| Message ID | 1444826502-49291-1-git-send-email-wangnan0@huawei.com |
|---|---|
| State | New |
| Headers | show |
Hello, On Wed, Oct 14, 2015 at 12:41:11PM +0000, Wang Nan wrote: > Hi Arnaldo, > > I know you don't have enough time to review my code. I send > this patchset to let you and other know what we are working on. > > In this new patchset, we create a new perf cmdline syntax so > perf users are able to pass perf events created by perf to BPF > maps, which makes bpf_perf_event_read() usable. Compare with out > previous solution[1] which embedded 'struct perf_event_attr' to > "maps" section, this solution is easier to use. > > If you or anyone have any different views on this solution, > please let us know so we can stop our further development base > on it as soon as possible. Thanks for working on this. I've only reviewed the first part and will continue to review it tomorrow (or later). :) For patch 01 - 08, Acked-by: Namhyung Kim <namhyung@kernel.org> Thanks, Namhyung > > Thank you. > > [1] http://lkml.kernel.org/r/1440672142-89311-1-git-send-email-xiakaixu@huawei.com > > The following changes since commit 31eb4360546b4bd890f349db01295a173c09b0fb: > > perf hists browser: Add 'm' key for context menu display (2015-10-12 23:29:14 -0300) > > are available in the git repository at: > > git://git.kernel.org/pub/scm/linux/kernel/git/pi3orama/linux.git tags/perf-ebpf-for-acme-20151014 > > for you to fetch changes up to 6df036cb7d42a2e0ebf312e127b02425bd57bc55: > > perf tools: Enable BPF object configure syntax (2015-10-14 10:09:17 +0000) > > ---------------------------------------------------------------- > EBPF support for perf > > - Rebase to newest perf/core > > - Bugfix: kprobe events not remove if bpf__probe() failure occur > after it creates some kprobe points successfully. > > - Bugfix: when multiple BPF functions reside in one BPF object, > the last BPF program would be attached to all kprobe events. > This bug is introduced by removal of dummy event placeholder. > > - New function: support BPF program reading counter through > bpf_perf_event_read() by adding new syntax and support code > in event selector. The new BPF object configuration mechanism > can be extended to support BPF data output. > > In this patchset, following BPF function can be used to measure > cycles a kernel function cost: > > ===== BPF program bpf_program.c ===== > > struct bpf_map_def SEC("maps") pmu_map = { > .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, > .key_size = sizeof(int), > .value_size = sizeof(u32), > .max_entries = __NR_CPUS__, > }; > > SEC("func_write=sys_write") > int func_write(void *ctx) > { > unsigned long long val; > char fmt[] = "sys_write: pmu=%llu\n"; > val = bpf_perf_event_read(&pmu_map, bpf_get_smp_processor_id()); > bpf_trace_printk(fmt, sizeof(fmt), val); > return 0; > } > > SEC("func_write_return=sys_write%return") > int func_write_return(void *ctx) > { > unsigned long long val = 0; > char fmt[] = "sys_write_return: pmu=%llu\n"; > val = bpf_perf_event_read(&pmu_map, bpf_get_smp_processor_id()); > bpf_trace_printk(fmt, sizeof(fmt), val); > return 0; > } > > With cmdline like this: > > ===== cmdline ===== > # echo "" > /sys/kernel/debug/tracing/trace > # perf record -e evt=cycles/period=0x7fffffffffffffff/ \ > -e bpf_program.c/maps.pmu_map.event=evt/ > -a ls > # cat /sys/kernel/debug/tracing/trace | grep ls > ls-3363 [003] d... 75475.056190: : sys_write: pmu=3961415 > ls-3363 [003] dN.. 75475.056212: : sys_write_return: pmu=4051390 > ls-3363 [003] d... 75475.056216: : sys_write: pmu=4065447 > ls-3363 [003] dN.. 75475.056227: : sys_write_return: pmu=4109760 > ls-3363 [003] d... 75475.056230: : sys_write: pmu=4120776 > ls-3363 [003] dN.. 75475.056245: : sys_write_return: pmu=4178441 > ... > # perf report --stdio > Error: > The perf.data file has no samples! > > Signed-off-by: Wang Nan <wangnan0@huawei.com> > > ---------------------------------------------------------------- > He Kuang (5): > perf tools: Add prologue for BPF programs for fetching arguments > perf record: Support custom vmlinux path > bpf tools: Add helper function for updating bpf maps elements > perf tools: Support perf event alias name > perf record: Apply config to BPF objects before recording > > Wang Nan (26): > perf tools: Make perf depend on libbpf > perf ebpf: Add the libbpf glue > perf tools: Enable passing bpf object file to --event > perf record, bpf: Create probe points for BPF programs > perf record: Load eBPF object into kernel > perf tools: Collect perf_evsel in BPF object files > perf tools: Attach eBPF program to perf event > perf record: Add clang options for compiling BPF scripts > perf tools: Compile scriptlets to BPF objects when passing '.c' to --event > perf test: Enforce LLVM test for BPF test > perf test: Add 'perf test BPF' > perf probe: Reset args and nargs for probe_trace_event when failure > bpf tools: Load a program with different instances using preprocessor > perf tools: Add BPF_PROLOGUE config options for further patches > perf tools: Compile dwarf-regs.c if CONFIG_BPF_PROLOGUE is on > perf tools: Generate prologue for BPF programs > perf tools: Use same BPF program if arguments are identical > perf tools: Allow BPF program attach to uprobe events > perf test: Enforce LLVM test, add kbuild test > perf test: Test BPF prologue > bpf tools: Collect map definition in bpf_object > bpf tools: Extract and collect map names from BPF object file > perf tools: Pass available CPU number to clang compiler > perf tools: Add API to config maps in bpf object > perf tools: Add API to apply config to BPF map > perf tools: Enable BPF object configure syntax > > tools/build/Makefile.feature | 6 +- > tools/lib/bpf/bpf.c | 14 + > tools/lib/bpf/bpf.h | 2 + > tools/lib/bpf/libbpf.c | 392 +++++++++--- > tools/lib/bpf/libbpf.h | 46 ++ > tools/perf/MANIFEST | 3 + > tools/perf/Makefile.perf | 21 +- > tools/perf/arch/x86/util/Build | 1 + > tools/perf/builtin-record.c | 21 + > tools/perf/config/Makefile | 31 +- > tools/perf/perf.c | 2 + > tools/perf/tests/Build | 24 +- > tools/perf/tests/bpf-script-example.c | 48 ++ > tools/perf/tests/bpf-script-test-kbuild.c | 21 + > tools/perf/tests/bpf-script-test-prologue.c | 35 ++ > tools/perf/tests/bpf.c | 227 +++++++ > tools/perf/tests/builtin-test.c | 10 + > tools/perf/tests/llvm.c | 210 ++++++- > tools/perf/tests/llvm.h | 29 + > tools/perf/tests/make | 4 +- > tools/perf/tests/tests.h | 5 + > tools/perf/util/Build | 2 + > tools/perf/util/bpf-loader.c | 933 ++++++++++++++++++++++++++++ > tools/perf/util/bpf-loader.h | 148 +++++ > tools/perf/util/bpf-prologue.c | 443 +++++++++++++ > tools/perf/util/bpf-prologue.h | 34 + > tools/perf/util/evlist.c | 16 + > tools/perf/util/evlist.h | 4 + > tools/perf/util/evsel.c | 17 + > tools/perf/util/evsel.h | 2 + > tools/perf/util/llvm-utils.c | 24 +- > tools/perf/util/parse-events.c | 221 ++++++- > tools/perf/util/parse-events.h | 15 + > tools/perf/util/parse-events.l | 6 + > tools/perf/util/parse-events.y | 55 +- > tools/perf/util/probe-finder.c | 4 + > 36 files changed, 2968 insertions(+), 108 deletions(-) > create mode 100644 tools/perf/tests/bpf-script-example.c > create mode 100644 tools/perf/tests/bpf-script-test-kbuild.c > create mode 100644 tools/perf/tests/bpf-script-test-prologue.c > create mode 100644 tools/perf/tests/bpf.c > create mode 100644 tools/perf/tests/llvm.h > create mode 100644 tools/perf/util/bpf-loader.c > create mode 100644 tools/perf/util/bpf-loader.h > create mode 100644 tools/perf/util/bpf-prologue.c > create mode 100644 tools/perf/util/bpf-prologue.h > > -- > 1.8.3.4 > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Hi Arnaldo, I know you don't have enough time to review my code. I send this patchset to let you and other know what we are working on. In this new patchset, we create a new perf cmdline syntax so perf users are able to pass perf events created by perf to BPF maps, which makes bpf_perf_event_read() usable. Compare with out previous solution[1] which embedded 'struct perf_event_attr' to "maps" section, this solution is easier to use. If you or anyone have any different views on this solution, please let us know so we can stop our further development base on it as soon as possible. Thank you. [1] http://lkml.kernel.org/r/1440672142-89311-1-git-send-email-xiakaixu@huawei.com The following changes since commit 31eb4360546b4bd890f349db01295a173c09b0fb: perf hists browser: Add 'm' key for context menu display (2015-10-12 23:29:14 -0300) are available in the git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/pi3orama/linux.git tags/perf-ebpf-for-acme-20151014 for you to fetch changes up to 6df036cb7d42a2e0ebf312e127b02425bd57bc55: perf tools: Enable BPF object configure syntax (2015-10-14 10:09:17 +0000) ---------------------------------------------------------------- EBPF support for perf - Rebase to newest perf/core - Bugfix: kprobe events not remove if bpf__probe() failure occur after it creates some kprobe points successfully. - Bugfix: when multiple BPF functions reside in one BPF object, the last BPF program would be attached to all kprobe events. This bug is introduced by removal of dummy event placeholder. - New function: support BPF program reading counter through bpf_perf_event_read() by adding new syntax and support code in event selector. The new BPF object configuration mechanism can be extended to support BPF data output. In this patchset, following BPF function can be used to measure cycles a kernel function cost: ===== BPF program bpf_program.c ===== struct bpf_map_def SEC("maps") pmu_map = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, .key_size = sizeof(int), .value_size = sizeof(u32), .max_entries = __NR_CPUS__, }; SEC("func_write=sys_write") int func_write(void *ctx) { unsigned long long val; char fmt[] = "sys_write: pmu=%llu\n"; val = bpf_perf_event_read(&pmu_map, bpf_get_smp_processor_id()); bpf_trace_printk(fmt, sizeof(fmt), val); return 0; } SEC("func_write_return=sys_write%return") int func_write_return(void *ctx) { unsigned long long val = 0; char fmt[] = "sys_write_return: pmu=%llu\n"; val = bpf_perf_event_read(&pmu_map, bpf_get_smp_processor_id()); bpf_trace_printk(fmt, sizeof(fmt), val); return 0; } With cmdline like this: ===== cmdline ===== # echo "" > /sys/kernel/debug/tracing/trace # perf record -e evt=cycles/period=0x7fffffffffffffff/ \ -e bpf_program.c/maps.pmu_map.event=evt/ -a ls # cat /sys/kernel/debug/tracing/trace | grep ls ls-3363 [003] d... 75475.056190: : sys_write: pmu=3961415 ls-3363 [003] dN.. 75475.056212: : sys_write_return: pmu=4051390 ls-3363 [003] d... 75475.056216: : sys_write: pmu=4065447 ls-3363 [003] dN.. 75475.056227: : sys_write_return: pmu=4109760 ls-3363 [003] d... 75475.056230: : sys_write: pmu=4120776 ls-3363 [003] dN.. 75475.056245: : sys_write_return: pmu=4178441 ... # perf report --stdio Error: The perf.data file has no samples! Signed-off-by: Wang Nan <wangnan0@huawei.com> ---------------------------------------------------------------- He Kuang (5): perf tools: Add prologue for BPF programs for fetching arguments perf record: Support custom vmlinux path bpf tools: Add helper function for updating bpf maps elements perf tools: Support perf event alias name perf record: Apply config to BPF objects before recording Wang Nan (26): perf tools: Make perf depend on libbpf perf ebpf: Add the libbpf glue perf tools: Enable passing bpf object file to --event perf record, bpf: Create probe points for BPF programs perf record: Load eBPF object into kernel perf tools: Collect perf_evsel in BPF object files perf tools: Attach eBPF program to perf event perf record: Add clang options for compiling BPF scripts perf tools: Compile scriptlets to BPF objects when passing '.c' to --event perf test: Enforce LLVM test for BPF test perf test: Add 'perf test BPF' perf probe: Reset args and nargs for probe_trace_event when failure bpf tools: Load a program with different instances using preprocessor perf tools: Add BPF_PROLOGUE config options for further patches perf tools: Compile dwarf-regs.c if CONFIG_BPF_PROLOGUE is on perf tools: Generate prologue for BPF programs perf tools: Use same BPF program if arguments are identical perf tools: Allow BPF program attach to uprobe events perf test: Enforce LLVM test, add kbuild test perf test: Test BPF prologue bpf tools: Collect map definition in bpf_object bpf tools: Extract and collect map names from BPF object file perf tools: Pass available CPU number to clang compiler perf tools: Add API to config maps in bpf object perf tools: Add API to apply config to BPF map perf tools: Enable BPF object configure syntax tools/build/Makefile.feature | 6 +- tools/lib/bpf/bpf.c | 14 + tools/lib/bpf/bpf.h | 2 + tools/lib/bpf/libbpf.c | 392 +++++++++--- tools/lib/bpf/libbpf.h | 46 ++ tools/perf/MANIFEST | 3 + tools/perf/Makefile.perf | 21 +- tools/perf/arch/x86/util/Build | 1 + tools/perf/builtin-record.c | 21 + tools/perf/config/Makefile | 31 +- tools/perf/perf.c | 2 + tools/perf/tests/Build | 24 +- tools/perf/tests/bpf-script-example.c | 48 ++ tools/perf/tests/bpf-script-test-kbuild.c | 21 + tools/perf/tests/bpf-script-test-prologue.c | 35 ++ tools/perf/tests/bpf.c | 227 +++++++ tools/perf/tests/builtin-test.c | 10 + tools/perf/tests/llvm.c | 210 ++++++- tools/perf/tests/llvm.h | 29 + tools/perf/tests/make | 4 +- tools/perf/tests/tests.h | 5 + tools/perf/util/Build | 2 + tools/perf/util/bpf-loader.c | 933 ++++++++++++++++++++++++++++ tools/perf/util/bpf-loader.h | 148 +++++ tools/perf/util/bpf-prologue.c | 443 +++++++++++++ tools/perf/util/bpf-prologue.h | 34 + tools/perf/util/evlist.c | 16 + tools/perf/util/evlist.h | 4 + tools/perf/util/evsel.c | 17 + tools/perf/util/evsel.h | 2 + tools/perf/util/llvm-utils.c | 24 +- tools/perf/util/parse-events.c | 221 ++++++- tools/perf/util/parse-events.h | 15 + tools/perf/util/parse-events.l | 6 + tools/perf/util/parse-events.y | 55 +- tools/perf/util/probe-finder.c | 4 + 36 files changed, 2968 insertions(+), 108 deletions(-) create mode 100644 tools/perf/tests/bpf-script-example.c create mode 100644 tools/perf/tests/bpf-script-test-kbuild.c create mode 100644 tools/perf/tests/bpf-script-test-prologue.c create mode 100644 tools/perf/tests/bpf.c create mode 100644 tools/perf/tests/llvm.h create mode 100644 tools/perf/util/bpf-loader.c create mode 100644 tools/perf/util/bpf-loader.h create mode 100644 tools/perf/util/bpf-prologue.c create mode 100644 tools/perf/util/bpf-prologue.h