Track processes properly for perf record --off-cpu (v2)

.github/workflows/test.yml

@@ -0,0 +1,81 @@
+name: bpf-ci
+
+on:
+  pull_request:
+
+concurrency: 
+  group: ci-test-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  VM_Test:
+    runs-on: ${{ matrix.runs_on }}
+    name: Kernel ${{ matrix.kernel }} on ${{ matrix.runs_on[0] }} with ${{ matrix.toolchain }}
+    timeout-minutes: 100
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - kernel: 'LATEST'
+            runs_on: [ubuntu-latest, self-hosted]
+            arch: 'x86_64'
+            toolchain: 'gcc'
+          - kernel: 'LATEST'
+            runs_on: [ubuntu-latest, self-hosted]
+            arch: 'x86_64'
+            toolchain: 'llvm-16'
+          - kernel: 'LATEST'
+            runs_on: [z15, self-hosted]
+            arch: 's390x'
+            toolchain: 'gcc'
+    env:
+      KERNEL: LATEST
+      REPO_ROOT: ${{ github.workspace }}
+      REPO_PATH: ""
+    steps:
+      - uses: actions/checkout@v2
+      - if: ${{ github.repository == 'kernel-patches/vmtest' }}
+        name: Download bpf-next tree
+        uses: libbpf/ci/get-linux-source@master
+        with:
+          dest: '.kernel'
+      - if: ${{ github.repository == 'kernel-patches/vmtest' }}
+        name: Move linux source in place
+        shell: bash
+        run: |
+          rm -rf .kernel/.git
+          cp -rf .kernel/. .
+          rm -rf .kernel
+      - uses: libbpf/ci/patch-kernel@master
+        with:
+          patches-root: '${{ github.workspace }}/travis-ci/diffs'
+          repo-root: '${{ github.workspace }}'
+      - name: Setup build environment
+        uses: libbpf/ci/setup-build-env@master
+      - name: Build kernel image
+        uses: libbpf/ci/build-linux@master
+        with:
+          arch: ${{ matrix.arch }}
+          toolchain: ${{ matrix.toolchain }}
+      - name: Build selftests
+        uses: libbpf/ci/build-selftests@master
+        with:
+          vmlinux_btf: ${{ github.workspace }}/vmlinux
+          toolchain: ${{ matrix.toolchain }}
+      - name: Build samples
+        uses: libbpf/ci/build-samples@master
+        with:
+          vmlinux_btf: ${{ github.workspace }}/vmlinux
+          toolchain: ${{ matrix.toolchain }}
+      - name: Prepare rootfs
+        uses: libbpf/ci/prepare-rootfs@master
+        with:
+          project-name: 'libbpf'
+          arch: ${{ matrix.arch }}
+          kernel-root: '.'
+      - name: Run selftests
+        uses: libbpf/ci/run-qemu@master
+        with:
+          arch: ${{ matrix.arch}}
+          img: '/tmp/root.img'
+          vmlinuz: '${{ github.workspace }}/vmlinuz'

README

@@ -1,18 +0,0 @@
-Linux kernel
-============
-
-There are several guides for kernel developers and users. These guides can
-be rendered in a number of formats, like HTML and PDF. Please read
-Documentation/admin-guide/README.rst first.
-
-In order to build the documentation, use ``make htmldocs`` or
-``make pdfdocs``.  The formatted documentation can also be read online at:
-
-    https://www.kernel.org/doc/html/latest/
-
-There are various text files in the Documentation/ subdirectory,
-several of them using the Restructured Text markup notation.
-
-Please read the Documentation/process/changes.rst file, as it contains the
-requirements for building and running the kernel, and information about
-the problems which may result by upgrading your kernel.

tools/perf/tests/shell/record_offcpu.sh

@@ -19,20 +19,26 @@ trap_cleanup() {
 }
 trap trap_cleanup exit term int
 
-test_offcpu() {
-  echo "Basic off-cpu test"
+test_offcpu_priv() {
+  echo "Checking off-cpu privilege"
+
   if [ `id -u` != 0 ]
   then
-    echo "Basic off-cpu test [Skipped permission]"
+    echo "off-cpu test [Skipped permission]"
     err=2
     return
   fi
-  if perf record --off-cpu -o ${perfdata} --quiet true 2>&1 | grep BUILD_BPF_SKEL
+  if perf record --off-cpu -o /dev/null --quiet true 2>&1 | grep BUILD_BPF_SKEL
   then
-    echo "Basic off-cpu test [Skipped missing BPF support]"
+    echo "off-cpu test [Skipped missing BPF support]"
     err=2
     return
   fi
+}
+
+test_offcpu_basic() {
+  echo "Basic off-cpu test"
+
   if ! perf record --off-cpu -e dummy -o ${perfdata} sleep 1 2> /dev/null
   then
     echo "Basic off-cpu test [Failed record]"
@@ -41,7 +47,7 @@ test_offcpu() {
   fi
   if ! perf evlist -i ${perfdata} | grep -q "offcpu-time"
   then
-    echo "Basic off-cpu test [Failed record]"
+    echo "Basic off-cpu test [Failed no event]"
     err=1
     return
   fi
@@ -54,7 +60,44 @@ test_offcpu() {
   echo "Basic off-cpu test [Success]"
 }
 
-test_offcpu
+test_offcpu_child() {
+  echo "Child task off-cpu test"
+
+  # perf bench sched messaging creates 400 processes
+  if ! perf record --off-cpu -e dummy -o ${perfdata} -- \
+    perf bench sched messaging -g 10 > /dev/null 2&>1
+  then
+    echo "Child task off-cpu test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf evlist -i ${perfdata} | grep -q "offcpu-time"
+  then
+    echo "Child task off-cpu test [Failed no event]"
+    err=1
+    return
+  fi
+  # each process waits for read and write, so it should be more than 800 events
+  if ! perf report -i ${perfdata} -s comm -q -n -t ';' --percent-limit=90 | \
+    awk -F ";" '{ if (NF > 3 && int($3) < 800) exit 1; }'
+  then
+    echo "Child task off-cpu test [Failed invalid output]"
+    err=1
+    return
+  fi
+  echo "Child task off-cpu test [Success]"
+}
+
+
+test_offcpu_priv
+
+if [ $err = 0 ]; then
+  test_offcpu_basic
+fi
+
+if [ $err = 0 ]; then
+  test_offcpu_child
+fi
 
 cleanup
 exit $err

tools/perf/util/bpf_off_cpu.c

@@ -11,11 +11,13 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/cgroup.h"
+#include "util/strlist.h"
 #include <bpf/bpf.h>
 
 #include "bpf_skel/off_cpu.skel.h"
 
 #define MAX_STACKS  32
+#define MAX_PROC  4096
 /* we don't need actual timestamp, just want to put the samples at last */
 #define OFF_CPU_TIMESTAMP  (~0ull << 32)
 
@@ -78,6 +80,7 @@ static void off_cpu_start(void *arg)
 		u8 val = 1;
 
 		skel->bss->has_task = 1;
+		skel->bss->uses_tgid = 1;
 		fd = bpf_map__fd(skel->maps.task_filter);
 		pid = perf_thread_map__pid(evlist->core.threads, 0);
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
@@ -124,6 +127,8 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target,
 {
 	int err, fd, i;
 	int ncpus = 1, ntasks = 1, ncgrps = 1;
+	struct strlist *pid_slist = NULL;
+	struct str_node *pos;
 
 	if (off_cpu_config(evlist) < 0) {
 		pr_err("Failed to config off-cpu BPF event\n");
@@ -142,9 +147,34 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target,
 		bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
 	}
 
-	if (target__has_task(target)) {
+	if (target->pid) {
+		pid_slist = strlist__new(target->pid, NULL);
+		if (!pid_slist) {
+			pr_err("Failed to create a strlist for pid\n");
+			return -1;
+		}
+
+		ntasks = 0;
+		strlist__for_each_entry(pos, pid_slist) {
+			char *end_ptr;
+			int pid = strtol(pos->s, &end_ptr, 10);
+
+			if (pid == INT_MIN || pid == INT_MAX ||
+			    (*end_ptr != '\0' && *end_ptr != ','))
+				continue;
+
+			ntasks++;
+		}
+
+		if (ntasks < MAX_PROC)
+			ntasks = MAX_PROC;
+
+		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+	} else if (target__has_task(target)) {
 		ntasks = perf_thread_map__nr(evlist->core.threads);
 		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+	} else if (target__none(target)) {
+		bpf_map__set_max_entries(skel->maps.task_filter, MAX_PROC);
 	}
 
 	if (evlist__first(evlist)->cgrp) {
@@ -184,7 +214,26 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target,
 		}
 	}
 
-	if (target__has_task(target)) {
+	if (target->pid) {
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		skel->bss->uses_tgid = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+
+		strlist__for_each_entry(pos, pid_slist) {
+			char *end_ptr;
+			u32 tgid;
+			int pid = strtol(pos->s, &end_ptr, 10);
+
+			if (pid == INT_MIN || pid == INT_MAX ||
+			    (*end_ptr != '\0' && *end_ptr != ','))
+				continue;
+
+			tgid = pid;
+			bpf_map_update_elem(fd, &tgid, &val, BPF_ANY);
+		}
+	} else if (target__has_task(target)) {
 		u32 pid;
 		u8 val = 1;
 

tools/perf/util/bpf_skel/off_cpu.bpf.c

@@ -12,6 +12,9 @@
 #define TASK_INTERRUPTIBLE	0x0001
 #define TASK_UNINTERRUPTIBLE	0x0002
 
+/* create a new thread */
+#define CLONE_THREAD  0x10000
+
 #define MAX_STACKS   32
 #define MAX_ENTRIES  102400
 
@@ -85,6 +88,7 @@ int enabled = 0;
 int has_cpu = 0;
 int has_task = 0;
 int has_cgroup = 0;
+int uses_tgid = 0;
 
 const volatile bool has_prev_state = false;
 const volatile bool needs_cgroup = false;
@@ -144,7 +148,12 @@ static inline int can_record(struct task_struct *t, int state)
 
 	if (has_task) {
 		__u8 *ok;
-		__u32 pid = t->pid;
+		__u32 pid;
+
+		if (uses_tgid)
+			pid = t->tgid;
+		else
+			pid = t->pid;
 
 		ok = bpf_map_lookup_elem(&task_filter, &pid);
 		if (!ok)
@@ -214,6 +223,33 @@ static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 	return 0;
 }
 
+SEC("tp_btf/task_newtask")
+int on_newtask(u64 *ctx)
+{
+	struct task_struct *task;
+	u64 clone_flags;
+	u32 pid;
+	u8 val = 1;
+
+	if (!uses_tgid)
+		return 0;
+
+	task = (struct task_struct *)bpf_get_current_task();
+
+	pid = BPF_CORE_READ(task, tgid);
+	if (!bpf_map_lookup_elem(&task_filter, &pid))
+		return 0;
+
+	task = (struct task_struct *)ctx[0];
+	clone_flags = ctx[1];
+
+	pid = task->tgid;
+	if (!(clone_flags & CLONE_THREAD))
+		bpf_map_update_elem(&task_filter, &pid, &val, BPF_NOEXIST);
+
+	return 0;
+}
+
 SEC("tp_btf/sched_switch")
 int on_switch(u64 *ctx)
 {