From b48279af636de613e9dd03857d9cadd4beca8e7e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 18 Feb 2023 08:27:24 -0800 Subject: perf test: Fix offcpu test prev_state check On Fedora 36, the 'perf record' offcpu profiling tests are failing. It was because the BPF checks the prev task's state being S or D but actually it has more bits set. Let's check the LSB 8 bits for the purpose of offcpu profiling. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230218162724.1292657-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/off_cpu.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index 38e3b287dbb2..d877a0a9731f 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -277,7 +277,7 @@ int on_switch(u64 *ctx) else prev_state = get_task_state(prev); - return off_cpu_stat(ctx, prev, next, prev_state); + return off_cpu_stat(ctx, prev, next, prev_state & 0xff); } char LICENSE[] SEC("license") = "Dual BSD/GPL"; -- cgit v1.2.3 From 3ef9fec011d471a259935f2e2ff58ab12886d683 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 22 Feb 2023 16:17:36 -0300 Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes from these csets: 8c29f01654053258 ("x86/sev: Add SEV-SNP guest feature negotiation support") That cause no changes to tooling: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after $ diff -u before after $ Just silences this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Cc: Borislav Petkov (AMD) Cc: Nikunj A Dadhania Link: https://lore.kernel.org/lkml/Y%2FZrNvtcijPWagCp@kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 37ff47552bcb..d3fe82c5d6b6 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -566,6 +566,26 @@ #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) +/* SNP feature bits enabled by the hypervisor */ +#define MSR_AMD64_SNP_VTOM BIT_ULL(3) +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) +#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) +#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) + +/* SNP feature bits reserved for future use. */ +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) + #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f /* AMD Collaborative Processor Performance Control MSRs */ -- cgit v1.2.3 From ce9f1c05d2edfa6cdf2c1a510495d333e11810a8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 22 Feb 2023 23:01:55 -0800 Subject: perf inject: Fix --buildid-all not to eat up MMAP2 When MMAP2 has the PERF_RECORD_MISC_MMAP_BUILD_ID flag, it means the record already has the build-id info. So it marks the DSO as hit, to skip if the same DSO is not processed if it happens to miss the build-id later. But it missed to copy the MMAP2 record itself so it'd fail to symbolize samples for those regions. For example, the following generates 249 MMAP2 events. $ perf record --buildid-mmap -o- true | perf report --stat -i- | grep MMAP2 MMAP2 events: 249 (86.8%) Adding perf inject should not change the number of events like this $ perf record --buildid-mmap -o- true | perf inject -b | \ > perf report --stat -i- | grep MMAP2 MMAP2 events: 249 (86.5%) But when --buildid-all is used, it eats most of the MMAP2 events. $ perf record --buildid-mmap -o- true | perf inject -b --buildid-all | \ > perf report --stat -i- | grep MMAP2 MMAP2 events: 1 ( 2.5%) With this patch, it shows the original number now. $ perf record --buildid-mmap -o- true | perf inject -b --buildid-all | \ > perf report --stat -i- | grep MMAP2 MMAP2 events: 249 (86.5%) Committer testing: Before: $ perf record --buildid-mmap -o- perf stat --null sleep 1 2> /dev/null | perf inject -b | perf report --stat -i- | grep MMAP2 MMAP2 events: 58 (36.2%) $ perf record --buildid-mmap -o- perf stat --null sleep 1 2> /dev/null | perf report --stat -i- | grep MMAP2 MMAP2 events: 58 (36.2%) $ perf record --buildid-mmap -o- perf stat --null sleep 1 2> /dev/null | perf inject -b --buildid-all | perf report --stat -i- | grep MMAP2 MMAP2 events: 2 ( 1.9%) $ After: $ perf record --buildid-mmap -o- perf stat --null sleep 1 2> /dev/null | perf inject -b | perf report --stat -i- | grep MMAP2 MMAP2 events: 58 (29.3%) $ perf record --buildid-mmap -o- perf stat --null sleep 1 2> /dev/null | perf report --stat -i- | grep MMAP2 MMAP2 events: 58 (34.3%) $ perf record --buildid-mmap -o- perf stat --null sleep 1 2> /dev/null | perf inject -b --buildid-all | perf report --stat -i- | grep MMAP2 MMAP2 events: 58 (38.4%) $ Fixes: f7fc0d1c915a74ff ("perf inject: Do not inject BUILD_ID record if MMAP2 has it") Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230223070155.54251-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index f8182417b734..10bb1d494258 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -538,6 +538,7 @@ static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool, dso->hit = 1; } dso__put(dso); + perf_event__repipe(tool, event, sample, machine); return 0; } -- cgit v1.2.3 From d3e104bb024e01a7da6af3b270a7b46054b74ac9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Feb 2023 23:18:17 -0800 Subject: perf tests stat+csv_output: Switch CSV separator to @ Commas may appear in events like: cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ which causes the commachecker to see more fields than expected. Use @ as the CSV separator to avoid this. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Claire Jensen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sumanth Korikkar Cc: Thomas Richter Link: https://lore.kernel.org/r/20230223071818.329671-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat+csv_output.sh | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'tools') diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index b7f050aa6210..324fc9e6edd7 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -7,6 +7,7 @@ set -e skip_test=0 +csv_sep=@ function commachecker() { @@ -34,7 +35,7 @@ function commachecker() [ "$x" = "Failed" ] && continue # Count the number of commas - x=$(echo $line | tr -d -c ',') + x=$(echo $line | tr -d -c $csv_sep) cnt="${#x}" # echo $line $cnt [[ ! "$cnt" =~ $exp ]] && { @@ -54,7 +55,7 @@ function ParanoidAndNotRoot() check_no_args() { echo -n "Checking CSV output: no args " - perf stat -x, true 2>&1 | commachecker --no-args + perf stat -x$csv_sep true 2>&1 | commachecker --no-args echo "[Success]" } @@ -66,7 +67,7 @@ check_system_wide() echo "[Skip] paranoid and not root" return fi - perf stat -x, -a true 2>&1 | commachecker --system-wide + perf stat -x$csv_sep -a true 2>&1 | commachecker --system-wide echo "[Success]" } @@ -79,14 +80,14 @@ check_system_wide_no_aggr() return fi echo -n "Checking CSV output: system wide no aggregation " - perf stat -x, -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr + perf stat -x$csv_sep -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr echo "[Success]" } check_interval() { echo -n "Checking CSV output: interval " - perf stat -x, -I 1000 true 2>&1 | commachecker --interval + perf stat -x$csv_sep -I 1000 true 2>&1 | commachecker --interval echo "[Success]" } @@ -94,7 +95,7 @@ check_interval() check_event() { echo -n "Checking CSV output: event " - perf stat -x, -e cpu-clock true 2>&1 | commachecker --event + perf stat -x$csv_sep -e cpu-clock true 2>&1 | commachecker --event echo "[Success]" } @@ -106,7 +107,7 @@ check_per_core() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-core -a true 2>&1 | commachecker --per-core + perf stat -x$csv_sep --per-core -a true 2>&1 | commachecker --per-core echo "[Success]" } @@ -118,7 +119,7 @@ check_per_thread() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-thread -a true 2>&1 | commachecker --per-thread + perf stat -x$csv_sep --per-thread -a true 2>&1 | commachecker --per-thread echo "[Success]" } @@ -130,7 +131,7 @@ check_per_die() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-die -a true 2>&1 | commachecker --per-die + perf stat -x$csv_sep --per-die -a true 2>&1 | commachecker --per-die echo "[Success]" } @@ -142,7 +143,7 @@ check_per_node() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-node -a true 2>&1 | commachecker --per-node + perf stat -x$csv_sep --per-node -a true 2>&1 | commachecker --per-node echo "[Success]" } @@ -154,7 +155,7 @@ check_per_socket() echo "[Skip] paranoid and not root" return fi - perf stat -x, --per-socket -a true 2>&1 | commachecker --per-socket + perf stat -x$csv_sep --per-socket -a true 2>&1 | commachecker --per-socket echo "[Success]" } -- cgit v1.2.3 From 3de34f85bf437e47556044191f0bd7d0eb644e21 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Feb 2023 23:18:18 -0800 Subject: perf test: Avoid counting commas in json linter Commas may appear in events like: cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ which causes the count of commas to see more items than expected. Switch to counting the entries in the dictionary, which is 1 more than the number of commas. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Claire Jensen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sumanth Korikkar Cc: Thomas Richter Link: https://lore.kernel.org/r/20230223071818.329671-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/tests/shell/lib/perf_json_output_lint.py | 29 ++++++++++------------ 1 file changed, 13 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index d90f8d102eb9..97598d14e532 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -40,19 +40,6 @@ def is_counter_value(num): return isfloat(num) or num == '' or num == '' def check_json_output(expected_items): - if expected_items != -1: - for line in Lines: - if 'failed' not in line: - count = 0 - count = line.count(',') - if count != expected_items and count >= 1 and count <= 3 and 'metric-value' in line: - # Events that generate >1 metric may have isolated metric - # values and possibly other prefixes like interval, core and - # aggregate-number. - continue - if count != expected_items: - raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' - f' in \'{line}\'') checks = { 'aggregate-number': lambda x: isfloat(x), 'core': lambda x: True, @@ -73,6 +60,16 @@ def check_json_output(expected_items): } input = '[\n' + ','.join(Lines) + '\n]' for item in json.loads(input): + if expected_items != -1: + count = len(item) + if count != expected_items and count >= 1 and count <= 4 and 'metric-value' in item: + # Events that generate >1 metric may have isolated metric + # values and possibly other prefixes like interval, core and + # aggregate-number. + pass + elif count != expected_items: + raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' + f' in \'{item}\'') for key, value in item.items(): if key not in checks: raise RuntimeError(f'Unexpected key: key={key} value={value}') @@ -82,11 +79,11 @@ def check_json_output(expected_items): try: if args.no_args or args.system_wide or args.event: - expected_items = 6 - elif args.interval or args.per_thread or args.system_wide_no_aggr: expected_items = 7 - elif args.per_core or args.per_socket or args.per_node or args.per_die: + elif args.interval or args.per_thread or args.system_wide_no_aggr: expected_items = 8 + elif args.per_core or args.per_socket or args.per_node or args.per_die: + expected_items = 9 else: # If no option is specified, don't check the number of items. expected_items = -1 -- cgit v1.2.3 From a98c0710b47d7dd44a351d08542360ff23f78330 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 23 Feb 2023 10:54:41 -0300 Subject: tools headers svm: Sync svm headers with the kernel sources To pick the changes in: 8c29f01654053258 ("x86/sev: Add SEV-SNP guest feature negotiation support") That triggers: CC /tmp/build/perf-tools/arch/x86/util/kvm-stat.o CC /tmp/build/perf-tools/util/header.o LD /tmp/build/perf-tools/arch/x86/util/perf-in.o LD /tmp/build/perf-tools/arch/x86/perf-in.o LD /tmp/build/perf-tools/arch/perf-in.o LD /tmp/build/perf-tools/util/perf-in.o LD /tmp/build/perf-tools/perf-in.o LINK /tmp/build/perf-tools/perf But this time causes no changes in tooling results, as the introduced SVM_VMGEXIT_TERM_REQUEST exit reason wasn't added to SVM_EXIT_REASONS, that is used in kvm-stat.c. And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/svm.h' differs from latest version at 'arch/x86/include/uapi/asm/svm.h' diff -u tools/arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/svm.h Cc: Adrian Hunter Cc: Borislav Petkov (AMD) Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Nikunj A Dadhania Link: http://lore.kernel.org/lkml/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/svm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools') diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index f69c168391aa..80e1df482337 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -116,6 +116,12 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd +#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe +#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ + /* SW_EXITINFO1[3:0] */ \ + (((((u64)reason_set) & 0xf)) | \ + /* SW_EXITINFO1[11:4] */ \ + ((((u64)reason_code) & 0xff) << 4)) #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ -- cgit v1.2.3 From 25f69c69bc3ca8c781a94473f28d443d745768e3 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 2 Mar 2023 11:11:44 +0800 Subject: perf stat: Fix counting when initial delay configured When creating counters with initial delay configured, the enable_on_exec field is not set. So we need to enable the counters later. The problem is, when a workload is specified the target__none() is true. So we also need to check stat_config.initial_delay. In this change, we add a new field 'initial_delay' for struct target which could be shared by other subcommands. And define target__enable_on_exec() which returns whether enable_on_exec should be set on normal cases. Before this fix the event is not counted: $ ./perf stat -e instructions -D 100 sleep 2 Events disabled Events enabled Performance counter stats for 'sleep 2': instructions 1.901661124 seconds time elapsed 0.001602000 seconds user 0.000000000 seconds sys After fix it works: $ ./perf stat -e instructions -D 100 sleep 2 Events disabled Events enabled Performance counter stats for 'sleep 2': 404,214 instructions 1.901743475 seconds time elapsed 0.001617000 seconds user 0.000000000 seconds sys Fixes: c587e77e100fa40e ("perf stat: Do not delay the workload with --delay") Signed-off-by: Changbin Du Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Hui Wang Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230302031146.2801588-2-changbin.du@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 15 +++++---------- tools/perf/util/stat.c | 6 +----- tools/perf/util/stat.h | 1 - tools/perf/util/target.h | 12 ++++++++++++ 4 files changed, 18 insertions(+), 16 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5d18a5a6f662..fa7c40956d0f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -539,12 +539,7 @@ static int enable_counters(void) return err; } - /* - * We need to enable counters only if: - * - we don't have tracee (attaching to task or cpu) - * - we have initial delay configured - */ - if (!target__none(&target)) { + if (!target__enable_on_exec(&target)) { if (!all_counters_use_bpf) evlist__enable(evsel_list); } @@ -914,7 +909,7 @@ try_again_reset: return err; } - if (stat_config.initial_delay) { + if (target.initial_delay) { pr_info(EVLIST_DISABLED_MSG); } else { err = enable_counters(); @@ -926,8 +921,8 @@ try_again_reset: if (forks) evlist__start_workload(evsel_list); - if (stat_config.initial_delay > 0) { - usleep(stat_config.initial_delay * USEC_PER_MSEC); + if (target.initial_delay > 0) { + usleep(target.initial_delay * USEC_PER_MSEC); err = enable_counters(); if (err) return -1; @@ -1248,7 +1243,7 @@ static struct option stat_options[] = { "aggregate counts per thread", AGGR_THREAD), OPT_SET_UINT(0, "per-node", &stat_config.aggr_mode, "aggregate counts per numa node", AGGR_NODE), - OPT_INTEGER('D', "delay", &stat_config.initial_delay, + OPT_INTEGER('D', "delay", &target.initial_delay, "ms to wait before starting measurement after program start (-1: start with events disabled)"), OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL, "Only print computed metrics. No raw values", enable_metric_only), diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 534d36d26fc3..a07473703c6d 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -842,11 +842,7 @@ int create_perf_stat_counter(struct evsel *evsel, if (evsel__is_group_leader(evsel)) { attr->disabled = 1; - /* - * In case of initial_delay we enable tracee - * events manually. - */ - if (target__none(target) && !config->initial_delay) + if (target__enable_on_exec(target)) attr->enable_on_exec = 1; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index b1c29156c560..bf1794ebc916 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -166,7 +166,6 @@ struct perf_stat_config { FILE *output; unsigned int interval; unsigned int timeout; - int initial_delay; unsigned int unit_width; unsigned int metric_only_len; int times; diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index daec6cba500d..880f1af7f6ad 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -18,6 +18,7 @@ struct target { bool per_thread; bool use_bpf; bool hybrid; + int initial_delay; const char *attr_map; }; @@ -72,6 +73,17 @@ static inline bool target__none(struct target *target) return !target__has_task(target) && !target__has_cpu(target); } +static inline bool target__enable_on_exec(struct target *target) +{ + /* + * Normally enable_on_exec should be set if: + * 1) The tracee process is forked (not attaching to existed task or cpu). + * 2) And initial_delay is not configured. + * Otherwise, we enable tracee events manually. + */ + return target__none(target) && !target->initial_delay; +} + static inline bool target__has_per_thread(struct target *target) { return target->system_wide && target->per_thread; -- cgit v1.2.3 From 31d2e6b5d44e436969c15e4613e6b16c4c032d4d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Mar 2023 11:05:19 -0300 Subject: tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench' We also continue with SYM_TYPED_FUNC_START() in util/include/linux/linkage.h and with an exception in tools/perf/check_headers.sh's diff check to ignore the include cfi_types.h line when checking if the kernel original files drifted from the copies we carry. This is to get the changes from: 69d4c0d3218692ff ("entry, kasan, x86: Disallow overriding mem*() functions") That addresses these perf tools build warning: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/lkml/ZAH%2FjsioJXGIOrkf@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/lib/memcpy_64.S | 5 ++--- tools/arch/x86/lib/memset_64.S | 4 +++- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 5418e2f99834..a91ac666f758 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -7,7 +7,7 @@ #include #include -.pushsection .noinstr.text, "ax" +.section .noinstr.text, "ax" /* * We build a jump to memcpy_orig by default which gets NOPped out on @@ -42,7 +42,7 @@ SYM_TYPED_FUNC_START(__memcpy) SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) -SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) +SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) /* @@ -183,4 +183,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig) RET SYM_FUNC_END(memcpy_orig) -.popsection diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index fc9ffd3ff3b2..6143b1a6fa2c 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -6,6 +6,8 @@ #include #include +.section .noinstr.text, "ax" + /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -43,7 +45,7 @@ SYM_FUNC_START(__memset) SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) -SYM_FUNC_ALIAS_WEAK(memset, __memset) +SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) /* -- cgit v1.2.3 From df4b933e0e51e43bd27a495dc747db0851e6dd34 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Mar 2023 11:48:09 -0300 Subject: tools headers UAPI: Sync linux/prctl.h with the kernel sources To pick new prctl options introduced in: b507808ebce23561 ("mm: implement memory-deny-write-execute as a prctl") That results in: $ diff -u tools/include/uapi/linux/prctl.h include/uapi/linux/prctl.h --- tools/include/uapi/linux/prctl.h 2022-06-20 17:54:43.884515663 -0300 +++ include/uapi/linux/prctl.h 2023-03-03 11:18:51.090923569 -0300 @@ -281,6 +281,12 @@ # define PR_SME_VL_LEN_MASK 0xffff # define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN 1 + +#define PR_GET_MDWE 66 + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 $ tools/perf/trace/beauty/prctl_option.sh > before $ cp include/uapi/linux/prctl.h tools/include/uapi/linux/prctl.h $ tools/perf/trace/beauty/prctl_option.sh > after $ diff -u before after --- before 2023-03-03 11:47:43.320013146 -0300 +++ after 2023-03-03 11:47:50.937216229 -0300 @@ -59,6 +59,8 @@ [62] = "SCHED_CORE", [63] = "SME_SET_VL", [64] = "SME_GET_VL", + [65] = "SET_MDWE", + [66] = "GET_MDWE", }; static const char *prctl_set_mm_options[] = { [1] = "START_CODE", $ Now users can do: # perf trace -e syscalls:sys_enter_prctl --filter "option==SET_MDWE||option==GET_MDWE" ^C# # trace -v -e syscalls:sys_enter_prctl --filter "option==SET_MDWE||option==GET_MDWE" New filter for syscalls:sys_enter_prctl: (option==65||option==66) && (common_pid != 5519 && common_pid != 3404) ^C# And when these prctl options appears in a session, they will be translated to the corresponding string. Cc: Adrian Hunter Cc: Andrew Morton Cc: Ian Rogers Cc: Jiri Olsa Cc: Joey Gouly Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZAI%2FAoPXb%2Fsxz1%2Fm@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/prctl.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index a5e06dcbba13..1312a137f7fb 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -281,6 +281,12 @@ struct prctl_mm_map { # define PR_SME_VL_LEN_MASK 0xffff # define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN 1 + +#define PR_GET_MDWE 66 + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 -- cgit v1.2.3 From 811f35ff59b6f99ae272d6f5b96bc9e974f88196 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Mar 2023 16:49:20 -0300 Subject: tools headers: Synchronize {linux,vdso}/bits.h with the kernel sources To pick up the changes in this cset: cbdb1f163af2bb90 ("vdso/bits.h: Add BIT_ULL() for the sake of consistency") That just causes perf to rebuild, the macro included doesn't clash with anything in tools/{perf,objtool,bpf}. This addresses this perf build warning: Warning: Kernel ABI header at 'tools/include/linux/bits.h' differs from latest version at 'include/linux/bits.h' diff -u tools/include/linux/bits.h include/linux/bits.h Warning: Kernel ABI header at 'tools/include/vdso/bits.h' differs from latest version at 'include/vdso/bits.h' diff -u tools/include/vdso/bits.h include/vdso/bits.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/bits.h | 1 - tools/include/vdso/bits.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 87d112650dfb..7c0cf5031abe 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -6,7 +6,6 @@ #include #include -#define BIT_ULL(nr) (ULL(1) << (nr)) #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) #define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG)) diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h index 6d005a1f5d94..388b212088ea 100644 --- a/tools/include/vdso/bits.h +++ b/tools/include/vdso/bits.h @@ -5,5 +5,6 @@ #include #define BIT(nr) (UL(1) << (nr)) +#define BIT_ULL(nr) (ULL(1) << (nr)) #endif /* __VDSO_BITS_H */ -- cgit v1.2.3 From 5f800380af3881f1a0528d332838d4619a64593b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Mar 2023 16:57:50 -0300 Subject: tools include UAPI: Synchronize linux/fcntl.h with the kernel sources To pick up the changes in: 6fd7353829cafc40 ("mm/memfd: add F_SEAL_EXEC") That doesn't add or change any perf tools functionality, only addresses these build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/fcntl.h' differs from latest version at 'include/uapi/linux/fcntl.h' diff -u tools/include/uapi/linux/fcntl.h include/uapi/linux/fcntl.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/fcntl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 2f86b2ad6d7e..e8c07da58c9f 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -43,6 +43,7 @@ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ #define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */ +#define F_SEAL_EXEC 0x0020 /* prevent chmod modifying exec bits */ /* (1U << 31) is reserved for signed error codes */ /* -- cgit v1.2.3 From 33c53f9b5ac60c7d5c6acc91a6b6d933e0a417e3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Mar 2023 17:26:24 -0300 Subject: tools headers kvm: Sync uapi/{asm/linux} kvm.h headers with the kernel sources To pick up the changes in: 89b0e7de3451a17f ("KVM: arm64: nv: Introduce nested virtualization VCPU feature") 14329b825ffb7f27 ("KVM: x86/pmu: Introduce masked events to the pmu event filter") 6213b701a9df0472 ("KVM: x86: Replace 0-length arrays with flexible arrays") 3fd49805d19d1c56 ("KVM: s390: Extend MEM_OP ioctl by storage key checked cmpxchg") 14329b825ffb7f27 ("KVM: x86/pmu: Introduce masked events to the pmu event filter") That don't change functionality in tools/perf, as no new ioctl is added for the 'perf trace' scripts to harvest. This addresses these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h' diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Cc: Aaron Lewis Cc: Adrian Hunter Cc: Christoffer Dall Cc: Ian Rogers Cc: Janis Schoetterl-Glausch Cc: Janosch Frank Cc: Jiri Olsa Cc: Kees Kook Cc: Namhyung Kim Cc: Oliver Upton Cc: Sean Christopherson Link: https://lore.kernel.org/lkml/ZAJlg7%2FfWDVGX0F3@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 1 + tools/arch/x86/include/uapi/asm/kvm.h | 34 +++++++++++++++++++++++++++++++-- tools/include/uapi/linux/kvm.h | 9 +++++++++ 3 files changed, 42 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index a7a857f1784d..f8129c624b07 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -109,6 +109,7 @@ struct kvm_regs { #define KVM_ARM_VCPU_SVE 4 /* enable SVE for this CPU */ #define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */ #define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */ +#define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */ struct kvm_vcpu_init { __u32 target; diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index e48deab8901d..7f467fe05d42 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -9,6 +9,7 @@ #include #include +#include #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 @@ -507,8 +508,8 @@ struct kvm_nested_state { * KVM_{GET,PUT}_NESTED_STATE ioctl values. */ union { - struct kvm_vmx_nested_state_data vmx[0]; - struct kvm_svm_nested_state_data svm[0]; + __DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx); + __DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm); } data; }; @@ -525,6 +526,35 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 55155e262646..d77aef872a0a 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -583,6 +583,8 @@ struct kvm_s390_mem_op { struct { __u8 ar; /* the access register number */ __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ }; __u32 sida_offset; /* offset into the sida */ __u8 reserved[32]; /* ignored */ @@ -595,11 +597,17 @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_SIDA_WRITE 3 #define KVM_S390_MEMOP_ABSOLUTE_READ 4 #define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) #define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -1175,6 +1183,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 +#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 3ee7cb4fdf37e3763b3b10da2a7715b7a7a2a783 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Mar 2023 22:36:04 -0300 Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes in: e7862eda309ecfcc ("x86/cpu: Support AMD Automatic IBRS") 0125acda7d76b943 ("x86/bugs: Reset speculation control settings on init") 38aaf921e92dc5cf ("perf/x86: Add Meteor Lake support") 5b6fac3fa44bafee ("x86/resctrl: Detect and configure Slow Memory Bandwidth Allocation") dc2a3e857981f859 ("x86/resctrl: Add interface to read mbm_total_bytes_config") Addressing these tools/perf build warnings: diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' That makes the beautification scripts to pick some new entries: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after $ diff -u before after --- before 2023-03-03 18:26:51.766923522 -0300 +++ after 2023-03-03 18:27:09.987415481 -0300 @@ -267,9 +267,11 @@ [0xc000010e - x86_64_specific_MSRs_offset] = "AMD64_LBR_SELECT", [0xc000010f - x86_64_specific_MSRs_offset] = "AMD_DBG_EXTN_CFG", [0xc0000200 - x86_64_specific_MSRs_offset] = "IA32_MBA_BW_BASE", + [0xc0000280 - x86_64_specific_MSRs_offset] = "IA32_SMBA_BW_BASE", [0xc0000300 - x86_64_specific_MSRs_offset] = "AMD64_PERF_CNTR_GLOBAL_STATUS", [0xc0000301 - x86_64_specific_MSRs_offset] = "AMD64_PERF_CNTR_GLOBAL_CTL", [0xc0000302 - x86_64_specific_MSRs_offset] = "AMD64_PERF_CNTR_GLOBAL_STATUS_CLR", + [0xc0000400 - x86_64_specific_MSRs_offset] = "IA32_EVT_CFG_BASE", }; #define x86_AMD_V_KVM_MSRs_offset 0xc0010000 $ Now one can trace systemwide asking to see backtraces to where that MSR is being read/written, see this example with a previous update: # perf trace -e msr:*_msr/max-stack=32/ --filter="msr>=IA32_U_CET && msr<=IA32_INT_SSP_TAB" ^C# If we use -v (verbose mode) we can see what it does behind the scenes: # perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr>=IA32_U_CET && msr<=IA32_INT_SSP_TAB" Using CPUID AuthenticAMD-25-21-0 0x6a0 0x6a8 New filter for msr:read_msr: (msr>=0x6a0 && msr<=0x6a8) && (common_pid != 597499 && common_pid != 3313) 0x6a0 0x6a8 New filter for msr:write_msr: (msr>=0x6a0 && msr<=0x6a8) && (common_pid != 597499 && common_pid != 3313) mmap size 528384B ^C# Example with a frequent msr: # perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr==IA32_SPEC_CTRL" --max-events 2 Using CPUID AuthenticAMD-25-21-0 0x48 New filter for msr:read_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841) 0x48 New filter for msr:write_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841) mmap size 528384B Looking at the vmlinux_path (8 entries long) symsrc__init: build id mismatch for vmlinux. Using /proc/kcore for kernel data Using /proc/kallsyms for symbols 0.000 Timer/2525383 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6) do_trace_write_msr ([kernel.kallsyms]) do_trace_write_msr ([kernel.kallsyms]) __switch_to_xtra ([kernel.kallsyms]) __switch_to ([kernel.kallsyms]) __schedule ([kernel.kallsyms]) schedule ([kernel.kallsyms]) futex_wait_queue_me ([kernel.kallsyms]) futex_wait ([kernel.kallsyms]) do_futex ([kernel.kallsyms]) __x64_sys_futex ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64_after_hwframe ([kernel.kallsyms]) __futex_abstimed_wait_common64 (/usr/lib64/libpthread-2.33.so) 0.030 :0/0 msr:write_msr(msr: IA32_SPEC_CTRL, val: 2) do_trace_write_msr ([kernel.kallsyms]) do_trace_write_msr ([kernel.kallsyms]) __switch_to_xtra ([kernel.kallsyms]) __switch_to ([kernel.kallsyms]) __schedule ([kernel.kallsyms]) schedule_idle ([kernel.kallsyms]) do_idle ([kernel.kallsyms]) cpu_startup_entry ([kernel.kallsyms]) secondary_startup_64_no_verify ([kernel.kallsyms]) # Cc: Adrian Hunter Cc: Babu Moger Cc: Borislav Petkov (AMD) Cc: Breno Leitao Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Kim Phillips Cc: Namhyung Kim Cc: Nikunj A Dadhania Link: https://lore.kernel.org/lkml/ZAJoaZ41+rU5H0vL@kernel.org [ I had published the perf-tools branch before with the sync with ] [ 8c29f01654053258 ("x86/sev: Add SEV-SNP guest feature negotiation support") ] [ I removed it from this new sync ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index d3fe82c5d6b6..ad35355ee43e 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -25,6 +25,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -33,6 +34,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -49,6 +51,10 @@ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +/* A mask for bits which the kernel toggles when controlling mitigations */ +#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ + | SPEC_CTRL_RRSBA_DIS_S) + #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -189,6 +195,9 @@ #define MSR_TURBO_RATIO_LIMIT1 0x000001ae #define MSR_TURBO_RATIO_LIMIT2 0x000001af +#define MSR_SNOOP_RSP_0 0x00001328 +#define MSR_SNOOP_RSP_1 0x00001329 + #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -1081,6 +1090,8 @@ /* - AMD: */ #define MSR_IA32_MBA_BW_BASE 0xc0000200 +#define MSR_IA32_SMBA_BW_BASE 0xc0000280 +#define MSR_IA32_EVT_CFG_BASE 0xc0000400 /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) -- cgit v1.2.3 From 14e998ed42208f60d5f848f5e025fa2c2e9667b0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 6 Mar 2023 09:26:35 -0300 Subject: tools include UAPI: Sync linux/vhost.h with the kernel sources To get the changes in: 3b688d7a086d0438 ("vhost-vdpa: uAPI to resume the device") To pick up these changes and support them: $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh > before $ cp ../linux/include/uapi/linux/vhost.h tools/include/uapi/linux/vhost.h $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh > after $ diff -u before after --- before 2023-03-06 09:26:14.889251817 -0300 +++ after 2023-03-06 09:26:20.594406270 -0300 @@ -30,6 +30,7 @@ [0x77] = "VDPA_SET_CONFIG_CALL", [0x7C] = "VDPA_SET_GROUP_ASID", [0x7D] = "VDPA_SUSPEND", + [0x7E] = "VDPA_RESUME", }; static const char *vhost_virtio_ioctl_read_cmds[] = { [0x00] = "GET_FEATURES", $ For instance, see how those 'cmd' ioctl arguments get translated, now VDPA_RESUME will be as well: # perf trace -a -e ioctl --max-events=10 0.000 ( 0.011 ms): pipewire/2261 ioctl(fd: 60, cmd: SNDRV_PCM_HWSYNC, arg: 0x1) = 0 21.353 ( 0.014 ms): pipewire/2261 ioctl(fd: 60, cmd: SNDRV_PCM_HWSYNC, arg: 0x1) = 0 25.766 ( 0.014 ms): gnome-shell/2196 ioctl(fd: 14, cmd: DRM_I915_IRQ_WAIT, arg: 0x7ffe4a22c740) = 0 25.845 ( 0.034 ms): gnome-shel:cs0/2212 ioctl(fd: 14, cmd: DRM_I915_IRQ_EMIT, arg: 0x7fd43915dc70) = 0 25.916 ( 0.011 ms): gnome-shell/2196 ioctl(fd: 9, cmd: DRM_MODE_ADDFB2, arg: 0x7ffe4a22c8a0) = 0 25.941 ( 0.025 ms): gnome-shell/2196 ioctl(fd: 9, cmd: DRM_MODE_ATOMIC, arg: 0x7ffe4a22c840) = 0 32.915 ( 0.009 ms): gnome-shell/2196 ioctl(fd: 9, cmd: DRM_MODE_RMFB, arg: 0x7ffe4a22cf9c) = 0 42.522 ( 0.013 ms): gnome-shell/2196 ioctl(fd: 14, cmd: DRM_I915_IRQ_WAIT, arg: 0x7ffe4a22c740) = 0 42.579 ( 0.031 ms): gnome-shel:cs0/2212 ioctl(fd: 14, cmd: DRM_I915_IRQ_EMIT, arg: 0x7fd43915dc70) = 0 42.644 ( 0.010 ms): gnome-shell/2196 ioctl(fd: 9, cmd: DRM_MODE_ADDFB2, arg: 0x7ffe4a22c8a0) = 0 # Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Michael S. Tsirkin Cc: Namhyung Kim Cc: Sebastien Boeuf Link: https://lore.kernel.org/lkml/ZAXdCTecxSNwAoeK@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/vhost.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index f9f115a7c75b..92e1b700b51c 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -180,4 +180,12 @@ */ #define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) +/* Resume a device so it can resume processing virtqueue requests + * + * After the return of this ioctl the device will have restored all the + * necessary states and it is fully operational to continue processing the + * virtqueue descriptors. + */ +#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) + #endif -- cgit v1.2.3 From 7d0930647c020f75592adde8712d2cb002b29387 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 6 Mar 2023 14:25:21 -0300 Subject: tools headers x86 cpufeatures: Sync with the kernel sources To pick the changes from: 8415a74852d7c247 ("x86/cpu, kvm: Add support for CPUID_80000021_EAX") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses these perf build warnings: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/required-features.h' differs from latest version at 'arch/x86/include/asm/required-features.h' diff -u tools/arch/x86/include/asm/required-features.h arch/x86/include/asm/required-features.h Cc: Adrian Hunter Cc: Borislav Petkov (AMD) Cc: Ian Rogers Cc: Jiri Olsa Cc: Kim Phillips Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZAYlS2XTJ5hRtss7@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 2 +- tools/arch/x86/include/asm/disabled-features.h | 3 ++- tools/arch/x86/include/asm/required-features.h | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 61012476d66e..d53e13048d2e 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 20 /* N 32-bit words worth of info */ +#define NCAPINTS 21 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index c44b56f7ffba..5dfa4fb76f4b 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -124,6 +124,7 @@ #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define DISABLED_MASK20 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index aff774775c67..7ba1726b71c7 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -98,6 +98,7 @@ #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define REQUIRED_MASK20 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ -- cgit v1.2.3 From 06a1574b94ee5272789eaea05a5bdddedea7cc0d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 6 Mar 2023 14:44:11 -0300 Subject: tools headers UAPI: Sync linux/perf_event.h with the kernel sources To pick up the changes in: 09519ec3b19e4144 ("perf: Add perf_event_attr::config3") The patches for the tooling side will come later. This addresses this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h' diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Rob Herring Cc: Will Deacon Link: https://lore.kernel.org/lkml/ZAZLYmDjWjSItWOq@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index ccb7f5dad59b..37675437b768 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -374,6 +374,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ #define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -515,6 +516,8 @@ struct perf_event_attr { * truncated accordingly on 32 bit architectures. */ __u64 sig_data; + + __u64 config3; /* extension of config2 */ }; /* -- cgit v1.2.3