDSIZE (__SIZEOF_LONG__ * 8) -#endif static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ - return (h * 11400714819323198485llu) >> (__WORDSIZE - bits); +#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) + /* LP64 case */ + return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); +#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__) + return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits); +#else +# error "Unsupported size_t size" +#endif } typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index e4dd8bf610ce..cb3c1e569a2d 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1735,6 +1735,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) u64 sample_type = evsel->core.attr.sample_type; u64 id = evsel->core.id[0]; u8 cpumode; + u64 regs[8 * sizeof(sample.intr_regs.mask)]; if (intel_pt_skip_event(pt)) return 0; @@ -1784,8 +1785,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) } if (sample_type & PERF_SAMPLE_REGS_INTR && - items->mask[INTEL_PT_GP_REGS_POS]) { - u64 regs[sizeof(sample.intr_regs.mask)]; + (items->mask[INTEL_PT_GP_REGS_POS] || + items->mask[INTEL_PT_XMM_POS])) { u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index 6e04304560ca..c3b56db8b921 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -285,7 +285,7 @@ struct cpufreq_available_governors *cpufreq_get_available_governors(unsigned } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -362,7 +362,7 @@ struct cpufreq_available_frequencies } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -418,7 +418,7 @@ struct cpufreq_available_frequencies } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -493,7 +493,7 @@ static struct cpufreq_affected_cpus *sysfs_get_cpu_list(unsigned int cpu, } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -726,7 +726,7 @@ struct cpufreq_stats *cpufreq_get_stats(unsigned int cpu, } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1 index 80a1311fa747..20b6345c53ad 100644 --- a/tools/power/cpupower/man/cpupower-idle-info.1 +++ b/tools/power/cpupower/man/cpupower-idle-info.1 @@ -75,7 +75,7 @@ By default only values of core zero are displayed. How to display settings of other cores is described in the cpupower(1) manpage in the \-\-cpu option section. .SH REFERENCES -http://www.acpi.info/spec.htm +https://uefi.org/specifications .SH "FILES" .nf \fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1 index 70a56476f4b0..8ee737eefa5c 100644 --- a/tools/power/cpupower/man/cpupower-monitor.1 +++ b/tools/power/cpupower/man/cpupower-monitor.1 @@ -170,7 +170,7 @@ displayed. .SH REFERENCES "BIOS and Kernel Developer’s Guide (BKDG) for AMD Family 14h Processors" -http://support.amd.com/us/Processor_TechDocs/43170.pdf +https://support.amd.com/us/Processor_TechDocs/43170.pdf "Intel® Turbo Boost Technology in Intel® Core™ Microarchitecture (Nehalem) Based Processors" @@ -178,7 +178,7 @@ http://download.intel.com/design/processor/applnots/320354.pdf "Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals +https://www.intel.com/products/processor/manuals .SH FILES .ta diff --git a/tools/power/cpupower/utils/helpers/bitmask.c b/tools/power/cpupower/utils/helpers/bitmask.c index 6c7932f5bd66..649d87cb8b0f 100644 --- a/tools/power/cpupower/utils/helpers/bitmask.c +++ b/tools/power/cpupower/utils/helpers/bitmask.c @@ -26,11 +26,11 @@ struct bitmask *bitmask_alloc(unsigned int n) struct bitmask *bmp; bmp = malloc(sizeof(*bmp)); - if (bmp == 0) + if (!bmp) return 0; bmp->size = n; bmp->maskp = calloc(longsperbits(n), sizeof(unsigned long)); - if (bmp->maskp == 0) { + if (!bmp->maskp) { free(bmp); return 0; } @@ -40,7 +40,7 @@ struct bitmask *bitmask_alloc(unsigned int n) /* Free `struct bitmask` */ void bitmask_free(struct bitmask *bmp) { - if (bmp == 0) + if (!bmp) return; free(bmp->maskp); bmp->maskp = (unsigned long *)0xdeadcdef; /* double free tripwire */ diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README index afe6beb40ad9..89d0a7dab4bc 100644 --- a/tools/power/pm-graph/README +++ b/tools/power/pm-graph/README @@ -6,7 +6,7 @@ |_| |___/ |_| pm-graph: suspend/resume/boot timing analysis tools - Version: 5.6 + Version: 5.7 Author: Todd Brandt <todd.e.brandt@intel.com> Home Page: https://01.org/pm-graph diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 602e64b68ba7..46ff97e909c6 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -81,7 +81,7 @@ def ascii(text): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.6' + version = '5.7' ansi = False rs = 0 display = '' @@ -198,7 +198,7 @@ class SystemValues: 'suspend_console': {}, 'acpi_pm_prepare': {}, 'syscore_suspend': {}, - 'arch_thaw_secondary_cpus_end': {}, + 'arch_enable_nonboot_cpus_end': {}, 'syscore_resume': {}, 'acpi_pm_finish': {}, 'resume_console': {}, @@ -924,10 +924,7 @@ class SystemValues: tp = TestProps() tf = self.openlog(self.ftracefile, 'r') for line in tf: - # determine the trace data type (required for further parsing) - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) + if tp.stampInfo(line, self): continue # parse only valid lines, if this is not one move on m = re.match(tp.ftrace_line_fmt, line) @@ -1244,8 +1241,8 @@ class DevProps: if self.xtraclass: return ' '+self.xtraclass if self.isasync: - return ' async_device' - return ' sync_device' + return ' (async)' + return ' (sync)' # Class: DeviceNode # Description: @@ -1301,6 +1298,7 @@ class Data: 'FAIL' : r'(?i).*\bFAILED\b.*', 'INVALID' : r'(?i).*\bINVALID\b.*', 'CRASH' : r'(?i).*\bCRASHED\b.*', + 'TIMEOUT' : r'(?i).*\bTIMEOUT\b.*', 'IRQ' : r'.*\bgenirq: .*', 'TASKFAIL': r'.*Freezing of tasks *.*', 'ACPI' : r'.*\bACPI *(?P<b>[A-Za-z]*) *Error[: ].*', @@ -1358,11 +1356,11 @@ class Data: if self.dmesg[p]['order'] == order: return p return '' - def lastPhase(self): + def lastPhase(self, depth=1): plist = self.sortedPhases() - if len(plist) < 1: + if len(plist) < depth: return '' - return plist[-1] + return plist[-1*depth] def turbostatInfo(self): tp = TestProps() out = {'syslpi':'N/A','pkgpc10':'N/A'} @@ -1382,9 +1380,12 @@ class Data: if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf = sysvals.openlog(sysvals.dmesgfile, 'r') i = 0 + tp = TestProps() list = [] for line in lf: i += 1 + if tp.stampInfo(line, sysvals): + continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if not m: continue @@ -1400,15 +1401,15 @@ class Data: list.append((msg, err, dir, t, i, i)) self.kerror = True break - msglist = [] + tp.msglist = [] for msg, type, dir, t, idx1, idx2 in list: - msglist.append(msg) + tp.msglist.append(msg) self.errorinfo[dir].append((type, t, idx1, idx2)) if self.kerror: sysvals.dmesglog = True if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf.close() - return msglist + return tp def setStart(self, time, msg=''): self.start = time if msg: @@ -1623,6 +1624,8 @@ class Data: if('src' in d): for e in d['src']: e.time = self.trimTimeVal(e.time, t0, dT, left) + e.end = self.trimTimeVal(e.end, t0, dT, left) + e.length = e.end - e.time for dir in ['suspend', 'resume']: list = [] for e in self.errorinfo[dir]: @@ -1640,7 +1643,12 @@ class Data: if tL > 0: left = True if tR > tZero else False self.trimTime(tS, tL, left) - self.tLow.append('%.0f'%(tL*1000)) + if 'trying' in self.dmesg[lp] and self.dmesg[lp]['trying'] >= 0.001: + tTry = round(self.dmesg[lp]['trying'] * 1000) + text = '%.0f (-%.0f waking)' % (tL * 1000, tTry) + else: + text = '%.0f' % (tL * 1000) + self.tLow.append(text) lp = phase def getMemTime(self): if not self.hwstart or not self.hwend: @@ -1776,7 +1784,7 @@ class Data: length = -1.0 if(start >= 0 and end >= 0): length = end - start - if pid == -2: + if pid == -2 or name not in sysvals.tracefuncs.keys(): i = 2 origname = name while(name in list): @@ -1789,6 +1797,15 @@ class Data: if color: list[name]['color'] = color return name + def findDevice(self, phase, name): + list = self.dmesg[phase]['list'] + mydev = '' + for devname in sorted(list): + if name == devname or re.match('^%s\[(?P<num>[0-9]*)\]$' % name, devname): + mydev = devname + if mydev: + return list[mydev] + return False def deviceChildren(self, devname, phase): devlist = [] list = self.dmesg[phase]['list'] @@ -2779,6 +2796,7 @@ class TestProps: testerrfmt = '^# enter_sleep_error (?P<e>.*)' sysinfofmt = '^# sysinfo .*' cmdlinefmt = '^# command \| (?P<cmd>.*)' + kparamsfmt = '^# kparams \| (?P<kp>.*)' devpropfmt = '# Device Properties: .*' pinfofmt = '# platform-(?P<val>[a-z,A-Z,0-9]*): (?P<info>.*)' tracertypefmt = '# tracer: (?P<t>.*)' @@ -2790,8 +2808,9 @@ class TestProps: '[ +!#\*@$]*(?P<dur>[0-9\.]*) .*\| (?P<msg>.*)' ftrace_line_fmt_nop = \ ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\[(?P<cpu>[0-9]*)\] *'+\ - '(?P<flags>.{4}) *(?P<time>[0-9\.]*): *'+\ + '(?P<flags>\S*) *(?P<time>[0-9\.]*): *'+\ '(?P<msg>.*)' + machinesuspend = 'machine_suspend\[.*' def __init__(self): self.stamp = '' self.sysinfo = '' @@ -2812,16 +2831,13 @@ class TestProps: self.ftrace_line_fmt = self.ftrace_line_fmt_nop else: doError('Invalid tracer format: [%s]' % tracer) - def stampInfo(self, line): + def stampInfo(self, line, sv): if re.match(self.stampfmt, line): self.stamp = line return True elif re.match(self.sysinfofmt, line): self.sysinfo = line return True - elif re.match(self.cmdlinefmt, line): - self.cmdline = line - return True elif re.match(self.tstatfmt, line): self.turbostat.append(line) return True @@ -2834,6 +2850,20 @@ class TestProps: elif re.match(self.firmwarefmt, line): self.fwdata.append(line) return True + elif(re.match(self.devpropfmt, line)): + self.parseDevprops(line, sv) + return True + elif(re.match(self.pinfofmt, line)): + self.parsePlatformInfo(line, sv) + return True + m = re.match(self.cmdlinefmt, line) + if m: + self.cmdline = m.group('cmd') + return True + m = re.match(self.tracertypefmt, line) + if(m): + self.setTracerType(m.group('t')) + return True return False def parseStamp(self, data, sv): # global test data @@ -2858,9 +2888,13 @@ class TestProps: data.stamp[key] = val sv.hostname = data.stamp['host'] sv.suspendmode = data.stamp['mode'] + if sv.suspendmode == 'freeze': + self.machinesuspend = 'timekeeping_freeze\[.*' + else: + self.machinesuspend = 'machine_suspend\[.*' if sv.suspendmode == 'command' and sv.ftracefile != '': modes = ['on', 'freeze', 'standby', 'mem', 'disk'] - fp = sysvals.openlog(sv.ftracefile, 'r') + fp = sv.openlog(sv.ftracefile, 'r') for line in fp: m = re.match('.* machine_suspend\[(?P<mode>.*)\]', line) if m and m.group('mode') in ['1', '2', '3', '4']: @@ -2868,9 +2902,7 @@ class TestProps: data.stamp['mode'] = sv.suspendmode break fp.close() - m = re.match(self.cmdlinefmt, self.cmdline) - if m: - sv.cmdline = m.group('cmd') + sv.cmdline = self.cmdline if not sv.stamp: sv.stamp = data.stamp # firmware data @@ -3052,20 +3084,7 @@ def appendIncompleteTraceLog(testruns): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - if tp.stampInfo(line): - continue - # determine the trace data type (required for further parsing) - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) - continue - # device properties line - if(re.match(tp.devpropfmt, line)): - tp.parseDevprops(line, sysvals) - continue - # platform info line - if(re.match(tp.pinfofmt, line)): - tp.parsePlatformInfo(line, sysvals) + if tp.stampInfo(line, sysvals): continue # parse only valid lines, if this is not one move on m = re.match(tp.ftrace_line_fmt, line) @@ -3166,33 +3185,19 @@ def parseTraceLog(live=False): if sysvals.usekprobes: tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend', 'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', - 'CPU_OFF', 'timekeeping_freeze', 'acpi_suspend'] + 'CPU_OFF', 'acpi_suspend'] # extract the callgraph and traceevent data + s2idle_enter = hwsus = False tp = TestProps() - testruns = [] - testdata = [] - testrun = 0 - data, limbo = 0, True + testruns, testdata = [], [] + testrun, data, limbo = 0, 0, True tf = sysvals.openlog(sysvals.ftracefile, 'r') phase = 'suspend_prepare' for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - if tp.stampInfo(line): - continue - # tracer type line: determine the trace data type - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) - continue - # device properties line - if(re.match(tp.devpropfmt, line)): - tp.parseDevprops(line, sysvals) - continue - # platform info line - if(re.match(tp.pinfofmt, line)): - tp.parsePlatformInfo(line, sysvals) + if tp.stampInfo(line, sysvals): continue # ignore all other commented lines if line[0] == '#': @@ -3303,16 +3308,29 @@ def parseTraceLog(live=False): phase = data.setPhase('suspend_noirq', t.time, isbegin) continue # suspend_machine/resume_machine - elif(re.match('machine_suspend\[.*', t.name)): + elif(re.match(tp.machinesuspend, t.name)): + lp = data.lastPhase() if(isbegin): - lp = data.lastPhase() + hwsus = True if lp.startswith('resume_machine'): - data.dmesg[lp]['end'] = t.time + # trim out s2idle loops, track time trying to freeze + llp = data.lastPhase(2) + if llp.startswith('suspend_machine'): + if 'trying' not in data.dmesg[llp]: + data.dmesg[llp]['trying'] = 0 + data.dmesg[llp]['trying'] += \ + t.time - data.dmesg[lp]['start'] + data.currphase = '' + del data.dmesg[lp] + continue phase = data.setPhase('suspend_machine', data.dmesg[lp]['end'], True) data.setPhase(phase, t.time, False) if data.tSuspended == 0: data.tSuspended = t.time else: + if lp.startswith('resume_machine'): + data.dmesg[lp]['end'] = t.time + continue phase = data.setPhase('resume_machine', t.time, True) if(sysvals.suspendmode in ['mem', 'disk']): susp = phase.replace('resume', 'suspend') @@ -3343,6 +3361,19 @@ def parseTraceLog(live=False): # global events (outside device calls) are graphed if(name not in testrun.ttemp): testrun.ttemp[name] = [] + # special handling for s2idle_enter + if name == 'machine_suspend': + if hwsus: + s2idle_enter = hwsus = False + elif s2idle_enter and not isbegin: + if(len(testrun.ttemp[name]) > 0): + testrun.ttemp[name][-1]['end'] = t.time + testrun.ttemp[name][-1]['loop'] += 1 + elif not s2idle_enter and isbegin: + s2idle_enter = True + testrun.ttemp[name].append({'begin': t.time, + 'end': t.time, 'pid': pid, 'loop': 0}) + continue if(isbegin): # create a new list entry testrun.ttemp[name].append(\ @@ -3374,9 +3405,8 @@ def parseTraceLog(live=False): if(not m): continue n = m.group('d') - list = data.dmesg[phase]['list'] - if(n in list): - dev = list[n] + dev = data.findDevice(phase, n) + if dev: dev['length'] = t.time - dev['start'] dev['end'] = t.time # kprobe event processing @@ -3479,7 +3509,12 @@ def parseTraceLog(live=False): # add actual trace funcs for name in sorted(test.ttemp): for event in test.ttemp[name]: - data.newActionGlobal(name, event['begin'], event['end'], event['pid']) + if event['end'] - event['begin'] <= 0: + continue + title = name + if name == 'machine_suspend' and 'loop' in event: + title = 's2idle_enter_%dx' % event['loop'] + data.newActionGlobal(title, event['begin'], event['end'], event['pid']) # add the kprobe based virtual tracefuncs as actual devices for key in sorted(tp.ktemp): name, pid = key @@ -3548,8 +3583,9 @@ def parseTraceLog(live=False): for p in sorted(phasedef, key=lambda k:phasedef[k]['order']): if p not in data.dmesg: if not terr: - pprint('TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)) - terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp) + ph = p if 'machine' in p else lp + terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, ph) + pprint('TEST%s FAILED: %s' % (tn, terr)) error.append(terr) if data.tSuspended == 0: data.tSuspended = data.dmesg[lp]['end'] @@ -3611,7 +3647,7 @@ def loadKernelLog(): idx = line.find('[') if idx > 1: line = line[idx:] - if tp.stampInfo(line): + if tp.stampInfo(line, sysvals): continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if(not m): @@ -3959,18 +3995,20 @@ def addCallgraphs(sv, hf, data): if sv.cgphase and p != sv.cgphase: continue list = data.dmesg[p]['list'] - for devname in data.sortedDevices(p): - if len(sv.cgfilter) > 0 and devname not in sv.cgfilter: + for d in data.sortedDevices(p): + if len(sv.cgfilter) > 0 and d not in sv.cgfilter: continue - dev = list[devname] + dev = list[d] color = 'white' if 'color' in data.dmesg[p]: color = data.dmesg[p]['color'] if 'color' in dev: color = dev['color'] - name = devname - if(devname in sv.devprops): - name = sv.devprops[devname].altName(devname) + name = d if '[' not in d else d.split('[')[0] + if(d in sv.devprops): + name = sv.devprops[d].altName(d) + if 'drv' in dev and dev['drv']: + name += ' {%s}' % dev['drv'] if sv.suspendmode in suspendmodename: name += ' '+p if('ftrace' in dev): @@ -4517,12 +4555,9 @@ def createHTML(testruns, testfail): # draw the devices for this phase phaselist = data.dmesg[b]['list'] for d in sorted(data.tdevlist[b]): - name = d - drv = '' - dev = phaselist[d] - xtraclass = '' - xtrainfo = '' - xtrastyle = '' + dname = d if '[' not in d else d.split('[')[0] + name, dev = dname, phaselist[d] + drv = xtraclass = xtrainfo = xtrastyle = '' if 'htmlclass' in dev: xtraclass = dev['htmlclass'] if 'color' in dev: @@ -4553,7 +4588,7 @@ def createHTML(testruns, testfail): title += b devtl.html += devtl.html_device.format(dev['id'], \ title, left, top, '%.3f'%rowheight, width, \ - d+drv, xtraclass, xtrastyle) + dname+drv, xtraclass, xtrastyle) if('cpuexec' in dev): for t in sorted(dev['cpuexec']): start, end = t @@ -4571,6 +4606,8 @@ def createHTML(testruns, testfail): continue # draw any trace events for this device for e in dev['src']: + if e.length == 0: + continue height = '%.3f' % devtl.rowH top = '%.3f' % (rowtop + devtl.scaleH + (e.row*devtl.rowH)) left = '%f' % (((e.time-m0)*100)/mTotal) @@ -5876,7 +5913,7 @@ def getArgFloat(name, args, min, max, main=True): def processData(live=False, quiet=False): if not quiet: - pprint('PROCESSING DATA') + pprint('PROCESSING: %s' % sysvals.htmlfile) sysvals.vprint('usetraceevents=%s, usetracemarkers=%s, usekprobes=%s' % \ (sysvals.usetraceevents, sysvals.usetracemarkers, sysvals.usekprobes)) error = '' @@ -5928,7 +5965,7 @@ def processData(live=False, quiet=False): sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) createHTML(testruns, error) if not quiet: - pprint('DONE') + pprint('DONE: %s' % sysvals.htmlfile) data = testruns[0] stamp = data.stamp stamp['suspend'], stamp['resume'] = data.getTimeValues() @@ -5984,25 +6021,27 @@ def runTest(n=0, quiet=False): return 0 def find_in_html(html, start, end, firstonly=True): - n, cnt, out = 0, len(html), [] - while n < cnt: - e = cnt if (n + 10000 > cnt or n == 0) else n + 10000 - m = re.search(start, html[n:e]) - if not m: - break - i = m.end() - m = re.search(end, html[n+i:e]) + cnt, out, list = len(html), [], [] + if firstonly: + m = re.search(start, html) + if m: + list.append(m) + else: + list = re.finditer(start, html) + for match in list: + s = match.end() + e = cnt if (len(out) < 1 or s + 10000 > cnt) else s + 10000 + m = re.search(end, html[s:e]) if not m: break - j = m.start() - str = html[n+i:n+i+j] + e = s + m.start() + str = html[s:e] if end == 'ms': num = re.search(r'[-+]?\d*\.\d+|\d+', str) str = num.group() if num else 'NaN' if firstonly: return str out.append(str) - n += i+j if firstonly: return '' return out @@ -6034,7 +6073,7 @@ def data_from_html(file, outpath, issues, fulldetail=False): else: result = 'pass' # extract error info - ilist = [] + tp, ilist = False, [] extra = dict() log = find_in_html(html, '<div id="dmesglog" style="display:none;">', '</div>').strip() @@ -6042,8 +6081,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): d = Data(0) d.end = 999999999 d.dmesgtext = log.split('\n') - msglist = d.extractErrorInfo() - for msg in msglist: + tp = d.extractErrorInfo() + for msg in tp.msglist: sysvals.errorSummary(issues, msg) if stmp[2] == 'freeze': extra = d.turbostatInfo() @@ -6059,8 +6098,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): if wifi: extra['wifi'] = wifi low = find_in_html(html, 'freeze time: <b>', ' ms</b>') - if low and '|' in low: - issue = 'FREEZEx%d' % len(low.split('|')) + if low and 'waking' in low: + issue = 'FREEZEWAKE' match = [i for i in issues if i['match'] == issue] if len(match) > 0: match[0]['count'] += 1 @@ -6126,6 +6165,11 @@ def data_from_html(file, outpath, issues, fulldetail=False): data[key] = extra[key] if fulldetail: data['funclist'] = find_in_html(html, '<div title="', '" class="traceevent"', False) + if tp: + for arg in ['-multi ', '-info ']: + if arg in tp.cmdline: + data['target'] = tp.cmdline[tp.cmdline.find(arg):].split()[1] + break return data def genHtml(subdir, force=False): @@ -6155,8 +6199,7 @@ def runSummary(subdir, local=True, genhtml=False): pprint('Generating a summary of folder:\n %s' % inpath) if genhtml: genHtml(subdir) - issues = [] - testruns = [] + target, issues, testruns = '', [], [] desc = {'host':[],'mode':[],'kernel':[]} for dirname, dirnames, filenames in os.walk(subdir): for filename in filenames: @@ -6165,6 +6208,8 @@ def runSummary(subdir, local=True, genhtml=False): data = data_from_html(os.path.join(dirname, filename), outpath, issues) if(not data): continue + if 'target' in data: + target = data['target'] testruns.append(data) for key in desc: if data[key] not in desc[key]: @@ -6172,6 +6217,8 @@ def runSummary(subdir, local=True, genhtml=False): pprint('Summary files:') if len(desc['host']) == len(desc['mode']) == len(desc['kernel']) == 1: title = '%s %s %s' % (desc['host'][0], desc['kernel'][0], desc['mode'][0]) + if target: + title += ' %s' % target else: title = inpath createHTMLSummarySimple(testruns, os.path.join(outpath, 'summary.html'), title) diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 9f68f51ca652..9f4b190f1d74 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.4"; +static const char *version_str = "v1.5"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -44,6 +44,9 @@ static int force_online_offline; static int auto_mode; static int fact_enable_fail; +static int mbox_delay; +static int mbox_retries = 3; + /* clos related */ static int current_clos = -1; static int clos_epp = -1; @@ -198,7 +201,7 @@ int out_format_is_json(void) static int get_stored_topology_info(int cpu, int *core_id, int *pkg_id, int *die_id) { - const char *pathname = "/tmp/isst_cpu_topology.dat"; + const char *pathname = "/var/run/isst_cpu_topology.dat"; struct cpu_topology cpu_top; FILE *fp; int ret; @@ -230,7 +233,7 @@ err_ret: static void store_cpu_topology(void) { - const char *pathname = "/tmp/isst_cpu_topology.dat"; + const char *pathname = "/var/run/isst_cpu_topology.dat"; FILE *fp; int i; @@ -247,6 +250,8 @@ static void store_cpu_topology(void) return; } + fprintf(stderr, "Caching topology information\n"); + for (i = 0; i < topo_max_cpus; ++i) { struct cpu_topology cpu_top; @@ -734,7 +739,7 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, unsigned int req_data, unsigned int *resp) { const char *pathname = "/dev/isst_interface"; - int fd; + int fd, retry; struct isst_if_mbox_cmds mbox_cmds = { 0 }; debug_printf( @@ -786,29 +791,42 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, mbox_cmds.mbox_cmd[0].parameter = parameter; mbox_cmds.mbox_cmd[0].req_data = req_data; + if (mbox_delay) + usleep(mbox_delay * 1000); + fd = open(pathname, O_RDWR); if (fd < 0) err(-1, "%s open failed", pathname); - if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { - if (errno == ENOTTY) { - perror("ISST_IF_MBOX_COMMAND\n"); - fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n"); - exit(0); + retry = mbox_retries; + + do { + if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { + if (errno == ENOTTY) { + perror("ISST_IF_MBOX_COMMAND\n"); + fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n"); + exit(0); + } + debug_printf( + "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n", + cpu, command, sub_command, parameter, req_data, errno); + --retry; + } else { + *resp = mbox_cmds.mbox_cmd[0].resp_data; + debug_printf( + "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", + cpu, command, sub_command, parameter, req_data, *resp); + break; } - debug_printf( - "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n", - cpu, command, sub_command, parameter, req_data, errno); - return -1; - } else { - *resp = mbox_cmds.mbox_cmd[0].resp_data; - debug_printf( - "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", - cpu, command, sub_command, parameter, req_data, *resp); - } + } while (retry); close(fd); + if (!retry) { + debug_printf("Failed mbox command even after retries\n"); + return -1; + + } return 0; } @@ -1245,7 +1263,11 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, fprintf(stderr, "Option is set to online/offline\n"); ctdp_level.core_cpumask_size = alloc_cpu_set(&ctdp_level.core_cpumask); - isst_get_coremask_info(cpu, tdp_level, &ctdp_level); + ret = isst_get_coremask_info(cpu, tdp_level, &ctdp_level); + if (ret) { + isst_display_error_info_message(1, "Can't get coremask, online/offline option is ignored", 0, 0); + return; + } if (ctdp_level.cpu_count) { int i, max_cpus = get_topo_max_cpus(); for (i = 0; i < max_cpus; ++i) { @@ -2593,6 +2615,8 @@ static void usage(void) printf("\t[-i|--info] : Print platform information\n"); printf("\t[-o|--out] : Output file\n"); printf("\t\t\tDefault : stderr\n"); + printf("\t[-p|--pause] : Delay between two mail box commands in milliseconds\n"); + printf("\t[-r|--retry] : Retry count for mail box commands on failure, default 3\n"); printf("\t[-v|--version] : Print version\n"); printf("\nResult format\n"); @@ -2624,6 +2648,7 @@ static void print_version(void) static void cmdline(int argc, char **argv) { const char *pathname = "/dev/isst_interface"; + char *ptr; FILE *fp; int opt; int option_index = 0; @@ -2635,7 +2660,9 @@ static void cmdline(int argc, char **argv) { "format", required_argument, 0, 'f' }, { "help", no_argument, 0, 'h' }, { "info", no_argument, 0, 'i' }, + { "pause", required_argument, 0, 'p' }, { "out", required_argument, 0, 'o' }, + { "retry", required_argument, 0, 'r' }, { "version", no_argument, 0, 'v' }, { 0, 0, 0, 0 } }; @@ -2688,6 +2715,20 @@ static void cmdline(int argc, char **argv) fclose(outf); outf = fopen_or_exit(optarg, "w"); break; + case 'p': + ret = strtol(optarg, &ptr, 10); + if (!ret) + fprintf(stderr, "Invalid pause interval, ignore\n"); + else + mbox_delay = ret; + break; + case 'r': + ret = strtol(optarg, &ptr, 10); + if (!ret) + fprintf(stderr, "Invalid retry count, ignore\n"); + else + mbox_retries = ret; + break; case 'v': print_version(); break; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1195bd85af38..227ca78a5b7f 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -15,6 +15,7 @@ TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll TARGETS += firmware +TARGETS += fpu TARGETS += ftrace TARGETS += futex TARGETS += gpio diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index f7ee8fa377ad..6ccecbd39476 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -5,10 +5,60 @@ #include "test_btf_map_in_map.skel.h" +static int duration; + +static __u32 bpf_map_id(struct bpf_map *map) +{ + struct bpf_map_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + if (err) + return 0; + return info.id; +} + +/* + * Trigger synchronize_rcu() in kernel. + * + * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu() + * if looking up an existing non-NULL element or updating the map with a valid + * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map, + * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then + * cleanup. At the end, at least one synchronize_rcu() would be called. + */ +static int kern_sync_rcu(void) +{ + int inner_map_fd, outer_map_fd, err, zero = 0; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno)) + return -1; + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), inner_map_fd, 1, 0); + if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) { + close(inner_map_fd); + return -1; + } + + err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0); + if (err) + err = -errno; + CHECK(err, "outer_map_update", "failed %d\n", err); + close(inner_map_fd); + close(outer_map_fd); + return err; +} + void test_btf_map_in_map(void) { - int duration = 0, err, key = 0, val; - struct test_btf_map_in_map* skel; + int err, key = 0, val, i; + struct test_btf_map_in_map *skel; + int outer_arr_fd, outer_hash_fd; + int fd, map1_fd, map2_fd, map1_id, map2_id; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -18,32 +68,78 @@ void test_btf_map_in_map(void) if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; + map1_fd = bpf_map__fd(skel->maps.inner_map1); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + outer_arr_fd = bpf_map__fd(skel->maps.outer_arr); + outer_hash_fd = bpf_map__fd(skel->maps.outer_hash); + /* inner1 = input, inner2 = input + 1 */ - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0); skel->bss->input = 1; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); /* inner1 = input + 1, inner2 = input */ - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0); + bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0); skel->bss->input = 3; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + for (i = 0; i < 5; i++) { + val = i % 2 ? map1_fd : map2_fd; + err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + } + + map1_id = bpf_map_id(skel->maps.inner_map1); + map2_id = bpf_map_id(skel->maps.inner_map2); + CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); + CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); + + test_btf_map_in_map__destroy(skel); + skel = NULL; + + /* we need to either wait for or force synchronize_rcu(), before + * checking for "still exists" condition, otherwise map could still be + * resolvable by ID, causing false positives. + * + * Older kernels (5.8 and earlier) freed map only after two + * synchronize_rcu()s, so trigger two, to be entirely sure. + */ + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + + fd = bpf_map_get_fd_by_id(map1_id); + if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { + close(fd); + goto cleanup; + } + fd = bpf_map_get_fd_by_id(map2_id); + if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { + close(fd); + goto cleanup; + } + cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 83493bd5745c..109d0345a2be 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -36,7 +36,7 @@ void test_fentry_fexit(void) fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss; printf("%lld\n", fentry_skel->bss->test1_result); - for (i = 0; i < 6; i++) { + for (i = 0; i < 8; i++) { CHECK(fentry_res[i] != 1, "result", "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); CHECK(fexit_res[i] != 1, "result", diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ea14e3ece812..f11f187990e9 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -527,8 +527,8 @@ static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd) run_tests_skb_less(tap_fd, skel->maps.last_dissection); - err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); - CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno); + err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno); } static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 15cb554a66d8..172c586b6996 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -1,9 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Test that the flow_dissector program can be updated with a single - * syscall by attaching a new program that replaces the existing one. - * - * Corner case - the same program cannot be attached twice. + * Tests for attaching, detaching, and replacing flow_dissector BPF program. */ #define _GNU_SOURCE @@ -116,7 +113,7 @@ static void test_prog_attach_prog_attach(int netns, int prog1, int prog2) CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); out_detach: - err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog2, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); CHECK_FAIL(prog_is_attached(netns)); @@ -152,7 +149,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); int err, link; - err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(err)) { perror("bpf_prog_attach(prog1)"); return; @@ -168,7 +165,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) close(link); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); - err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); CHECK_FAIL(prog_is_attached(netns)); @@ -188,7 +185,7 @@ static void test_link_create_prog_attach(int netns, int prog1, int prog2) /* Expect failure attaching prog when link exists */ errno = 0; - err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(!err || errno != EEXIST)) perror("bpf_prog_attach(prog2) expected EEXIST"); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -211,7 +208,7 @@ static void test_link_create_prog_detach(int netns, int prog1, int prog2) /* Expect failure detaching prog when link exists */ errno = 0; - err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(!err || errno != EINVAL)) perror("bpf_prog_detach expected EINVAL"); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -231,7 +228,7 @@ static void test_prog_attach_detach_query(int netns, int prog1, int prog2) } CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); - err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) { perror("bpf_prog_detach"); return; @@ -308,6 +305,31 @@ static void test_link_update_replace_old_prog(int netns, int prog1, int prog2) CHECK_FAIL(prog_is_attached(netns)); } +static void test_link_update_same_prog(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect success updating the prog with the same one */ + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog1, &update_opts); + if (CHECK_FAIL(err)) + perror("bpf_link_update"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + static void test_link_update_invalid_opts(int netns, int prog1, int prog2) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); @@ -571,6 +593,8 @@ static void run_tests(int netns) test_link_update_no_old_prog }, { "link update with replace old prog", test_link_update_replace_old_prog }, + { "link update with same prog", + test_link_update_same_prog }, { "link update invalid opts", test_link_update_invalid_opts }, { "link update invalid prog", diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index e7b8753eac0b..75ecf956a2df 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -25,7 +25,7 @@ struct bpf_iter__netlink { struct netlink_sock *sk; } __attribute__((preserve_access_index)); -static inline struct inode *SOCK_INODE(struct socket *socket) +static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 9365b686f84b..5f645fdaba6f 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -55,3 +55,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f) e == (void *)20 && f == 21; return 0; } + +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +__u64 test7_result = 0; +SEC("fentry/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (arg == 0) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fentry/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index bd1e17d8024c..0952affb22a6 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -56,3 +56,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret) e == (void *)20 && f == 21 && ret == 111; return 0; } + +struct bpf_fentry_test_t { + struct bpf_fentry_test *a; +}; + +__u64 test7_result = 0; +SEC("fexit/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (arg == 0) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fexit/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 057036ca1111..3dca4c2e2418 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -79,7 +79,7 @@ struct { struct { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 2); + __uint(max_entries, 3); __type(key, int); __type(value, int); } sock_skb_opts SEC(".maps"); @@ -94,6 +94,12 @@ struct { SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { + int *f, two = 2; + + f = bpf_map_lookup_elem(&sock_skb_opts, &two); + if (f && *f) { + return *f; + } return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 330811260123..0ac086497722 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -27,7 +27,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) /* valid program on DEVMAP entry via SEC name; * has access to egress and ingress ifindex */ -SEC("xdp_devmap") +SEC("xdp_devmap/map_prog") int xdp_dummy_dm(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 6a12a0e01e07..754cf611723e 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -789,19 +789,19 @@ static void test_sockmap(unsigned int tasks, void *data) } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER); - if (err) { + if (!err) { printf("Failed empty parser prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT); - if (err) { + if (!err) { printf("Failed empty verdict prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_MSG_VERDICT); - if (err) { + if (!err) { printf("Failed empty msg verdict prog detach\n"); goto out_sockmap; } @@ -1090,19 +1090,19 @@ static void test_sockmap(unsigned int tasks, void *data) assert(status == 0); } - err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE); + err = bpf_prog_detach2(parse_prog, map_fd_rx, __MAX_BPF_ATTACH_TYPE); if (!err) { printf("Detached an invalid prog type.\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER); + err = bpf_prog_detach2(parse_prog, map_fd_rx, BPF_SK_SKB_STREAM_PARSER); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); + err = bpf_prog_detach2(verdict_prog, map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 8294ae3ffb3c..43c9cda199b8 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -318,6 +318,9 @@ class DebugfsDir: continue if os.path.isfile(p): + # We need to init trap_flow_action_cookie before read it + if f == "trap_flow_action_cookie": + cmd('echo deadbeef > %s/%s' % (path, f)) _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() elif os.path.isdir(p): diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 37695fc8096a..78789b27e573 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -85,6 +85,7 @@ int txmsg_ktls_skb_drop; int txmsg_ktls_skb_redir; int ktls; int peek_flag; +int skb_use_parser; static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, @@ -174,6 +175,7 @@ static void test_reset(void) txmsg_apply = txmsg_cork = 0; txmsg_ingress = txmsg_redir_skb = 0; txmsg_ktls_skb = txmsg_ktls_skb_drop = txmsg_ktls_skb_redir = 0; + skb_use_parser = 0; } static int test_start_subtest(const struct _test *t, struct sockmap_options *o) @@ -1211,6 +1213,11 @@ run: } } + if (skb_use_parser) { + i = 2; + err = bpf_map_update_elem(map_fd[7], &i, &skb_use_parser, BPF_ANY); + } + if (txmsg_drop) options->drop_expected = true; @@ -1650,6 +1657,16 @@ static void test_txmsg_cork(int cgrp, struct sockmap_options *opt) test_send(opt, cgrp); } +static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt) +{ + txmsg_pass = 1; + skb_use_parser = 512; + opt->iov_length = 256; + opt->iov_count = 1; + opt->rate = 2; + test_exec(cgrp, opt); +} + char *map_names[] = { "sock_map", "sock_map_txmsg", @@ -1748,6 +1765,7 @@ struct _test test[] = { {"txmsg test pull-data", test_txmsg_pull}, {"txmsg test pop-data", test_txmsg_pop}, {"txmsg test push/pop data", test_txmsg_push_pop}, + {"txmsg text ingress parser", test_txmsg_ingress_parser}, }; static int check_whitelist(struct _test *t, struct sockmap_options *opt) diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 99f8f582c02b..c5e805980409 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -112,6 +112,7 @@ "perfevent for cgroup sockopt", .insns = { __PERF_EVENT_INSNS__ }, .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .fixup_map_event_output = { 4 }, .result = ACCEPT, .retval = 1, diff --git a/tools/testing/selftests/fpu/.gitignore b/tools/testing/selftests/fpu/.gitignore new file mode 100644 index 000000000000..d6d12ac1d9c3 --- /dev/null +++ b/tools/testing/selftests/fpu/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0+ +test_fpu diff --git a/tools/testing/selftests/fpu/Makefile b/tools/testing/selftests/fpu/Makefile new file mode 100644 index 000000000000..ea62c176ede7 --- /dev/null +++ b/tools/testing/selftests/fpu/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0+ + +LDLIBS := -lm + +TEST_GEN_PROGS := test_fpu + +TEST_PROGS := run_test_fpu.sh + +include ../lib.mk diff --git a/tools/testing/selftests/fpu/run_test_fpu.sh b/tools/testing/selftests/fpu/run_test_fpu.sh new file mode 100755 index 000000000000..d77be93ec139 --- /dev/null +++ b/tools/testing/selftests/fpu/run_test_fpu.sh @@ -0,0 +1,46 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Load kernel module for FPU tests + +uid=$(id -u) +if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit 1 +fi + +if ! which modprobe > /dev/null 2>&1; then + echo "$0: You need modprobe installed" + exit 4 +fi + +if ! modinfo test_fpu > /dev/null 2>&1; then + echo "$0: You must have the following enabled in your kernel:" + echo "CONFIG_TEST_FPU=m" + exit 4 +fi + +NR_CPUS=$(getconf _NPROCESSORS_ONLN) +if [ ! $NR_CPUS ]; then + NR_CPUS=1 +fi + +modprobe test_fpu + +if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + mount -t debugfs none /sys/kernel/debug + + if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + echo "$0: Error mounting debugfs" + exit 4 + fi +fi + +echo "Running 1000 iterations on all CPUs... " +for i in $(seq 1 1000); do + for c in $(seq 1 $NR_CPUS); do + ./test_fpu & + done +done + +rmmod test_fpu diff --git a/tools/testing/selftests/fpu/test_fpu.c b/tools/testing/selftests/fpu/test_fpu.c new file mode 100644 index 000000000000..200238522a9d --- /dev/null +++ b/tools/testing/selftests/fpu/test_fpu.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* This testcase operates with the test_fpu kernel driver. + * It modifies the FPU control register in user mode and calls the kernel + * module to perform floating point operations in the kernel. The control + * register value should be independent between kernel and user mode. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <fenv.h> +#include <unistd.h> +#include <fcntl.h> + +const char *test_fpu_path = "/sys/kernel/debug/selftest_helpers/test_fpu"; + +int main(void) +{ + char dummy[1]; + int fd = open(test_fpu_path, O_RDONLY); + + if (fd < 0) { + printf("[SKIP]\tcan't access %s: %s\n", + test_fpu_path, strerror(errno)); + return 0; + } + + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with default rounding mode failed\n"); + return 1; + } + + fesetround(FE_DOWNWARD); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with downward rounding mode failed\n"); + return 2; + } + if (fegetround() != FE_DOWNWARD) { + printf("[FAIL]\tusermode rounding mode clobbered\n"); + return 3; + } + + /* Note: the tests up to this point are quite safe and will only return + * an error. But the exception mask setting can cause misbehaving kernel + * to crash. + */ + feclearexcept(FE_ALL_EXCEPT); + feenableexcept(FE_ALL_EXCEPT); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with fpu exceptions unmasked failed\n"); + return 4; + } + if (fegetexcept() != FE_ALL_EXCEPT) { + printf("[FAIL]\tusermode fpu exception mask clobbered\n"); + return 5; + } + + printf("[OK]\ttest_fpu\n"); + return 0; +} diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index 3702dbcc90a7..c82aa77958e5 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -63,6 +63,8 @@ ALL_TESTS="$ALL_TESTS 0008:150:1" ALL_TESTS="$ALL_TESTS 0009:150:1" ALL_TESTS="$ALL_TESTS 0010:1:1" ALL_TESTS="$ALL_TESTS 0011:1:1" +ALL_TESTS="$ALL_TESTS 0012:1:1" +ALL_TESTS="$ALL_TESTS 0013:1:1" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -470,6 +472,38 @@ kmod_test_0011() echo "$MODPROBE" > /proc/sys/kernel/modprobe } +kmod_check_visibility() +{ + local name="$1" + local cmd="$2" + + modprobe $DEFAULT_KMOD_DRIVER + + local priv=$(eval $cmd) + local unpriv=$(capsh --drop=CAP_SYSLOG -- -c "$cmd") + + if [ "$priv" = "$unpriv" ] || \ + [ "${priv:0:3}" = "0x0" ] || \ + [ "${unpriv:0:3}" != "0x0" ] ; then + echo "${FUNCNAME[0]}: FAIL, $name visible to unpriv: '$priv' vs '$unpriv'" >&2 + exit 1 + else + echo "${FUNCNAME[0]}: OK!" + fi +} + +kmod_test_0012() +{ + kmod_check_visibility /proc/modules \ + "grep '^${DEFAULT_KMOD_DRIVER}\b' /proc/modules | awk '{print \$NF}'" +} + +kmod_test_0013() +{ + kmod_check_visibility '/sys/module/*/sections/*' \ + "cat /sys/module/${DEFAULT_KMOD_DRIVER}/sections/.*text | head -n1" +} + list_tests() { echo "Test ID list:" @@ -489,6 +523,8 @@ list_tests() echo "0009 x $(get_test_count 0009) - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()" echo "0010 x $(get_test_count 0010) - test nonexistent modprobe path" echo "0011 x $(get_test_count 0011) - test completely disabling module autoloading" + echo "0012 x $(get_test_count 0012) - test /proc/modules address visibility under CAP_SYSLOG" + echo "0013 x $(get_test_count 0013) - test /sys/module/*/sections/* visibility under CAP_SYSLOG" } usage() diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 0ac49d91a260..862eee734553 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -36,7 +36,7 @@ struct ksft_count { static struct ksft_count ksft_cnt; static unsigned int ksft_plan; -static inline int ksft_test_num(void) +static inline unsigned int ksft_test_num(void) { return ksft_cnt.ksft_pass + ksft_cnt.ksft_fail + ksft_cnt.ksft_xfail + ksft_cnt.ksft_xpass + diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index c9f03ef93338..7f32a7099a81 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -195,8 +195,9 @@ * * .. code-block:: c * - * FIXTURE_DATA(datatype name) + * FIXTURE_DATA(datatype_name) * + * Almost always, you want just FIXTURE() instead (see below). * This call may be used when the type of the fixture data * is needed. In general, this should not be needed unless * the *self* is being passed to a helper directly. @@ -211,7 +212,7 @@ * * .. code-block:: c * - * FIXTURE(datatype name) { + * FIXTURE(fixture_name) { * type property1; * ... * }; @@ -238,7 +239,7 @@ * * .. code-block:: c * - * FIXTURE_SETUP(fixture name) { implementation } + * FIXTURE_SETUP(fixture_name) { implementation } * * Populates the required "setup" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -264,7 +265,7 @@ * * .. code-block:: c * - * FIXTURE_TEARDOWN(fixture name) { implementation } + * FIXTURE_TEARDOWN(fixture_name) { implementation } * * Populates the required "teardown" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -285,7 +286,7 @@ * * .. code-block:: c * - * FIXTURE_VARIANT(datatype name) { + * FIXTURE_VARIANT(fixture_name) { * type property1; * ... * }; @@ -305,8 +306,8 @@ * * .. code-block:: c * - * FIXTURE_ADD(datatype name) { - * .property1 = val1; + * FIXTURE_VARIANT_ADD(fixture_name, variant_name) { + * .property1 = val1, * ... * }; * diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 54cdefdfb49d..d59f3eb67c8f 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -76,10 +76,8 @@ void set_default_state(struct kvm_nested_state *state) void set_default_vmx_state(struct kvm_nested_state *state, int size) { memset(state, 0, size); - state->flags = KVM_STATE_NESTED_GUEST_MODE | - KVM_STATE_NESTED_RUN_PENDING; if (have_evmcs) - state->flags |= KVM_STATE_NESTED_EVMCS; + state->flags = KVM_STATE_NESTED_EVMCS; state->format = 0; state->size = size; state->hdr.vmx.vmxon_pa = 0x1000; @@ -148,6 +146,11 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = 1; test_nested_state_expect_einval(vm, state); + /* Invalid flags are rejected. */ + set_default_vmx_state(state, state_sz); + state->hdr.vmx.flags = ~0; + test_nested_state_expect_einval(vm, state); + /* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; @@ -185,20 +188,41 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; test_nested_state_expect_einval(vm, state); - /* Size must be large enough to fit kvm_nested_state and vmcs12. */ + /* + * Size must be large enough to fit kvm_nested_state and vmcs12 + * if VMCS12 physical address is set + */ set_default_vmx_state(state, state_sz); state->size = sizeof(*state); + state->flags = 0; + test_nested_state_expect_einval(vm, state); + + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; test_nested_state(vm, state); - /* vmxon_pa cannot be the same address as vmcs_pa. */ + /* + * KVM_SET_NESTED_STATE succeeds with invalid VMCS + * contents but L2 not running. + */ set_default_vmx_state(state, state_sz); - state->hdr.vmx.vmxon_pa = 0; - state->hdr.vmx.vmcs12_pa = 0; + state->flags = 0; + test_nested_state(vm, state); + + /* Invalid flags are rejected, even if no VMCS loaded. */ + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; + state->hdr.vmx.flags = ~0; test_nested_state_expect_einval(vm, state); - /* The revision id for vmcs12 must be VMCS12_REVISION. */ + /* vmxon_pa cannot be the same address as vmcs_pa. */ set_default_vmx_state(state, state_sz); - set_revision_id_for_vmcs12(state, 0); + state->hdr.vmx.vmxon_pa = 0; + state->hdr.vmx.vmcs12_pa = 0; test_nested_state_expect_einval(vm, state); /* diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh index 9dc35a16e415..51df5e305855 100755 --- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh +++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh @@ -144,7 +144,7 @@ setup() cleanup() { - for n in h1 r1 h2 h3 h4 + for n in h0 r1 h1 h2 h3 do ip netns del ${n} 2>/dev/null done diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index dee567f7576a..22dc2f3d428b 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -747,6 +747,19 @@ ipv6_fcnal_runtime() run_cmd "$IP nexthop add id 86 via 2001:db8:91::2 dev veth1" run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81" + # rpfilter and default route + $IP nexthop flush >/dev/null 2>&1 + run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP" + run_cmd "$IP nexthop add id 91 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 92 via 2001:db8:92::2 dev veth3" + run_cmd "$IP nexthop add id 93 group 91/92" + run_cmd "$IP -6 ro add default nhid 91" + run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1" + log_test $? 0 "Nexthop with default route and rpfilter" + run_cmd "$IP -6 ro replace default nhid 93" + run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1" + log_test $? 0 "Nexthop with multipath default route and rpfilter" + # TO-DO: # existing route with old nexthop; append route with new nexthop # existing route with old nexthop; replace route with new diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index eb8e2a23bbb4..43a948feed26 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -252,8 +252,6 @@ check_highest_speed_is_chosen() fi local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1)) - # Remove the first speed, h1 does not advertise this speed. - unset speeds_arr[0] max_speed=${speeds_arr[0]} for current in ${speeds_arr[@]}; do diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index 15d3489ecd9c..ceb7ad4dbd94 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -6,6 +6,8 @@ set +x set -e +modprobe -q nf_defrag_ipv6 + readonly NETNS="ns-$(mktemp -u XXXXXX)" setup() { diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 422e7761254d..bcb79ba1f214 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -329,8 +329,7 @@ int main(int argc, char **argv) bool all_tests = true; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index ceaad78e9667..3155fbbf644b 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (labs(tstop - texpect) > cfg_variance_us) + if (llabs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); return false; diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4555f88252ba..a61b7b3da549 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -344,7 +344,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - size_t total = 0; + uint64_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -473,12 +473,12 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - ssize_t wr = FILE_SZ - total; + int64_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; /* Note : we just want to fill the pipe with 0 bytes */ - wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0); if (wr <= 0) break; total += wr; diff --git a/tools/testing/selftests/net/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh index eea6f5193693..31637769f59f 100755 --- a/tools/testing/selftests/net/txtimestamp.sh +++ b/tools/testing/selftests/net/txtimestamp.sh @@ -75,7 +75,7 @@ main() { fi } -if [[ "$(ip netns identify)" == "root" ]]; then +if [[ -z "$(ip netns identify)" ]]; then ./in_netns.sh $0 $@ else main $@ diff --git a/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c b/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c index 6ee0fded0391..7c23d3dd7d6d 100644 --- a/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c +++ b/tools/testing/selftests/powerpc/nx-gzip/gunz_test.c @@ -698,13 +698,13 @@ restart_nx: switch (cc) { - case ERR_NX_TRANSLATION: + case ERR_NX_AT_FAULT: /* We touched the pages ahead of time. In the most common case * we shouldn't be here. But may be some pages were paged out. * Kernel should have placed the faulting address to fsaddr. */ - NXPRT(fprintf(stderr, "ERR_NX_TRANSLATION %p\n", + NXPRT(fprintf(stderr, "ERR_NX_AT_FAULT %p\n", (void *)cmdp->crb.csb.fsaddr)); if (pgfault_retries == NX_MAX_FAULTS) { diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c index 7496a83f9c9d..02dffb65de48 100644 --- a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c +++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c @@ -306,13 +306,13 @@ int compress_file(int argc, char **argv, void *handle) lzcounts, cmdp, handle); if (cc != ERR_NX_OK && cc != ERR_NX_TPBC_GT_SPBC && - cc != ERR_NX_TRANSLATION) { + cc != ERR_NX_AT_FAULT) { fprintf(stderr, "nx error: cc= %d\n", cc); exit(-1); } /* Page faults are handled by the user code */ - if (cc == ERR_NX_TRANSLATION) { + if (cc == ERR_NX_AT_FAULT) { NXPRT(fprintf(stderr, "page fault: cc= %d, ", cc)); NXPRT(fprintf(stderr, "try= %d, fsa= %08llx\n", fault_tries, diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 93e80a42249a..d6e5ce084b1c 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -32,11 +32,11 @@ if test -z "$TORTURE_TRUST_MAKE" then make clean > $resdir/Make.clean 2>&1 fi -make $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 +make $TORTURE_KMAKE_ARG $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv .config .config.sav sh $T/upd.sh < .config.sav > .config cp .config .config.new -yes '' | make oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err +yes '' | make $TORTURE_KMAKE_ARG oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh .config $c diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh new file mode 100755 index 000000000000..0e4c0b2eb7f0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Scan standard input for error messages, dumping any found to standard +# output. +# +# Usage: console-badness.sh +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +grep -v 'ODEBUG: ' | +grep -v 'This means that this is a DEBUG kernel and it is' | +grep -v 'Warning: unable to open an initial console' diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 12810229fddc..51f3464b96d3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -215,9 +215,6 @@ identify_qemu_args () { then echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC echo -netdev bridge,br=br0,id=net0 - elif test -n "$TORTURE_QEMU_INTERACTIVE" - then - echo -net nic -net user fi ;; esac @@ -234,7 +231,7 @@ identify_qemu_args () { # Returns the number of virtual CPUs available to the aggregate of the # guest OSes. identify_qemu_vcpus () { - lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' + lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ ]*//g' } # print_bug @@ -275,3 +272,21 @@ specify_qemu_cpus () { esac fi } + +# specify_qemu_net qemu-args +# +# Appends a string containing "-net none" to qemu-args, unless the incoming +# qemu-args already contains "-smp" or unless the TORTURE_QEMU_INTERACTIVE +# environment variable is set, in which case the string that is be added is +# instead "-net nic -net user". +specify_qemu_net () { + if echo $1 | grep -q -e -net + then + echo $1 + elif test -n "$TORTURE_QEMU_INTERACTIVE" + then + echo $1 -net nic -net user + else + echo $1 -net none + fi +} diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index 30cb5b27d32e..188b864bc4bf 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -46,6 +46,12 @@ do exit 0; fi + # Check for stop request. + if test -f "$TORTURE_STOPFILE" + then + exit 1; + fi + # Set affinity to randomly selected online CPU if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 | sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 18d6518504ee..115e1822b26f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -9,6 +9,12 @@ # # Authors: Paul E. McKenney <paulmck@linux.ibm.com> +if test -f "$TORTURE_STOPFILE" +then + echo "kvm-build.sh early exit due to run STOP request" + exit 1 +fi + config_template=${1} if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh new file mode 100755 index 000000000000..6e65c134e5f1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Run a group of kvm.sh tests on the specified commits. This currently +# unconditionally does three-minute runs on each scenario in CFLIST, +# taking advantage of all available CPUs and trusting the "make" utility. +# In the short term, adjustments can be made by editing this script and +# CFLIST. If some adjustments appear to have ongoing value, this script +# might grow some command-line arguments. +# +# Usage: kvm-check-branches.sh commit1 commit2..commit3 commit4 ... +# +# This script considers its arguments one at a time. If more elaborate +# specification of commits is needed, please use "git rev-list" to +# produce something that this simple script can understand. The reason +# for retaining the simplicity is that it allows the user to more easily +# see which commit came from which branch. +# +# This script creates a yyyy.mm.dd-hh.mm.ss-group entry in the "res" +# directory. The calls to kvm.sh create the usual entries, but this script +# moves them under the yyyy.mm.dd-hh.mm.ss-group entry, each in its own +# directory numbered in run order, that is, "0001", "0002", and so on. +# For successful runs, the large build artifacts are removed. Doing this +# reduces the disk space required by about two orders of magnitude for +# successful runs. +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +if ! git status > /dev/null 2>&1 +then + echo '!!!' This script needs to run in a git archive. 1>&2 + echo '!!!' Giving up. 1>&2 + exit 1 +fi + +# Remember where we started so that we can get back and the end. +curcommit="`git status | head -1 | awk '{ print $NF }'`" + +nfail=0 +ntry=0 +resdir="tools/testing/selftests/rcutorture/res" +ds="`date +%Y.%m.%d-%H.%M.%S`-group" +if ! test -e $resdir +then + mkdir $resdir || : +fi +mkdir $resdir/$ds +echo Results directory: $resdir/$ds + +KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM +PATH=${KVM}/bin:$PATH; export PATH +. functions.sh +cpus="`identify_qemu_vcpus`" +echo Using up to $cpus CPUs. + +# Each pass through this loop does one command-line argument. +for gitbr in $@ +do + echo ' --- git branch ' $gitbr + + # Each pass through this loop tests one commit. + for i in `git rev-list "$gitbr"` + do + ntry=`expr $ntry + 1` + idir=`awk -v ntry="$ntry" 'END { printf "%04d", ntry; }' < /dev/null` + echo ' --- commit ' $i from branch $gitbr + date + mkdir $resdir/$ds/$idir + echo $gitbr > $resdir/$ds/$idir/gitbr + echo $i >> $resdir/$ds/$idir/gitbr + + # Test the specified commit. + git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1 + echo git checkout return code: $? "(Commit $ntry: $i)" + kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1 + ret=$? + echo kvm.sh return code $ret for commit $i from branch $gitbr + + # Move the build products to their resting place. + runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`" + mv $runresdir $resdir/$ds/$idir + rrd="`echo $runresdir | sed -e 's,^.*/,,'`" + echo Run results: $resdir/$ds/$idir/$rrd + if test "$ret" -ne 0 + then + # Failure, so leave all evidence intact. + nfail=`expr $nfail + 1` + else + # Success, so remove large files to save about 1GB. + ( cd $resdir/$ds/$idir/$rrd; rm -f */vmlinux */bzImage */System.map */Module.symvers ) + fi + done +done +date + +# Go back to the original commit. +git checkout "$curcommit" + +if test $nfail -ne 0 +then + echo '!!! ' $nfail failures in $ntry 'runs!!!' + exit 1 +else + echo No failures in $ntry runs. + exit 0 +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh new file mode 100755 index 000000000000..35a463dddffe --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh @@ -0,0 +1,71 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Analyze a given results directory for refscale performance measurements. +# +# Usage: kvm-recheck-refscale.sh resdir +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +i="$1" +if test -d "$i" -a -r "$i" +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. functions.sh + +configfile=`echo $i | sed -e 's/^.*\///'` + +sed -e 's/^\[[^]]*]//' < $i/console.log | tr -d '\015' | +awk -v configfile="$configfile" ' +/^[ ]*Runs Time\(ns\) *$/ { + if (dataphase + 0 == 0) { + dataphase = 1; + # print configfile, $0; + } + next; +} + +/[^ ]*[0-9][0-9]* [0-9][0-9]*\.[0-9][0-9]*$/ { + if (dataphase == 1) { + # print $0; + readertimes[++n] = $2; + sum += $2; + } + next; +} + +{ + if (dataphase == 1) + dataphase == 2; + next; +} + +END { + print configfile " results:"; + newNR = asort(readertimes); + if (newNR <= 0) { + print "No refscale records found???" + exit; + } + medianidx = int(newNR / 2); + if (newNR == medianidx * 2) + medianvalue = (readertimes[medianidx - 1] + readertimes[medianidx]) / 2; + else + medianvalue = readertimes[medianidx]; + points = "Points:"; + for (i = 1; i <= newNR; i++) + points = points " " readertimes[i]; + print points; + print "Average reader duration: " sum / newNR " nanoseconds"; + print "Minimum reader duration: " readertimes[1]; + print "Median reader duration: " medianvalue; + print "Maximum reader duration: " readertimes[newNR]; + print "Computed from refscale printk output."; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 736f04749b90..840a4679a0d7 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -31,6 +31,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 @@ -43,7 +44,8 @@ do then echo QEMU killed fi - configcheck.sh $i/.config $i/ConfigFragment + configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1 + cat $T if test -r $i/Make.oldconfig.err then cat $i/Make.oldconfig.err @@ -55,15 +57,15 @@ do cat $i/Warnings fi else - if test -f "$i/qemu-cmd" - then - print_bug qemu failed - echo " $i" - elif test -f "$i/buildonly" + if test -f "$i/buildonly" then echo Build-only run, no boot/test configcheck.sh $i/.config $i/ConfigFragment parse-build.sh $i/Make.out $configfile + elif test -f "$i/qemu-cmd" + then + print_bug qemu failed + echo " $i" else print_bug Build failed echo " $i" @@ -72,7 +74,11 @@ do done if test -f "$rd/kcsan.sum" then - if test -s "$rd/kcsan.sum" + if grep -q CONFIG_KCSAN=y $T + then + echo "Compiler or architecture does not support KCSAN!" + echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'? + elif test -s "$rd/kcsan.sum" then echo KCSAN summary in $rd/kcsan.sum else diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 6ff611c630d1..e07779a62634 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -124,7 +124,6 @@ seconds=$4 qemu_args=$5 boot_args=$6 -cd $KVM kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then @@ -141,6 +140,7 @@ then cpu_count=$TORTURE_ALLOTED_CPUS fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" +qemu_args="`specify_qemu_net "$qemu_args"`" # Generate architecture-specific and interaction-specific qemu arguments qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" @@ -152,6 +152,7 @@ qemu_append="`identify_qemu_append "$QEMU"`" boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" +echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then @@ -159,9 +160,16 @@ then touch $resdir/buildonly exit 0 fi + +# Decorate qemu-cmd with redirection, backgrounding, and PID capture +sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd +echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd + +# In case qemu refuses to run... echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log -echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args" > $resdir/qemu-output 2>&1 & echo $! > $resdir/qemu_pid; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & + +# Attempt to run qemu +( . $T/qemu-cmd; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 sleep 10 # Give qemu's pid a chance to reach the file if test -s "$resdir/qemu_pid" @@ -181,7 +189,7 @@ do kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then - if test $kruntime -ge $seconds + if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE" then break; fi @@ -210,10 +218,19 @@ then fi if test $commandcompleted -eq 0 -a -n "$qemu_pid" then - echo Grace period for qemu job at pid $qemu_pid + if ! test -f "$TORTURE_STOPFILE" + then + echo Grace period for qemu job at pid $qemu_pid + fi oldline="`tail $resdir/console.log`" while : do + if test -f "$TORTURE_STOPFILE" + then + echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1 + kill -KILL $qemu_pid + break + fi kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh new file mode 100755 index 000000000000..c45a953ef393 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Transform a qemu-cmd file to allow reuse. +# +# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out +# +# bzImage: Kernel and initrd from the same prior kvm.sh run. +# console.log: File into which to place console output. +# +# The original qemu-cmd file is provided on standard input. +# The transformed qemu-cmd file is on standard output. +# The transformation assumes that the qemu command is confined to a +# single line. It also assumes no whitespace in filenames. +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +image="$1" +if test -z "$image" +then + echo Need kernel image file. + exit 1 +fi +consolelog="$2" +if test -z "$consolelog" +then + echo "Need console log file name." + exit 1 +fi + +awk -v image="$image" -v consolelog="$consolelog" ' +{ + line = ""; + for (i = 1; i <= NF; i++) { + if (line == "") + line = $i; + else + line = line " " $i; + if ($i == "-serial") { + i++; + line = line " file:" consolelog; + } + if ($i == "-kernel") { + i++; + line = line " " image; + } + } + print line; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index c279cf9cb010..e655983b7429 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -73,6 +73,10 @@ usage () { while test $# -gt 0 do case "$1" in + --allcpus) + cpus=$TORTURE_ALLOTED_CPUS + max_cpus=$TORTURE_ALLOTED_CPUS + ;; --bootargs|--bootarg) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' TORTURE_BOOTARGS="$2" @@ -180,13 +184,14 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--' TORTURE_SUITE=$2 shift - if test "$TORTURE_SUITE" = rcuperf + if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale then - # If you really want jitter for rcuperf, specify - # it after specifying rcuperf. (But why?) + # If you really want jitter for refscale or + # rcuperf, specify it after specifying the rcuperf + # or the refscale. (But why jitter in these cases?) jitter=0 fi ;; @@ -333,6 +338,8 @@ then mkdir -p "$resdir" || : fi mkdir $resdir/$ds +TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR +TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE echo Results directory: $resdir/$ds echo $scriptname $args touch $resdir/$ds/log @@ -497,3 +504,7 @@ fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier # Function-graph tracing: ftrace=function_graph ftrace_graph_filter=sched_setaffinity,migration_cpu_stop # Also --kconfig "CONFIG_FUNCTION_TRACER=y CONFIG_FUNCTION_GRAPH_TRACER=y" +# Control buffer size: --bootargs trace_buf_size=3k +# Get trace-buffer dumps on all oopses: --bootargs ftrace_dump_on_oops +# Ditto, but dump only the oopsing CPU: --bootargs ftrace_dump_on_oops=orig_cpu +# Heavy-handed way to also dump on warnings: --bootargs panic_on_warn diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4bf62d7b1cbc..71a9f43a3918 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,8 +33,8 @@ then fi cat /dev/null > $file.diags -# Check for proper termination, except that rcuperf runs don't indicate this. -if test "$TORTURE_SUITE" != rcuperf +# Check for proper termination, except for rcuperf and refscale. +if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale then # check for abject failure @@ -44,11 +44,23 @@ then tail -1 | awk ' { - for (i=NF-8;i<=NF;i++) + normalexit = 1; + for (i=NF-8;i<=NF;i++) { + if (i <= 0 || i !~ /^[0-9]*$/) { + bangstring = $0; + gsub(/^\[[^]]*] /, "", bangstring); + print bangstring; + normalexit = 0; + exit 0; + } sum+=$i; + } } - END { print sum }'` - print_bug $title FAILURE, $nerrs instances + END { + if (normalexit) + print sum " instances" + }'` + print_bug $title FAILURE, $nerrs exit fi @@ -104,10 +116,7 @@ then fi fi | tee -a $file.diags -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | -grep -v 'ODEBUG: ' | -grep -v 'This means that this is a DEBUG kernel and it is' | -grep -v 'Warning: unable to open an initial console' > $T.diags +console-badness.sh < $file > $T.diags if test -s $T.diags then print_warning "Assertion failure in $file $title" diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFLIST b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST new file mode 100644 index 000000000000..4d62eb4a39f9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST @@ -0,0 +1,2 @@ +NOPREEMPT +PREEMPT diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon new file mode 100644 index 000000000000..a98b58b54bb1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_REF_SCALE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT new file mode 100644 index 000000000000..1cd25b7314e3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT new file mode 100644 index 000000000000..d10bc694f42c --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh new file mode 100644 index 000000000000..321e82641287 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# Copyright (C) IBM Corporation, 2015 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 refscale.shutdown=1 \ + refscale.verbose=1 +} diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config index db1e11b08c8a..64c19d8eba79 100644 --- a/tools/testing/selftests/seccomp/config +++ b/tools/testing/selftests/seccomp/config @@ -1,2 +1,3 @@ CONFIG_SECCOMP=y CONFIG_SECCOMP_FILTER=y +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5838c8697ec3..91f5a89cadac 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -18,9 +18,9 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) { - pid_t pid, ret; - unsigned long long i; struct timespec start, finish; + unsigned long long i; + pid_t pid, ret; pid = getpid(); assert(clock_gettime(clk_id, &start) == 0); @@ -31,30 +31,43 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) assert(clock_gettime(clk_id, &finish) == 0); i = finish.tv_sec - start.tv_sec; - i *= 1000000000; + i *= 1000000000ULL; i += finish.tv_nsec - start.tv_nsec; - printf("%lu.%09lu - %lu.%09lu = %llu\n", + printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", finish.tv_sec, finish.tv_nsec, start.tv_sec, start.tv_nsec, - i); + i, (double)i / 1000000000.0); return i; } unsigned long long calibrate(void) { - unsigned long long i; - - printf("Calibrating reasonable sample size...\n"); + struct timespec start, finish; + unsigned long long i, samples, step = 9973; + pid_t pid, ret; + int seconds = 15; - for (i = 5; ; i++) { - unsigned long long samples = 1 << i; + printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); - /* Find something that takes more than 5 seconds to run. */ - if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5) - return samples; - } + samples = 0; + pid = getpid(); + assert(clock_gettime(CLOCK_MONOTONIC, &start) == 0); + do { + for (i = 0; i < step; i++) { + ret = syscall(__NR_getpid); + assert(pid == ret); + } + assert(clock_gettime(CLOCK_MONOTONIC, &finish) == 0); + + samples += step; + i = finish.tv_sec - start.tv_sec; + i *= 1000000000ULL; + i += finish.tv_nsec - start.tv_nsec; + } while (i < 1000000000ULL); + + return samples * seconds; } int main(int argc, char *argv[]) @@ -68,32 +81,55 @@ int main(int argc, char *argv[]) }; long ret; unsigned long long samples; - unsigned long long native, filtered; + unsigned long long native, filter1, filter2; + + printf("Current BPF sysctl settings:\n"); + system("sysctl net.core.bpf_jit_enable"); + system("sysctl net.core.bpf_jit_harden"); if (argc > 1) samples = strtoull(argv[1], NULL, 0); else samples = calibrate(); - printf("Benchmarking %llu samples...\n", samples); + printf("Benchmarking %llu syscalls...\n", samples); + /* Native call */ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; printf("getpid native: %llu ns\n", native); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); assert(ret == 0); + /* One filter */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); assert(ret == 0); - filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW: %llu ns\n", filtered); + filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1); + + if (filter1 == native) + printf("No overhead measured!? Try running again with more samples.\n"); + + /* Two filters */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + assert(ret == 0); + + filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2); + + /* Calculations */ + printf("Estimated total seccomp overhead for 1 filter: %llu ns\n", + filter1 - native); + + printf("Estimated total seccomp overhead for 2 filters: %llu ns\n", + filter2 - native); - printf("Estimated seccomp overhead per syscall: %llu ns\n", - filtered - native); + printf("Estimated seccomp per-filter overhead: %llu ns\n", + filter2 - filter1); - if (filtered == native) - printf("Trying running again with more samples.\n"); + printf("Estimated seccomp entry overhead: %llu ns\n", + filter1 - native - (filter2 - filter1)); return 0; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 252140a52553..5267b9fb7c0f 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -45,12 +45,19 @@ #include <sys/socket.h> #include <sys/ioctl.h> #include <linux/kcmp.h> +#include <sys/resource.h> #include <unistd.h> #include <sys/syscall.h> #include <poll.h> #include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +/* Attempt to de-conflict with the selftests tree. */ +#ifndef SKIP +#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 @@ -167,7 +174,9 @@ struct seccomp_metadata { #ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#endif +#ifndef SECCOMP_RET_USER_NOTIF #define SECCOMP_RET_USER_NOTIF 0x7fc00000U #define SECCOMP_IOC_MAGIC '!' @@ -180,7 +189,7 @@ struct seccomp_metadata { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) struct seccomp_notif { __u64 id; @@ -203,6 +212,39 @@ struct seccomp_notif_sizes { }; #endif +#ifndef SECCOMP_IOCTL_NOTIF_ADDFD +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ + +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; +#endif + +struct seccomp_notif_addfd_small { + __u64 id; + char weird[4]; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_SMALL \ + SECCOMP_IOW(3, struct seccomp_notif_addfd_small) + +struct seccomp_notif_addfd_big { + union { + struct seccomp_notif_addfd addfd; + char buf[sizeof(struct seccomp_notif_addfd) + 8]; + }; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_BIG \ + SECCOMP_IOWR(3, struct seccomp_notif_addfd_big) + #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY #define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 #define PTRACE_EVENTMSG_SYSCALL_EXIT 2 @@ -236,6 +278,40 @@ int seccomp(unsigned int op, unsigned int flags, void *args) #define SIBLING_EXIT_FAILURE 0xbadface #define SIBLING_EXIT_NEWPRIVS 0xbadfeed +static int __filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) +{ +#ifdef __NR_kcmp + errno = 0; + return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); +#else + errno = ENOSYS; + return -1; +#endif +} + +/* Have TH_LOG report actual location filecmp() is used. */ +#define filecmp(pid1, pid2, fd1, fd2) ({ \ + int _ret; \ + \ + _ret = __filecmp(pid1, pid2, fd1, fd2); \ + if (_ret != 0) { \ + if (_ret < 0 && errno == ENOSYS) { \ + TH_LOG("kcmp() syscall missing (test is less accurate)");\ + _ret = 0; \ + } \ + } \ + _ret; }) + +TEST(kcmp) +{ + int ret; + + ret = __filecmp(getpid(), getpid(), 1, 1); + EXPECT_EQ(ret, 0); + if (ret != 0 && errno == ENOSYS) + SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)"); +} + TEST(mode_strict_support) { long ret; @@ -1470,6 +1546,7 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata, return tracer_pid; } + void teardown_trace_fixture(struct __test_metadata *_metadata, pid_t tracer) { @@ -1750,7 +1827,7 @@ void change_syscall(struct __test_metadata *_metadata, EXPECT_EQ(0, ret); } -void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, +void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, int status, void *args) { int ret; @@ -1827,6 +1904,24 @@ FIXTURE(TRACE_syscall) { pid_t tracer, mytid, mypid, parent; }; +FIXTURE_VARIANT(TRACE_syscall) { + /* + * All of the SECCOMP_RET_TRACE behaviors can be tested with either + * SECCOMP_RET_TRACE+PTRACE_CONT or plain ptrace()+PTRACE_SYSCALL. + * This indicates if we should use SECCOMP_RET_TRACE (false), or + * ptrace (true). + */ + bool use_ptrace; +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, ptrace) { + .use_ptrace = true, +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, seccomp) { + .use_ptrace = false, +}; + FIXTURE_SETUP(TRACE_syscall) { struct sock_filter filter[] = { @@ -1842,12 +1937,11 @@ FIXTURE_SETUP(TRACE_syscall) BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; - - memset(&self->prog, 0, sizeof(self->prog)); - self->prog.filter = malloc(sizeof(filter)); - ASSERT_NE(NULL, self->prog.filter); - memcpy(self->prog.filter, filter, sizeof(filter)); - self->prog.len = (unsigned short)ARRAY_SIZE(filter); + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; /* Prepare some testable syscall results. */ self->mytid = syscall(__NR_gettid); @@ -1865,60 +1959,48 @@ FIXTURE_SETUP(TRACE_syscall) ASSERT_NE(self->parent, self->mypid); /* Launch tracer. */ - self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL, - false); -} + self->tracer = setup_trace_fixture(_metadata, + variant->use_ptrace ? tracer_ptrace + : tracer_seccomp, + NULL, variant->use_ptrace); -FIXTURE_TEARDOWN(TRACE_syscall) -{ - teardown_trace_fixture(_metadata, self->tracer); - if (self->prog.filter) - free(self->prog.filter); -} + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); -TEST_F(TRACE_syscall, ptrace_syscall_redirected) -{ - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + if (variant->use_ptrace) + return; - /* Tracer will redirect getpid to getppid. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); } -TEST_F(TRACE_syscall, ptrace_syscall_errno) +FIXTURE_TEARDOWN(TRACE_syscall) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - /* Tracer should skip the open syscall, resulting in ESRCH. */ - EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } -TEST_F(TRACE_syscall, ptrace_syscall_faked) +TEST(negative_ENOSYS) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + /* + * There should be no difference between an "internal" skip + * and userspace asking for syscall "-1". + */ + errno = 0; + EXPECT_EQ(-1, syscall(-1)); + EXPECT_EQ(errno, ENOSYS); + /* And no difference for "still not valid but not -1". */ + errno = 0; + EXPECT_EQ(-1, syscall(-101)); + EXPECT_EQ(errno, ENOSYS); +} - /* Tracer should skip the gettid syscall, resulting fake pid. */ - EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); +TEST_F(TRACE_syscall, negative_ENOSYS) +{ + negative_ENOSYS(_metadata); } TEST_F(TRACE_syscall, syscall_allowed) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getppid works as expected (no changes). */ EXPECT_EQ(self->parent, syscall(__NR_getppid)); EXPECT_NE(self->mypid, syscall(__NR_getppid)); @@ -1926,14 +2008,6 @@ TEST_F(TRACE_syscall, syscall_allowed) TEST_F(TRACE_syscall, syscall_redirected) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getpid has been redirected to getppid as expected. */ EXPECT_EQ(self->parent, syscall(__NR_getpid)); EXPECT_NE(self->mypid, syscall(__NR_getpid)); @@ -1941,33 +2015,17 @@ TEST_F(TRACE_syscall, syscall_redirected) TEST_F(TRACE_syscall, syscall_errno) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* openat has been skipped and an errno return. */ + /* Tracer should skip the open syscall, resulting in ESRCH. */ EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } TEST_F(TRACE_syscall, syscall_faked) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* gettid has been skipped and an altered return value stored. */ + /* Tracer skips the gettid syscall and store altered return value. */ EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } -TEST_F(TRACE_syscall, skip_after_RET_TRACE) +TEST_F(TRACE_syscall, skip_after) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -1982,14 +2040,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) }; long ret; - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ + /* Install additional "errno on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -1999,69 +2050,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) EXPECT_EQ(EPERM, errno); } -TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should die. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); -} - -TEST_F(TRACE_syscall, skip_after_ptrace) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should see EPERM. */ - EXPECT_EQ(-1, syscall(__NR_getpid)); - EXPECT_EQ(EPERM, errno); -} - -TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) +TEST_F_SIGNAL(TRACE_syscall, kill_after, SIGSYS) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -2076,15 +2065,7 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) }; long ret; - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ + /* Install additional "death on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -3069,7 +3050,7 @@ TEST(get_metadata) /* Only real root can get metadata. */ if (geteuid()) { - XFAIL(return, "get_metadata requires real root"); + SKIP(return, "get_metadata requires real root"); return; } @@ -3112,7 +3093,7 @@ TEST(get_metadata) ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md); EXPECT_EQ(sizeof(md), ret) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); + SKIP(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); } EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG); @@ -3128,7 +3109,7 @@ skip: ASSERT_EQ(0, kill(pid, SIGKILL)); } -static int user_trap_syscall(int nr, unsigned int flags) +static int user_notif_syscall(int nr, unsigned int flags) { struct sock_filter filter[] = { BPF_STMT(BPF_LD+BPF_W+BPF_ABS, @@ -3174,7 +3155,7 @@ TEST(user_notification_basic) /* Check that we get -ENOSYS with no listener attached */ if (pid == 0) { - if (user_trap_syscall(__NR_getppid, 0) < 0) + if (user_notif_syscall(__NR_getppid, 0) < 0) exit(1); ret = syscall(__NR_getppid); exit(ret >= 0 || errno != ENOSYS); @@ -3191,13 +3172,13 @@ TEST(user_notification_basic) EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); /* Check that the basic notification machinery works */ - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* Installing a second listener in the chain should EBUSY */ - EXPECT_EQ(user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER), + EXPECT_EQ(user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER), -1); EXPECT_EQ(errno, EBUSY); @@ -3258,15 +3239,20 @@ TEST(user_notification_with_tsync) int ret; unsigned int flags; + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + /* these were exclusive */ flags = SECCOMP_FILTER_FLAG_NEW_LISTENER | SECCOMP_FILTER_FLAG_TSYNC; - ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags)); + ASSERT_EQ(-1, user_notif_syscall(__NR_getppid, flags)); ASSERT_EQ(EINVAL, errno); /* but now they're not */ flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH; - ret = user_trap_syscall(__NR_getppid, flags); + ret = user_notif_syscall(__NR_getppid, flags); close(ret); ASSERT_LE(0, ret); } @@ -3284,8 +3270,8 @@ TEST(user_notification_kill_in_middle) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3338,8 +3324,8 @@ TEST(user_notification_signal) ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); - listener = user_trap_syscall(__NR_gettid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_gettid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3408,8 +3394,8 @@ TEST(user_notification_closed_listener) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3440,10 +3426,13 @@ TEST(user_notification_child_pid_ns) struct seccomp_notif req = {}; struct seccomp_notif_resp resp = {}; - ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0) { + if (errno == EINVAL) + SKIP(return, "kernel missing CLONE_NEWUSER support"); + }; - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3482,8 +3471,8 @@ TEST(user_notification_sibling_pid_ns) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3505,7 +3494,10 @@ TEST(user_notification_sibling_pid_ns) } /* Create the sibling ns, and sibling in it. */ - ASSERT_EQ(unshare(CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWPID), 0) { + if (errno == EPERM) + SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN"); + } ASSERT_EQ(errno, 0); pid2 = fork(); @@ -3547,8 +3539,8 @@ TEST(user_notification_fault_recv) ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3585,16 +3577,6 @@ TEST(seccomp_get_notif_sizes) EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp)); } -static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) -{ -#ifdef __NR_kcmp - return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); -#else - errno = ENOSYS; - return -1; -#endif -} - TEST(user_notification_continue) { pid_t pid; @@ -3609,7 +3591,7 @@ TEST(user_notification_continue) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3619,20 +3601,14 @@ TEST(user_notification_continue) int dup_fd, pipe_fds[2]; pid_t self; - ret = pipe(pipe_fds); - if (ret < 0) - exit(1); + ASSERT_GE(pipe(pipe_fds), 0); dup_fd = dup(pipe_fds[0]); - if (dup_fd < 0) - exit(1); + ASSERT_GE(dup_fd, 0); + EXPECT_NE(pipe_fds[0], dup_fd); self = getpid(); - - ret = filecmp(self, self, pipe_fds[0], dup_fd); - if (ret) - exit(2); - + ASSERT_EQ(filecmp(self, self, pipe_fds[0], dup_fd), 0); exit(0); } @@ -3673,7 +3649,7 @@ TEST(user_notification_continue) resp.val = 0; EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); + SKIP(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); } skip: @@ -3681,15 +3657,342 @@ skip: EXPECT_EQ(true, WIFEXITED(status)); EXPECT_EQ(0, WEXITSTATUS(status)) { if (WEXITSTATUS(status) == 2) { - XFAIL(return, "Kernel does not support kcmp() syscall"); + SKIP(return, "Kernel does not support kcmp() syscall"); return; } } } +TEST(user_notification_filter_empty) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int listener; + + listener = user_notif_syscall(__NR_mknod, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + _exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +static void *do_thread(void *data) +{ + return NULL; +} + +TEST(user_notification_filter_empty_threaded) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t pid1, pid2; + int listener, status; + pthread_t thread; + + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + pid1 = fork(); + if (pid1 < 0) + _exit(EXIT_FAILURE); + + if (pid1 == 0) + _exit(EXIT_SUCCESS); + + pid2 = fork(); + if (pid2 < 0) + _exit(EXIT_FAILURE); + + if (pid2 == 0) + _exit(EXIT_SUCCESS); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (waitpid(pid1, &status, 0) != pid1 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + if (waitpid(pid2, &status, 0) != pid2 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +TEST(user_notification_addfd) +{ + pid_t pid; + long ret; + int status, listener, memfd, fd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif_addfd_small small = {}; + struct seccomp_notif_addfd_big big = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (syscall(__NR_getppid) != USER_NOTIF_MAGIC) + exit(1); + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + } + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + addfd.srcfd = memfd; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0x0; + + /* Verify bad newfd_flags cannot be set */ + addfd.newfd_flags = ~O_CLOEXEC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd_flags = O_CLOEXEC; + + /* Verify bad flags cannot be set */ + addfd.flags = 0xff; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.flags = 0; + + /* Verify that remote_fd cannot be set without setting flags */ + addfd.newfd = 1; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd = 0; + + /* Verify small size cannot be set */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_SMALL, &small), -1); + EXPECT_EQ(errno, EINVAL); + + /* Verify we can't send bits filled in unknown buffer area */ + memset(&big, 0xAA, sizeof(big)); + big.addfd = addfd; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big), -1); + EXPECT_EQ(errno, E2BIG); + + + /* Verify we can set an arbitrary remote fd */ + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + /* + * The child has fds 0(stdin), 1(stdout), 2(stderr), 3(memfd), + * 4(listener), so the newly allocated fd should be 5. + */ + EXPECT_EQ(fd, 5); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Verify we can set an arbitrary remote fd with large size */ + memset(&big, 0x0, sizeof(big)); + big.addfd = addfd; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big); + EXPECT_EQ(fd, 6); + + /* Verify we can set a specific remote fd */ + addfd.newfd = 42; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + EXPECT_EQ(fd, 42); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Resume syscall */ + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* + * This sets the ID of the ADD FD to the last request plus 1. The + * notification ID increments 1 per notification. + */ + addfd.id = req.id + 1; + + /* This spins until the underlying notification is generated */ + while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 && + errno != -EINPROGRESS) + nanosleep(&delay, NULL); + + memset(&req, 0, sizeof(req)); + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + ASSERT_EQ(addfd.id, req.id); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + +TEST(user_notification_addfd_rlimit) +{ + pid_t pid; + long ret; + int status, listener, memfd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + const struct rlimit lim = { + .rlim_cur = 0, + .rlim_max = 0, + }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0); + + addfd.srcfd = memfd; + addfd.newfd_flags = O_CLOEXEC; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0; + + /* Should probably spot check /proc/sys/fs/file-nr */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EMFILE); + + addfd.newfd = 100; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EBADF); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + /* * TODO: - * - add microbenchmarks * - expand NNP testing * - better arch-specific TRACE and TRAP handlers. * - endianness checking when appropriate @@ -3697,7 +4000,6 @@ skip: * - arch value testing (x86 modes especially) * - verify that FILTER_FLAG_LOG filters generate log messages * - verify that RET_LOG generates log messages - * - ... */ TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/seccomp/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 1334e301d2a0..3e5ff29ee1dd 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -6,5 +6,5 @@ ksft_skip=4 [ -e /dev/tpm0 ] || exit $ksft_skip -python -m unittest -v tpm2_tests.SmokeTest -python -m unittest -v tpm2_tests.AsyncTest +python3 -m unittest -v tpm2_tests.SmokeTest +python3 -m unittest -v tpm2_tests.AsyncTest diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index 00259cb746cf..04c47b13fe8a 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -6,4 +6,4 @@ ksft_skip=4 [ -e /dev/tpmrm0 ] || exit $ksft_skip -python -m unittest -v tpm2_tests.SpaceTest +python3 -m unittest -v tpm2_tests.SpaceTest diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index d0fcb66a88a6..f34486cd7342 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -247,14 +247,14 @@ class ProtocolError(Exception): class AuthCommand(object): """TPMS_AUTH_COMMAND""" - def __init__(self, session_handle=TPM2_RS_PW, nonce='', session_attributes=0, - hmac=''): + def __init__(self, session_handle=TPM2_RS_PW, nonce=bytes(), + session_attributes=0, hmac=bytes()): self.session_handle = session_handle self.nonce = nonce self.session_attributes = session_attributes self.hmac = hmac - def __str__(self): + def __bytes__(self): fmt = '>I H%us B H%us' % (len(self.nonce), len(self.hmac)) return struct.pack(fmt, self.session_handle, len(self.nonce), self.nonce, self.session_attributes, len(self.hmac), @@ -268,11 +268,11 @@ class AuthCommand(object): class SensitiveCreate(object): """TPMS_SENSITIVE_CREATE""" - def __init__(self, user_auth='', data=''): + def __init__(self, user_auth=bytes(), data=bytes()): self.user_auth = user_auth self.data = data - def __str__(self): + def __bytes__(self): fmt = '>H%us H%us' % (len(self.user_auth), len(self.data)) return struct.pack(fmt, len(self.user_auth), self.user_auth, len(self.data), self.data) @@ -296,8 +296,9 @@ class Public(object): return '>HHIH%us%usH%us' % \ (len(self.auth_policy), len(self.parameters), len(self.unique)) - def __init__(self, object_type, name_alg, object_attributes, auth_policy='', - parameters='', unique=''): + def __init__(self, object_type, name_alg, object_attributes, + auth_policy=bytes(), parameters=bytes(), + unique=bytes()): self.object_type = object_type self.name_alg = name_alg self.object_attributes = object_attributes @@ -305,7 +306,7 @@ class Public(object): self.parameters = parameters self.unique = unique - def __str__(self): + def __bytes__(self): return struct.pack(self.__fmt(), self.object_type, self.name_alg, @@ -343,7 +344,7 @@ def get_algorithm(name): def hex_dump(d): d = [format(ord(x), '02x') for x in d] - d = [d[i: i + 16] for i in xrange(0, len(d), 16)] + d = [d[i: i + 16] for i in range(0, len(d), 16)] d = [' '.join(x) for x in d] d = os.linesep.join(d) @@ -401,7 +402,7 @@ class Client: pcrsel_len = max((i >> 3) + 1, 3) pcrsel = [0] * pcrsel_len pcrsel[i >> 3] = 1 << (i & 7) - pcrsel = ''.join(map(chr, pcrsel)) + pcrsel = ''.join(map(chr, pcrsel)).encode() fmt = '>HII IHB%us' % (pcrsel_len) cmd = struct.pack(fmt, @@ -443,7 +444,7 @@ class Client: TPM2_CC_PCR_EXTEND, i, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), 1, bank_alg, dig) self.send_cmd(cmd) @@ -457,7 +458,7 @@ class Client: TPM2_RH_NULL, TPM2_RH_NULL, 16, - '\0' * 16, + ('\0' * 16).encode(), 0, session_type, TPM2_ALG_NULL, @@ -472,7 +473,7 @@ class Client: for i in pcrs: pcr = self.read_pcr(i, bank_alg) - if pcr == None: + if pcr is None: return None x += pcr @@ -489,7 +490,7 @@ class Client: pcrsel = [0] * pcrsel_len for i in pcrs: pcrsel[i >> 3] |= 1 << (i & 7) - pcrsel = ''.join(map(chr, pcrsel)) + pcrsel = ''.join(map(chr, pcrsel)).encode() fmt = '>HII IH%usIHB3s' % ds cmd = struct.pack(fmt, @@ -497,7 +498,8 @@ class Client: struct.calcsize(fmt), TPM2_CC_POLICY_PCR, handle, - len(dig), str(dig), + len(dig), + bytes(dig), 1, bank_alg, pcrsel_len, pcrsel) @@ -534,7 +536,7 @@ class Client: self.send_cmd(cmd) - def create_root_key(self, auth_value = ''): + def create_root_key(self, auth_value = bytes()): attributes = \ Public.FIXED_TPM | \ Public.FIXED_PARENT | \ @@ -570,11 +572,11 @@ class Client: TPM2_CC_CREATE_PRIMARY, TPM2_RH_OWNER, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), len(sensitive), - str(sensitive), + bytes(sensitive), len(public), - str(public), + bytes(public), 0, 0) return struct.unpack('>I', self.send_cmd(cmd)[10:14])[0] @@ -587,7 +589,7 @@ class Client: attributes = 0 if not policy_dig: attributes |= Public.USER_WITH_AUTH - policy_dig = '' + policy_dig = bytes() auth_cmd = AuthCommand() sensitive = SensitiveCreate(user_auth=auth_value, data=data) @@ -608,11 +610,11 @@ class Client: TPM2_CC_CREATE, parent_key, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), len(sensitive), - str(sensitive), + bytes(sensitive), len(public), - str(public), + bytes(public), 0, 0) rsp = self.send_cmd(cmd) @@ -635,7 +637,7 @@ class Client: TPM2_CC_LOAD, parent_key, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), blob) data_handle = struct.unpack('>I', self.send_cmd(cmd)[10:14])[0] @@ -653,7 +655,7 @@ class Client: TPM2_CC_UNSEAL, data_handle, len(auth_cmd), - str(auth_cmd)) + bytes(auth_cmd)) try: rsp = self.send_cmd(cmd) @@ -675,7 +677,7 @@ class Client: TPM2_CC_DICTIONARY_ATTACK_LOCK_RESET, TPM2_RH_LOCKOUT, len(auth_cmd), - str(auth_cmd)) + bytes(auth_cmd)) self.send_cmd(cmd) @@ -693,7 +695,7 @@ class Client: more_data, cap, cnt = struct.unpack('>BII', rsp[:9]) rsp = rsp[9:] - for i in xrange(0, cnt): + for i in range(0, cnt): handle = struct.unpack('>I', rsp[:4])[0] handles.append(handle) rsp = rsp[4:] diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 728be7c69b76..9d764306887b 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -20,8 +20,8 @@ class SmokeTest(unittest.TestCase): self.client.close() def test_seal_with_auth(self): - data = 'X' * 64 - auth = 'A' * 15 + data = ('X' * 64).encode() + auth = ('A' * 15).encode() blob = self.client.seal(self.root_key, data, auth, None) result = self.client.unseal(self.root_key, blob, auth, None) @@ -30,8 +30,8 @@ class SmokeTest(unittest.TestCase): def test_seal_with_policy(self): handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) - data = 'X' * 64 - auth = 'A' * 15 + data = ('X' * 64).encode() + auth = ('A' * 15).encode() pcrs = [16] try: @@ -58,14 +58,15 @@ class SmokeTest(unittest.TestCase): self.assertEqual(data, result) def test_unseal_with_wrong_auth(self): - data = 'X' * 64 - auth = 'A' * 20 + data = ('X' * 64).encode() + auth = ('A' * 20).encode() rc = 0 blob = self.client.seal(self.root_key, data, auth, None) try: - result = self.client.unseal(self.root_key, blob, auth[:-1] + 'B', None) - except ProtocolError, e: + result = self.client.unseal(self.root_key, blob, + auth[:-1] + 'B'.encode(), None) + except ProtocolError as e: rc = e.rc self.assertEqual(rc, tpm2.TPM2_RC_AUTH_FAIL) @@ -73,8 +74,8 @@ class SmokeTest(unittest.TestCase): def test_unseal_with_wrong_policy(self): handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) - data = 'X' * 64 - auth = 'A' * 17 + data = ('X' * 64).encode() + auth = ('A' * 17).encode() pcrs = [16] try: @@ -91,7 +92,7 @@ class SmokeTest(unittest.TestCase): # This should succeed. ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1) - self.client.extend_pcr(1, 'X' * ds) + self.client.extend_pcr(1, ('X' * ds).encode()) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) @@ -108,7 +109,7 @@ class SmokeTest(unittest.TestCase): # Then, extend a PCR that is part of the policy and try to unseal. # This should fail. - self.client.extend_pcr(16, 'X' * ds) + self.client.extend_pcr(16, ('X' * ds).encode()) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) @@ -119,7 +120,7 @@ class SmokeTest(unittest.TestCase): self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) - except ProtocolError, e: + except ProtocolError as e: rc = e.rc self.client.flush_context(handle) except: @@ -130,13 +131,13 @@ class SmokeTest(unittest.TestCase): def test_seal_with_too_long_auth(self): ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1) - data = 'X' * 64 - auth = 'A' * (ds + 1) + data = ('X' * 64).encode() + auth = ('A' * (ds + 1)).encode() rc = 0 try: blob = self.client.seal(self.root_key, data, auth, None) - except ProtocolError, e: + except ProtocolError as e: rc = e.rc self.assertEqual(rc, tpm2.TPM2_RC_SIZE) @@ -152,7 +153,7 @@ class SmokeTest(unittest.TestCase): 0xDEADBEEF) self.client.send_cmd(cmd) - except IOError, e: + except IOError as e: rejected = True except: pass @@ -212,7 +213,7 @@ class SmokeTest(unittest.TestCase): self.client.tpm.write(cmd) rsp = self.client.tpm.read() - except IOError, e: + except IOError as e: # read the response rsp = self.client.tpm.read() rejected = True @@ -283,7 +284,7 @@ class SpaceTest(unittest.TestCase): rc = 0 try: space1.send_cmd(cmd) - except ProtocolError, e: + except ProtocolError as e: rc = e.rc self.assertEqual(rc, tpm2.TPM2_RC_COMMAND_CODE | diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index caab980211a6..315e85cabeda 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -110,8 +110,6 @@ static inline void free_page(unsigned long addr) const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -#define uninitialized_var(x) x = x - # ifndef likely # define likely(x) (__builtin_expect(!!(x), 1)) # endif |