From 297d6b6e56c2977fc504c61bbeeaa21296923f89 Mon Sep 17 00:00:00 2001 From: Paul Meyer Date: Tue, 14 Nov 2017 13:06:47 -0700 Subject: hv: kvp: Avoid reading past allocated blocks from KVP file While reading in more than one block (50) of KVP records, the allocation goes per block, but the reads used the total number of allocated records (without resetting the pointer/stream). This causes the records buffer to overrun when the refresh reads more than one block over the previous capacity (e.g. reading more than 100 KVP records whereas the in-memory database was empty before). Fix this by reading the correct number of KVP records from file each time. Signed-off-by: Paul Meyer Signed-off-by: Long Li Cc: stable@vger.kernel.org Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- tools/hv/hv_kvp_daemon.c | 70 ++++++++++-------------------------------------- 1 file changed, 14 insertions(+), 56 deletions(-) (limited to 'tools') diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index eaa3bec273c8..4c99c57736ce 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -193,11 +193,14 @@ static void kvp_update_mem_state(int pool) for (;;) { readp = &record[records_read]; records_read += fread(readp, sizeof(struct kvp_record), - ENTRIES_PER_BLOCK * num_blocks, - filep); + ENTRIES_PER_BLOCK * num_blocks - records_read, + filep); if (ferror(filep)) { - syslog(LOG_ERR, "Failed to read file, pool: %d", pool); + syslog(LOG_ERR, + "Failed to read file, pool: %d; error: %d %s", + pool, errno, strerror(errno)); + kvp_release_lock(pool); exit(EXIT_FAILURE); } @@ -210,6 +213,7 @@ static void kvp_update_mem_state(int pool) if (record == NULL) { syslog(LOG_ERR, "malloc failed"); + kvp_release_lock(pool); exit(EXIT_FAILURE); } continue; @@ -224,15 +228,11 @@ static void kvp_update_mem_state(int pool) fclose(filep); kvp_release_lock(pool); } + static int kvp_file_init(void) { int fd; - FILE *filep; - size_t records_read; char *fname; - struct kvp_record *record; - struct kvp_record *readp; - int num_blocks; int i; int alloc_unit = sizeof(struct kvp_record) * ENTRIES_PER_BLOCK; @@ -246,61 +246,19 @@ static int kvp_file_init(void) for (i = 0; i < KVP_POOL_COUNT; i++) { fname = kvp_file_info[i].fname; - records_read = 0; - num_blocks = 1; sprintf(fname, "%s/.kvp_pool_%d", KVP_CONFIG_LOC, i); fd = open(fname, O_RDWR | O_CREAT | O_CLOEXEC, 0644 /* rw-r--r-- */); if (fd == -1) return 1; - - filep = fopen(fname, "re"); - if (!filep) { - close(fd); - return 1; - } - - record = malloc(alloc_unit * num_blocks); - if (record == NULL) { - fclose(filep); - close(fd); - return 1; - } - for (;;) { - readp = &record[records_read]; - records_read += fread(readp, sizeof(struct kvp_record), - ENTRIES_PER_BLOCK, - filep); - - if (ferror(filep)) { - syslog(LOG_ERR, "Failed to read file, pool: %d", - i); - exit(EXIT_FAILURE); - } - - if (!feof(filep)) { - /* - * We have more data to read. - */ - num_blocks++; - record = realloc(record, alloc_unit * - num_blocks); - if (record == NULL) { - fclose(filep); - close(fd); - return 1; - } - continue; - } - break; - } kvp_file_info[i].fd = fd; - kvp_file_info[i].num_blocks = num_blocks; - kvp_file_info[i].records = record; - kvp_file_info[i].num_records = records_read; - fclose(filep); - + kvp_file_info[i].num_blocks = 1; + kvp_file_info[i].records = malloc(alloc_unit); + if (kvp_file_info[i].records == NULL) + return 1; + kvp_file_info[i].num_records = 0; + kvp_update_mem_state(i); } return 0; -- cgit v1.2.3 From 555b4ec4d589eb0fcdf9d7b4b05a71984dbcaeee Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Nov 2017 15:13:29 -0300 Subject: perf evlist: Set the correct idx when adding dummy events The evsel->idx field is used mainly to access the right bucket in per-event arrays such as the annotation ones, but also to set evsel->tracking, that in turn will decide what of the events will ask for PERF_RECORD_{MMAP,COMM,EXEC} to be generated, i.e. which perf_event_attr will have its mmap, etc fields set. When we were adding the "dummy" event using perf_evlist__add_dummy() we were not setting it correctly, which could result in multiple tracking events. Now that I'll try using a dummy event to be the tracking one when using 'perf record --delay', i.e. when we process the --delay setting we may already have the evlist set up, like with: perf record -e cycles,instructions --delay 1000 ./workload We will need to add a "dummy" event, then reset evsel->tracking for the first event, "cycles", and set it instead to the dummy one, and also setting its attr.enable_on_exec, so that we get the PERF_RECORD_MMAP, etc metadata events while waiting to enable the explicitely requested events, so lets get this straight and set the right evsel->idx. Cc: Adrian Hunter Cc: Bram Stolk Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-nrdfchshqxf7diszhxcecqb9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c6c891e154a6..ccb749f9a83f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -257,7 +257,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist) .config = PERF_COUNT_SW_DUMMY, .size = sizeof(attr), /* to capture ABI version */ }; - struct perf_evsel *evsel = perf_evsel__new(&attr); + struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries); if (evsel == NULL) return -ENOMEM; -- cgit v1.2.3 From dffdcbdbb0205ac10daec64f7fa519f1904f5481 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Nov 2017 15:34:34 -0300 Subject: perf record: Generate PERF_RECORD_{MMAP,COMM,EXEC} with --delay When we use an initial delay, e.g.: 'perf record --delay 1000', we do not enable the events until that delay has passed after we started the workload, including the tracking event, i.e. the one for which we have attr.mmap, etc, enabled to ask the kernel to generate the PERF_RECORD_{MMAP,COMM,EXEC} metadata events that will then allow us to resolve addresses in samples to the map, dso and symbol. There will be a shadow that even synthesizing samples won't cover, i.e. the workload that we start and other processes forking while we wait for the initial delay to expire. So use a dummy event to be the tracking one and make it be enabled on exec. Before: # perf record --delay 1000 stress --cpu 1 --timeout 5 stress: info: [9029] dispatching hogs: 1 cpu, 0 io, 0 vm, 0 hdd stress: info: [9029] successful run completed in 5s [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 0.624 MB perf.data (15908 samples) ] # perf script | head :9031 9031 32001.826888: 1 cycles:ppp: ffffffff831aa30d event_function (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826893: 1 cycles:ppp: ffffffff8300d1a0 intel_bts_enable_local (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826895: 7 cycles:ppp: ffffffff83023870 sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826897: 103 cycles:ppp: ffffffff8300c331 intel_pmu_handle_irq (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826899: 1615 cycles:ppp: ffffffff830231f8 native_sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826902: 26724 cycles:ppp: ffffffff8384c6a7 native_irq_return_iret (/lib/modules/4.14.0-rc6+/build/vmlinux) :9031 9031 32001.826913: 329739 cycles:ppp: 7fb2a5410932 [unknown] ([unknown]) :9031 9031 32001.827033: 1225451 cycles:ppp: 7fb2a5410930 [unknown] ([unknown]) :9031 9031 32001.827474: 1391725 cycles:ppp: 7fb2a5410930 [unknown] ([unknown]) :9031 9031 32001.827978: 1233697 cycles:ppp: 7fb2a5410928 [unknown] ([unknown]) # After: # perf record --delay 1000 stress --cpu 1 --timeout 5 stress: info: [9741] dispatching hogs: 1 cpu, 0 io, 0 vm, 0 hdd stress: info: [9741] successful run completed in 5s [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 0.751 MB perf.data (15976 samples) ] # perf script | head stress 9742 32110.959106: 1 cycles:ppp: ffffffff831b26f6 __perf_event_task_sched_in (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959110: 1 cycles:ppp: ffffffff8300c2e9 intel_pmu_handle_irq (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959112: 7 cycles:ppp: ffffffff830231e0 native_sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959115: 101 cycles:ppp: ffffffff83023870 sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959117: 1533 cycles:ppp: ffffffff830231f8 native_sched_clock (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959119: 23992 cycles:ppp: ffffffff831b0900 ctx_sched_in (/lib/modules/4.14.0-rc6+/build/vmlinux) stress 9742 32110.959129: 329406 cycles:ppp: 7f4b1b661930 __random_r (/usr/lib64/libc-2.25.so) stress 9742 32110.959249: 1288322 cycles:ppp: 5566e1e7cbc9 hogcpu (/usr/bin/stress) stress 9742 32110.959712: 1464046 cycles:ppp: 7f4b1b66179e __random (/usr/lib64/libc-2.25.so) stress 9742 32110.960241: 1266918 cycles:ppp: 7f4b1b66195b __random_r (/usr/lib64/libc-2.25.so) # Reported-by: Bram Stolk Tested-by: Bram Stolk Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: 6619a53ef757 ("perf record: Add --initial-delay option") Link: http://lkml.kernel.org/n/tip-nrdfchshqxf7diszhxcecqb9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 3d7f33e19df2..5f78ce943407 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -339,6 +339,22 @@ static int record__open(struct record *rec) struct perf_evsel_config_term *err_term; int rc = 0; + /* + * For initial_delay we need to add a dummy event so that we can track + * PERF_RECORD_MMAP while we wait for the initial delay to enable the + * real events, the ones asked by the user. + */ + if (opts->initial_delay) { + if (perf_evlist__add_dummy(evlist)) + return -ENOMEM; + + pos = perf_evlist__first(evlist); + pos->tracking = 0; + pos = perf_evlist__last(evlist); + pos->tracking = 1; + pos->attr.enable_on_exec = 1; + } + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, pos) { -- cgit v1.2.3 From 59622fd496a3175c7bf549046e091d81c303ecff Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 20 Oct 2017 13:27:55 -0700 Subject: perf record: Fix -c/-F options for cpu event aliases The Intel PMU event aliases have a implicit period= specifier to set the default period. Unfortunately this breaks overriding these periods with -c or -F, because the alias terms look like they are user specified to the internal parser, and user specified event qualifiers override the command line options. Track that they are coming from aliases by adding a "weak" state to the term. Any weak terms don't override command line options. I only did it for -c/-F for now, I think that's the only case that's broken currently. Before: $ perf record -c 1000 -vv -e uops_issued.any ... { sample_period, sample_freq } 2000003 After: $ perf record -c 1000 -vv -e uops_issued.any ... { sample_period, sample_freq } 1000 Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20171020202755.21410-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 12 ++++++++---- tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 2 ++ tools/perf/util/parse-events.h | 3 +++ tools/perf/util/pmu.c | 5 +++++ 5 files changed, 19 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f894893c203d..bfde6a7a80f2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -733,12 +733,16 @@ static void apply_config_terms(struct perf_evsel *evsel, list_for_each_entry(term, config_terms, list) { switch (term->type) { case PERF_EVSEL__CONFIG_TERM_PERIOD: - attr->sample_period = term->val.period; - attr->freq = 0; + if (!(term->weak && opts->user_interval != ULLONG_MAX)) { + attr->sample_period = term->val.period; + attr->freq = 0; + } break; case PERF_EVSEL__CONFIG_TERM_FREQ: - attr->sample_freq = term->val.freq; - attr->freq = 1; + if (!(term->weak && opts->user_freq != UINT_MAX)) { + attr->sample_freq = term->val.freq; + attr->freq = 1; + } break; case PERF_EVSEL__CONFIG_TERM_TIME: if (term->val.time) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 9277df96ffda..157f49e8a772 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -67,6 +67,7 @@ struct perf_evsel_config_term { bool overwrite; char *branch; } val; + bool weak; }; struct perf_stat_evsel; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index a7fcd95961ef..170316795a18 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1116,6 +1116,7 @@ do { \ INIT_LIST_HEAD(&__t->list); \ __t->type = PERF_EVSEL__CONFIG_TERM_ ## __type; \ __t->val.__name = __val; \ + __t->weak = term->weak; \ list_add_tail(&__t->list, head_terms); \ } while (0) @@ -2410,6 +2411,7 @@ static int new_term(struct parse_events_term **_term, *term = *temp; INIT_LIST_HEAD(&term->list); + term->weak = false; switch (term->type_val) { case PARSE_EVENTS__TERM_TYPE_NUM: diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index be337c266697..88108cd11b4c 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -101,6 +101,9 @@ struct parse_events_term { /* error string indexes for within parsed string */ int err_term; int err_val; + + /* Coming from implicit alias */ + bool weak; }; struct parse_events_error { diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 07cb2ac041d7..80fb1593913a 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -405,6 +405,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, parse_events_terms__purge(&list); return ret; } + /* + * Weak terms don't override command line options, + * which we don't want for implicit terms in aliases. + */ + cloned->weak = true; list_add_tail(&cloned->list, &list); } list_splice(&list, terms); -- cgit v1.2.3 From 35c33633abc14b906e84b7b0115ede6df6830120 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 7 Nov 2017 16:22:46 -0800 Subject: perf trace: Fix an exit code of trace__symbols_init Currently if trace_event__register_resolver() fails, we return -errno, but we can't be sure that errno isn't zero in this case. Signed-off-by: Andrei Vagin Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Vasily Averin Link: http://lkml.kernel.org/r/20171108002246.8924-2-avagin@openvz.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f2757d38c7d7..84debdbad327 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1152,12 +1152,14 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) if (trace->host == NULL) return -ENOMEM; - if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0) - return -errno; + err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr); + if (err < 0) + goto out; err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, evlist->threads, trace__tool_process, false, trace->opts.proc_map_timeout, 1); +out: if (err) symbol__exit(); -- cgit v1.2.3 From 8e2d8e204247aa9eeb87893f6b8bf0cf29428b31 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 9 Nov 2017 12:03:40 -0300 Subject: perf evsel: Fix up leftover perf_evsel_stat usage via evsel->priv I forgot one conversion, which got noticed by Thomas when running: $ perf stat -e '{cpu-clock,instructions}' kill kill: not enough arguments Segmentation fault (core dumped) $ Fix it, those stats are in evsel->stats, not anymore in evsel->priv. Reported-by: Thomas-Mich Richter Tested-by: Thomas-Mich Richter Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Hendrik Brueckner Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: e669e833da8d ("perf evsel: Restore evsel->priv as a tool private area") Link: http://lkml.kernel.org/r/20171109150046.GN4333@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index bfde6a7a80f2..d5fbcf8c7aa7 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1375,7 +1375,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader, static int perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) { - struct perf_stat_evsel *ps = leader->priv; + struct perf_stat_evsel *ps = leader->stats; u64 read_format = leader->attr.read_format; int size = perf_evsel__read_size(leader); u64 *data = ps->group_data; -- cgit v1.2.3 From 501e5bbec3c19498fa520fd3ffd68bd907f31bf7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 9 Nov 2017 16:04:26 -0300 Subject: perf script: Fix --per-event-dump for auxtrace synth evsels When processing PERF_RECORD_AUXTRACE_INFO several perf_evsel entries will be synthesized and inserted into session->evlist, eventually ending in perf_script.tool.sample(), which ends up calling builtin-script.c's process_event(), that expects evsel->priv to be a perf_evsel_script object with a valid FILE pointer in fp. So we need to intercept the processing of PERF_RECORD_AUXTRACE_INFO and then setup evsel->priv for these newly created perf_evsel instances, do it to fix the segfault in process_event() trying to use a NULL for that FILE pointer. Reported-by: Alexander Shishkin Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Wang Nan Cc: yuzhoujian Fixes: a14390fde64e ("perf script: Allow creating per-event dump files") Link: http://lkml.kernel.org/n/tip-bthnur8r8de01gxvn2qayx6e@git.kernel.org [ Merge fix by Ravi Bangoria before pushing upstream to preserv bisectability ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 68f36dc0344f..9b43bda45a41 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1955,6 +1955,16 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script) struct perf_evsel *evsel; evlist__for_each_entry(script->session->evlist, evsel) { + /* + * Already setup? I.e. we may be called twice in cases like + * Intel PT, one for the intel_pt// and dummy events, then + * for the evsels syntheized from the auxtrace info. + * + * Ses perf_script__process_auxtrace_info. + */ + if (evsel->priv != NULL) + continue; + evsel->priv = perf_evsel_script__new(evsel, script->session->data); if (evsel->priv == NULL) goto out_err_fclose; @@ -2838,6 +2848,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } +#ifdef HAVE_AUXTRACE_SUPPORT +static int perf_script__process_auxtrace_info(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session) +{ + int ret = perf_event__process_auxtrace_info(tool, event, session); + + if (ret == 0) { + struct perf_script *script = container_of(tool, struct perf_script, tool); + + ret = perf_script__setup_per_event_dump(script); + } + + return ret; +} +#else +#define perf_script__process_auxtrace_info 0 +#endif + int cmd_script(int argc, const char **argv) { bool show_full_info = false; @@ -2866,7 +2895,7 @@ int cmd_script(int argc, const char **argv) .feature = perf_event__process_feature, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, - .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace_info = perf_script__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, .auxtrace_error = perf_event__process_auxtrace_error, .stat = perf_event__process_stat_event, -- cgit v1.2.3 From 4a2233b194c77ae1ea8304cb7c00b551de4313f0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 13 Nov 2017 16:06:29 -0300 Subject: perf machine: Guard against NULL in machine__exit() A recent fix for 'perf trace' introduced a bug where machine__exit(trace->host) could be called while trace->host was still NULL, so make this more robust by guarding against NULL, just like free() does. The problem happens, for instance, when !root users try to run 'perf trace': [acme@jouet linux]$ trace Error: No permissions to read /sys/kernel/debug/tracing/events/raw_syscalls/sys_(enter|exit) Hint: Try 'sudo mount -o remount,mode=755 /sys/kernel/debug/tracing' perf: Segmentation fault Obtained 7 stack frames. [0x4f1b2e] /lib64/libc.so.6(+0x3671f) [0x7f43a1dd971f] [0x4f3fec] [0x47468b] [0x42a2db] /lib64/libc.so.6(__libc_start_main+0xe9) [0x7f43a1dc3509] [0x42a6c9] Segmentation fault (core dumped) [acme@jouet linux]$ Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrei Vagin Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Vasily Averin Cc: Wang Nan Fixes: 33974a414ce2 ("perf trace: Call machine__exit() at exit") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 6a8d03c3d9b7..270f3223c6df 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -172,6 +172,9 @@ void machine__exit(struct machine *machine) { int i; + if (machine == NULL) + return; + machine__destroy_kernel_maps(machine); map_groups__exit(&machine->kmaps); dsos__exit(&machine->dsos); -- cgit v1.2.3 From af98f2273fd0af31ce327cd1406b67c7be0b6734 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Nov 2017 09:15:42 +0900 Subject: perf help: Fix a bug during strstart() conversion The commit 8e99b6d4533c changed prefixcmp() to strstart() but missed to change the return value in some place. It makes perf help print annoying output even for sane config items like below: $ perf help '.root': unsupported man viewer sub key. ... Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Tested-by: Taeung Song Cc: Jiri Olsa Cc: Sihyeon Jang Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20171114001542.GA16464@sejong Fixes: 8e99b6d4533c ("tools include: Adopt strstarts() from the kernel") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-help.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index bd1fedef3d1c..a0f7ed2b869b 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb) add_man_viewer(value); return 0; } - if (!strstarts(var, "man.")) + if (strstarts(var, "man.")) return add_man_viewer_info(var, value); return 0; @@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd) if (!perf_cmd) return "perf"; - else if (!strstarts(perf_cmd, "perf")) + else if (strstarts(perf_cmd, "perf")) return perf_cmd; return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s; -- cgit v1.2.3 From 05d0e62d9fa0f1002cf82009ef31b36174da5472 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Tue, 14 Nov 2017 08:55:40 +0530 Subject: perf annotate: Do not truncate instruction names at 6 chars There are many instructions, esp on PowerPC, whose mnemonics are longer than 6 characters. Using precision limit causes truncation of such mnemonics. Fix this by removing precision limit. Note that, 'width' is still 6, so alignment won't get affected for length <= 6. Before: li r11,-1 xscvdp vs1,vs1 add. r10,r10,r11 After: li r11,-1 xscvdpsxds vs1,vs1 add. r10,r10,r11 Reported-by: Donald Stence Signed-off-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Taeung Song Link: http://lkml.kernel.org/r/20171114032540.4564-1-ravi.bangoria@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index da1c4c4a0dd8..3369c7830260 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -165,7 +165,7 @@ static void ins__delete(struct ins_operands *ops) static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { - return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw); + return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw); } int ins__scnprintf(struct ins *ins, char *bf, size_t size, @@ -230,12 +230,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { if (ops->target.name) - return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name); + return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name); if (ops->target.addr == 0) return ins__raw_scnprintf(ins, bf, size, ops); - return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr); + return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr); } static struct ins_ops call_ops = { @@ -299,7 +299,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, c++; } - return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64, + return scnprintf(bf, size, "%-6s %.*s%" PRIx64, ins->name, c ? c - ops->raw : 0, ops->raw, ops->target.offset); } @@ -372,7 +372,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size, if (ops->locked.ins.ops == NULL) return ins__raw_scnprintf(ins, bf, size, ops); - printed = scnprintf(bf, size, "%-6.6s ", ins->name); + printed = scnprintf(bf, size, "%-6s ", ins->name); return printed + ins__scnprintf(&ops->locked.ins, bf + printed, size - printed, ops->locked.ops); } @@ -448,7 +448,7 @@ out_free_source: static int mov__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { - return scnprintf(bf, size, "%-6.6s %s,%s", ins->name, + return scnprintf(bf, size, "%-6s %s,%s", ins->name, ops->source.name ?: ops->source.raw, ops->target.name ?: ops->target.raw); } @@ -488,7 +488,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops static int dec__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { - return scnprintf(bf, size, "%-6.6s %s", ins->name, + return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name ?: ops->target.raw); } @@ -500,7 +500,7 @@ static struct ins_ops dec_ops = { static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size, struct ins_operands *ops __maybe_unused) { - return scnprintf(bf, size, "%-6.6s", "nop"); + return scnprintf(bf, size, "%-6s", "nop"); } static struct ins_ops nop_ops = { @@ -924,7 +924,7 @@ void disasm_line__free(struct disasm_line *dl) int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw) { if (raw || !dl->ins.ops) - return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw); + return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw); return ins__scnprintf(&dl->ins, bf, size, &dl->ops); } -- cgit v1.2.3 From ccafc38f1c778847ab6d53dd7933260426731cf3 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 14 Nov 2017 08:18:46 +0100 Subject: perf test shell: Fix check open filename arg using 'perf trace' on s390x This 'perf test' case fails on s390x. The 'touch' command on s390x uses the 'openat' system call to open the file named on the command line: [root@s35lp76 perf]# perf probe -l probe:vfs_getname (on getname_flags:72@fs/namei.c with pathname) [root@s35lp76 perf]# perf trace -e open touch /tmp/abc 0.400 ( 0.015 ms): touch/27542 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3 [root@s35lp76 perf]# There is no 'open' system call for file '/tmp/abc'. Instead the 'openat' system call is used: [root@s35lp76 perf]# strace touch /tmp/abc execve("/usr/bin/touch", ["touch", "/tmp/abc"], 0x3ffd547ec98 /* 30 vars */) = 0 [...] openat(AT_FDCWD, "/tmp/abc", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 [...] On s390x the 'egrep' command does not find a matching pattern and returns an error. Fix this for s390x create a platform dependent command line to enable the 'perf probe' call to listen to the 'openat' system call and get the expected output. Signed-off-by: Thomas-Mich Richter Tested-by: Arnaldo Carvalho de Melo Cc: Hendrik Brueckner Cc: Thomas-Mich Richter LPU-Reference: 20171114071847.2381-1-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-3qf38jk0prz54rhmhyu871my@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/trace+probe_vfs_getname.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 2e68c5f120da..2a9ef080efd0 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -17,8 +17,10 @@ skip_if_no_perf_probe || exit 2 file=$(mktemp /tmp/temporary_file.XXXXX) trace_open_vfs_getname() { - perf trace -e open touch $file 2>&1 | \ - egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" + test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; } + + perf trace -e ${svc:-open} touch $file 2>&1 | \ + egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } -- cgit v1.2.3 From d5c5e46aa7a2b256a526f9ce832ffbf622c3c19a Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 14 Nov 2017 08:18:47 +0100 Subject: perf test shell: Fix test case probe libc's inet_pton on s390x The 'perf test' case "probe libc's inet_pton & backtrace it with ping" fails on s390x. The reason is the 'realpath /lib64/ld*.so.* | uniq' line which returns 2 libraries: root@s35lp76 shell]# realpath /lib64/ld*.so.* | uniq /usr/lib64/ld-2.26.so /usr/lib64/ld_pre_smc.so.1.0.1 [root@s35lp76 shell] This output makes the "perf probe" command lines invalid. Use ldd tool to find out the libraries required by "bash" and check if symbol "inet_pton" is part of the "libc" library. Some distros do not have a /lib64 directory. I have also added a check for the existence of an IPv6 network interface before it is being used. Committer changes: We can't really use ldd for libc, as in some systems, such as x86_64, it has hardlinks and then ldd sees one and the kernel the other, so grep for libc in /proc/self/maps to get the one we'll receive from PERF_RECORD_MMAP. Thomas checked this change and acked it. Signed-off-by: Thomas-Mich Richter Tested-by: Arnaldo Carvalho de Melo Suggested-by: Hendrik Brückner Reviewed-by: Hendrik Brückner Link: http://lkml.kernel.org/r/20171114133409.GN8836@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/trace+probe_libc_inet_pton.sh | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh index 7a84d73324e3..8b3da21a08f1 100755 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -10,8 +10,8 @@ . $(dirname $0)/lib/probe.sh -ld=$(realpath /lib64/ld*.so.* | uniq) -libc=$(echo $ld | sed 's/ld/libc/g') +libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') +nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254 trace_libc_inet_pton_backtrace() { idx=0 @@ -37,6 +37,9 @@ trace_libc_inet_pton_backtrace() { done } +# Check for IPv6 interface existence +ip a sh lo | fgrep -q inet6 || exit 2 + skip_if_no_perf_probe && \ perf probe -q $libc inet_pton && \ trace_libc_inet_pton_backtrace -- cgit v1.2.3 From 5b0d1cb40698056f3df8ed579dde4b80c6b7508d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Nov 2017 11:01:06 -0300 Subject: perf evlist: Add helper to check if attr.exclude_kernel is set in all evsels The warning about kptr_restrict needs to be emitted only when it is set and we ask for kernel space samples, so add a helper to help with that. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-fh7drty6yljei9gxxzer6eup@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 12 ++++++++++++ tools/perf/util/evlist.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ccb749f9a83f..b62e523a7035 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1786,3 +1786,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, state_err: return; } + +bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (!evsel->attr.exclude_kernel) + return false; + } + + return true; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index e72ae64c11ac..491f69542920 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -312,4 +312,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, union perf_event *event); + +bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); #endif /* __PERF_EVLIST_H */ -- cgit v1.2.3 From 3f0a4c873cb341d0cb61493d8dec7662bcaa7ca7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Nov 2017 11:12:11 -0300 Subject: perf report: Ignore kptr_restrict when not sampling the kernel If none of the evsels has attr.exclude_kernel set to zero, no kernel samples, so no point in warning the user about problems in processing kernel samples, as there will be none. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-7dn926v3at8txxkky92aesz2@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1394cd8d96f7..af5dd038195e 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -441,6 +441,9 @@ static void report__warn_kptr_restrict(const struct report *rep) struct map *kernel_map = machine__kernel_map(&rep->session->machines.host); struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL; + if (perf_evlist__exclude_kernel(rep->session->evlist)) + return; + if (kernel_map == NULL || (kernel_map->dso->hit && (kernel_kmap->ref_reloc_sym == NULL || -- cgit v1.2.3 From b0ebd811af889721d3fbef3657092cf028c16b7c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Nov 2017 11:03:19 -0300 Subject: perf record: Ignore kptr_restrict when not sampling the kernel If we're not sampling the kernel, we shouldn't care about kptr_restrict neither synthesize anything for assisting in resolving kernel samples, like the reference relocation symbol or kernel modules information. Before: $ cat /proc/sys/kernel/kptr_restrict /proc/sys/kernel/perf_event_paranoid 2 2 $ perf record sleep 1 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check /proc/sys/kernel/kptr_restrict. Samples in kernel functions may not be resolved if a suitable vmlinux file is not found in the buildid cache or in the vmlinux path. Samples in kernel modules won't be resolved at all. If some relocation was applied (e.g. kexec) symbols may be misresolved even with a suitable vmlinux or kallsyms file. Couldn't record kernel reference relocation symbol Symbol resolution may be skewed if relocation was used (e.g. kexec). Check /proc/kallsyms permission or run as root. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ] $ perf evlist -v cycles:uppp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ After: $ perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (10 samples) ] $ Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-t025e9zftbx2b8cq2w01g5e5@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 5f78ce943407..003255910c05 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -765,17 +765,19 @@ static int record__synthesize(struct record *rec, bool tail) goto out; } - err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, - machine); - WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n" - "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" - "Check /proc/kallsyms permission or run as root.\n"); - - err = perf_event__synthesize_modules(tool, process_synthesized_event, - machine); - WARN_ONCE(err < 0, "Couldn't record kernel module information.\n" - "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" - "Check /proc/modules permission or run as root.\n"); + if (!perf_evlist__exclude_kernel(rec->evlist)) { + err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, + machine); + WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n" + "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" + "Check /proc/kallsyms permission or run as root.\n"); + + err = perf_event__synthesize_modules(tool, process_synthesized_event, + machine); + WARN_ONCE(err < 0, "Couldn't record kernel module information.\n" + "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" + "Check /proc/modules permission or run as root.\n"); + } if (perf_guest) { machines__process_guests(&session->machines, @@ -1709,7 +1711,7 @@ int cmd_record(int argc, const char **argv) err = -ENOMEM; - if (symbol_conf.kptr_restrict) + if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist)) pr_warning( "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n" "check /proc/sys/kernel/kptr_restrict.\n\n" -- cgit v1.2.3 From df7ccfa21ef343c602ae4aa1eb7893da4408b219 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Nov 2017 13:30:19 -0300 Subject: perf top: Ignore kptr_restrict when not sampling the kernel If all events have attr.exclude_kernel set, no need to look at kptr_restrict. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-yegpzg5bf2im69g0tfizqaqz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 477a8699f0b5..1b01c277bab9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -732,14 +732,16 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!machine->kptr_restrict_warned && symbol_conf.kptr_restrict && al.cpumode == PERF_RECORD_MISC_KERNEL) { - ui__warning( + if (!perf_evlist__exclude_kernel(top->session->evlist)) { + ui__warning( "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict.\n\n" "Kernel%s samples will not be resolved.\n", al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ? " modules" : ""); - if (use_browser <= 0) - sleep(5); + if (use_browser <= 0) + sleep(5); + } machine->kptr_restrict_warned = true; } -- cgit v1.2.3 From 89d0aeab4252adc2a7ea693637dd21c588bfa2d1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 14 Nov 2017 10:23:39 +0100 Subject: perf top: Fix window dimensions change handling The stdio perf top crashes when we change the terminal window size. The reason is that we assumed we get the perf_top pointer as a signal handler argument which is not the case. Changing the SIGWINCH handler logic to change global resize variable, which is checked in the main thread loop. Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Tested-by: Ravi Bangoria Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-ysuzwz77oev1ftgvdscn9bpu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1b01c277bab9..489573883936 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -77,6 +77,7 @@ #include "sane_ctype.h" static volatile int done; +static volatile int resize; #define HEADER_LINE_NR 5 @@ -86,10 +87,13 @@ static void perf_top__update_print_entries(struct perf_top *top) } static void perf_top__sig_winch(int sig __maybe_unused, - siginfo_t *info __maybe_unused, void *arg) + siginfo_t *info __maybe_unused, void *arg __maybe_unused) { - struct perf_top *top = arg; + resize = 1; +} +static void perf_top__resize(struct perf_top *top) +{ get_term_dimensions(&top->winsize); perf_top__update_print_entries(top); } @@ -477,7 +481,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) .sa_sigaction = perf_top__sig_winch, .sa_flags = SA_SIGINFO, }; - perf_top__sig_winch(SIGWINCH, NULL, top); + perf_top__resize(top); sigaction(SIGWINCH, &act, NULL); } else { signal(SIGWINCH, SIG_DFL); @@ -1032,6 +1036,11 @@ static int __cmd_top(struct perf_top *top) if (hits == top->samples) ret = perf_evlist__poll(top->evlist, 100); + + if (resize) { + perf_top__resize(top); + resize = 0; + } } ret = 0; -- cgit v1.2.3 From bdaab8c4b3db820b0946ed4516bc5ec811e0cc82 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Nov 2017 14:30:57 +0100 Subject: perf top: Use signal interface for SIGWINCH handler There's no need for SA_SIGINFO data in SIGWINCH handler, switching it to register the handler via signal interface as we do for the rest of the signals in perf top. Signed-off-by: Jiri Olsa Tested-by: Ravi Bangoria Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-elxp1vdnaog1scaj13cx7cu0@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 489573883936..9e0d2645ae13 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -86,8 +86,7 @@ static void perf_top__update_print_entries(struct perf_top *top) top->print_entries = top->winsize.ws_row - HEADER_LINE_NR; } -static void perf_top__sig_winch(int sig __maybe_unused, - siginfo_t *info __maybe_unused, void *arg __maybe_unused) +static void winch_sig(int sig __maybe_unused) { resize = 1; } @@ -477,12 +476,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) case 'e': prompt_integer(&top->print_entries, "Enter display entries (lines)"); if (top->print_entries == 0) { - struct sigaction act = { - .sa_sigaction = perf_top__sig_winch, - .sa_flags = SA_SIGINFO, - }; perf_top__resize(top); - sigaction(SIGWINCH, &act, NULL); + signal(SIGWINCH, winch_sig); } else { signal(SIGWINCH, SIG_DFL); } @@ -1363,12 +1358,8 @@ int cmd_top(int argc, const char **argv) get_term_dimensions(&top.winsize); if (top.print_entries == 0) { - struct sigaction act = { - .sa_sigaction = perf_top__sig_winch, - .sa_flags = SA_SIGINFO, - }; perf_top__update_print_entries(&top); - sigaction(SIGWINCH, &act, NULL); + signal(SIGWINCH, winch_sig); } status = __cmd_top(&top); -- cgit v1.2.3 From 321a7c35c90cc834851ceda18a8ee18f1d032b92 Mon Sep 17 00:00:00 2001 From: Satheesh Rajendran Date: Wed, 22 Nov 2017 22:13:53 +0530 Subject: perf bench numa: Fixup discontiguous/sparse numa nodes Certain systems are designed to have sparse/discontiguous nodes. On such systems, 'perf bench numa' hangs, shows wrong number of nodes and shows values for non-existent nodes. Handle this by only taking nodes that are exposed by kernel to userspace. Signed-off-by: Satheesh Rajendran Reviewed-by: Srikar Dronamraju Acked-by: Naveen N. Rao Link: http://lkml.kernel.org/r/1edbcd353c009e109e93d78f2f46381930c340fe.1511368645.git.sathnaga@linux.vnet.ibm.com Signed-off-by: Balamuruhan S Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/numa.c | 56 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index d95fdcc26f4b..944070e98a2c 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -216,6 +216,47 @@ static const char * const numa_usage[] = { NULL }; +/* + * To get number of numa nodes present. + */ +static int nr_numa_nodes(void) +{ + int i, nr_nodes = 0; + + for (i = 0; i < g->p.nr_nodes; i++) { + if (numa_bitmask_isbitset(numa_nodes_ptr, i)) + nr_nodes++; + } + + return nr_nodes; +} + +/* + * To check if given numa node is present. + */ +static int is_node_present(int node) +{ + return numa_bitmask_isbitset(numa_nodes_ptr, node); +} + +/* + * To check given numa node has cpus. + */ +static bool node_has_cpus(int node) +{ + struct bitmask *cpu = numa_allocate_cpumask(); + unsigned int i; + + if (cpu && !numa_node_to_cpus(node, cpu)) { + for (i = 0; i < cpu->size; i++) { + if (numa_bitmask_isbitset(cpu, i)) + return true; + } + } + + return false; /* lets fall back to nocpus safely */ +} + static cpu_set_t bind_to_cpu(int target_cpu) { cpu_set_t orig_mask, mask; @@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu) static cpu_set_t bind_to_node(int target_node) { - int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes; + int cpus_per_node = g->p.nr_cpus / nr_numa_nodes(); cpu_set_t orig_mask, mask; int cpu; int ret; - BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus); + BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus); BUG_ON(!cpus_per_node); ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); @@ -649,7 +690,7 @@ static int parse_setup_node_list(void) int i; for (i = 0; i < mul; i++) { - if (t >= g->p.nr_tasks) { + if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) { printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node); goto out; } @@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence) sum = 0; for (node = 0; node < g->p.nr_nodes; node++) { + if (!is_node_present(node)) + continue; nr = nodes[node]; nr_min = min(nr, nr_min); nr_max = max(nr, nr_max); @@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence) process_groups = 0; for (node = 0; node < g->p.nr_nodes; node++) { - int processes = count_node_processes(node); + int processes; + if (!is_node_present(node)) + continue; + processes = count_node_processes(node); nr = nodes[node]; tprintf(" %2d/%-2d", nr, processes); @@ -1291,7 +1337,7 @@ static void print_summary(void) printf("\n ###\n"); printf(" # %d %s will execute (on %d nodes, %d CPUs):\n", - g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus); + g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus); printf(" # %5dx %5ldMB global shared mem operations\n", g->p.nr_loops, g->p.bytes_global/1024/1024); printf(" # %5dx %5ldMB process shared mem operations\n", -- cgit v1.2.3 From 996548499df61babae5306544c7daf5fd39db31c Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 23 Nov 2017 12:46:11 +0100 Subject: perf test: Fix test 21 for s390x Test case 21 (Number of exit events of a simple workload) fails on s390x. The reason is the invalid sample frequency supplied for this test. On s390x the minimum sample frequency is much higher (see output of /proc/service_levels). Supply a save sample frequency value for s390x to fix this. The value will be adjusted by the s390x CPUMF frequency convertion function to a value well below the sysctl kernel.perf_event_max_sample_rate value. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Cc: Martin Schwidefsky LPU-Reference: 20171123114611.93397-1-tmricht@linux.vnet.ibm.com Link: https://lkml.kernel.org/n/tip-1ynblyhi1n81idpido59nt1y@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/task-exit.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index bc4a7344e274..89c8e1604ca7 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused evsel = perf_evlist__first(evlist); evsel->attr.task = 1; +#ifdef __s390x__ + evsel->attr.sample_freq = 1000000; +#else evsel->attr.sample_freq = 1; +#endif evsel->attr.inherit = 0; evsel->attr.watermark = 0; evsel->attr.wakeup_events = 1; -- cgit v1.2.3 From 51cacdc89852e91448518c616758c4421c83e057 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 21 Nov 2017 10:35:26 +0200 Subject: perf intel-pt: Bring instruction decoder files into line with the kernel There are just a few new defines which do not affect perf tools. Signed-off-by: Adrian Hunter Link: http://lkml.kernel.org/r/1511253326-22308-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/inat.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h index 125ecd2a300d..52dc8d911173 100644 --- a/tools/perf/util/intel-pt-decoder/inat.h +++ b/tools/perf/util/intel-pt-decoder/inat.h @@ -97,6 +97,16 @@ #define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) #define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) +/* Identifiers for segment registers */ +#define INAT_SEG_REG_IGNORE 0 +#define INAT_SEG_REG_DEFAULT 1 +#define INAT_SEG_REG_CS 2 +#define INAT_SEG_REG_SS 3 +#define INAT_SEG_REG_DS 4 +#define INAT_SEG_REG_ES 5 +#define INAT_SEG_REG_FS 6 +#define INAT_SEG_REG_GS 7 + /* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); extern int inat_get_last_prefix_id(insn_byte_t last_pfx); -- cgit v1.2.3 From 0b44cfb8e40f64cd72520be223414a7ef79c5d90 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 18 Nov 2017 09:00:46 +0100 Subject: tools/headers: Synchronize kernel x86 UAPI headers Two x86 headers got modified in this merge window: arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/disabled-features.h To support x86 UMIP feature, to add new AVX instructions, plus cleanups. None of those changes have an effect on tooling, so do a plain copy. Cc: Arnaldo Carvalho de Melo Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Namhyung Kim Cc: Jiri Olsa Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/arch/x86/include/asm/cpufeatures.h | 537 +++++++++++++------------ tools/arch/x86/include/asm/disabled-features.h | 8 +- 2 files changed, 281 insertions(+), 264 deletions(-) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 793690fbda36..c0b0e9e8aa66 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,173 +13,176 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NBUGINTS 1 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used * in /proc/cpuinfo instead of the macro name. If the string is "", * this feature bit is not displayed in /proc/cpuinfo at all. + * + * When adding new features here that depend on other features, + * please update the table in kernel/cpu/cpuid-deps.c as well. */ -/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ - /* (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ -#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ -#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ -#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ -#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ -#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ +/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ -#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -/* cpu types for specific tunings: */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ -#define X86_FEATURE_ART ( 3*32+10) /* Platform has always running timer (ART) */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ -#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ -#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ + +/* CPU types for specific tunings: */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ +#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ +#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" MFENCE synchronizes RDTSC */ +#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ -/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ -#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ -#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ -#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ -#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */ -#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ -#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ -#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */ -#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */ -#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ -#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ +/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ +#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ -#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ -#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ -#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ -#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ -/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ -#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ +/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -187,146 +190,154 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ -#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ -#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ -#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ +#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ +#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ +#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ +#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ -#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ -#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ +#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ -/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ +/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ -#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ -#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ -#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ -/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ -#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ -#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ +/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ -/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ -/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ -#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ -#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ -#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ -#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ -#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ -#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ -#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ -#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ -/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ -#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ -#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ -#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ +/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ /* * BUG word(s) */ -#define X86_BUG(x) (NCAPINTS*32 + (x)) +#define X86_BUG(x) (NCAPINTS*32 + (x)) -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ -#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ -#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional * to avoid confusion. */ -#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif -#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ -#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ -#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ + #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index c10c9128f54e..14d6d5007314 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -16,6 +16,12 @@ # define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) #endif +#ifdef CONFIG_X86_INTEL_UMIP +# define DISABLE_UMIP 0 +#else +# define DISABLE_UMIP (1<<(X86_FEATURE_UMIP & 31)) +#endif + #ifdef CONFIG_X86_64 # define DISABLE_VME (1<<(X86_FEATURE_VME & 31)) # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) @@ -63,7 +69,7 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP) #define DISABLED_MASK17 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) -- cgit v1.2.3 From 85369131895643c6510416fdcb215a855d39afb1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 7 Nov 2017 13:41:35 -0300 Subject: tools headers: Synchronize kernel ABI headers wrt SPDX tags Two more, that were just in perf/core and thus weren't covered by Ingo's latest headers synch, kcmp.h and prctl.h, silencing this: Warning: Kernel ABI header at 'tools/include/uapi/linux/kcmp.h' differs from latest version at 'include/uapi/linux/kcmp.h' Warning: Kernel ABI header at 'tools/include/uapi/linux/prctl.h' differs from latest version at 'include/uapi/linux/prctl.h' Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-2a0r7iybyqpkftllyy5t9hfk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/kcmp.h | 1 + tools/include/uapi/linux/prctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h index 481e103da78e..ef1305010925 100644 --- a/tools/include/uapi/linux/kcmp.h +++ b/tools/include/uapi/linux/kcmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_KCMP_H #define _UAPI_LINUX_KCMP_H diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index a8d0759a9e40..b640071421f7 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_PRCTL_H #define _LINUX_PRCTL_H -- cgit v1.2.3 From 0f1aabeb4932e48ce067cb8c88322277dd7af371 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2017 11:35:52 -0300 Subject: tools headers: Synchronize perf_event.h header To get the changes in the 085b30625e39 ("perf/core: Add PERF_AUX_FLAG_COLLISION to report colliding samples") commit, that will be eventually used by perf to handle the ARM SPE architecture. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Cc: Will Deacon Link: https://lkml.kernel.org/n/tip-178ohv0oy0csq3kzfdk8ky4n@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 362493a2f950..b9a4953018ed 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -942,6 +942,7 @@ enum perf_callchain_context { #define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ #define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ #define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) -- cgit v1.2.3 From 8ce6d5eb01cba83db9077c88a533bfeff39c679c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2017 11:43:00 -0300 Subject: tools headers uapi: Synchronize drm/drm.h To pick up the new ioctls added in these csets: 3064abfa932b ("drm: Add CRTC_GET_SEQUENCE and CRTC_QUEUE_SEQUENCE ioctls [v3]") 62884cd386b8 ("drm: Add four ioctls for managing drm mode object leases [v7]") That will be automatically decoded (the ioctl cmd parameter, the structs will be supported when we start using eBPF for that, which is in the works). This silences this warning when building tools/perf: Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h' Cc: Adrian Hunter Cc: Dave Airlie Cc: David Ahern Cc: Jiri Olsa Cc: Keith Packard Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-bivwf1pkfmi1ugpswbsxd9e9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 97677cd6964d..6fdff5945c8a 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -737,6 +737,28 @@ struct drm_syncobj_array { __u32 pad; }; +/* Query current scanout sequence number */ +struct drm_crtc_get_sequence { + __u32 crtc_id; /* requested crtc_id */ + __u32 active; /* return: crtc output is active */ + __u64 sequence; /* return: most recent vblank sequence */ + __s64 sequence_ns; /* return: most recent time of first pixel out */ +}; + +/* Queue event to be delivered at specified sequence. Time stamp marks + * when the first pixel of the refresh cycle leaves the display engine + * for the display + */ +#define DRM_CRTC_SEQUENCE_RELATIVE 0x00000001 /* sequence is relative to current */ +#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS 0x00000002 /* Use next sequence if we've missed */ + +struct drm_crtc_queue_sequence { + __u32 crtc_id; + __u32 flags; + __u64 sequence; /* on input, target sequence. on output, actual sequence */ + __u64 user_data; /* user data passed to event */ +}; + #if defined(__cplusplus) } #endif @@ -819,6 +841,9 @@ extern "C" { #define DRM_IOCTL_WAIT_VBLANK DRM_IOWR(0x3a, union drm_wait_vblank) +#define DRM_IOCTL_CRTC_GET_SEQUENCE DRM_IOWR(0x3b, struct drm_crtc_get_sequence) +#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE DRM_IOWR(0x3c, struct drm_crtc_queue_sequence) + #define DRM_IOCTL_UPDATE_DRAW DRM_IOW(0x3f, struct drm_update_draw) #define DRM_IOCTL_MODE_GETRESOURCES DRM_IOWR(0xA0, struct drm_mode_card_res) @@ -863,6 +888,11 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) #define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) +#define DRM_IOCTL_MODE_CREATE_LEASE DRM_IOWR(0xC6, struct drm_mode_create_lease) +#define DRM_IOCTL_MODE_LIST_LESSEES DRM_IOWR(0xC7, struct drm_mode_list_lessees) +#define DRM_IOCTL_MODE_GET_LEASE DRM_IOWR(0xC8, struct drm_mode_get_lease) +#define DRM_IOCTL_MODE_REVOKE_LEASE DRM_IOWR(0xC9, struct drm_mode_revoke_lease) + /** * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. @@ -893,6 +923,7 @@ struct drm_event { #define DRM_EVENT_VBLANK 0x01 #define DRM_EVENT_FLIP_COMPLETE 0x02 +#define DRM_EVENT_CRTC_SEQUENCE 0x03 struct drm_event_vblank { struct drm_event base; @@ -903,6 +934,16 @@ struct drm_event_vblank { __u32 crtc_id; /* 0 on older kernels that do not support this */ }; +/* Event delivered at sequence. Time stamp marks when the first pixel + * of the refresh cycle leaves the display engine for the display + */ +struct drm_event_crtc_sequence { + struct drm_event base; + __u64 user_data; + __s64 time_ns; + __u64 sequence; +}; + /* typedef area */ #ifndef __KERNEL__ typedef struct drm_clip_rect drm_clip_rect_t; -- cgit v1.2.3 From 485be0cb0c71da167cb7f27c20130dc04fec33ff Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2017 11:50:07 -0300 Subject: tools headers: Synchronize drm/i915_drm.h To pick up the changes from these csets: bf64e0b00e1f ("drm/i915: Expand I915_PARAM_HAS_SCHEDULER into a capability bitmask") ac14fbd460d0 ("drm/i915/scheduler: Support user-defined priorities") 822a4b673284 ("drm/i915: Don't use BIT() in UAPI section") 3fd3a6ffe279 ("drm/i915: Simplify i915_reg_read_ioctl") None of them affects how the tools are built, this os done just to silence this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' Cc: Adrian Hunter Cc: Chris Wilson Cc: David Ahern Cc: Jiri Olsa Cc: Joonas Lahtinen Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-d2gor8brpcowe7bcxovjhqwm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 9816590d3ad2..ac3c6503ca27 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -397,10 +397,20 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_MIN_EU_IN_POOL 39 #define I915_PARAM_MMAP_GTT_VERSION 40 -/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution * priorities and the driver will attempt to execute batches in priority order. + * The param returns a capability bitmask, nonzero implies that the scheduler + * is enabled, with different features present according to the mask. + * + * The initial priority for each batch is supplied by the context and is + * controlled via I915_CONTEXT_PARAM_PRIORITY. */ #define I915_PARAM_HAS_SCHEDULER 41 +#define I915_SCHEDULER_CAP_ENABLED (1ul << 0) +#define I915_SCHEDULER_CAP_PRIORITY (1ul << 1) +#define I915_SCHEDULER_CAP_PREEMPTION (1ul << 2) + #define I915_PARAM_HUC_STATUS 42 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of @@ -1309,14 +1319,16 @@ struct drm_i915_reg_read { * be specified */ __u64 offset; +#define I915_REG_READ_8B_WA (1ul << 0) + __u64 val; /* Return value */ }; /* Known registers: * * Render engine timestamp - 0x2358 + 64bit - gen7+ * - Note this register returns an invalid value if using the default - * single instruction 8byte read, in order to workaround that use - * offset (0x2538 | 1) instead. + * single instruction 8byte read, in order to workaround that pass + * flag I915_REG_READ_8B_WA in offset field. * */ @@ -1359,6 +1371,10 @@ struct drm_i915_gem_context_param { #define I915_CONTEXT_PARAM_GTT_SIZE 0x3 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 #define I915_CONTEXT_PARAM_BANNABLE 0x5 +#define I915_CONTEXT_PARAM_PRIORITY 0x6 +#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ +#define I915_CONTEXT_DEFAULT_PRIORITY 0 +#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ __u64 value; }; @@ -1510,9 +1526,14 @@ struct drm_i915_perf_oa_config { __u32 n_boolean_regs; __u32 n_flex_regs; - __u64 __user mux_regs_ptr; - __u64 __user boolean_regs_ptr; - __u64 __user flex_regs_ptr; + /* + * These fields are pointers to tuples of u32 values (register + * address, value). For example the expected length of the buffer + * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs). + */ + __u64 mux_regs_ptr; + __u64 boolean_regs_ptr; + __u64 flex_regs_ptr; }; #if defined(__cplusplus) -- cgit v1.2.3 From 374fbe56068c36126fc6903aaaa78f1ae8a95f91 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2017 12:04:21 -0300 Subject: tools headers: Synchronize KVM arch ABI headers To pick up changes from these csets: da9a1446d248 ("KVM: s390: provide a capability for AIS state migration") 5c5196da4e96 ("KVM: arm/arm64: Support EL1 phys timer register access in set/get reg") None of which affects buildint tools/perf/. Cc: Adrian Hunter Cc: Christian Borntraeger Cc: Christoffer Dall Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-dd72s6izo4qdzt1isowlz8ji@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm/include/uapi/asm/kvm.h | 7 +++++++ tools/arch/arm64/include/uapi/asm/kvm.h | 7 +++++++ tools/include/uapi/linux/kvm.h | 1 + 3 files changed, 15 insertions(+) (limited to 'tools') diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 1f57bbe82b6f..6edd177bb1c7 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -152,6 +152,12 @@ struct kvm_arch_memory_slot { (__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64) #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__) +/* PL1 Physical Timer Registers */ +#define KVM_REG_ARM_PTIMER_CTL ARM_CP15_REG32(0, 14, 2, 1) +#define KVM_REG_ARM_PTIMER_CNT ARM_CP15_REG64(0, 14) +#define KVM_REG_ARM_PTIMER_CVAL ARM_CP15_REG64(2, 14) + +/* Virtual Timer Registers */ #define KVM_REG_ARM_TIMER_CTL ARM_CP15_REG32(0, 14, 3, 1) #define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14) #define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14) @@ -216,6 +222,7 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_ITS_SAVE_TABLES 1 #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 #define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 +#define KVM_DEV_ARM_ITS_CTRL_RESET 4 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 51149ec75fe4..9abbf3044654 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -196,6 +196,12 @@ struct kvm_arch_memory_slot { #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64) +/* Physical Timer EL0 Registers */ +#define KVM_REG_ARM_PTIMER_CTL ARM64_SYS_REG(3, 3, 14, 2, 1) +#define KVM_REG_ARM_PTIMER_CVAL ARM64_SYS_REG(3, 3, 14, 2, 2) +#define KVM_REG_ARM_PTIMER_CNT ARM64_SYS_REG(3, 3, 14, 0, 1) + +/* EL0 Virtual Timer Registers */ #define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1) #define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) @@ -228,6 +234,7 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_ITS_SAVE_TABLES 1 #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 #define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 +#define KVM_DEV_ARM_ITS_CTRL_RESET 4 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 7e99999d6236..282d7613fce8 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -931,6 +931,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_SMT_POSSIBLE 147 #define KVM_CAP_HYPERV_SYNIC2 148 #define KVM_CAP_HYPERV_VP_INDEX 149 +#define KVM_CAP_S390_AIS_MIGRATION 150 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From d9744f940923ea341a289d1920a55e3a3de7fc9a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2017 12:11:02 -0300 Subject: tools headers: Synchronize prctl.h ABI header To pick up changes from: 2d2123bc7c7f ("arm64/sve: Add prctl controls for userspace vector length management") 7582e22038a2 ("arm64/sve: Backend logic for setting the vector length") That showed a limitation of the regexp used in tools/perf/trace/beauty/prctl_option.sh, that matches only PR_{SET,GET}_, but should match a few more, like PR_MPX_*, PR_CAP_* and the one added by the above commit, PR_SVE_SET_*. This silences this warning when building tools/perf: Warning: Kernel ABI header at 'tools/include/uapi/linux/prctl.h' differs from latest version at 'include/uapi/linux/prctl.h' Support for those extra prctl options should be left for the next merge window tho. Cc: Adrian Hunter Cc: Dave Martin Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Cc: Will Deacon Link: https://lkml.kernel.org/n/tip-r52dsyuzy04qzqyfcifjs35t@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/prctl.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index b640071421f7..af5f8c2df87a 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -198,4 +198,13 @@ struct prctl_mm_map { # define PR_CAP_AMBIENT_LOWER 3 # define PR_CAP_AMBIENT_CLEAR_ALL 4 +/* arm64 Scalable Vector Extension controls */ +/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */ +#define PR_SVE_SET_VL 50 /* set task vector length */ +# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SVE_GET_VL 51 /* get task vector length */ +/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */ +# define PR_SVE_VL_LEN_MASK 0xffff +# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ + #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From 1b3b5219abfd6a214e99018747e9fe98514b43ca Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 27 Nov 2017 12:18:23 -0300 Subject: tools headers: Syncronize mman.h ABI header To add support for the MAP_SYNC flag introduced in: b6fb293f2497 ("mm: Define MAP_SYNC and VM_SYNC flags") Update tools/perf/trace/beauty/mmap.c to support that flag. This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/mman.h' differs from latest version at 'include/uapi/asm-generic/mman.h' Cc: Adrian Hunter Cc: Dan Williams Cc: David Ahern Cc: Jan Kara Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-14zyk3iywrj37c7g1eagmzbo@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/mman.h | 1 + tools/perf/trace/beauty/mmap.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 2dffcbf705b3..653687d9771b 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -13,6 +13,7 @@ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ +#define MAP_SYNC 0x80000 /* perform synchronous page faults for the mapping */ /* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */ diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index 9e1668b2c5d7..417e3ecfe9d7 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -62,6 +62,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, P_MMAP_FLAG(POPULATE); P_MMAP_FLAG(STACK); P_MMAP_FLAG(UNINITIALIZED); +#ifdef MAP_SYNC + P_MMAP_FLAG(SYNC); +#endif #undef P_MMAP_FLAG if (flags) -- cgit v1.2.3 From 9b85c2d4508563f4bb1de0d971ed02fea0d0d757 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:28 -0800 Subject: tools: bpftool: fix crash on bad parameters with JSON If bad or unrecognised parameters are specified after JSON output is requested, `usage()` will try to output null JSON object before the writer is created. To prevent this, create the writer as soon as the `--json` option is parsed. Fixes: 004b45c0e51a ("tools: bpftool: provide JSON output for all possible commands") Reported-by: Jakub Kicinski Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d6e4762170a4..14ad54a1c404 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -291,7 +291,15 @@ int main(int argc, char **argv) pretty_output = true; /* fall through */ case 'j': - json_output = true; + if (!json_output) { + json_wtr = jsonw_new(stdout); + if (!json_wtr) { + p_err("failed to create JSON writer"); + return -1; + } + json_output = true; + } + jsonw_pretty(json_wtr, pretty_output); break; case 'f': show_pinned = true; @@ -306,15 +314,6 @@ int main(int argc, char **argv) if (argc < 0) usage(); - if (json_output) { - json_wtr = jsonw_new(stdout); - if (!json_wtr) { - p_err("failed to create JSON writer"); - return -1; - } - jsonw_pretty(json_wtr, pretty_output); - } - bfd_init(); ret = cmd_select(cmds, argc, argv, do_help); -- cgit v1.2.3 From 7868620a3c15dbc661fb5d849de403ac04624c50 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:29 -0800 Subject: tools: bpftool: clean up the JSON writer before exiting in usage() The writer is cleaned at the end of the main function, but not if the program exits sooner in usage(). Let's keep it clean and destroy the writer before exiting. Destruction and actual call to exit() are moved to another function so that clean exit can also be performed without printing usage() hints. Fixes: d35efba99d92 ("tools: bpftool: introduce --json and --pretty options") Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.c | 10 +++++++++- tools/bpf/bpftool/main.h | 3 ++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 14ad54a1c404..d72dd73a4016 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -58,11 +58,19 @@ bool show_pinned; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; +static void __noreturn clean_and_exit(int i) +{ + if (json_output) + jsonw_destroy(&json_wtr); + + exit(i); +} + void usage(void) { last_do_help(last_argc - 1, last_argv + 1); - exit(-1); + clean_and_exit(-1); } static int do_help(int argc, char **argv) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 9c191e222d6f..0b60ddfb2b93 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -80,7 +81,7 @@ void p_info(const char *fmt, ...); bool is_prefix(const char *pfx, const char *str); void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); -void usage(void) __attribute__((noreturn)); +void usage(void) __noreturn; struct pinned_obj_table { DECLARE_HASHTABLE(table, 16); -- cgit v1.2.3 From 146882a37da7aa566c7ec088b42c6495d769f2ba Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:30 -0800 Subject: tools: bpftool: make error message from getopt_long() JSON-friendly If `getopt_long()` meets an unknown option, it prints its own error message to standard error output. While this does not strictly break JSON output, it is the only case bpftool prints something to standard error output if JSON output is required. All other errors are printed on standard output as JSON objects, so that an external program does not have to parse stderr. This is changed by setting the global variable `opterr` to 0. Furthermore, p_err() is used to reproduce the error message in a more JSON-friendly way, so that users still get to know what the erroneous option is. Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d72dd73a4016..d294bc8168be 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -288,6 +288,7 @@ int main(int argc, char **argv) hash_init(prog_table.table); hash_init(map_table.table); + opterr = 0; while ((opt = getopt_long(argc, argv, "Vhpjf", options, NULL)) >= 0) { switch (opt) { @@ -313,7 +314,11 @@ int main(int argc, char **argv) show_pinned = true; break; default: - usage(); + p_err("unrecognized option '%s'", argv[optind - 1]); + if (json_output) + clean_and_exit(-1); + else + usage(); } } -- cgit v1.2.3 From 0d954eeb99eee63964a07a68fcac61e1df8488e7 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:31 -0800 Subject: tools: bpftool: remove spurious line break from error message The end-of-line character inside the string would break JSON compliance. Remove it, `p_err()` already adds a '\n' character for plain output anyway. Fixes: 9a5ab8bf1d6d ("tools: bpftool: turn err() and info() macros into functions") Reported-by: Jakub Kicinski Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 0b60ddfb2b93..bff330b49791 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -51,7 +51,7 @@ #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) -#define BAD_ARG() ({ p_err("what is '%s'?\n", *argv); -1; }) +#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; }) #define ERR_MAX_LEN 1024 -- cgit v1.2.3 From 507e590da398a0e3438d563b5e736c3f2a7749d7 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:32 -0800 Subject: tools: bpftool: unify installation directories Programs and documentation not managed by package manager are generally installed under /usr/local/, instead of the user's home directory. In particular, `man` is generally able to find manual pages under `/usr/local/share/man`. bpftool generally follows perf's example, and perf installs to home directory. However bpftool requires root credentials, so it seems sensible to follow the more common convention of installing files under /usr/local instead. So, make /usr/local the default prefix for installing the binary with `make install`, and the documentation with `make doc-install`. Also, create /usr/local/sbin if it does not exist. Note that the bash-completion file, however, is still installed under /usr/share/bash-completion/completions, as the default setup for bash does not attempt to load completion files under /usr/local/. Reported-by: David Beckett Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/Documentation/Makefile | 2 +- tools/bpf/bpftool/Makefile | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index bde77d7c4390..37292bb5ce60 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -6,7 +6,7 @@ RM ?= rm -f # Make the path relative to DESTDIR, not prefix ifndef DESTDIR -prefix?=$(HOME) +prefix ?= /usr/local endif mandir ?= $(prefix)/share/man man8dir = $(mandir)/man8 diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 813826c50936..c5b21f2cbca5 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -45,8 +45,8 @@ $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null -prefix = /usr -bash_compdir ?= $(prefix)/share/bash-completion/completions +prefix = /usr/local +bash_compdir ?= /usr/share/bash-completion/completions CC = gcc @@ -76,6 +76,7 @@ clean: $(LIBBPF)-clean $(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d install: + install -m 0755 -d $(prefix)/sbin install $(OUTPUT)bpftool $(prefix)/sbin/bpftool install -m 0755 -d $(bash_compdir) install -m 0644 bash-completion/bpftool $(bash_compdir) -- cgit v1.2.3 From ad3cda064402b69148faf5f7cd1ac8c2eee52645 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 28 Nov 2017 17:44:33 -0800 Subject: tools: bpftool: declare phony targets as such In the Makefile, targets install, doc and doc-install should be added to .PHONY. Let's fix this. Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool") Signed-off-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index c5b21f2cbca5..ec3052c0b004 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -89,5 +89,5 @@ doc-install: FORCE: -.PHONY: all clean FORCE +.PHONY: all clean FORCE install doc doc-install .DEFAULT_GOAL := all -- cgit v1.2.3 From 1ac7c8a78be85f84b019d3d2742d1a9f07255cc5 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 29 Nov 2017 15:24:22 -0700 Subject: usbip: fix usbip attach to find a port that matches the requested speed usbip attach fails to find a free port when the device on the first port is a USB_SPEED_SUPER device and non-super speed device is being attached. It keeps checking the first port and returns without a match getting stuck in a loop. Fix it check to find the first port with matching speed. Reported-by: Juan Zea Signed-off-by: Shuah Khan Cc: stable Signed-off-by: Greg Kroah-Hartman --- tools/usb/usbip/libsrc/vhci_driver.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index 5727dfb15a83..8a1cd1616de4 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -329,9 +329,17 @@ err: int usbip_vhci_get_free_port(uint32_t speed) { for (int i = 0; i < vhci_driver->nports; i++) { - if (speed == USB_SPEED_SUPER && - vhci_driver->idev[i].hub != HUB_SPEED_SUPER) - continue; + + switch (speed) { + case USB_SPEED_SUPER: + if (vhci_driver->idev[i].hub != HUB_SPEED_SUPER) + continue; + break; + default: + if (vhci_driver->idev[i].hub != HUB_SPEED_HIGH) + continue; + break; + } if (vhci_driver->idev[i].status == VDEV_ST_NULL) return vhci_driver->idev[i].port; -- cgit v1.2.3 From 2b279419567105d63f1e524bb1ac34ae8f918e5d Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 30 Nov 2017 08:52:42 -0800 Subject: tools/bpf: adjust rlimit RLIMIT_MEMLOCK for test_verifier_log The default rlimit RLIMIT_MEMLOCK is 64KB. In certain cases, e.g. in a test machine mimicking our production system, this test may fail due to unable to charge the required memory for prog load: # ./test_verifier_log Test log_level 0... ERROR: Program load returned: ret:-1/errno:1, expected ret:-1/errno:22 Changing the default rlimit RLIMIT_MEMLOCK to unlimited makes the test always pass. Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_verifier_log.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c index 3cc0b561489e..e9626cf5607a 100644 --- a/tools/testing/selftests/bpf/test_verifier_log.c +++ b/tools/testing/selftests/bpf/test_verifier_log.c @@ -3,6 +3,8 @@ #include #include #include +#include +#include #include #include @@ -131,11 +133,16 @@ static void test_log_bad(char *log, size_t log_len, int log_level) int main(int argc, char **argv) { + struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; char full_log[LOG_SIZE]; char log[LOG_SIZE]; size_t want_len; int i; + /* allow unlimited locked memory to have more consistent error code */ + if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0) + perror("Unable to lift memlock rlimit"); + memset(log, 1, LOG_SIZE); /* Test incorrect attr */ -- cgit v1.2.3 From 618e165b2a8e10765dd2a4f9866d118a474f0faf Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Mon, 4 Dec 2017 10:56:48 +0100 Subject: selftests/bpf: sync kernel headers and introduce arch support in Makefile Synchronize the uapi kernel header files which solves the broken uapi export of pt_regs. Because of arch-specific uapi headers, extended the include path in the Makefile. With this change, the test_verifier program compiles and runs successfully on s390. Signed-off-by: Hendrik Brueckner Reviewed-and-tested-by: Thomas Richter Acked-by: Alexei Starovoitov Cc: Daniel Borkmann Cc: Shuah Khan Signed-off-by: Daniel Borkmann --- tools/arch/arm64/include/uapi/asm/bpf_perf_event.h | 9 + tools/arch/s390/include/uapi/asm/bpf_perf_event.h | 9 + tools/arch/s390/include/uapi/asm/ptrace.h | 457 +++++++++++++++++++++ tools/include/uapi/asm-generic/bpf_perf_event.h | 9 + tools/include/uapi/linux/bpf_perf_event.h | 6 +- tools/testing/selftests/bpf/Makefile | 14 +- 6 files changed, 500 insertions(+), 4 deletions(-) create mode 100644 tools/arch/arm64/include/uapi/asm/bpf_perf_event.h create mode 100644 tools/arch/s390/include/uapi/asm/bpf_perf_event.h create mode 100644 tools/arch/s390/include/uapi/asm/ptrace.h create mode 100644 tools/include/uapi/asm-generic/bpf_perf_event.h (limited to 'tools') diff --git a/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h b/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..b551b741653d --- /dev/null +++ b/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include + +typedef struct user_pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ diff --git a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..cefe7c7cd4f6 --- /dev/null +++ b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include + +typedef user_pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ diff --git a/tools/arch/s390/include/uapi/asm/ptrace.h b/tools/arch/s390/include/uapi/asm/ptrace.h new file mode 100644 index 000000000000..543dd70e12c8 --- /dev/null +++ b/tools/arch/s390/include/uapi/asm/ptrace.h @@ -0,0 +1,457 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * S390 version + * Copyright IBM Corp. 1999, 2000 + * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) + */ + +#ifndef _UAPI_S390_PTRACE_H +#define _UAPI_S390_PTRACE_H + +/* + * Offsets in the user_regs_struct. They are used for the ptrace + * system call and in entry.S + */ +#ifndef __s390x__ + +#define PT_PSWMASK 0x00 +#define PT_PSWADDR 0x04 +#define PT_GPR0 0x08 +#define PT_GPR1 0x0C +#define PT_GPR2 0x10 +#define PT_GPR3 0x14 +#define PT_GPR4 0x18 +#define PT_GPR5 0x1C +#define PT_GPR6 0x20 +#define PT_GPR7 0x24 +#define PT_GPR8 0x28 +#define PT_GPR9 0x2C +#define PT_GPR10 0x30 +#define PT_GPR11 0x34 +#define PT_GPR12 0x38 +#define PT_GPR13 0x3C +#define PT_GPR14 0x40 +#define PT_GPR15 0x44 +#define PT_ACR0 0x48 +#define PT_ACR1 0x4C +#define PT_ACR2 0x50 +#define PT_ACR3 0x54 +#define PT_ACR4 0x58 +#define PT_ACR5 0x5C +#define PT_ACR6 0x60 +#define PT_ACR7 0x64 +#define PT_ACR8 0x68 +#define PT_ACR9 0x6C +#define PT_ACR10 0x70 +#define PT_ACR11 0x74 +#define PT_ACR12 0x78 +#define PT_ACR13 0x7C +#define PT_ACR14 0x80 +#define PT_ACR15 0x84 +#define PT_ORIGGPR2 0x88 +#define PT_FPC 0x90 +/* + * A nasty fact of life that the ptrace api + * only supports passing of longs. + */ +#define PT_FPR0_HI 0x98 +#define PT_FPR0_LO 0x9C +#define PT_FPR1_HI 0xA0 +#define PT_FPR1_LO 0xA4 +#define PT_FPR2_HI 0xA8 +#define PT_FPR2_LO 0xAC +#define PT_FPR3_HI 0xB0 +#define PT_FPR3_LO 0xB4 +#define PT_FPR4_HI 0xB8 +#define PT_FPR4_LO 0xBC +#define PT_FPR5_HI 0xC0 +#define PT_FPR5_LO 0xC4 +#define PT_FPR6_HI 0xC8 +#define PT_FPR6_LO 0xCC +#define PT_FPR7_HI 0xD0 +#define PT_FPR7_LO 0xD4 +#define PT_FPR8_HI 0xD8 +#define PT_FPR8_LO 0XDC +#define PT_FPR9_HI 0xE0 +#define PT_FPR9_LO 0xE4 +#define PT_FPR10_HI 0xE8 +#define PT_FPR10_LO 0xEC +#define PT_FPR11_HI 0xF0 +#define PT_FPR11_LO 0xF4 +#define PT_FPR12_HI 0xF8 +#define PT_FPR12_LO 0xFC +#define PT_FPR13_HI 0x100 +#define PT_FPR13_LO 0x104 +#define PT_FPR14_HI 0x108 +#define PT_FPR14_LO 0x10C +#define PT_FPR15_HI 0x110 +#define PT_FPR15_LO 0x114 +#define PT_CR_9 0x118 +#define PT_CR_10 0x11C +#define PT_CR_11 0x120 +#define PT_IEEE_IP 0x13C +#define PT_LASTOFF PT_IEEE_IP +#define PT_ENDREGS 0x140-1 + +#define GPR_SIZE 4 +#define CR_SIZE 4 + +#define STACK_FRAME_OVERHEAD 96 /* size of minimum stack frame */ + +#else /* __s390x__ */ + +#define PT_PSWMASK 0x00 +#define PT_PSWADDR 0x08 +#define PT_GPR0 0x10 +#define PT_GPR1 0x18 +#define PT_GPR2 0x20 +#define PT_GPR3 0x28 +#define PT_GPR4 0x30 +#define PT_GPR5 0x38 +#define PT_GPR6 0x40 +#define PT_GPR7 0x48 +#define PT_GPR8 0x50 +#define PT_GPR9 0x58 +#define PT_GPR10 0x60 +#define PT_GPR11 0x68 +#define PT_GPR12 0x70 +#define PT_GPR13 0x78 +#define PT_GPR14 0x80 +#define PT_GPR15 0x88 +#define PT_ACR0 0x90 +#define PT_ACR1 0x94 +#define PT_ACR2 0x98 +#define PT_ACR3 0x9C +#define PT_ACR4 0xA0 +#define PT_ACR5 0xA4 +#define PT_ACR6 0xA8 +#define PT_ACR7 0xAC +#define PT_ACR8 0xB0 +#define PT_ACR9 0xB4 +#define PT_ACR10 0xB8 +#define PT_ACR11 0xBC +#define PT_ACR12 0xC0 +#define PT_ACR13 0xC4 +#define PT_ACR14 0xC8 +#define PT_ACR15 0xCC +#define PT_ORIGGPR2 0xD0 +#define PT_FPC 0xD8 +#define PT_FPR0 0xE0 +#define PT_FPR1 0xE8 +#define PT_FPR2 0xF0 +#define PT_FPR3 0xF8 +#define PT_FPR4 0x100 +#define PT_FPR5 0x108 +#define PT_FPR6 0x110 +#define PT_FPR7 0x118 +#define PT_FPR8 0x120 +#define PT_FPR9 0x128 +#define PT_FPR10 0x130 +#define PT_FPR11 0x138 +#define PT_FPR12 0x140 +#define PT_FPR13 0x148 +#define PT_FPR14 0x150 +#define PT_FPR15 0x158 +#define PT_CR_9 0x160 +#define PT_CR_10 0x168 +#define PT_CR_11 0x170 +#define PT_IEEE_IP 0x1A8 +#define PT_LASTOFF PT_IEEE_IP +#define PT_ENDREGS 0x1B0-1 + +#define GPR_SIZE 8 +#define CR_SIZE 8 + +#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */ + +#endif /* __s390x__ */ + +#define NUM_GPRS 16 +#define NUM_FPRS 16 +#define NUM_CRS 16 +#define NUM_ACRS 16 + +#define NUM_CR_WORDS 3 + +#define FPR_SIZE 8 +#define FPC_SIZE 4 +#define FPC_PAD_SIZE 4 /* gcc insists on aligning the fpregs */ +#define ACR_SIZE 4 + + +#define PTRACE_OLDSETOPTIONS 21 + +#ifndef __ASSEMBLY__ +#include +#include + +typedef union { + float f; + double d; + __u64 ui; + struct + { + __u32 hi; + __u32 lo; + } fp; +} freg_t; + +typedef struct { + __u32 fpc; + __u32 pad; + freg_t fprs[NUM_FPRS]; +} s390_fp_regs; + +#define FPC_EXCEPTION_MASK 0xF8000000 +#define FPC_FLAGS_MASK 0x00F80000 +#define FPC_DXC_MASK 0x0000FF00 +#define FPC_RM_MASK 0x00000003 + +/* this typedef defines how a Program Status Word looks like */ +typedef struct { + unsigned long mask; + unsigned long addr; +} __attribute__ ((aligned(8))) psw_t; + +#ifndef __s390x__ + +#define PSW_MASK_PER 0x40000000UL +#define PSW_MASK_DAT 0x04000000UL +#define PSW_MASK_IO 0x02000000UL +#define PSW_MASK_EXT 0x01000000UL +#define PSW_MASK_KEY 0x00F00000UL +#define PSW_MASK_BASE 0x00080000UL /* always one */ +#define PSW_MASK_MCHECK 0x00040000UL +#define PSW_MASK_WAIT 0x00020000UL +#define PSW_MASK_PSTATE 0x00010000UL +#define PSW_MASK_ASC 0x0000C000UL +#define PSW_MASK_CC 0x00003000UL +#define PSW_MASK_PM 0x00000F00UL +#define PSW_MASK_RI 0x00000000UL +#define PSW_MASK_EA 0x00000000UL +#define PSW_MASK_BA 0x00000000UL + +#define PSW_MASK_USER 0x0000FF00UL + +#define PSW_ADDR_AMODE 0x80000000UL +#define PSW_ADDR_INSN 0x7FFFFFFFUL + +#define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 20) + +#define PSW_ASC_PRIMARY 0x00000000UL +#define PSW_ASC_ACCREG 0x00004000UL +#define PSW_ASC_SECONDARY 0x00008000UL +#define PSW_ASC_HOME 0x0000C000UL + +#else /* __s390x__ */ + +#define PSW_MASK_PER 0x4000000000000000UL +#define PSW_MASK_DAT 0x0400000000000000UL +#define PSW_MASK_IO 0x0200000000000000UL +#define PSW_MASK_EXT 0x0100000000000000UL +#define PSW_MASK_BASE 0x0000000000000000UL +#define PSW_MASK_KEY 0x00F0000000000000UL +#define PSW_MASK_MCHECK 0x0004000000000000UL +#define PSW_MASK_WAIT 0x0002000000000000UL +#define PSW_MASK_PSTATE 0x0001000000000000UL +#define PSW_MASK_ASC 0x0000C00000000000UL +#define PSW_MASK_CC 0x0000300000000000UL +#define PSW_MASK_PM 0x00000F0000000000UL +#define PSW_MASK_RI 0x0000008000000000UL +#define PSW_MASK_EA 0x0000000100000000UL +#define PSW_MASK_BA 0x0000000080000000UL + +#define PSW_MASK_USER 0x0000FF0180000000UL + +#define PSW_ADDR_AMODE 0x0000000000000000UL +#define PSW_ADDR_INSN 0xFFFFFFFFFFFFFFFFUL + +#define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 52) + +#define PSW_ASC_PRIMARY 0x0000000000000000UL +#define PSW_ASC_ACCREG 0x0000400000000000UL +#define PSW_ASC_SECONDARY 0x0000800000000000UL +#define PSW_ASC_HOME 0x0000C00000000000UL + +#endif /* __s390x__ */ + + +/* + * The s390_regs structure is used to define the elf_gregset_t. + */ +typedef struct { + psw_t psw; + unsigned long gprs[NUM_GPRS]; + unsigned int acrs[NUM_ACRS]; + unsigned long orig_gpr2; +} s390_regs; + +/* + * The user_pt_regs structure exports the beginning of + * the in-kernel pt_regs structure to user space. + */ +typedef struct { + unsigned long args[1]; + psw_t psw; + unsigned long gprs[NUM_GPRS]; +} user_pt_regs; + +/* + * Now for the user space program event recording (trace) definitions. + * The following structures are used only for the ptrace interface, don't + * touch or even look at it if you don't want to modify the user-space + * ptrace interface. In particular stay away from it for in-kernel PER. + */ +typedef struct { + unsigned long cr[NUM_CR_WORDS]; +} per_cr_words; + +#define PER_EM_MASK 0xE8000000UL + +typedef struct { +#ifdef __s390x__ + unsigned : 32; +#endif /* __s390x__ */ + unsigned em_branching : 1; + unsigned em_instruction_fetch : 1; + /* + * Switching on storage alteration automatically fixes + * the storage alteration event bit in the users std. + */ + unsigned em_storage_alteration : 1; + unsigned em_gpr_alt_unused : 1; + unsigned em_store_real_address : 1; + unsigned : 3; + unsigned branch_addr_ctl : 1; + unsigned : 1; + unsigned storage_alt_space_ctl : 1; + unsigned : 21; + unsigned long starting_addr; + unsigned long ending_addr; +} per_cr_bits; + +typedef struct { + unsigned short perc_atmid; + unsigned long address; + unsigned char access_id; +} per_lowcore_words; + +typedef struct { + unsigned perc_branching : 1; + unsigned perc_instruction_fetch : 1; + unsigned perc_storage_alteration : 1; + unsigned perc_gpr_alt_unused : 1; + unsigned perc_store_real_address : 1; + unsigned : 3; + unsigned atmid_psw_bit_31 : 1; + unsigned atmid_validity_bit : 1; + unsigned atmid_psw_bit_32 : 1; + unsigned atmid_psw_bit_5 : 1; + unsigned atmid_psw_bit_16 : 1; + unsigned atmid_psw_bit_17 : 1; + unsigned si : 2; + unsigned long address; + unsigned : 4; + unsigned access_id : 4; +} per_lowcore_bits; + +typedef struct { + union { + per_cr_words words; + per_cr_bits bits; + } control_regs; + /* + * The single_step and instruction_fetch bits are obsolete, + * the kernel always sets them to zero. To enable single + * stepping use ptrace(PTRACE_SINGLESTEP) instead. + */ + unsigned single_step : 1; + unsigned instruction_fetch : 1; + unsigned : 30; + /* + * These addresses are copied into cr10 & cr11 if single + * stepping is switched off + */ + unsigned long starting_addr; + unsigned long ending_addr; + union { + per_lowcore_words words; + per_lowcore_bits bits; + } lowcore; +} per_struct; + +typedef struct { + unsigned int len; + unsigned long kernel_addr; + unsigned long process_addr; +} ptrace_area; + +/* + * S/390 specific non posix ptrace requests. I chose unusual values so + * they are unlikely to clash with future ptrace definitions. + */ +#define PTRACE_PEEKUSR_AREA 0x5000 +#define PTRACE_POKEUSR_AREA 0x5001 +#define PTRACE_PEEKTEXT_AREA 0x5002 +#define PTRACE_PEEKDATA_AREA 0x5003 +#define PTRACE_POKETEXT_AREA 0x5004 +#define PTRACE_POKEDATA_AREA 0x5005 +#define PTRACE_GET_LAST_BREAK 0x5006 +#define PTRACE_PEEK_SYSTEM_CALL 0x5007 +#define PTRACE_POKE_SYSTEM_CALL 0x5008 +#define PTRACE_ENABLE_TE 0x5009 +#define PTRACE_DISABLE_TE 0x5010 +#define PTRACE_TE_ABORT_RAND 0x5011 + +/* + * The numbers chosen here are somewhat arbitrary but absolutely MUST + * not overlap with any of the number assigned in . + */ +#define PTRACE_SINGLEBLOCK 12 /* resume execution until next branch */ + +/* + * PT_PROT definition is loosely based on hppa bsd definition in + * gdb/hppab-nat.c + */ +#define PTRACE_PROT 21 + +typedef enum { + ptprot_set_access_watchpoint, + ptprot_set_write_watchpoint, + ptprot_disable_watchpoint +} ptprot_flags; + +typedef struct { + unsigned long lowaddr; + unsigned long hiaddr; + ptprot_flags prot; +} ptprot_area; + +/* Sequence of bytes for breakpoint illegal instruction. */ +#define S390_BREAKPOINT {0x0,0x1} +#define S390_BREAKPOINT_U16 ((__u16)0x0001) +#define S390_SYSCALL_OPCODE ((__u16)0x0a00) +#define S390_SYSCALL_SIZE 2 + +/* + * The user_regs_struct defines the way the user registers are + * store on the stack for signal handling. + */ +struct user_regs_struct { + psw_t psw; + unsigned long gprs[NUM_GPRS]; + unsigned int acrs[NUM_ACRS]; + unsigned long orig_gpr2; + s390_fp_regs fp_regs; + /* + * These per registers are in here so that gdb can modify them + * itself as there is no "official" ptrace interface for hardware + * watchpoints. This is the way intel does it. + */ + per_struct per_info; + unsigned long ieee_instruction_pointer; /* obsolete, always 0 */ +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* _UAPI_S390_PTRACE_H */ diff --git a/tools/include/uapi/asm-generic/bpf_perf_event.h b/tools/include/uapi/asm-generic/bpf_perf_event.h new file mode 100644 index 000000000000..53815d2cd047 --- /dev/null +++ b/tools/include/uapi/asm-generic/bpf_perf_event.h @@ -0,0 +1,9 @@ +#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ + +#include + +/* Export kernel pt_regs structure */ +typedef struct pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */ diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h index 067427259820..8f95303f9d80 100644 --- a/tools/include/uapi/linux/bpf_perf_event.h +++ b/tools/include/uapi/linux/bpf_perf_event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or @@ -7,11 +8,10 @@ #ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__ #define _UAPI__LINUX_BPF_PERF_EVENT_H__ -#include -#include +#include struct bpf_perf_event_data { - struct pt_regs regs; + bpf_user_pt_regs_t regs; __u64 sample_period; }; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 333a48655ee0..21a2d76b67dc 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,7 +1,19 @@ # SPDX-License-Identifier: GPL-2.0 + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif +include $(srctree)/tools/scripts/Makefile.arch + +$(call detected_var,SRCARCH) + LIBDIR := ../../../lib BPFDIR := $(LIBDIR)/bpf APIDIR := ../../../include/uapi +ASMDIR:= ../../../arch/$(ARCH)/include/uapi GENDIR := ../../../../include/generated GENHDR := $(GENDIR)/autoconf.h @@ -9,7 +21,7 @@ ifneq ($(wildcard $(GENHDR)),) GENFLAGS := -DHAVE_GENHDR endif -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(ASMDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ -- cgit v1.2.3 From a81c42136604fb660b366d1ff6d9e0969f166413 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Mon, 4 Dec 2017 10:56:49 +0100 Subject: perf s390: add regs_query_register_offset() The regs_query_register_offset() helper function converts register name like "%r0" to an offset of a register in user_pt_regs It is required by the BPF prologue generator. The user_pt_regs structure was recently added to "asm/ptrace.h". Hence, update tools/perf/check-headers.sh to keep the header file in sync with kernel changes. Suggested-by: Thomas Richter Signed-off-by: Hendrik Brueckner Reviewed-and-tested-by: Thomas Richter Acked-by: Alexei Starovoitov Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Heiko Carstens Signed-off-by: Daniel Borkmann --- tools/perf/arch/s390/Makefile | 1 + tools/perf/arch/s390/util/dwarf-regs.c | 32 +++++++++++++++++++++++++++++--- tools/perf/check-headers.sh | 1 + 3 files changed, 31 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 21322e0385b8..09ba923debe8 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -2,3 +2,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif HAVE_KVM_STAT_SUPPORT := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c index f47576ce13ea..a8ace5cc6301 100644 --- a/tools/perf/arch/s390/util/dwarf-regs.c +++ b/tools/perf/arch/s390/util/dwarf-regs.c @@ -2,17 +2,43 @@ /* * Mapping of DWARF debug register numbers into register names. * - * Copyright IBM Corp. 2010 - * Author(s): Heiko Carstens , + * Copyright IBM Corp. 2010, 2017 + * Author(s): Heiko Carstens , + * Hendrik Brueckner * */ +#include #include -#include +#include #include +#include +#include +#include #include "dwarf-regs-table.h" const char *get_arch_regstr(unsigned int n) { return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n]; } + +/* + * Convert the register name into an offset to struct pt_regs (kernel). + * This is required by the BPF prologue generator. The BPF + * program is called in the BPF overflow handler in the perf + * core. + */ +int regs_query_register_offset(const char *name) +{ + unsigned long gpr; + + if (!name || strncmp(name, "%r", 2)) + return -EINVAL; + + errno = 0; + gpr = strtoul(name + 2, NULL, 10); + if (errno || gpr >= 16) + return -EINVAL; + + return offsetof(user_pt_regs, gprs) + 8 * gpr; +} diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 77406d25e521..6db9d809fe97 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -30,6 +30,7 @@ arch/x86/include/uapi/asm/vmx.h arch/powerpc/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm_perf.h +arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h -- cgit v1.2.3 From 14c47b54b0d9389e3ca0718e805cdd90c5a4303a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Sat, 2 Dec 2017 16:17:44 -0600 Subject: objtool: Fix 64-bit build on 32-bit host The new ORC unwinder breaks the build of a 64-bit kernel on a 32-bit host. Building the kernel on a i386 or x32 host fails with: orc_dump.c: In function 'orc_dump': orc_dump.c:105:26: error: passing argument 2 of 'elf_getshdrnum' from incompatible pointer type [-Werror=incompatible-pointer-types] if (elf_getshdrnum(elf, &nr_sections)) { ^ In file included from /usr/local/include/gelf.h:32:0, from elf.h:22, from warn.h:26, from orc_dump.c:20: /usr/local/include/libelf.h:304:12: note: expected 'size_t * {aka unsigned int *}' but argument is of type 'long unsigned int *' extern int elf_getshdrnum (Elf *__elf, size_t *__dst); ^~~~~~~~~~~~~~ orc_dump.c:190:17: error: format '%lx' expects argument of type 'long unsigned int', but argument 3 has type 'Elf64_Sxword {aka long long int}' [-Werror=format=] printf("%s+%lx:", name, rela.r_addend); ~~^ ~~~~~~~~~~~~~ %llx Fix the build failure. Another problem is that if the user specifies HOSTCC or HOSTLD variables, they are ignored in the objtool makefile. Change the Makefile to respect these variables. Signed-off-by: Mikulas Patocka Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sven Joachim Cc: Thomas Gleixner Fixes: 627fce14809b ("objtool: Add ORC unwind table generation") Link: http://lkml.kernel.org/r/19f0e64d8e07e30a7b307cd010eb780c404fe08d.1512252895.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/Makefile | 8 +++++--- tools/objtool/orc_dump.c | 7 ++++--- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 0f94af3ccaaa..ae0272f9a091 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -7,9 +7,11 @@ ARCH := x86 endif # always use the host compiler -CC = gcc -LD = ld -AR = ar +HOSTCC ?= gcc +HOSTLD ?= ld +CC = $(HOSTCC) +LD = $(HOSTLD) +AR = ar ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(CURDIR))) diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 36c5bf6a2675..c3343820916a 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -76,7 +76,8 @@ int orc_dump(const char *_objname) int fd, nr_entries, i, *orc_ip = NULL, orc_size = 0; struct orc_entry *orc = NULL; char *name; - unsigned long nr_sections, orc_ip_addr = 0; + size_t nr_sections; + Elf64_Addr orc_ip_addr = 0; size_t shstrtab_idx; Elf *elf; Elf_Scn *scn; @@ -187,10 +188,10 @@ int orc_dump(const char *_objname) return -1; } - printf("%s+%lx:", name, rela.r_addend); + printf("%s+%llx:", name, (unsigned long long)rela.r_addend); } else { - printf("%lx:", orc_ip_addr + (i * sizeof(int)) + orc_ip[i]); + printf("%llx:", (unsigned long long)(orc_ip_addr + (i * sizeof(int)) + orc_ip[i])); } -- cgit v1.2.3 From 34c9ca37aaec2e307b837bb099d3b44f0ea04ddc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 6 Dec 2017 22:41:53 +0100 Subject: tooling/headers: Synchronize updated s390 and x86 UAPI headers There were two trivial updates to these upstream UAPI headers: arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm_perf.h arch/x86/lib/x86-opcode-map.txt Synchronize them with their tooling copies. (The x86 opcode map includes a new instruction pattern now.) Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Namhyung Kim Cc: Jiri Olsa Cc: Linus Torvalds Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/arch/s390/include/uapi/asm/kvm.h | 4 ---- tools/arch/s390/include/uapi/asm/kvm_perf.h | 4 ---- tools/perf/util/intel-pt-decoder/x86-opcode-map.txt | 2 +- 3 files changed, 1 insertion(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 9ad172dcd912..38535a57fef8 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -6,10 +6,6 @@ * * Copyright IBM Corp. 2008 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - * * Author(s): Carsten Otte * Christian Borntraeger */ diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h index c36c97ffdc6f..84606b8cc49e 100644 --- a/tools/arch/s390/include/uapi/asm/kvm_perf.h +++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h @@ -4,10 +4,6 @@ * * Copyright 2014 IBM Corp. * Author(s): Alexander Yarygin - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. */ #ifndef __LINUX_KVM_PERF_S390_H diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 12e377184ee4..c4d55919fac1 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -896,7 +896,7 @@ EndTable GrpTable: Grp3_1 0: TEST Eb,Ib -1: +1: TEST Eb,Ib 2: NOT Eb 3: NEG Eb 4: MUL AL,Eb -- cgit v1.2.3 From 5790eabc6e7c3ce2d6ca2e3bbf4de467ce2b64b3 Mon Sep 17 00:00:00 2001 From: Michael S. Tsirkin Date: Fri, 8 Dec 2017 17:31:37 +0200 Subject: ptr_ring: fix up after recent ptr_ring changes Add more stubs to make it build. Fixes: 81fbfe8a ("ptr_ring: use kmalloc_array()") Signed-off-by: Michael S. Tsirkin --- tools/virtio/ringtest/ptr_ring.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c index 38bb171aceba..e6e81305ef46 100644 --- a/tools/virtio/ringtest/ptr_ring.c +++ b/tools/virtio/ringtest/ptr_ring.c @@ -16,24 +16,41 @@ #define unlikely(x) (__builtin_expect(!!(x), 0)) #define likely(x) (__builtin_expect(!!(x), 1)) #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a)) +#define SIZE_MAX (~(size_t)0) + typedef pthread_spinlock_t spinlock_t; typedef int gfp_t; -static void *kmalloc(unsigned size, gfp_t gfp) -{ - return memalign(64, size); -} +#define __GFP_ZERO 0x1 -static void *kzalloc(unsigned size, gfp_t gfp) +static void *kmalloc(unsigned size, gfp_t gfp) { void *p = memalign(64, size); if (!p) return p; - memset(p, 0, size); + if (gfp & __GFP_ZERO) + memset(p, 0, size); return p; } +static inline void *kzalloc(unsigned size, gfp_t flags) +{ + return kmalloc(size, flags | __GFP_ZERO); +} + +static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) +{ + if (size != 0 && n > SIZE_MAX / size) + return NULL; + return kmalloc(n * size, flags); +} + +static inline void *kcalloc(size_t n, size_t size, gfp_t flags) +{ + return kmalloc_array(n, size, flags | __GFP_ZERO); +} + static void kfree(void *p) { if (p) -- cgit v1.2.3 From 82a2b827c96883d8b39a58bba23d222d6b0de7ff Mon Sep 17 00:00:00 2001 From: Julien BOIBESSOT Date: Tue, 5 Dec 2017 16:09:04 +0100 Subject: tools/usbip: fixes potential (minor) "buffer overflow" (detected on recent gcc with -Werror) Fixes following build error: vhci_driver.c: In function 'refresh_imported_device_list': vhci_driver.c:118:37: error: 'snprintf' output may be truncated before the last format character [-Werror=format-truncation=] snprintf(status, sizeof(status), "status.%d", i); ^~~~~~~~~~~ vhci_driver.c:118:4: note: 'snprintf' output between 9 and 18 bytes into a destination of size 17 snprintf(status, sizeof(status), "status.%d", i); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors Signed-off-by: Julien BOIBESSOT Acked-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- tools/usb/usbip/libsrc/vhci_driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index 8a1cd1616de4..627d1dfc332b 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -106,7 +106,7 @@ static int parse_status(const char *value) return 0; } -#define MAX_STATUS_NAME 16 +#define MAX_STATUS_NAME 18 static int refresh_imported_device_list(void) { -- cgit v1.2.3 From 2f2d0088eb93db5c649d2a5e34a3800a8a935fc5 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 7 Dec 2017 14:16:49 -0700 Subject: usbip: prevent vhci_hcd driver from leaking a socket pointer address When a client has a USB device attached over IP, the vhci_hcd driver is locally leaking a socket pointer address via the /sys/devices/platform/vhci_hcd/status file (world-readable) and in debug output when "usbip --debug port" is run. Fix it to not leak. The socket pointer address is not used at the moment and it was made visible as a convenient way to find IP address from socket pointer address by looking up /proc/net/{tcp,tcp6}. As this opens a security hole, the fix replaces socket pointer address with sockfd. Reported-by: Secunia Research Cc: stable Signed-off-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- drivers/usb/usbip/usbip_common.h | 1 + drivers/usb/usbip/vhci_sysfs.c | 25 ++++++++++++++++--------- tools/usb/usbip/libsrc/vhci_driver.c | 8 ++++---- 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'tools') diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index e5de35c8c505..473fb8a87289 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -256,6 +256,7 @@ struct usbip_device { /* lock for status */ spinlock_t lock; + int sockfd; struct socket *tcp_socket; struct task_struct *tcp_rx; diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c index e78f7472cac4..091f76b7196d 100644 --- a/drivers/usb/usbip/vhci_sysfs.c +++ b/drivers/usb/usbip/vhci_sysfs.c @@ -17,15 +17,20 @@ /* * output example: - * hub port sta spd dev socket local_busid - * hs 0000 004 000 00000000 c5a7bb80 1-2.3 + * hub port sta spd dev sockfd local_busid + * hs 0000 004 000 00000000 3 1-2.3 * ................................................ - * ss 0008 004 000 00000000 d8cee980 2-3.4 + * ss 0008 004 000 00000000 4 2-3.4 * ................................................ * - * IP address can be retrieved from a socket pointer address by looking - * up /proc/net/{tcp,tcp6}. Also, a userland program may remember a - * port number and its peer IP address. + * Output includes socket fd instead of socket pointer address to avoid + * leaking kernel memory address in: + * /sys/devices/platform/vhci_hcd.0/status and in debug output. + * The socket pointer address is not used at the moment and it was made + * visible as a convenient way to find IP address from socket pointer + * address by looking up /proc/net/{tcp,tcp6}. As this opens a security + * hole, the change is made to use sockfd instead. + * */ static void port_show_vhci(char **out, int hub, int port, struct vhci_device *vdev) { @@ -39,8 +44,8 @@ static void port_show_vhci(char **out, int hub, int port, struct vhci_device *vd if (vdev->ud.status == VDEV_ST_USED) { *out += sprintf(*out, "%03u %08x ", vdev->speed, vdev->devid); - *out += sprintf(*out, "%16p %s", - vdev->ud.tcp_socket, + *out += sprintf(*out, "%u %s", + vdev->ud.sockfd, dev_name(&vdev->udev->dev)); } else { @@ -160,7 +165,8 @@ static ssize_t nports_show(struct device *dev, struct device_attribute *attr, char *s = out; /* - * Half the ports are for SPEED_HIGH and half for SPEED_SUPER, thus the * 2. + * Half the ports are for SPEED_HIGH and half for SPEED_SUPER, + * thus the * 2. */ out += sprintf(out, "%d\n", VHCI_PORTS * vhci_num_controllers); return out - s; @@ -366,6 +372,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr, vdev->devid = devid; vdev->speed = speed; + vdev->ud.sockfd = sockfd; vdev->ud.tcp_socket = socket; vdev->ud.status = VDEV_ST_NOTASSIGNED; diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index 627d1dfc332b..c9c81614a66a 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -50,14 +50,14 @@ static int parse_status(const char *value) while (*c != '\0') { int port, status, speed, devid; - unsigned long socket; + int sockfd; char lbusid[SYSFS_BUS_ID_SIZE]; struct usbip_imported_device *idev; char hub[3]; - ret = sscanf(c, "%2s %d %d %d %x %lx %31s\n", + ret = sscanf(c, "%2s %d %d %d %x %u %31s\n", hub, &port, &status, &speed, - &devid, &socket, lbusid); + &devid, &sockfd, lbusid); if (ret < 5) { dbg("sscanf failed: %d", ret); @@ -66,7 +66,7 @@ static int parse_status(const char *value) dbg("hub %s port %d status %d speed %d devid %x", hub, port, status, speed, devid); - dbg("socket %lx lbusid %s", socket, lbusid); + dbg("sockfd %u lbusid %s", sockfd, lbusid); /* if a device is connected, look at it */ idev = &vhci_driver->idev[port]; -- cgit v1.2.3 From f335195adf043168ee69d78ea72ac3e30f0c57ce Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Dec 2017 11:27:57 +0100 Subject: kmemcheck: rip it out for real Commit 4675ff05de2d ("kmemcheck: rip it out") has removed the code but for some reason SPDX header stayed in place. This looks like a rebase mistake in the mmotm tree or the merge mistake. Let's drop those leftovers as well. Signed-off-by: Michal Hocko Signed-off-by: Linus Torvalds --- arch/x86/include/asm/kmemcheck.h | 1 - arch/x86/mm/kmemcheck/error.c | 1 - arch/x86/mm/kmemcheck/error.h | 1 - arch/x86/mm/kmemcheck/opcode.c | 1 - arch/x86/mm/kmemcheck/opcode.h | 1 - arch/x86/mm/kmemcheck/pte.c | 1 - arch/x86/mm/kmemcheck/pte.h | 1 - arch/x86/mm/kmemcheck/selftest.c | 1 - arch/x86/mm/kmemcheck/selftest.h | 1 - arch/x86/mm/kmemcheck/shadow.h | 1 - include/linux/kmemcheck.h | 1 - mm/kmemcheck.c | 1 - tools/include/linux/kmemcheck.h | 1 - 13 files changed, 13 deletions(-) delete mode 100644 arch/x86/include/asm/kmemcheck.h delete mode 100644 arch/x86/mm/kmemcheck/error.c delete mode 100644 arch/x86/mm/kmemcheck/error.h delete mode 100644 arch/x86/mm/kmemcheck/opcode.c delete mode 100644 arch/x86/mm/kmemcheck/opcode.h delete mode 100644 arch/x86/mm/kmemcheck/pte.c delete mode 100644 arch/x86/mm/kmemcheck/pte.h delete mode 100644 arch/x86/mm/kmemcheck/selftest.c delete mode 100644 arch/x86/mm/kmemcheck/selftest.h delete mode 100644 arch/x86/mm/kmemcheck/shadow.h delete mode 100644 include/linux/kmemcheck.h delete mode 100644 mm/kmemcheck.c delete mode 100644 tools/include/linux/kmemcheck.h (limited to 'tools') diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/include/asm/kmemcheck.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/error.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/error.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/opcode.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/opcode.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/pte.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/pte.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/selftest.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/selftest.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/shadow.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/include/linux/kmemcheck.h b/include/linux/kmemcheck.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/include/linux/kmemcheck.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c deleted file mode 100644 index cec594032515..000000000000 --- a/mm/kmemcheck.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/tools/include/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/tools/include/linux/kmemcheck.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -- cgit v1.2.3 From f971e511cb7d6f1b3730248cf2967d3ccdd8874c Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 27 Nov 2017 10:38:21 +0000 Subject: tools/perf: Convert ACCESS_ONCE() to READ_ONCE() Recently there was a treewide conversion of ACCESS_ONCE() to {READ,WRITE}_ONCE(), but a new use was introduced concurrently by commit: 1695849735752d2a ("perf mmap: Move perf_mmap and methods to separate mmap.[ch] files") Let's convert this over to READ_ONCE() so that we can remove the ACCESS_ONCE() definitions in subsequent patches. Tested-by: Paul E. McKenney Signed-off-by: Mark Rutland Reviewed-by: Paul E. McKenney Cc: Arnaldo Carvalho de Melo Cc: Joe Perches Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: apw@canonical.com Link: http://lkml.kernel.org/r/20171127103824.36526-2-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- tools/perf/util/mmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index efd78b827b05..3a5cb5a6e94a 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -70,7 +70,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md); static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; - u64 head = ACCESS_ONCE(pc->data_head); + u64 head = READ_ONCE(pc->data_head); rmb(); return head; } -- cgit v1.2.3 From 2a22f692bbe0a7933acbd50045479ffc0fdf11f7 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 27 Nov 2017 10:38:22 +0000 Subject: tools/include: Remove ACCESS_ONCE() There are no longer any usersapce uses of ACCESS_ONCE(), so we can remove the definition from our userspace , which is only used by tools in the kernel directory (i.e. it isn't a uapi header). This patch removes the ACCESS_ONCE() definition, and updates comments which referred to it. At the same time, some inconsistent and redundant whitespace is removed from comments. Tested-by: Paul E. McKenney Signed-off-by: Mark Rutland Cc: Arnaldo Carvalho de Melo Cc: Joe Perches Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: apw@canonical.com Link: http://lkml.kernel.org/r/20171127103824.36526-3-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- tools/include/linux/compiler.h | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'tools') diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 07fd03c74a77..04e32f965ad7 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -84,8 +84,6 @@ #define uninitialized_var(x) x = *(&(x)) -#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) - #include /* @@ -135,20 +133,19 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of - * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the - * compiler is aware of some particular ordering. One way to make the - * compiler aware of ordering is to put the two invocations of READ_ONCE, - * WRITE_ONCE or ACCESS_ONCE() in different C statements. + * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some + * particular ordering. One way to make the compiler aware of ordering is to + * put the two invocations of READ_ONCE or WRITE_ONCE in different C + * statements. * - * In contrast to ACCESS_ONCE these two macros will also work on aggregate - * data types like structs or unions. If the size of the accessed data - * type exceeds the word size of the machine (e.g., 32 bits or 64 bits) - * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a - * compile-time warning. + * These two macros will also work on aggregate data types like structs or + * unions. If the size of the accessed data type exceeds the word size of + * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will + * fall back to memcpy and print a compile-time warning. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, - * and (2) Ensuring that the compiler does not fold, spindle, or otherwise + * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. -- cgit v1.2.3 From 720f228e8d3128b7ab1d39f51fdd8da07a7640c9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 12 Dec 2017 02:25:32 +0100 Subject: bpf: fix broken BPF selftest build At least on x86_64, the kernel's BPF selftests seemed to have stopped to build due to 618e165b2a8e ("selftests/bpf: sync kernel headers and introduce arch support in Makefile"): [...] In file included from test_verifier.c:29:0: ../../../include/uapi/linux/bpf_perf_event.h:11:32: fatal error: asm/bpf_perf_event.h: No such file or directory #include ^ compilation terminated. [...] While pulling in tools/arch/*/include/uapi/asm/bpf_perf_event.h seems to work fine, there's no automated fall-back logic right now that would do the same out of tools/include/uapi/asm-generic/bpf_perf_event.h. The usual convention today is to add a include/[uapi/]asm/ equivalent that would pull in the correct arch header or generic one as fall-back, all ifdef'ed based on compiler target definition. It's similarly done also in other cases such as tools/include/asm/barrier.h, thus adapt the same here. Fixes: 618e165b2a8e ("selftests/bpf: sync kernel headers and introduce arch support in Makefile") Signed-off-by: Daniel Borkmann Cc: Hendrik Brueckner Cc: Arnaldo Carvalho de Melo Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- tools/include/uapi/asm/bpf_perf_event.h | 7 +++++++ tools/testing/selftests/bpf/Makefile | 13 +------------ 2 files changed, 8 insertions(+), 12 deletions(-) create mode 100644 tools/include/uapi/asm/bpf_perf_event.h (limited to 'tools') diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..13a58531e6fa --- /dev/null +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,7 @@ +#if defined(__aarch64__) +#include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h" +#elif defined(__s390__) +#include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" +#else +#include +#endif diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 21a2d76b67dc..792af7c3b74f 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,19 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(CURDIR))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -endif -include $(srctree)/tools/scripts/Makefile.arch - -$(call detected_var,SRCARCH) - LIBDIR := ../../../lib BPFDIR := $(LIBDIR)/bpf APIDIR := ../../../include/uapi -ASMDIR:= ../../../arch/$(ARCH)/include/uapi GENDIR := ../../../../include/generated GENHDR := $(GENDIR)/autoconf.h @@ -21,7 +10,7 @@ ifneq ($(wildcard $(GENHDR)),) GENFLAGS := -DHAVE_GENHDR endif -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(ASMDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ -- cgit v1.2.3 From 92ccc262e485781ff4c0fb3b7c77a619282df49a Mon Sep 17 00:00:00 2001 From: Mengting Zhang Date: Tue, 12 Dec 2017 18:16:57 +0000 Subject: tools/lib/lockdep: Add missing declaration of 'pr_cont()' Commit: 681fbec881de ("lockdep: Use consistent printing primitives") has moved lockdep away from using printk() for printing. The commit added usage of pr_cont() which wasn't wrapped in the userspace headers, causing the following warning for the liblockdep build: ../../../kernel/locking/lockdep.c:3544:2: warning: implicit declaration of function 'pr_cont' [-Wimplicit-function-declaration] Adding an empty declaration of 'pr_cont' fixes the problem. Signed-off-by: Mengting Zhang Signed-off-by: Sasha Levin Reviewed-by: Alexander Sverdlin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: a.p.zijlstra@chello.nl Link: http://lkml.kernel.org/r/20171212181644.11913-2-alexander.levin@verizon.com Signed-off-by: Ingo Molnar --- tools/include/linux/lockdep.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 940c1b075659..6b0c36a58fcb 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -48,6 +48,7 @@ static inline int debug_locks_off(void) #define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) #define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) #define pr_warn pr_err +#define pr_cont pr_err #define list_del_rcu list_del -- cgit v1.2.3 From 19e8e54f4309eaa438237aa1973fe40c331903d4 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:19 +0100 Subject: tools/kvm_stat: fix command line option '-g' Specifying a guest via '-g foo' always results in an error: $ kvm_stat -g foo Usage: kvm_stat [options] kvm_stat: error: Error while searching for guest "foo", use "-p" to specify a pid instead Reason is that Tui.get_pid_from_gname() is not static, as it is supposed to be. Signed-off-by: Stefan Raspl Tested-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 217cf6f95c36..884a74b8ca87 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -950,7 +950,8 @@ class Tui(object): curses.nocbreak() curses.endwin() - def get_all_gnames(self): + @staticmethod + def get_all_gnames(): """Returns a list of (pid, gname) tuples of all running guests""" res = [] try: @@ -963,7 +964,7 @@ class Tui(object): # perform a sanity check before calling the more expensive # function to possibly extract the guest name if ' -name ' in line[1]: - res.append((line[0], self.get_gname_from_pid(line[0]))) + res.append((line[0], Tui.get_gname_from_pid(line[0]))) child.stdout.close() return res @@ -984,7 +985,8 @@ class Tui(object): except Exception: self.screen.addstr(row + 1, 2, 'Not available') - def get_pid_from_gname(self, gname): + @staticmethod + def get_pid_from_gname(gname): """Fuzzy function to convert guest name to QEMU process pid. Returns a list of potential pids, can be empty if no match found. @@ -992,7 +994,7 @@ class Tui(object): """ pids = [] - for line in self.get_all_gnames(): + for line in Tui.get_all_gnames(): if gname == line[1]: pids.append(int(line[0])) -- cgit v1.2.3 From faa06650418bf28d07426fcfdc5213782fb131f6 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:20 +0100 Subject: tools/kvm_stat: fix drilldown in events-by-guests mode When displaying debugfs events listed by guests, an attempt to switch to reporting of stats for individual child trace events results in garbled output. Reason is that when toggling drilldown, the update of the stats doesn't honor when events are displayed by guests, as indicated by Tui._display_guests. To reproduce, run 'kvm_stat -d' and press 'b' followed by 'x'. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 884a74b8ca87..6347ad5d0d35 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1360,7 +1360,7 @@ class Tui(object): if char == 'x': self.update_drilldown() # prevents display of current values on next refresh - self.stats.get() + self.stats.get(self._display_guests) except KeyboardInterrupt: break except curses.error: -- cgit v1.2.3 From 67c162b0892ac481e47bef06d9c6231ee993843a Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:21 +0100 Subject: tools/kvm_stat: fix missing field update after filter change When updating the fields filter, tracepoint events of fields previously not visible were not enabled, as TracepointProvider.update_fields() updated the member variable directly instead of using the setter, which triggers the event enable/disable. To reproduce, run 'kvm_stat -f kvm_exit', press 'c' to remove the filter, and notice that no add'l fields that do not match the regex 'kvm_exit' will appear. This issue was introduced by commit c469117df059 ("tools/kvm_stat: simplify initializers"). Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 6347ad5d0d35..f133755fdde2 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -549,8 +549,8 @@ class TracepointProvider(Provider): def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" - self._fields = [field for field in self.get_available_fields() - if self.is_field_wanted(fields_filter, field)] + self.fields = [field for field in self.get_available_fields() + if self.is_field_wanted(fields_filter, field)] @staticmethod def get_online_cpus(): -- cgit v1.2.3 From b74faa930deb2e37ed5caa0abfc687c8c532e946 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:22 +0100 Subject: tools/kvm_stat: fix extra handling of 'help' with fields filter Commit 67fbcd62f54d ("tools/kvm_stat: add '-f help' to get the available event list") added support for '-f help'. However, the extra handling of 'help' will also take effect when 'help' is specified as a regex in interactive mode via 'f'. This results in display of all events while only those matching this regex should be shown. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index f133755fdde2..4faf9f85a00e 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -478,7 +478,7 @@ class Provider(object): @staticmethod def is_field_wanted(fields_filter, field): """Indicate whether field is valid according to fields_filter.""" - if not fields_filter or fields_filter == "help": + if not fields_filter: return True return re.match(fields_filter, field) is not None @@ -1567,6 +1567,7 @@ def main(): stats = Stats(options) if options.fields == "help": + stats.fields_filter = None event_list = "\n" s = stats.get() for key in s.keys(): -- cgit v1.2.3 From fff8c9eb48aa58259071b5df0e6d4c1c0bc1ba51 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:23 +0100 Subject: tools/kvm_stat: fix child trace events accounting Child trace events were included in calculation of the overall total, which is used for calculation of the percentages of the '%Total' column. However, the parent trace envents' stats summarize the child trace events, hence we'd incorrectly account for them twice, leading to slightly wrong stats. With this fix, we use the correct total. Consequently, the sum of the child trace events' '%Total' column values is identical to the respective value of the respective parent event. However, this also means that the sum of the '%Total' column values will aggregate to more than 100 percent. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 6 +++--- tools/kvm/kvm_stat/kvm_stat.txt | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 4faf9f85a00e..90f0445d7808 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1092,14 +1092,14 @@ class Tui(object): # sort by totals return (0, -stats[x][0]) total = 0. - for val in stats.values(): - total += val[0] + for key in stats.keys(): + if key.find('(') is -1: + total += stats[key][0] if self._sorting == SORT_DEFAULT: sortkey = sortCurAvg else: sortkey = sortTotal for key in sorted(stats.keys(), key=sortkey): - if row >= self.screen.getmaxyx()[0]: break values = stats[key] diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index e5cf836be8a1..75368a3c285f 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -50,6 +50,8 @@ INTERACTIVE COMMANDS *s*:: set update interval *x*:: toggle reporting of stats for child trace events + :: *Note*: The stats for the parents summarize the respective child trace + events Press any other key to refresh statistics immediately. -- cgit v1.2.3 From f3d11b0e8619bbb053d3e13f2271819fb01c1e2a Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:24 +0100 Subject: tools/kvm_stat: add hint on '-f help' to man page The man page update for this new functionality was omitted. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index 75368a3c285f..b5b3810c9e94 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -88,7 +88,7 @@ OPTIONS -f:: --fields=:: - fields to display (regex) + fields to display (regex), "-f help" for a list of available events -h:: --help:: -- cgit v1.2.3 From 08e20a6300e106d5feb89c9e47ea479533fec46f Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:25 +0100 Subject: tools/kvm_stat: handle invalid regular expressions Passing an invalid regular expression on the command line results in a traceback. Note that interactive specification of invalid regular expressions is not affected To reproduce, run "kvm_stat -f '*'". Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 90f0445d7808..29c56f3a05dc 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1521,6 +1521,13 @@ Press any other key to refresh statistics immediately. callback=cb_guest_to_pid, ) (options, _) = optparser.parse_args(sys.argv) + try: + # verify that we were passed a valid regex up front + re.compile(options.fields) + except re.error: + sys.exit('Error: "' + options.fields + '" is not a valid regular ' + 'expression') + return options -- cgit v1.2.3 From 822cfe3e4813c8f52199362b0e689fba9459ddc9 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:26 +0100 Subject: tools/kvm_stat: suppress usage information on command line errors Errors while parsing the '-g' command line argument result in display of usage information prior to the error message. This is a bit confusing, as the command line is syntactically correct. To reproduce, run 'kvm_stat -g' and specify a non-existing or inactive guest. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 29c56f3a05dc..bf65531570f5 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1453,16 +1453,13 @@ Press any other key to refresh statistics immediately. try: pids = Tui.get_pid_from_gname(val) except: - raise optparse.OptionValueError('Error while searching for guest ' - '"{}", use "-p" to specify a pid ' - 'instead'.format(val)) + sys.exit('Error while searching for guest "{}". Use "-p" to ' + 'specify a pid instead?'.format(val)) if len(pids) == 0: - raise optparse.OptionValueError('No guest by the name "{}" ' - 'found'.format(val)) + sys.exit('Error: No guest by the name "{}" found'.format(val)) if len(pids) > 1: - raise optparse.OptionValueError('Multiple processes found (pids: ' - '{}) - use "-p" to specify a pid ' - 'instead'.format(" ".join(pids))) + sys.exit('Error: Multiple processes found (pids: {}). Use "-p" ' + 'to specify the desired pid'.format(" ".join(pids))) parser.values.pid = pids[0] optparser = optparse.OptionParser(description=description_text, -- cgit v1.2.3 From 73fab6ffbd83795e38974bb438e7afce0242c61a Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:27 +0100 Subject: tools/kvm_stat: stop ignoring unhandled arguments Unhandled arguments, which could easily include typos, are simply ignored. We should be strict to avoid undetected typos. To reproduce start kvm_stat with an extra argument, e.g. 'kvm_stat -d bnuh5ol' and note that this will actually work. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index bf65531570f5..aa3bc47af1d0 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1517,7 +1517,9 @@ Press any other key to refresh statistics immediately. help='restrict statistics to guest by name', callback=cb_guest_to_pid, ) - (options, _) = optparser.parse_args(sys.argv) + options, unkn = optparser.parse_args(sys.argv) + if len(unkn) != 1: + sys.exit('Error: Extra argument(s): ' + ' '.join(unkn[1:])) try: # verify that we were passed a valid regex up front re.compile(options.fields) -- cgit v1.2.3 From cf656c76614c6ec5b016233cac29738881c83c08 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Mon, 11 Dec 2017 12:25:29 +0100 Subject: tools/kvm_stat: add line for totals Add a line for the total number of events and current average at the bottom of the body. Note that both values exclude child trace events. I.e. if drilldown is activated via interactive command 'x', only the totals are accounted, or we'd be counting these twice (see previous commit "tools/kvm_stat: fix child trace events accounting"). Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index aa3bc47af1d0..566a70ddd005 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1099,8 +1099,9 @@ class Tui(object): sortkey = sortCurAvg else: sortkey = sortTotal + tavg = 0 for key in sorted(stats.keys(), key=sortkey): - if row >= self.screen.getmaxyx()[0]: + if row >= self.screen.getmaxyx()[0] - 1: break values = stats[key] if not values[0] and not values[1]: @@ -1112,9 +1113,15 @@ class Tui(object): self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key, values[0], values[0] * 100 / total, cur)) + if cur is not '' and key.find('(') is -1: + tavg += cur row += 1 if row == 3: self.screen.addstr(4, 1, 'No matching events reported yet') + else: + self.screen.addstr(row, 1, '%-40s %10d %8s' % + ('Total', total, tavg if tavg else ''), + curses.A_BOLD) self.screen.refresh() def show_msg(self, text): -- cgit v1.2.3 From 0b265c3b3b721dca03e82719ac0e15bc2c89aa3a Mon Sep 17 00:00:00 2001 From: Liu, Changcheng Date: Thu, 14 Dec 2017 15:33:05 -0800 Subject: tools/slabinfo-gnuplot: force to use bash shell On some linux distributions, the default link of sh is dash which deoesn't support split array like "${var//,/ }" It's better to force to use bash shell directly. Link: http://lkml.kernel.org/r/20171208093751.GA175471@sofia Signed-off-by: Liu Changcheng Reviewed-by: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/vm/slabinfo-gnuplot.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/vm/slabinfo-gnuplot.sh b/tools/vm/slabinfo-gnuplot.sh index 35b039864b77..0cf28aa6f21c 100644 --- a/tools/vm/slabinfo-gnuplot.sh +++ b/tools/vm/slabinfo-gnuplot.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # Sergey Senozhatsky, 2015 # sergey.senozhatsky.work@gmail.com -- cgit v1.2.3 From f5b5fab1780c98b74526dbac527574bd02dc16f8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 11 Dec 2017 10:38:36 -0800 Subject: x86/decoder: Fix and update the opcodes map Update x86-opcode-map.txt based on the October 2017 Intel SDM publication. Fix INVPID to INVVPID. Add UD0 and UD1 instruction opcodes. Also sync the objtool and perf tooling copies of this file. Signed-off-by: Randy Dunlap Acked-by: Masami Hiramatsu Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/aac062d7-c0f6-96e3-5c92-ed299e2bd3da@infradead.org Signed-off-by: Ingo Molnar --- arch/x86/lib/x86-opcode-map.txt | 13 +++++++++++-- tools/objtool/arch/x86/insn/x86-opcode-map.txt | 15 ++++++++++++--- tools/perf/util/intel-pt-decoder/x86-opcode-map.txt | 15 ++++++++++++--- 3 files changed, 35 insertions(+), 8 deletions(-) (limited to 'tools') diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index c4d55919fac1..e0b85930dd77 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt index 12e377184ee4..e0b85930dd77 100644 --- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt +++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -896,7 +896,7 @@ EndTable GrpTable: Grp3_1 0: TEST Eb,Ib -1: +1: TEST Eb,Ib 2: NOT Eb 3: NEG Eb 4: MUL AL,Eb @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 12e377184ee4..e0b85930dd77 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1) fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1) fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1) fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1) -ff: +ff: UD0 EndTable Table: 3-byte opcode 1 (0x0f 0x38) @@ -717,7 +717,7 @@ AVXcode: 2 7e: vpermt2d/q Vx,Hx,Wx (66),(ev) 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) -81: INVPID Gy,Mdq (66) +81: INVVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) 83: vpmultishiftqb Vx,Hx,Wx (66),(ev) 88: vexpandps/d Vpd,Wpd (66),(ev) @@ -896,7 +896,7 @@ EndTable GrpTable: Grp3_1 0: TEST Eb,Ib -1: +1: TEST Eb,Ib 2: NOT Eb 3: NEG Eb 4: MUL AL,Eb @@ -970,6 +970,15 @@ GrpTable: Grp9 EndTable GrpTable: Grp10 +# all are UD1 +0: UD1 +1: UD1 +2: UD1 +3: UD1 +4: UD1 +5: UD1 +6: UD1 +7: UD1 EndTable # Grp11A and Grp11B are expressed as Grp11 in Intel SDM -- cgit v1.2.3 From 215eada73e77ede7e15531d99f712481ddd429be Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 15 Dec 2017 13:36:56 +0100 Subject: objtool: Resync objtool's instruction decoder source code copy with the kernel's latest version This fixes the following warning: warning: objtool: x86 instruction decoder differs from kernel Note that there are cleanups queued up for v4.16 that will make this warning more informative and will make the syncing easier as well. Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/objtool/arch/x86/insn/inat.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'tools') diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/insn/inat.h index 125ecd2a300d..52dc8d911173 100644 --- a/tools/objtool/arch/x86/insn/inat.h +++ b/tools/objtool/arch/x86/insn/inat.h @@ -97,6 +97,16 @@ #define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) #define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) +/* Identifiers for segment registers */ +#define INAT_SEG_REG_IGNORE 0 +#define INAT_SEG_REG_DEFAULT 1 +#define INAT_SEG_REG_CS 2 +#define INAT_SEG_REG_SS 3 +#define INAT_SEG_REG_DS 4 +#define INAT_SEG_REG_ES 5 +#define INAT_SEG_REG_FS 6 +#define INAT_SEG_REG_GS 7 + /* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); extern int inat_get_last_prefix_id(insn_byte_t last_pfx); -- cgit v1.2.3 From 643e345c95f0b4a4082c60755e06e3e635658da6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 15 Dec 2017 13:47:51 +0100 Subject: tools/headers: Synchronize kernel <-> tooling headers Two kernel headers got modified recently, which are used by tooling as well: tools/include/uapi/linux/kvm.h arch/x86/include/asm/cpufeatures.h None of those changes have an effect on tooling, so do a plain copy. Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Namhyung Kim Cc: Jiri Olsa Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/arch/x86/include/asm/cpufeatures.h | 1 + tools/include/uapi/linux/kvm.h | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index c0b0e9e8aa66..800104c8a3ed 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -266,6 +266,7 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 282d7613fce8..496e59a2738b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -630,9 +630,9 @@ struct kvm_s390_irq { struct kvm_s390_irq_state { __u64 buf; - __u32 flags; + __u32 flags; /* will stay unused for compatibility reasons */ __u32 len; - __u32 reserved[4]; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ }; /* for KVM_SET_GUEST_DEBUG */ -- cgit v1.2.3 From 87ab8194303e73af2898e9e1c8b3b9bcfe91e7a9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 14 Dec 2017 21:07:27 +0100 Subject: bpf: add test case for ld_abs and helper changing pkt data Add a test that i) uses LD_ABS, ii) zeroing R6 before call, iii) calls a helper that triggers reload of cached skb data, iv) uses LD_ABS again. It's added for test_bpf in order to do runtime testing after JITing as well as test_verifier to test that the sequence is allowed. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- lib/test_bpf.c | 43 +++++++++++++++++++++++++++++ tools/testing/selftests/bpf/test_verifier.c | 24 ++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'tools') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index aa8812ae6776..9e9748089270 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -435,6 +435,41 @@ loop: return 0; } +static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self) +{ + struct bpf_insn *insn; + + insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + /* Due to func address being non-const, we need to + * assemble this here. + */ + insn[0] = BPF_MOV64_REG(R6, R1); + insn[1] = BPF_LD_ABS(BPF_B, 0); + insn[2] = BPF_LD_ABS(BPF_H, 0); + insn[3] = BPF_LD_ABS(BPF_W, 0); + insn[4] = BPF_MOV64_REG(R7, R6); + insn[5] = BPF_MOV64_IMM(R6, 0); + insn[6] = BPF_MOV64_REG(R1, R7); + insn[7] = BPF_MOV64_IMM(R2, 1); + insn[8] = BPF_MOV64_IMM(R3, 2); + insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + bpf_skb_vlan_push_proto.func - __bpf_call_base); + insn[10] = BPF_MOV64_REG(R6, R7); + insn[11] = BPF_LD_ABS(BPF_B, 0); + insn[12] = BPF_LD_ABS(BPF_H, 0); + insn[13] = BPF_LD_ABS(BPF_W, 0); + insn[14] = BPF_MOV64_IMM(R0, 42); + insn[15] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = 16; + + return 0; +} + static int bpf_fill_jump_around_ld_abs(struct bpf_test *self) { unsigned int len = BPF_MAXINSNS; @@ -6066,6 +6101,14 @@ static struct bpf_test tests[] = { {}, { {0x1, 0x42 } }, }, + { + "LD_ABS with helper changing skb data", + { }, + INTERNAL, + { 0x34 }, + { { ETH_HLEN, 42 } }, + .fill_helper = bpf_fill_ld_abs_vlan_push_pop2, + }, }; static struct net_device dev; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3c64f30cf63c..b03ecfd7185b 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -6116,6 +6116,30 @@ static struct bpf_test tests[] = { }, .result = ACCEPT, }, + { + "ld_abs: tests on r6 and skb data reload helper", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, { "ld_ind: check calling conv, r1", .insns = { -- cgit v1.2.3 From 5cfee7a357f60675cae32b494bb2096d7203efd3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 Nov 2017 11:27:37 +0100 Subject: perf tools: Use shell function for perl cflags retrieval Using the shell function for perl CFLAGS retrieval instead of back quotes (``). Both execute shell with the command, but the latter is more explicit and seems to be the preferred way. Also we don't have any other use of the back quotes in perf Makefiles. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171108102739.30338-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index ed65e82f034e..710623ddb8af 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -583,7 +583,7 @@ else PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) - PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` + PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) ifneq ($(feature-libperl), 1) -- cgit v1.2.3 From 61fb26a6a23c0f1a07a0f8a11b54bafb1ac2398b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 4 Dec 2017 12:23:08 -0300 Subject: perf tools: Fix up build in hardened environments On Fedora systems the perl and python CFLAGS/LDFLAGS include the hardened specs from redhat-rpm-config package. We apply them only for perl/python objects, which makes them not compatible with the rest of the objects and the build fails with: /usr/bin/ld: perf-in.o: relocation R_X86_64_32 against `.rodata.str1.1' can not be used when making a shared object; recompile with -f +PIC /usr/bin/ld: libperf.a(libperf-in.o): relocation R_X86_64_32S against `.text' can not be used when making a shared object; recompile w +ith -fPIC /usr/bin/ld: final link failed: Nonrepresentable section on output collect2: error: ld returned 1 exit status make[2]: *** [Makefile.perf:507: perf] Error 1 make[1]: *** [Makefile.perf:210: sub-make] Error 2 make: *** [Makefile:69: all] Error 2 Mainly it's caused by perl/python objects being compiled with: -specs=/usr/lib/rpm/redhat/redhat-hardened-cc1 which prevent the final link impossible, because it will check for 'proper' objects with following option: -specs=/usr/lib/rpm/redhat/redhat-hardened-ld Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/20171204082437.GC30564@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 710623ddb8af..0294bfb6c5f8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -188,9 +188,7 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - ifeq ($(CC_NO_CLANG), 1) - PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) - endif + PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) endif @@ -576,7 +574,6 @@ ifndef NO_GTK2 endif endif - ifdef NO_LIBPERL CFLAGS += -DNO_LIBPERL else @@ -584,6 +581,8 @@ else PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) ifneq ($(feature-libperl), 1) -- cgit v1.2.3 From ca58d7e64bdfc54f7dfe46713c1e2acc68d7522d Mon Sep 17 00:00:00 2001 From: Ben Gainey Date: Wed, 22 Nov 2017 18:25:41 -0600 Subject: perf jvmti: Generate correct debug information for inlined code tools/perf/jvmti is broken in so far as it generates incorrect debug information. Specifically it attributes all debug lines to the original method being output even in the case that some code is being inlined from elsewhere. This patch fixes the issue. To test (from within linux/tools/perf): export JDIR=/usr/lib/jvm/java-8-openjdk-amd64/ make cat << __EOF > Test.java public class Test { private StringBuilder b = new StringBuilder(); private void loop(int i, String... args) { for (String a : args) b.append(a); long hc = b.hashCode() * System.nanoTime(); b = new StringBuilder(); b.append(hc); System.out.printf("Iteration %d = %d\n", i, hc); } public void run(String... args) { for (int i = 0; i < 10000; ++i) { loop(i, args); } } public static void main(String... args) { Test t = new Test(); t.run(args); } } __EOF $JDIR/bin/javac Test.java ./perf record -F 10000 -g -k mono $JDIR/bin/java -agentpath:`pwd`/libperf-jvmti.so Test ./perf inject --jit -i perf.data -o perf.data.jitted ./perf annotate -i perf.data.jitted --stdio | grep Test\.java: | sort -u Before this patch, Test.java line numbers get reported that are greater than the number of lines in the Test.java file. They come from the source file of the inlined function, e.g. java/lang/String.java:1085. For further validation one can examine those lines in the JDK source distribution and confirm that they map to inlined functions called by Test.java. After this patch, the filename of the inlined function is output rather than the incorrect original source filename. Signed-off-by: Ben Gainey Tested-by: Arnaldo Carvalho de Melo Tested-by: Stephane Eranian Cc: Alexander Shishkin Cc: Ben Gainey Cc: Colin King Cc: Darren Hart Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 598b7c6919c7 ("perf jit: add source line info support") Link: http://lkml.kernel.org/r/20171122182541.d25599a3eb1ada3480d142fa@arm.com Signed-off-by: Kim Phillips Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/jvmti/jvmti_agent.c | 16 +++-- tools/perf/jvmti/jvmti_agent.h | 7 +- tools/perf/jvmti/libjvmti.c | 147 ++++++++++++++++++++++++++++++++++------- 3 files changed, 134 insertions(+), 36 deletions(-) (limited to 'tools') diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index cf36de7ea255..0c6d1002b524 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -384,13 +384,13 @@ jvmti_write_code(void *agent, char const *sym, } int -jvmti_write_debug_info(void *agent, uint64_t code, const char *file, - jvmti_line_info_t *li, int nr_lines) +jvmti_write_debug_info(void *agent, uint64_t code, + int nr_lines, jvmti_line_info_t *li, + const char * const * file_names) { struct jr_code_debug_info rec; - size_t sret, len, size, flen; + size_t sret, len, size, flen = 0; uint64_t addr; - const char *fn = file; FILE *fp = agent; int i; @@ -405,7 +405,9 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file, return -1; } - flen = strlen(file) + 1; + for (i = 0; i < nr_lines; ++i) { + flen += strlen(file_names[i]) + 1; + } rec.p.id = JIT_CODE_DEBUG_INFO; size = sizeof(rec); @@ -421,7 +423,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file, * file[] : source file name */ size += nr_lines * sizeof(struct debug_entry); - size += flen * nr_lines; + size += flen; rec.p.total_size = size; /* @@ -452,7 +454,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file, if (sret != 1) goto error; - sret = fwrite_unlocked(fn, flen, 1, fp); + sret = fwrite_unlocked(file_names[i], strlen(file_names[i]) + 1, 1, fp); if (sret != 1) goto error; } diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h index fe32d8344a82..6ed82f6c06dd 100644 --- a/tools/perf/jvmti/jvmti_agent.h +++ b/tools/perf/jvmti/jvmti_agent.h @@ -14,6 +14,7 @@ typedef struct { unsigned long pc; int line_number; int discrim; /* discriminator -- 0 for now */ + jmethodID methodID; } jvmti_line_info_t; void *jvmti_open(void); @@ -22,11 +23,9 @@ int jvmti_write_code(void *agent, char const *symbol_name, uint64_t vma, void const *code, const unsigned int code_size); -int jvmti_write_debug_info(void *agent, - uint64_t code, - const char *file, +int jvmti_write_debug_info(void *agent, uint64_t code, int nr_lines, jvmti_line_info_t *li, - int nr_lines); + const char * const * file_names); #if defined(__cplusplus) } diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c index c62c9fc9a525..6add3e982614 100644 --- a/tools/perf/jvmti/libjvmti.c +++ b/tools/perf/jvmti/libjvmti.c @@ -47,6 +47,7 @@ do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci, tab[lines].pc = (unsigned long)pc; tab[lines].line_number = loc_tab[i].line_number; tab[lines].discrim = 0; /* not yet used */ + tab[lines].methodID = m; lines++; } else { break; @@ -125,6 +126,99 @@ get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t ** return JVMTI_ERROR_NONE; } +static void +copy_class_filename(const char * class_sign, const char * file_name, char * result, size_t max_length) +{ + /* + * Assume path name is class hierarchy, this is a common practice with Java programs + */ + if (*class_sign == 'L') { + int j, i = 0; + char *p = strrchr(class_sign, '/'); + if (p) { + /* drop the 'L' prefix and copy up to the final '/' */ + for (i = 0; i < (p - class_sign); i++) + result[i] = class_sign[i+1]; + } + /* + * append file name, we use loops and not string ops to avoid modifying + * class_sign which is used later for the symbol name + */ + for (j = 0; i < (max_length - 1) && file_name && j < strlen(file_name); j++, i++) + result[i] = file_name[j]; + + result[i] = '\0'; + } else { + /* fallback case */ + size_t file_name_len = strlen(file_name); + strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length); + } +} + +static jvmtiError +get_source_filename(jvmtiEnv *jvmti, jmethodID methodID, char ** buffer) +{ + jvmtiError ret; + jclass decl_class; + char *file_name = NULL; + char *class_sign = NULL; + char fn[PATH_MAX]; + size_t len; + + ret = (*jvmti)->GetMethodDeclaringClass(jvmti, methodID, &decl_class); + if (ret != JVMTI_ERROR_NONE) { + print_error(jvmti, "GetMethodDeclaringClass", ret); + return ret; + } + + ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name); + if (ret != JVMTI_ERROR_NONE) { + print_error(jvmti, "GetSourceFileName", ret); + return ret; + } + + ret = (*jvmti)->GetClassSignature(jvmti, decl_class, &class_sign, NULL); + if (ret != JVMTI_ERROR_NONE) { + print_error(jvmti, "GetClassSignature", ret); + goto free_file_name_error; + } + + copy_class_filename(class_sign, file_name, fn, PATH_MAX); + len = strlen(fn); + *buffer = malloc((len + 1) * sizeof(char)); + if (!*buffer) { + print_error(jvmti, "GetClassSignature", ret); + ret = JVMTI_ERROR_OUT_OF_MEMORY; + goto free_class_sign_error; + } + strcpy(*buffer, fn); + ret = JVMTI_ERROR_NONE; + +free_class_sign_error: + (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign); +free_file_name_error: + (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name); + + return ret; +} + +static jvmtiError +fill_source_filenames(jvmtiEnv *jvmti, int nr_lines, + const jvmti_line_info_t * line_tab, + char ** file_names) +{ + int index; + jvmtiError ret; + + for (index = 0; index < nr_lines; ++index) { + ret = get_source_filename(jvmti, line_tab[index].methodID, &(file_names[index])); + if (ret != JVMTI_ERROR_NONE) + return ret; + } + + return JVMTI_ERROR_NONE; +} + static void JNICALL compiled_method_load_cb(jvmtiEnv *jvmti, jmethodID method, @@ -135,16 +229,18 @@ compiled_method_load_cb(jvmtiEnv *jvmti, const void *compile_info) { jvmti_line_info_t *line_tab = NULL; + char ** line_file_names = NULL; jclass decl_class; char *class_sign = NULL; char *func_name = NULL; char *func_sign = NULL; - char *file_name= NULL; + char *file_name = NULL; char fn[PATH_MAX]; uint64_t addr = (uint64_t)(uintptr_t)code_addr; jvmtiError ret; int nr_lines = 0; /* in line_tab[] */ size_t len; + int output_debug_info = 0; ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method, &decl_class); @@ -158,6 +254,19 @@ compiled_method_load_cb(jvmtiEnv *jvmti, if (ret != JVMTI_ERROR_NONE) { warnx("jvmti: cannot get line table for method"); nr_lines = 0; + } else if (nr_lines > 0) { + line_file_names = malloc(sizeof(char*) * nr_lines); + if (!line_file_names) { + warnx("jvmti: cannot allocate space for line table method names"); + } else { + memset(line_file_names, 0, sizeof(char*) * nr_lines); + ret = fill_source_filenames(jvmti, nr_lines, line_tab, line_file_names); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: fill_source_filenames failed"); + } else { + output_debug_info = 1; + } + } } } @@ -181,33 +290,14 @@ compiled_method_load_cb(jvmtiEnv *jvmti, goto error; } - /* - * Assume path name is class hierarchy, this is a common practice with Java programs - */ - if (*class_sign == 'L') { - int j, i = 0; - char *p = strrchr(class_sign, '/'); - if (p) { - /* drop the 'L' prefix and copy up to the final '/' */ - for (i = 0; i < (p - class_sign); i++) - fn[i] = class_sign[i+1]; - } - /* - * append file name, we use loops and not string ops to avoid modifying - * class_sign which is used later for the symbol name - */ - for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++) - fn[i] = file_name[j]; - fn[i] = '\0'; - } else { - /* fallback case */ - strcpy(fn, file_name); - } + copy_class_filename(class_sign, file_name, fn, PATH_MAX); + /* * write source line info record if we have it */ - if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines)) - warnx("jvmti: write_debug_info() failed"); + if (output_debug_info) + if (jvmti_write_debug_info(jvmti_agent, addr, nr_lines, line_tab, (const char * const *) line_file_names)) + warnx("jvmti: write_debug_info() failed"); len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2; { @@ -223,6 +313,13 @@ error: (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign); (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name); free(line_tab); + while (line_file_names && (nr_lines > 0)) { + if (line_file_names[nr_lines - 1]) { + free(line_file_names[nr_lines - 1]); + } + nr_lines -= 1; + } + free(line_file_names); } static void JNICALL -- cgit v1.2.3 From 10b9baa701d5023897f70a4acb3bf0235da3dc4f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 28 Nov 2017 11:08:41 -0300 Subject: tools arch s390: Do not include header files from the kernel sources Long ago we decided to be verbotten including files in the kernel git sources from tools/ living source code, to avoid disturbing kernel development (and perf's and other tools/) when, say, a kernel hacker adds something, tests everything but tools/ and have tools/ build broken. This got broken recently by s/390, fix it by copying arch/s390/include/uapi/asm/perf_regs.h to tools/arch/s390/include/uapi/asm/, making this one be used by means of and updating tools/perf/check_headers.sh to make sure we are notified when the original changes, so that we can check if anything is needed on the tooling side. This would have been caught by the 'tarkpg' test entry in: $ make -C tools/perf build-test When run on a s/390 build system or container. Acked-by: Heiko Carstens Cc: Hendrik Brueckner Cc: Thomas Richter Cc: Martin Schwidefsky Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: f704ef44602f ("s390/perf: add support for perf_regs and libdw") Link: https://lkml.kernel.org/n/tip-n57139ic0v9uffx8wdqi3d8a@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/s390/include/uapi/asm/perf_regs.h | 44 ++++++++++++++++++++++++++++ tools/perf/arch/s390/include/perf_regs.h | 2 +- tools/perf/check-headers.sh | 1 + 3 files changed, 46 insertions(+), 1 deletion(-) create mode 100644 tools/arch/s390/include/uapi/asm/perf_regs.h (limited to 'tools') diff --git a/tools/arch/s390/include/uapi/asm/perf_regs.h b/tools/arch/s390/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..d17dd9e5d516 --- /dev/null +++ b/tools/arch/s390/include/uapi/asm/perf_regs.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_S390_PERF_REGS_H +#define _ASM_S390_PERF_REGS_H + +enum perf_event_s390_regs { + PERF_REG_S390_R0, + PERF_REG_S390_R1, + PERF_REG_S390_R2, + PERF_REG_S390_R3, + PERF_REG_S390_R4, + PERF_REG_S390_R5, + PERF_REG_S390_R6, + PERF_REG_S390_R7, + PERF_REG_S390_R8, + PERF_REG_S390_R9, + PERF_REG_S390_R10, + PERF_REG_S390_R11, + PERF_REG_S390_R12, + PERF_REG_S390_R13, + PERF_REG_S390_R14, + PERF_REG_S390_R15, + PERF_REG_S390_FP0, + PERF_REG_S390_FP1, + PERF_REG_S390_FP2, + PERF_REG_S390_FP3, + PERF_REG_S390_FP4, + PERF_REG_S390_FP5, + PERF_REG_S390_FP6, + PERF_REG_S390_FP7, + PERF_REG_S390_FP8, + PERF_REG_S390_FP9, + PERF_REG_S390_FP10, + PERF_REG_S390_FP11, + PERF_REG_S390_FP12, + PERF_REG_S390_FP13, + PERF_REG_S390_FP14, + PERF_REG_S390_FP15, + PERF_REG_S390_MASK, + PERF_REG_S390_PC, + + PERF_REG_S390_MAX +}; + +#endif /* _ASM_S390_PERF_REGS_H */ diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index d2df54a6bc5a..bcfbaed78cc2 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -3,7 +3,7 @@ #include #include -#include <../../../../arch/s390/include/uapi/asm/perf_regs.h> +#include void perf_regs_load(u64 *regs); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 6db9d809fe97..3e64f10b6d66 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -21,6 +21,7 @@ arch/x86/include/asm/cpufeatures.h arch/arm/include/uapi/asm/perf_regs.h arch/arm64/include/uapi/asm/perf_regs.h arch/powerpc/include/uapi/asm/perf_regs.h +arch/s390/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm_perf.h -- cgit v1.2.3 From c682ccc4962a8fab949e1f2d7325b3e825dbf6d1 Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Mon, 18 Dec 2017 14:09:57 +0100 Subject: bpf: fix broken BPF selftest build on s390 With 720f228e8d31 ("bpf: fix broken BPF selftest build") the inclusion of arch-specific header files changed. Including the asm/bpf_perf_event.h on s390, correctly includes the s390 specific header file. This header file tries then to include the s390 asm/ptrace.h and the build fails with: cc -Wall -O2 -I../../../include/uapi -I../../../lib -I../../../../include/generated -I../../../include test_verifier.c +/root/git/linux/tools/testing/selftests/bpf/libbpf.a /root/git/linux/tools/testing/selftests/bpf/cgroup_helpers.c -lcap -lelf -o +/root/git/linux/tools/testing/selftests/bpf/test_verifier In file included from ../../../include/uapi/asm/bpf_perf_event.h:4:0, from ../../../include/uapi/linux/bpf_perf_event.h:11, from test_verifier.c:29: ../../../include/uapi/../../arch/s390/include/uapi/asm/bpf_perf_event.h:7:9: error: unknown type name 'user_pt_regs' typedef user_pt_regs bpf_user_pt_regs_t; ^~~~~~~~~~~~ make: *** [../lib.mk:109: /root/git/linux/tools/testing/selftests/bpf/test_verifier] Error 1 This is caused by a recent update to the s390 asm/ptrace.h file that is not (yet) available in the local installation. That means, the s390 asm/ptrace.h must be included from the tools/arch/s390 directory. Because there is no proper framework to deal with asm specific includes in tools/, slightly modify the s390 asm/bpf_perf_event.h to include the local ptrace.h header file. See also discussion on https://marc.info/?l=linux-s390&m=151359424420691&w=2 Please note that this needs to be preserved until tools/ is able to correctly handle asm specific headers. References: https://marc.info/?l=linux-s390&m=151359424420691&w=2 Fixes: 720f228e8d31 ("bpf: fix broken BPF selftest build") Signed-off-by: Hendrik Brueckner Cc: Daniel Borkmann Cc: Hendrik Brueckner Cc: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/arch/s390/include/uapi/asm/bpf_perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h index cefe7c7cd4f6..0a8e37a519f2 100644 --- a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h +++ b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h @@ -2,7 +2,7 @@ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ -#include +#include "ptrace.h" typedef user_pt_regs bpf_user_pt_regs_t; -- cgit v1.2.3 From 544c4605acc5ae4afe7dd5914147947db182f2fb Mon Sep 17 00:00:00 2001 From: Juan Zea Date: Fri, 15 Dec 2017 10:21:20 +0100 Subject: usbip: fix usbip bind writing random string after command in match_busid usbip bind writes commands followed by random string when writing to match_busid attribute in sysfs, caused by using full variable size instead of string length. Signed-off-by: Juan Zea Acked-by: Shuah Khan Cc: stable Signed-off-by: Greg Kroah-Hartman --- tools/usb/usbip/src/utils.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c index 2b3d6d235015..3d7b42e77299 100644 --- a/tools/usb/usbip/src/utils.c +++ b/tools/usb/usbip/src/utils.c @@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add) char command[SYSFS_BUS_ID_SIZE + 4]; char match_busid_attr_path[SYSFS_PATH_MAX]; int rc; + int cmd_size; snprintf(match_busid_attr_path, sizeof(match_busid_attr_path), "%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME, @@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add) attr_name); if (add) - snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid); + cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", + busid); else - snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid); + cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", + busid); rc = write_sysfs_attribute(match_busid_attr_path, command, - sizeof(command)); + cmd_size); if (rc < 0) { dbg("failed to write match_busid: %s", strerror(errno)); return -1; -- cgit v1.2.3 From 19c832ed9b8f7b49fa5eeef06b4338af5fe5c1dc Mon Sep 17 00:00:00 2001 From: David Miller Date: Tue, 19 Dec 2017 15:22:03 -0500 Subject: bpf: Fix tools and testing build. I'm getting various build failures on sparc64. The key is usually that the userland tools get built 32-bit. 1) clock_gettime() is in librt, so that must be added to the link libraries. 2) "sizeof(x)" must be printed with "%Z" printf prefix. Signed-off-by: David S. Miller Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/Makefile | 2 +- tools/testing/selftests/bpf/test_progs.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 792af7c3b74f..05fc4e2e7b3a 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -11,7 +11,7 @@ ifneq ($(wildcard $(GENHDR)),) endif CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include -LDLIBS += -lcap -lelf +LDLIBS += -lcap -lelf -lrt TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 69427531408d..6761be18a91f 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -351,7 +351,7 @@ static void test_bpf_obj_id(void) info_len != sizeof(struct bpf_map_info) || strcmp((char *)map_infos[i].name, expected_map_name), "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", + "err %d errno %d type %d(%d) info_len %u(%Zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", err, errno, map_infos[i].type, BPF_MAP_TYPE_ARRAY, info_len, sizeof(struct bpf_map_info), @@ -395,7 +395,7 @@ static void test_bpf_obj_id(void) *(int *)prog_infos[i].map_ids != map_infos[i].id || strcmp((char *)prog_infos[i].name, expected_prog_name), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", + "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -463,7 +463,7 @@ static void test_bpf_obj_id(void) memcmp(&prog_info, &prog_infos[i], info_len) || *(int *)prog_info.map_ids != saved_map_id, "get-prog-info(next_id->fd)", - "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n", + "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n", err, errno, info_len, sizeof(struct bpf_prog_info), memcmp(&prog_info, &prog_infos[i], info_len), *(int *)prog_info.map_ids, saved_map_id); @@ -509,7 +509,7 @@ static void test_bpf_obj_id(void) memcmp(&map_info, &map_infos[i], info_len) || array_value != array_magic_value, "check get-map-info(next_id->fd)", - "err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n", + "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n", err, errno, info_len, sizeof(struct bpf_map_info), memcmp(&map_info, &map_infos[i], info_len), array_value, array_magic_value); -- cgit v1.2.3 From 1c8e77fb361a4a116a41ac1d9819eb79d068735d Mon Sep 17 00:00:00 2001 From: Naresh Kamboju Date: Wed, 20 Dec 2017 12:50:22 +0530 Subject: selftests: net: Adding config fragment CONFIG_NUMA=y kernel config fragement CONFIG_NUMA=y is need for reuseport_bpf_numa. Signed-off-by: Naresh Kamboju Signed-off-by: David S. Miller --- tools/testing/selftests/net/config | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index e57b4ac40e72..7177bea1fdfa 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -1,3 +1,4 @@ CONFIG_USER_NS=y CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m +CONFIG_NUMA=y -- cgit v1.2.3 From 2255f8d520b0a318fc6d387d0940854b2f522a7f Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 18 Dec 2017 20:12:01 -0800 Subject: selftests/bpf: add tests for recent bugfixes These tests should cover the following cases: - MOV with both zero-extended and sign-extended immediates - implicit truncation of register contents via ALU32/MOV32 - implicit 32-bit truncation of ALU32 output - oversized register source operand for ALU32 shift - right-shift of a number that could be positive or negative - map access where adding the operation size to the offset causes signed 32-bit overflow - direct stack access at a ~4GiB offset Also remove the F_LOAD_WITH_STRICT_ALIGNMENT flag from a bunch of tests that should fail independent of what flags userspace passes. Signed-off-by: Jann Horn Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_verifier.c | 549 +++++++++++++++++++++++++++- 1 file changed, 533 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index b03ecfd7185b..961c1426fbf2 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -606,7 +606,6 @@ static struct bpf_test tests[] = { }, .errstr = "misaligned stack access", .result = REJECT, - .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "invalid map_fd for function call", @@ -1797,7 +1796,6 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "misaligned stack access off (0x0; 0x0)+-8+2 size 8", - .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - bad alignment on reg", @@ -1810,7 +1808,6 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "misaligned stack access off (0x0; 0x0)+-10+8 size 8", - .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - out of bounds low", @@ -6324,7 +6321,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6348,7 +6345,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6374,7 +6371,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R8 invalid mem access 'inv'", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6399,7 +6396,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R8 invalid mem access 'inv'", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6447,7 +6444,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6518,7 +6515,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6569,7 +6566,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6596,7 +6593,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6622,7 +6619,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6651,7 +6648,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6681,7 +6678,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JA, 0, 0, -7), }, .fixup_map1 = { 4 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6709,8 +6706,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer comparison prohibited", - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, .result_unpriv = REJECT, }, @@ -6765,6 +6761,462 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result = REJECT, }, + { + "bounds check based on zero-extended MOV", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* r2 = 0x0000'0000'ffff'ffff */ + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff), + /* r2 = 0 */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32), + /* no-op */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + /* access at offset 0 */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT + }, + { + "bounds check based on sign-extended MOV. test1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* r2 = 0xffff'ffff'ffff'ffff */ + BPF_MOV64_IMM(BPF_REG_2, 0xffffffff), + /* r2 = 0xffff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32), + /* r0 = */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + /* access to OOB pointer */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "map_value pointer and 4294967295", + .result = REJECT + }, + { + "bounds check based on sign-extended MOV. test2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* r2 = 0xffff'ffff'ffff'ffff */ + BPF_MOV64_IMM(BPF_REG_2, 0xffffffff), + /* r2 = 0xfff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36), + /* r0 = */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + /* access to OOB pointer */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is outside of the array range", + .result = REJECT + }, + { + "bounds check based on reg_off + var_off + insn_off. test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 29) - 1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr = "value_size=8 off=1073741825", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "bounds check based on reg_off + var_off + insn_off. test2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 30) - 1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr = "value 1073741823", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "bounds check after truncation of non-boundary-crossing range", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_2, 1), + /* r2 = 0x10'0000'0000 */ + BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 36), + /* r1 = [0x10'0000'0000, 0x10'0000'00ff] */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + /* r1 = [0x10'7fff'ffff, 0x10'8000'00fe] */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + /* r1 = [0x00, 0xff] */ + BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 0x7fffffff), + /* r1 = 0 */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* no-op */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* access at offset 0 */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT + }, + { + "bounds check after truncation of boundary-crossing range (1)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0x1'0000'007f] */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0xffff'ffff] or + * [0x0000'0000, 0x0000'007f] + */ + BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0x00, 0xff] or + * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = 0 or + * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* no-op or OOB pointer computation */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + /* not actually fully unbounded, but the bound is very high */ + .errstr = "R0 unbounded memory access", + .result = REJECT + }, + { + "bounds check after truncation of boundary-crossing range (2)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0x1'0000'007f] */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0xffff'ffff] or + * [0x0000'0000, 0x0000'007f] + * difference to previous test: truncation via MOV32 + * instead of ALU32. + */ + BPF_MOV32_REG(BPF_REG_1, BPF_REG_1), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0x00, 0xff] or + * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = 0 or + * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* no-op or OOB pointer computation */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + /* not actually fully unbounded, but the bound is very high */ + .errstr = "R0 unbounded memory access", + .result = REJECT + }, + { + "bounds check after wrapping 32-bit addition", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + /* r1 = 0x7fff'ffff */ + BPF_MOV64_IMM(BPF_REG_1, 0x7fffffff), + /* r1 = 0xffff'fffe */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + /* r1 = 0 */ + BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 2), + /* no-op */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* access at offset 0 */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT + }, + { + "bounds check after shift with oversized count operand", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_2, 32), + BPF_MOV64_IMM(BPF_REG_1, 1), + /* r1 = (u32)1 << (u32)32 = ? */ + BPF_ALU32_REG(BPF_LSH, BPF_REG_1, BPF_REG_2), + /* r1 = [0x0000, 0xffff] */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xffff), + /* computes unknown pointer, potentially OOB */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 max value is outside of the array range", + .result = REJECT + }, + { + "bounds check after right shift of maybe-negative number", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + /* r1 = [-0x01, 0xfe] */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1), + /* r1 = 0 or 0xff'ffff'ffff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* r1 = 0 or 0xffff'ffff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* computes unknown pointer, potentially OOB */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 unbounded memory access", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7ffffffe), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "map_value pointer and 2147483646", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "pointer offset 1073741822", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "pointer offset -1073741822", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 1000000), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_1, 1000000), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "map_value pointer and 1000000000000", + .result = REJECT + }, + { + "pointer/scalar confusion in state equality check (way 1)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_A(1), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr as return value" + }, + { + "pointer/scalar confusion in state equality check (way 2)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + BPF_JMP_A(1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr as return value" + }, { "variable-offset ctx access", .insns = { @@ -6806,6 +7258,71 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_LWT_IN, }, + { + "indirect variable-offset stack access", + .insns = { + /* Fill the top 8 bytes of the stack */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8), + /* add it to fp. We now have either fp-4 or fp-8, but + * we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* dereference it indirectly */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 5 }, + .errstr = "variable stack read R2", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "direct stack access with 32-bit wraparound. test1", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN() + }, + .errstr = "fp pointer and 2147483647", + .result = REJECT + }, + { + "direct stack access with 32-bit wraparound. test2", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN() + }, + .errstr = "fp pointer and 1073741823", + .result = REJECT + }, + { + "direct stack access with 32-bit wraparound. test3", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN() + }, + .errstr = "fp pointer offset 1073741822", + .result = REJECT + }, { "liveness pruning and write screening", .insns = { -- cgit v1.2.3 From 82abbf8d2fc46d79611ab58daa7c608df14bb3ee Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 18 Dec 2017 20:15:20 -0800 Subject: bpf: do not allow root to mangle valid pointers Do not allow root to convert valid pointers into unknown scalars. In particular disallow: ptr &= reg ptr <<= reg ptr += ptr and explicitly allow: ptr -= ptr since pkt_end - pkt == length 1. This minimizes amount of address leaks root can do. In the future may need to further tighten the leaks with kptr_restrict. 2. If program has such pointer math it's likely a user mistake and when verifier complains about it right away instead of many instructions later on invalid memory access it's easier for users to fix their progs. 3. when register holding a pointer cannot change to scalar it allows JITs to optimize better. Like 32-bit archs could use single register for pointers instead of a pair required to hold 64-bit scalars. 4. reduces architecture dependent behavior. Since code: r1 = r10; r1 &= 0xff; if (r1 ...) will behave differently arm64 vs x64 and offloaded vs native. A significant chunk of ptr mangling was allowed by commit f1174f77b50c ("bpf/verifier: rework value tracking") yet some of it was allowed even earlier. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/verifier.c | 102 ++++++++++------------------ tools/testing/selftests/bpf/test_verifier.c | 56 +++++++-------- 2 files changed, 63 insertions(+), 95 deletions(-) (limited to 'tools') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 86dfe6b5c243..04b24876cd23 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1890,29 +1890,25 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ - if (!env->allow_ptr_leaks) - verbose(env, - "R%d 32-bit pointer arithmetic prohibited\n", - dst); + verbose(env, + "R%d 32-bit pointer arithmetic prohibited\n", + dst); return -EACCES; } if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", - dst); + verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + dst); return -EACCES; } if (ptr_reg->type == CONST_PTR_TO_MAP) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", - dst); + verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + dst); return -EACCES; } if (ptr_reg->type == PTR_TO_PACKET_END) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", - dst); + verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + dst); return -EACCES; } @@ -1979,9 +1975,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case BPF_SUB: if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ - if (!env->allow_ptr_leaks) - verbose(env, "R%d tried to subtract pointer from scalar\n", - dst); + verbose(env, "R%d tried to subtract pointer from scalar\n", + dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to @@ -1989,9 +1984,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d subtraction from stack pointer prohibited\n", - dst); + verbose(env, "R%d subtraction from stack pointer prohibited\n", + dst); return -EACCES; } if (known && (ptr_reg->off - smin_val == @@ -2040,19 +2034,14 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case BPF_AND: case BPF_OR: case BPF_XOR: - /* bitwise ops on pointers are troublesome, prohibit for now. - * (However, in principle we could allow some cases, e.g. - * ptr &= ~3 which would reduce min_value by 3.) - */ - if (!env->allow_ptr_leaks) - verbose(env, "R%d bitwise operator %s on pointer prohibited\n", - dst, bpf_alu_string[opcode >> 4]); + /* bitwise ops on pointers are troublesome, prohibit. */ + verbose(env, "R%d bitwise operator %s on pointer prohibited\n", + dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", - dst, bpf_alu_string[opcode >> 4]); + verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", + dst, bpf_alu_string[opcode >> 4]); return -EACCES; } @@ -2308,7 +2297,6 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); - int rc; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; @@ -2319,43 +2307,29 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields - * an arbitrary scalar. + * an arbitrary scalar. Disallow all math except + * pointer subtraction */ - if (!env->allow_ptr_leaks) { - verbose(env, "R%d pointer %s pointer prohibited\n", - insn->dst_reg, - bpf_alu_string[opcode >> 4]); - return -EACCES; + if (opcode == BPF_SUB){ + mark_reg_unknown(env, regs, insn->dst_reg); + return 0; } - mark_reg_unknown(env, regs, insn->dst_reg); - return 0; + verbose(env, "R%d pointer %s pointer prohibited\n", + insn->dst_reg, + bpf_alu_string[opcode >> 4]); + return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ - rc = adjust_ptr_min_max_vals(env, insn, - src_reg, dst_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* scalar += unknown scalar */ - __mark_reg_unknown(&off_reg); - return adjust_scalar_min_max_vals( - env, insn, - dst_reg, off_reg); - } - return rc; + return adjust_ptr_min_max_vals(env, insn, + src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ - rc = adjust_ptr_min_max_vals(env, insn, - dst_reg, src_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* unknown scalar += scalar */ - __mark_reg_unknown(dst_reg); - return adjust_scalar_min_max_vals( - env, insn, dst_reg, *src_reg); - } - return rc; + return adjust_ptr_min_max_vals(env, insn, + dst_reg, src_reg); } } else { /* Pretend the src is a reg with a known value, since we only @@ -2364,17 +2338,9 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; - if (ptr_reg) { /* pointer += K */ - rc = adjust_ptr_min_max_vals(env, insn, - ptr_reg, src_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* unknown scalar += K */ - __mark_reg_unknown(dst_reg); - return adjust_scalar_min_max_vals( - env, insn, dst_reg, off_reg); - } - return rc; - } + if (ptr_reg) /* pointer += K */ + return adjust_ptr_min_max_vals(env, insn, + ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 961c1426fbf2..b51017404c62 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -422,9 +422,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R1 subtraction from stack pointer", - .result_unpriv = REJECT, - .errstr = "R1 invalid mem access", + .errstr = "R1 subtraction from stack pointer", .result = REJECT, }, { @@ -1859,9 +1857,8 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R1 pointer += pointer", + .result = REJECT, + .errstr = "R1 pointer += pointer", }, { "unpriv: neg pointer", @@ -2589,7 +2586,8 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct __sk_buff, data)), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, len)), BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 49), BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 49), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2), @@ -2896,7 +2894,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "invalid access to packet", + .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -3882,9 +3880,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3, 11 }, - .errstr_unpriv = "R0 pointer += pointer", - .errstr = "R0 invalid mem access 'inv'", - .result_unpriv = REJECT, + .errstr = "R0 pointer += pointer", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3925,7 +3921,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 invalid mem access", + .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -3946,7 +3942,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 invalid mem access", + .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -3967,7 +3963,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 invalid mem access", + .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -5192,10 +5188,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 bitwise operator &= on pointer", - .errstr = "invalid mem access 'inv'", + .errstr = "R0 bitwise operator &= on pointer", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value illegal alu op, 2", @@ -5211,10 +5205,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 32-bit pointer arithmetic prohibited", - .errstr = "invalid mem access 'inv'", + .errstr = "R0 32-bit pointer arithmetic prohibited", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value illegal alu op, 3", @@ -5230,10 +5222,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic with /= operator", - .errstr = "invalid mem access 'inv'", + .errstr = "R0 pointer arithmetic with /= operator", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value illegal alu op, 4", @@ -6016,8 +6006,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map_in_map = { 3 }, - .errstr = "R1 type=inv expected=map_ptr", - .errstr_unpriv = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", + .errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", .result = REJECT, }, { @@ -7644,6 +7633,19 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, + { + "pkt_end - pkt_start is allowed", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, { "XDP pkt read, pkt_end mangling, bad access 1", .insns = { @@ -7659,7 +7661,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R1 offset is outside of the packet", + .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", .result = REJECT, .prog_type = BPF_PROG_TYPE_XDP, }, @@ -7678,7 +7680,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R1 offset is outside of the packet", + .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", .result = REJECT, .prog_type = BPF_PROG_TYPE_XDP, }, -- cgit v1.2.3 From aa12f594f97efe50223611dbd13ecca4e8dafee6 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Thu, 21 Dec 2017 13:03:27 +0100 Subject: tools/kvm_stat: sort '-f help' output Sort the fields returned by specifying '-f help' on the command line. While at it, simplify the code a bit, indent the output and eliminate an extra blank line at the beginning. Signed-off-by: Stefan Raspl Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 566a70ddd005..a5684d0968b4 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1579,17 +1579,13 @@ def main(): stats = Stats(options) - if options.fields == "help": + if options.fields == 'help': stats.fields_filter = None - event_list = "\n" - s = stats.get() - for key in s.keys(): - if key.find('(') != -1: - key = key[0:key.find('(')] - if event_list.find('\n' + key + '\n') == -1: - event_list += key + '\n' - sys.stdout.write(event_list) - return "" + event_list = [] + for key in stats.get().keys(): + event_list.append(key.split('(', 1)[0]) + sys.stdout.write(' ' + '\n '.join(sorted(set(event_list))) + '\n') + sys.exit(0) if options.log: log(stats) -- cgit v1.2.3 From cd95a89282ef61458c3758d70ebfbd91f303033f Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Thu, 21 Dec 2017 08:52:50 -0800 Subject: selftests/bpf: fix Makefile for passing LLC to the command line Makefile has a LLC variable that is initialised to "llc", but can theoretically be overridden from the command line ("make LLC=llc-6.0"). However, this fails because for LLVM probe check, "llc" is called directly. Use the $(LLC) variable instead to fix this. Fixes: 22c8852624fc ("bpf: improve selftests and add tests for meta pointer") Signed-off-by: Quentin Monnet Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 05fc4e2e7b3a..9316e648a880 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -39,7 +39,7 @@ $(BPFOBJ): force CLANG ?= clang LLC ?= llc -PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) +PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) # Let newer LLVM versions transparently probe the kernel for availability # of full BPF instruction set. -- cgit v1.2.3 From a4828f81037f491b2cc986595e3a969a6eeb2fb5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Dec 2017 12:27:31 +0100 Subject: x86/ldt: Prevent LDT inheritance on exec The LDT is inherited across fork() or exec(), but that makes no sense at all because exec() is supposed to start the process clean. The reason why this happens is that init_new_context_ldt() is called from init_new_context() which obviously needs to be called for both fork() and exec(). It would be surprising if anything relies on that behaviour, so it seems to be safe to remove that misfeature. Split the context initialization into two parts. Clear the LDT pointer and initialize the mutex from the general context init and move the LDT duplication to arch_dup_mmap() which is only called on fork(). Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra Cc: Andy Lutomirski Cc: Andy Lutomirsky Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Will Deacon Cc: aliguori@amazon.com Cc: dan.j.williams@intel.com Cc: hughd@google.com Cc: keescook@google.com Cc: kirill.shutemov@linux.intel.com Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 21 ++++++++++++++------- arch/x86/kernel/ldt.c | 18 +++++------------- tools/testing/selftests/x86/ldt_gdt.c | 9 +++------ 3 files changed, 22 insertions(+), 26 deletions(-) (limited to 'tools') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 4fdbe5efe535..5e25423bf9bb 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -57,11 +57,17 @@ struct ldt_struct { /* * Used for LDT copy/destruction. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm); +static inline void init_new_context_ldt(struct mm_struct *mm) +{ + mm->context.ldt = NULL; + init_rwsem(&mm->context.ldt_usr_sem); +} +int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ -static inline int init_new_context_ldt(struct task_struct *tsk, - struct mm_struct *mm) +static inline void init_new_context_ldt(struct mm_struct *mm) { } +static inline int ldt_dup_context(struct mm_struct *oldmm, + struct mm_struct *mm) { return 0; } @@ -137,15 +143,16 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and always allocated */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } - #endif - return init_new_context_ldt(tsk, mm); +#endif + init_new_context_ldt(mm); + return 0; } static inline void destroy_context(struct mm_struct *mm) { @@ -181,7 +188,7 @@ do { \ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { paravirt_arch_dup_mmap(oldmm, mm); - return 0; + return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 1600aebc1ec7..a6b5d62f45a7 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -131,28 +131,20 @@ static void free_ldt_struct(struct ldt_struct *ldt) } /* - * we do not have to muck with descriptors here, that is - * done in switch_mm() as needed. + * Called on fork from arch_dup_mmap(). Just copy the current LDT state, + * the new task is not running, so nothing can be installed. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) +int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm) { struct ldt_struct *new_ldt; - struct mm_struct *old_mm; int retval = 0; - init_rwsem(&mm->context.ldt_usr_sem); - - old_mm = current->mm; - if (!old_mm) { - mm->context.ldt = NULL; + if (!old_mm) return 0; - } mutex_lock(&old_mm->context.lock); - if (!old_mm->context.ldt) { - mm->context.ldt = NULL; + if (!old_mm->context.ldt) goto out_unlock; - } new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 66e5ce5b91f0..0304ffb714f2 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -627,13 +627,10 @@ static void do_multicpu_tests(void) static int finish_exec_test(void) { /* - * In a sensible world, this would be check_invalid_segment(0, 1); - * For better or for worse, though, the LDT is inherited across exec. - * We can probably change this safely, but for now we test it. + * Older kernel versions did inherit the LDT on exec() which is + * wrong because exec() starts from a clean state. */ - check_valid_segment(0, 1, - AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB, - 42, true); + check_invalid_segment(0, 1); return nerrs ? 1 : 0; } -- cgit v1.2.3 From b3b1b6532890c70987821946f90c22b8021aaaf8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 22 Dec 2017 11:36:05 -0800 Subject: tools: bpftool: maps: close json array on error paths of show We can't return from the middle of do_show(), because json_array will not be closed. Break out of the loop. Note that the error handling after the loop depends on errno, so no need to set err. Fixes: 831a0aafe5c3 ("tools: bpftool: add JSON output for `bpftool map *` commands") Signed-off-by: Jakub Kicinski Acked-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/map.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e2450c8e88e6..8368b7ea31b5 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -523,21 +523,21 @@ static int do_show(int argc, char **argv) break; p_err("can't get next map: %s%s", strerror(errno), errno == EINVAL ? " -- kernel too old?" : ""); - return -1; + break; } fd = bpf_map_get_fd_by_id(id); if (fd < 0) { p_err("can't get map by id (%u): %s", id, strerror(errno)); - return -1; + break; } err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); - return -1; + break; } if (json_output) -- cgit v1.2.3 From 8207c6dd4746c345b689684c4cd0ce00a18c7ef2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 22 Dec 2017 11:36:06 -0800 Subject: tools: bpftool: protect against races with disappearing objects On program/map show we may get an ID of an object from GETNEXT, but the object may disappear before we call GET_FD_BY_ID. If that happens, ignore the object and continue. Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool") Signed-off-by: Jakub Kicinski Acked-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/map.c | 2 ++ tools/bpf/bpftool/prog.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'tools') diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 8368b7ea31b5..a8c3a33dd185 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -528,6 +528,8 @@ static int do_show(int argc, char **argv) fd = bpf_map_get_fd_by_id(id); if (fd < 0) { + if (errno == ENOENT) + continue; p_err("can't get map by id (%u): %s", id, strerror(errno)); break; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index ad619b96c276..dded77345bfb 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -382,6 +382,8 @@ static int do_show(int argc, char **argv) fd = bpf_prog_get_fd_by_id(id); if (fd < 0) { + if (errno == ENOENT) + continue; p_err("can't get prog by id (%u): %s", id, strerror(errno)); err = -1; -- cgit v1.2.3 From 9f5cb6b32d9e0a3a7453222baaf15664d92adbf2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 15 Dec 2017 20:35:11 +0100 Subject: x86/ldt: Make the LDT mapping RO Now that the LDT mapping is in a known area when PAGE_TABLE_ISOLATION is enabled its a primary target for attacks, if a user space interface fails to validate a write address correctly. That can never happen, right? The SDM states: If the segment descriptors in the GDT or an LDT are placed in ROM, the processor can enter an indefinite loop if software or the processor attempts to update (write to) the ROM-based segment descriptors. To prevent this problem, set the accessed bits for all segment descriptors placed in a ROM. Also, remove operating-system or executive code that attempts to modify segment descriptors located in ROM. So its a valid approach to set the ACCESS bit when setting up the LDT entry and to map the table RO. Fixup the selftest so it can handle that new mode. Remove the manual ACCESS bit setter in set_tls_desc() as this is now pointless. Folded the patch from Peter Ziljstra. Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/include/asm/desc.h | 2 ++ arch/x86/kernel/ldt.c | 7 ++++++- arch/x86/kernel/tls.c | 11 ++--------- tools/testing/selftests/x86/ldt_gdt.c | 3 +-- 4 files changed, 11 insertions(+), 12 deletions(-) (limited to 'tools') diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index bc359dd2f7f6..85e23bb7b34e 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -21,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; + /* Set the ACCESS bit so it can be mapped RO */ + desc->type |= 1; desc->s = 1; desc->dpl = 0x3; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 9629c5d8267a..579cc4a66fdf 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -158,7 +158,12 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) ptep = get_locked_pte(mm, va, &ptl); if (!ptep) return -ENOMEM; - pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL & ~_PAGE_GLOBAL)); + /* + * Map it RO so the easy to find address is not a primary + * target via some kernel interface which misses a + * permission check. + */ + pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL)); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 9a9c9b076955..a5b802a12212 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info) || LDT_zero(info)) { + if (LDT_empty(info) || LDT_zero(info)) memset(desc, 0, sizeof(*desc)); - } else { + else fill_ldt(desc, info); - - /* - * Always set the accessed bit so that the CPU - * doesn't try to write to the (read-only) GDT. - */ - desc->type |= 1; - } ++info; ++desc; } diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 0304ffb714f2..1aef72df20a1 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -122,8 +122,7 @@ static void check_valid_segment(uint16_t index, int ldt, * NB: Different Linux versions do different things with the * accessed bit in set_thread_area(). */ - if (ar != expected_ar && - (ldt || ar != (expected_ar | AR_ACCESSED))) { + if (ar != expected_ar && ar != (expected_ar | AR_ACCESSED)) { printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n", (ldt ? "LDT" : "GDT"), index, ar, expected_ar); nerrs++; -- cgit v1.2.3 From e7e83dd3ff1dd2f9e60213f6eedc7e5b08192062 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Tue, 26 Dec 2017 15:27:20 -0600 Subject: objtool: Fix Clang enum conversion warning Fix the following Clang enum conversion warning: arch/x86/decode.c:141:20: error: implicit conversion from enumeration type 'enum op_src_type' to different enumeration type 'enum op_dest_type' [-Werror,-Wenum-conversion] op->dest.type = OP_SRC_REG; ~ ^~~~~~~~~~ It just happened to work before because OP_SRC_REG and OP_DEST_REG have the same value. Signed-off-by: Lukas Bulwahn Signed-off-by: Josh Poimboeuf Reviewed-by: Nicholas Mc Guire Reviewed-by: Nick Desaulniers Cc: Jiri Slaby Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: baa41469a7b9 ("objtool: Implement stack validation 2.0") Link: http://lkml.kernel.org/r/b4156c5738bae781c392e7a3691aed4514ebbdf2.1514323568.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/arch/x86/decode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 8acfc47af70e..540a209b78ab 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -138,7 +138,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, *type = INSN_STACK; op->src.type = OP_SRC_ADD; op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; - op->dest.type = OP_SRC_REG; + op->dest.type = OP_DEST_REG; op->dest.reg = CFI_SP; } break; -- cgit v1.2.3 From d89e426499cf36b96161bd32970d6783f1fbcb0e Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Sat, 30 Dec 2017 14:43:31 -0600 Subject: objtool: Fix seg fault caused by missing parameter Fix a seg fault when no parameter is provided to 'objtool orc'. Signed-off-by: Simon Ser Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/9172803ec7ebb72535bcd0b7f966ae96d515968e.1514666459.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/builtin-orc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c index 4c6b5c9ef073..91e8e19ff5e0 100644 --- a/tools/objtool/builtin-orc.c +++ b/tools/objtool/builtin-orc.c @@ -44,6 +44,9 @@ int cmd_orc(int argc, const char **argv) const char *objname; argc--; argv++; + if (argc <= 0) + usage_with_options(orc_usage, check_options); + if (!strncmp(argv[0], "gen", 3)) { argc = parse_options(argc, argv, check_options, orc_usage, 0); if (argc != 1) @@ -52,7 +55,6 @@ int cmd_orc(int argc, const char **argv) objname = argv[0]; return check(objname, no_fp, no_unreachable, true); - } if (!strcmp(argv[0], "dump")) { -- cgit v1.2.3 From ce90aaf5cde4ce057b297bb6c955caf16ef00ee6 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Sat, 30 Dec 2017 14:43:32 -0600 Subject: objtool: Fix seg fault with clang-compiled objects Fix a seg fault which happens when an input file provided to 'objtool orc generate' doesn't have a '.shstrtab' section (for instance, object files produced by clang don't have this section). Signed-off-by: Simon Ser Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/c0f2231683e9bed40fac1f13ce2c33b8389854bc.1514666459.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/orc_gen.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index e5ca31429c9b..e61fe703197b 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -165,6 +165,8 @@ int create_orc_sections(struct objtool_file *file) /* create .orc_unwind_ip and .rela.orc_unwind_ip sections */ sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx); + if (!sec) + return -1; ip_relasec = elf_create_rela_section(file->elf, sec); if (!ip_relasec) -- cgit v1.2.3 From e8d5134833006a46fcbefc5f4a84d0b62bd520e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 29 Dec 2017 08:54:05 +0100 Subject: memremap: change devm_memremap_pages interface to use struct dev_pagemap This new interface is similar to how struct device (and many others) work. The caller initializes a 'struct dev_pagemap' as required and calls 'devm_memremap_pages'. This allows the pagemap structure to be embedded in another structure and thus container_of can be used. In this way application specific members can be stored in a containing struct. This will be used by the P2P infrastructure and HMM could probably be cleaned up to use it as well (instead of having it's own, similar 'hmm_devmem_pages_create' function). Signed-off-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- drivers/dax/pmem.c | 20 ++++++++------- drivers/nvdimm/nd.h | 9 +++---- drivers/nvdimm/pfn_devs.c | 27 ++++++++++++--------- drivers/nvdimm/pmem.c | 37 +++++++++++++++------------- drivers/nvdimm/pmem.h | 1 + include/linux/memremap.h | 6 ++--- kernel/memremap.c | 51 ++++++++++++++++----------------------- tools/testing/nvdimm/test/iomap.c | 7 +++--- 8 files changed, 77 insertions(+), 81 deletions(-) (limited to 'tools') diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index 8d8c852ba8f2..31b6ecce4c64 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -21,6 +21,7 @@ struct dax_pmem { struct device *dev; struct percpu_ref ref; + struct dev_pagemap pgmap; struct completion cmp; }; @@ -69,20 +70,23 @@ static int dax_pmem_probe(struct device *dev) struct nd_namespace_common *ndns; struct nd_dax *nd_dax = to_nd_dax(dev); struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; - struct vmem_altmap __altmap, *altmap = NULL; ndns = nvdimm_namespace_common_probe(dev); if (IS_ERR(ndns)) return PTR_ERR(ndns); nsio = to_nd_namespace_io(&ndns->dev); + dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL); + if (!dax_pmem) + return -ENOMEM; + /* parse the 'pfn' info block via ->rw_bytes */ rc = devm_nsio_enable(dev, nsio); if (rc) return rc; - altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap); - if (IS_ERR(altmap)) - return PTR_ERR(altmap); + rc = nvdimm_setup_pfn(nd_pfn, &dax_pmem->pgmap); + if (rc) + return rc; devm_nsio_disable(dev, nsio); pfn_sb = nd_pfn->pfn_sb; @@ -94,10 +98,6 @@ static int dax_pmem_probe(struct device *dev) return -EBUSY; } - dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL); - if (!dax_pmem) - return -ENOMEM; - dax_pmem->dev = dev; init_completion(&dax_pmem->cmp); rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0, @@ -110,7 +110,8 @@ static int dax_pmem_probe(struct device *dev) if (rc) return rc; - addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap); + dax_pmem->pgmap.ref = &dax_pmem->ref; + addr = devm_memremap_pages(dev, &dax_pmem->pgmap); if (IS_ERR(addr)) return PTR_ERR(addr); @@ -120,6 +121,7 @@ static int dax_pmem_probe(struct device *dev) return rc; /* adjust the dax_region resource to the start of data */ + memcpy(&res, &dax_pmem->pgmap.res, sizeof(res)); res.start += le64_to_cpu(pfn_sb->dataoff); rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", ®ion_id, &id); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index e958f3724c41..8d6375ee0fda 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -368,15 +368,14 @@ unsigned int pmem_sector_size(struct nd_namespace_common *ndns); void nvdimm_badblocks_populate(struct nd_region *nd_region, struct badblocks *bb, const struct resource *res); #if IS_ENABLED(CONFIG_ND_CLAIM) -struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn, - struct resource *res, struct vmem_altmap *altmap); +int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap); int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio); void devm_nsio_disable(struct device *dev, struct nd_namespace_io *nsio); #else -static inline struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn, - struct resource *res, struct vmem_altmap *altmap) +static inline int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, + struct dev_pagemap *pgmap) { - return ERR_PTR(-ENXIO); + return -ENXIO; } static inline int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio) diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 2adada1a5855..f5c4e8c6e29d 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -542,9 +542,10 @@ static unsigned long init_altmap_reserve(resource_size_t base) return reserve; } -static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn, - struct resource *res, struct vmem_altmap *altmap) +static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap) { + struct resource *res = &pgmap->res; + struct vmem_altmap *altmap = &pgmap->altmap; struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; u64 offset = le64_to_cpu(pfn_sb->dataoff); u32 start_pad = __le32_to_cpu(pfn_sb->start_pad); @@ -561,11 +562,13 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn, res->start += start_pad; res->end -= end_trunc; + pgmap->type = MEMORY_DEVICE_HOST; + if (nd_pfn->mode == PFN_MODE_RAM) { if (offset < SZ_8K) - return ERR_PTR(-EINVAL); + return -EINVAL; nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns); - altmap = NULL; + pgmap->altmap_valid = false; } else if (nd_pfn->mode == PFN_MODE_PMEM) { nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res) - offset) / PAGE_SIZE); @@ -577,10 +580,11 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn, memcpy(altmap, &__altmap, sizeof(*altmap)); altmap->free = PHYS_PFN(offset - SZ_8K); altmap->alloc = 0; + pgmap->altmap_valid = true; } else - return ERR_PTR(-ENXIO); + return -ENXIO; - return altmap; + return 0; } static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys) @@ -708,19 +712,18 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) * Determine the effective resource range and vmem_altmap from an nd_pfn * instance. */ -struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn, - struct resource *res, struct vmem_altmap *altmap) +int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap) { int rc; if (!nd_pfn->uuid || !nd_pfn->ndns) - return ERR_PTR(-ENODEV); + return -ENODEV; rc = nd_pfn_init(nd_pfn); if (rc) - return ERR_PTR(rc); + return rc; - /* we need a valid pfn_sb before we can init a vmem_altmap */ - return __nvdimm_setup_pfn(nd_pfn, res, altmap); + /* we need a valid pfn_sb before we can init a dev_pagemap */ + return __nvdimm_setup_pfn(nd_pfn, pgmap); } EXPORT_SYMBOL_GPL(nvdimm_setup_pfn); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7fbc5c5dc8e1..cf074b1ce219 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -298,34 +298,34 @@ static int pmem_attach_disk(struct device *dev, { struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); struct nd_region *nd_region = to_nd_region(dev->parent); - struct vmem_altmap __altmap, *altmap = NULL; int nid = dev_to_node(dev), fua, wbc; struct resource *res = &nsio->res; + struct resource bb_res; struct nd_pfn *nd_pfn = NULL; struct dax_device *dax_dev; struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; - struct resource pfn_res; struct request_queue *q; struct device *gendev; struct gendisk *disk; void *addr; + int rc; + + pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); + if (!pmem) + return -ENOMEM; /* while nsio_rw_bytes is active, parse a pfn info block if present */ if (is_nd_pfn(dev)) { nd_pfn = to_nd_pfn(dev); - altmap = nvdimm_setup_pfn(nd_pfn, &pfn_res, &__altmap); - if (IS_ERR(altmap)) - return PTR_ERR(altmap); + rc = nvdimm_setup_pfn(nd_pfn, &pmem->pgmap); + if (rc) + return rc; } /* we're attaching a block device, disable raw namespace access */ devm_nsio_disable(dev, nsio); - pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); - if (!pmem) - return -ENOMEM; - dev_set_drvdata(dev, pmem); pmem->phys_addr = res->start; pmem->size = resource_size(res); @@ -350,19 +350,22 @@ static int pmem_attach_disk(struct device *dev, return -ENOMEM; pmem->pfn_flags = PFN_DEV; + pmem->pgmap.ref = &q->q_usage_counter; if (is_nd_pfn(dev)) { - addr = devm_memremap_pages(dev, &pfn_res, &q->q_usage_counter, - altmap); + addr = devm_memremap_pages(dev, &pmem->pgmap); pfn_sb = nd_pfn->pfn_sb; pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); - pmem->pfn_pad = resource_size(res) - resource_size(&pfn_res); + pmem->pfn_pad = resource_size(res) - + resource_size(&pmem->pgmap.res); pmem->pfn_flags |= PFN_MAP; - res = &pfn_res; /* for badblocks populate */ - res->start += pmem->data_offset; + memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res)); + bb_res.start += pmem->data_offset; } else if (pmem_should_map_pages(dev)) { - addr = devm_memremap_pages(dev, &nsio->res, - &q->q_usage_counter, NULL); + memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res)); + pmem->pgmap.altmap_valid = false; + addr = devm_memremap_pages(dev, &pmem->pgmap); pmem->pfn_flags |= PFN_MAP; + memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res)); } else addr = devm_memremap(dev, pmem->phys_addr, pmem->size, ARCH_MEMREMAP_PMEM); @@ -401,7 +404,7 @@ static int pmem_attach_disk(struct device *dev, / 512); if (devm_init_badblocks(dev, &pmem->bb)) return -ENOMEM; - nvdimm_badblocks_populate(nd_region, &pmem->bb, res); + nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res); disk->bb = &pmem->bb; dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops); diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h index 6a3cd2a10db6..a64ebc78b5df 100644 --- a/drivers/nvdimm/pmem.h +++ b/drivers/nvdimm/pmem.h @@ -22,6 +22,7 @@ struct pmem_device { struct badblocks bb; struct dax_device *dax_dev; struct gendisk *disk; + struct dev_pagemap pgmap; }; long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1cb5f39d25c1..7b4899c06f49 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -123,8 +123,7 @@ struct dev_pagemap { }; #ifdef CONFIG_ZONE_DEVICE -void *devm_memremap_pages(struct device *dev, struct resource *res, - struct percpu_ref *ref, struct vmem_altmap *altmap); +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); @@ -134,8 +133,7 @@ void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); static inline bool is_zone_device_page(const struct page *page); #else static inline void *devm_memremap_pages(struct device *dev, - struct resource *res, struct percpu_ref *ref, - struct vmem_altmap *altmap) + struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without diff --git a/kernel/memremap.c b/kernel/memremap.c index 9207c44cce20..a9a948cd3d7f 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -275,9 +275,10 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap) #define for_each_device_pfn(pfn, map) \ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++) -static void devm_memremap_pages_release(struct device *dev, void *data) +static void devm_memremap_pages_release(void *data) { struct dev_pagemap *pgmap = data; + struct device *dev = pgmap->dev; struct resource *res = &pgmap->res; resource_size_t align_start, align_size; unsigned long pfn; @@ -316,29 +317,34 @@ static struct dev_pagemap *find_dev_pagemap(resource_size_t phys) /** * devm_memremap_pages - remap and provide memmap backing for the given resource * @dev: hosting device for @res - * @res: "host memory" address range - * @ref: a live per-cpu reference count - * @altmap: optional descriptor for allocating the memmap from @res + * @pgmap: pointer to a struct dev_pgmap * * Notes: - * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time - * (or devm release event). The expected order of events is that @ref has + * 1/ At a minimum the res, ref and type members of @pgmap must be initialized + * by the caller before passing it to this function + * + * 2/ The altmap field may optionally be initialized, in which case altmap_valid + * must be set to true + * + * 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages() + * time (or devm release event). The expected order of events is that ref has * been through percpu_ref_kill() before devm_memremap_pages_release(). The * wait for the completion of all references being dropped and * percpu_ref_exit() must occur after devm_memremap_pages_release(). * - * 2/ @res is expected to be a host memory range that could feasibly be + * 4/ res is expected to be a host memory range that could feasibly be * treated as a "System RAM" range, i.e. not a device mmio range, but * this is not enforced. */ -void *devm_memremap_pages(struct device *dev, struct resource *res, - struct percpu_ref *ref, struct vmem_altmap *altmap) +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { resource_size_t align_start, align_size, align_end; + struct vmem_altmap *altmap = pgmap->altmap_valid ? + &pgmap->altmap : NULL; unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; - struct dev_pagemap *pgmap; int error, nid, is_ram, i = 0; + struct resource *res = &pgmap->res; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -355,27 +361,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (is_ram == REGION_INTERSECTS) return __va(res->start); - if (!ref) + if (!pgmap->ref) return ERR_PTR(-EINVAL); - pgmap = devres_alloc_node(devm_memremap_pages_release, - sizeof(*pgmap), GFP_KERNEL, dev_to_node(dev)); - if (!pgmap) - return ERR_PTR(-ENOMEM); - - memcpy(&pgmap->res, res, sizeof(*res)); - pgmap->dev = dev; - if (altmap) { - memcpy(&pgmap->altmap, altmap, sizeof(*altmap)); - pgmap->altmap_valid = true; - altmap = &pgmap->altmap; - } - pgmap->ref = ref; - pgmap->type = MEMORY_DEVICE_HOST; - pgmap->page_fault = NULL; - pgmap->page_free = NULL; - pgmap->data = NULL; mutex_lock(&pgmap_lock); error = 0; @@ -423,11 +412,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, */ list_del(&page->lru); page->pgmap = pgmap; - percpu_ref_get(ref); + percpu_ref_get(pgmap->ref); if (!(++i % 1024)) cond_resched(); } - devres_add(dev, pgmap); + + devm_add_action(dev, devm_memremap_pages_release, pgmap); + return __va(res->start); err_add_memory: diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index e1f75a1914a1..ff9d3a5825e1 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -104,15 +104,14 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, } EXPORT_SYMBOL(__wrap_devm_memremap); -void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res, - struct percpu_ref *ref, struct vmem_altmap *altmap) +void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { - resource_size_t offset = res->start; + resource_size_t offset = pgmap->res.start; struct nfit_test_resource *nfit_res = get_nfit_res(offset); if (nfit_res) return nfit_res->buf + offset - nfit_res->res.start; - return devm_memremap_pages(dev, res, ref, altmap); + return devm_memremap_pages(dev, pgmap); } EXPORT_SYMBOL(__wrap_devm_memremap_pages); -- cgit v1.2.3