This test shows a simplified logic that monitors a subtree. This is
simplified as it doesn't handle all the scenarios, such as:
1) moving a subsubtree into/outof the being monitoring subtree;
2) mount point inside the being monitored subtree
Therefore, this is not to show a way to reliably monitor a subtree.
Instead, this is to test the functionalities of bpf based fastpath.
To really monitor a subtree reliably, we will need more complex logic.
Overview of the logic:
1. fanotify is created for the whole file system (/tmp).
2. dentry of the subtree root is saved in map subtree_root.
3. bpf_is_subdir() is used to check whether a fanotify event happens
inside the subtree. Only events happened in the subtree are passed
to userspace.
4. A bpf map (inode_storage_map) is used to cache result from
bpf_is_subdir().
5. subsubtree moving is not handled. This is because we don't yet have
a good way to walk a subtree from BPF (something similar to d_walk).
Signed-off-by: Song Liu <song@kernel.org>
---
tools/testing/selftests/bpf/bpf_kfuncs.h | 5 +
tools/testing/selftests/bpf/config | 2 +
.../testing/selftests/bpf/prog_tests/fan_fp.c | 264 ++++++++++++++++++
tools/testing/selftests/bpf/progs/fan_fp.c | 154 ++++++++++
4 files changed, 425 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/fan_fp.c
create mode 100644 tools/testing/selftests/bpf/progs/fan_fp.c
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 2eb3483f2fb0..6ccfef9685e1 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -87,4 +87,9 @@ struct dentry;
*/
extern int bpf_get_dentry_xattr(struct dentry *dentry, const char *name,
struct bpf_dynptr *value_ptr) __ksym __weak;
+
+struct fanotify_fastpath_event;
+extern struct inode *bpf_fanotify_data_inode(struct fanotify_fastpath_event *event) __ksym __weak;
+extern void bpf_iput(struct inode *inode) __ksym __weak;
+extern bool bpf_is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) __ksym __weak;
#endif
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 4ca84c8d9116..505327f53f07 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -24,6 +24,8 @@ CONFIG_DEBUG_INFO_BTF=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_DUMMY=y
CONFIG_DYNAMIC_FTRACE=y
+CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_FASTPATH=y
CONFIG_FPROBE=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_FUNCTION_ERROR_INJECTION=y
diff --git a/tools/testing/selftests/bpf/prog_tests/fan_fp.c b/tools/testing/selftests/bpf/prog_tests/fan_fp.c
new file mode 100644
index 000000000000..92929b811282
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fan_fp.c
@@ -0,0 +1,264 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/fanotify.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+
+#include <test_progs.h>
+
+#include "fan_fp.skel.h"
+
+#define TEST_FS "/tmp/"
+#define TEST_DIR "/tmp/fanotify_test/"
+
+static int create_test_subtree(void)
+{
+ int err;
+
+ err = mkdir(TEST_DIR, 0777);
+ if (err && errno != EEXIST)
+ return err;
+
+ return open(TEST_DIR, O_RDONLY);
+}
+
+static int create_fanotify_fd(void)
+{
+ int fanotify_fd, err;
+
+ fanotify_fd = fanotify_init(FAN_CLASS_NOTIF | FAN_REPORT_NAME | FAN_REPORT_DIR_FID,
+ O_RDONLY);
+
+ if (!ASSERT_OK_FD(fanotify_fd, "fanotify_init"))
+ return -1;
+
+ err = fanotify_mark(fanotify_fd, FAN_MARK_ADD | FAN_MARK_FILESYSTEM,
+ FAN_CREATE | FAN_OPEN | FAN_ONDIR | FAN_EVENT_ON_CHILD,
+ AT_FDCWD, TEST_FS);
+ if (!ASSERT_OK(err, "fanotify_mark")) {
+ close(fanotify_fd);
+ return -1;
+ }
+
+ return fanotify_fd;
+}
+
+static int attach_global_fastpath(int fanotify_fd)
+{
+ struct fanotify_fastpath_args args = {
+ .name = "_tmp_test_sub_tree",
+ .version = 1,
+ .flags = 0,
+ };
+
+ if (ioctl(fanotify_fd, FAN_IOC_ADD_FP, &args))
+ return -1;
+
+ return 0;
+}
+
+#define EVENT_BUFFER_SIZE 4096
+struct file_access_result {
+ char name_prefix[16];
+ bool accessed;
+} access_results[3] = {
+ {"aa", false},
+ {"bb", false},
+ {"cc", false},
+};
+
+static void update_access_results(char *name)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(access_results); i++) {
+ if (strcmp(name, access_results[i].name_prefix) == 0)
+ access_results[i].accessed = true;
+ }
+}
+
+static void parse_event(char *buffer, int len)
+{
+ struct fanotify_event_metadata *event =
+ (struct fanotify_event_metadata *) buffer;
+ struct fanotify_event_info_header *info;
+ struct fanotify_event_info_fid *fid;
+ struct file_handle *handle;
+ char *name;
+ int off;
+
+ for (; FAN_EVENT_OK(event, len); event = FAN_EVENT_NEXT(event, len)) {
+ for (off = sizeof(*event) ; off < event->event_len;
+ off += info->len) {
+ info = (struct fanotify_event_info_header *)
+ ((char *) event + off);
+ switch (info->info_type) {
+ case FAN_EVENT_INFO_TYPE_DFID_NAME:
+ fid = (struct fanotify_event_info_fid *) info;
+ handle = (struct file_handle *)&fid->handle;
+ name = (char *)handle + sizeof(*handle) + handle->handle_bytes;
+ update_access_results(name);
+ break;
+ default:
+ break;
+ }
+ }
+ }
+}
+
+static void touch_file(const char *path)
+{
+ int fd;
+
+ fd = open(path, O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666);
+ if (!ASSERT_OK_FD(fd, "open"))
+ goto cleanup;
+ close(fd);
+cleanup:
+ unlink(path);
+}
+
+static void generate_and_test_event(int fanotify_fd, struct fan_fp *skel)
+{
+ char buffer[EVENT_BUFFER_SIZE];
+ int len, err, fd;
+
+ /* Open the dir, so initialize_subdir_root can work */
+ fd = open(TEST_DIR, O_RDONLY);
+ close(fd);
+
+ if (!ASSERT_EQ(skel->bss->initialized, true, "initialized"))
+ goto cleanup;
+
+ /* access /tmp/fanotify_test/aa, this will generate event */
+ touch_file(TEST_DIR "aa");
+
+ /* create /tmp/fanotify_test/subdir, this will get tag from the
+ * parent directory (added in the bpf program on fsnotify_mkdir)
+ */
+ err = mkdir(TEST_DIR "subdir", 0777);
+ ASSERT_OK(err, "mkdir");
+
+ /* access /tmp/fanotify_test/subdir/bb, this will generate event */
+ touch_file(TEST_DIR "subdir/bb");
+
+ /* access /tmp/cc, this will NOT generate event, as the BPF
+ * fastpath filtered this event out. (Because /tmp doesn't have
+ * the tag.)
+ */
+ touch_file(TEST_FS "cc");
+
+ /* read and parse the events */
+ len = read(fanotify_fd, buffer, EVENT_BUFFER_SIZE);
+ if (!ASSERT_GE(len, 0, "read event"))
+ goto cleanup;
+ parse_event(buffer, len);
+
+ /* verify we generated events for aa and bb, but filtered out the
+ * event for cc.
+ */
+ ASSERT_TRUE(access_results[0].accessed, "access aa");
+ ASSERT_TRUE(access_results[1].accessed, "access bb");
+ ASSERT_FALSE(access_results[2].accessed, "access cc");
+
+ /* Each touch_file() generates two events: FAN_CREATE then
+ * FAN_OPEN. The second event will hit cache.
+ * open(TEST_DIR) also hit cache, as we updated it cache for
+ * TEST_DIR from userspace.
+ * Therefore, we expect 4 cache hits: aa, bb, cc, and TEST_DIR.
+ */
+ ASSERT_EQ(skel->bss->cache_hit, 4, "cache_hit");
+
+cleanup:
+ rmdir(TEST_DIR "subdir");
+ rmdir(TEST_DIR);
+}
+
+/* This test shows a simplified logic that monitors a subtree. This is
+ * simplified as it doesn't handle all the scenarios, such as:
+ *
+ * 1) moving a subsubtree into/outof the being monitoring subtree;
+ * 2) mount point inside the being monitored subtree
+ *
+ * Therefore, this is not to show a way to reliably monitor a subtree.
+ * Instead, this is to test the functionalities of bpf based fastpath.
+ *
+ * Overview of the logic:
+ * 1. fanotify is created for the whole file system (/tmp);
+ * 2. A bpf map (inode_storage_map) is used to tag directories to
+ * monitor (starting from /tmp/fanotify_test);
+ * 3. On fsnotify_mkdir, thee tag is propagated to newly created sub
+ * directories (/tmp/fanotify_test/subdir);
+ * 4. The bpf fastpath checks whether the event happens in a directory
+ * with the tag. If yes, the event is sent to user space; otherwise,
+ * the event is dropped.
+ */
+static void test_monitor_subtree(void)
+{
+ struct bpf_link *link;
+ struct fan_fp *skel;
+ int test_root_fd;
+ int zero = 0;
+ int err, fanotify_fd;
+ struct stat st;
+
+ test_root_fd = create_test_subtree();
+
+ if (!ASSERT_OK_FD(test_root_fd, "create_test_subtree"))
+ return;
+
+ err = fstat(test_root_fd, &st);
+ if (!ASSERT_OK(err, "fstat test_root_fd"))
+ goto close_test_root_fd;
+
+ skel = fan_fp__open_and_load();
+
+ if (!ASSERT_OK_PTR(skel, "fan_fp__open_and_load"))
+ goto close_test_root_fd;
+
+ skel->bss->root_ino = st.st_ino;
+
+ /* Add tag to /tmp/fanotify_test/ */
+ err = bpf_map_update_elem(bpf_map__fd(skel->maps.inode_storage_map),
+ &test_root_fd, &zero, BPF_ANY);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ goto destroy_skel;
+ link = bpf_map__attach_struct_ops(skel->maps.bpf_fanotify_fastpath_ops);
+ if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops"))
+ goto destroy_skel;
+
+ fanotify_fd = create_fanotify_fd();
+ if (!ASSERT_OK_FD(fanotify_fd, "create_fanotify_fd"))
+ goto destroy_link;
+
+ err = attach_global_fastpath(fanotify_fd);
+ if (!ASSERT_OK(err, "attach_global_fastpath"))
+ goto close_fanotify_fd;
+
+ generate_and_test_event(fanotify_fd, skel);
+
+close_fanotify_fd:
+ close(fanotify_fd);
+
+destroy_link:
+ bpf_link__destroy(link);
+destroy_skel:
+ fan_fp__destroy(skel);
+
+close_test_root_fd:
+ close(test_root_fd);
+ rmdir(TEST_DIR);
+}
+
+void test_bpf_fanotify_fastpath(void)
+{
+ if (test__start_subtest("subtree"))
+ test_monitor_subtree();
+}
diff --git a/tools/testing/selftests/bpf/progs/fan_fp.c b/tools/testing/selftests/bpf/progs/fan_fp.c
new file mode 100644
index 000000000000..97e7d0b9e644
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fan_fp.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+struct __dentry_kptr_value {
+ struct dentry __kptr * dentry;
+};
+
+/* subdir_root map holds a single dentry pointer to the subtree root.
+ * This pointer is used to call bpf_is_subdir().
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, int);
+ __type(value, struct __dentry_kptr_value);
+ __uint(max_entries, 1);
+} subdir_root SEC(".maps");
+
+/* inode_storage_map serves as cache for bpf_is_subdir(). inode local
+ * storage has O(1) access time. So this is preferred over calling
+ * bpf_is_subdir().
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_INODE_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} inode_storage_map SEC(".maps");
+
+unsigned long root_ino;
+bool initialized;
+
+/* This function initialize map subdir_root. The logic is a bit ungly.
+ * First, user space sets root_ino. Then a fanotify event is triggered.
+ * If the event dentry matches root_ino, we take a reference on the
+ * dentry and save it in subdir_root map. The reference will be freed on
+ * the termination of subdir_root map.
+ */
+static void initialize_subdir_root(struct fanotify_fastpath_event *fp_event)
+{
+ struct __dentry_kptr_value *v;
+ struct dentry *dentry, *old;
+ int zero = 0;
+
+ if (initialized)
+ return;
+
+ dentry = bpf_fanotify_data_dentry(fp_event);
+ if (!dentry)
+ return;
+
+ if (dentry->d_inode->i_ino != root_ino) {
+ bpf_dput(dentry);
+ return;
+ }
+
+ v = bpf_map_lookup_elem(&subdir_root, &zero);
+ if (!v) {
+ bpf_dput(dentry);
+ return;
+ }
+
+ old = bpf_kptr_xchg(&v->dentry, dentry);
+ if (old)
+ bpf_dput(old);
+ initialized = true;
+}
+
+int cache_hit;
+
+/* bpf_fp_handler is sleepable, as it calls bpf_dput() */
+SEC("struct_ops.s")
+int BPF_PROG(bpf_fp_handler,
+ struct fsnotify_group *group,
+ struct fanotify_fastpath_hook *fp_hook,
+ struct fanotify_fastpath_event *fp_event)
+{
+ struct __dentry_kptr_value *v;
+ struct dentry *dentry;
+ int zero = 0;
+ int *value;
+ int ret;
+
+ initialize_subdir_root(fp_event);
+
+ /* Before the subdir_root map is initialized, send all events to
+ * user space.
+ */
+ if (!initialized)
+ return FAN_FP_RET_SEND_TO_USERSPACE;
+
+ dentry = bpf_fanotify_data_dentry(fp_event);
+ if (!dentry)
+ return FAN_FP_RET_SEND_TO_USERSPACE;
+
+ /* If inode_storage_map has cached value, just return it */
+ value = bpf_inode_storage_get(&inode_storage_map, dentry->d_inode, 0, 0);
+ if (value) {
+ bpf_dput(dentry);
+ cache_hit++;
+ return *value;
+ }
+
+ /* Hold rcu read lock for bpf_is_subdir */
+ bpf_rcu_read_lock();
+ v = bpf_map_lookup_elem(&subdir_root, &zero);
+ if (!v || !v->dentry) {
+ /* This shouldn't happen, but we need this to pass
+ * the verifier.
+ */
+ ret = FAN_FP_RET_SEND_TO_USERSPACE;
+ goto out;
+ }
+
+ if (bpf_is_subdir(dentry, v->dentry))
+ ret = FAN_FP_RET_SEND_TO_USERSPACE;
+ else
+ ret = FAN_FP_RET_SKIP_EVENT;
+out:
+ bpf_rcu_read_unlock();
+
+ /* Save current result to the inode_storage_map */
+ value = bpf_inode_storage_get(&inode_storage_map, dentry->d_inode, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (value)
+ *value = ret;
+ bpf_dput(dentry);
+ return ret;
+}
+
+SEC("struct_ops")
+int BPF_PROG(bpf_fp_init, struct fanotify_fastpath_hook *hook, const char *args)
+{
+ return 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fp_free, struct fanotify_fastpath_hook *hook)
+{
+}
+
+SEC(".struct_ops.link")
+struct fanotify_fastpath_ops bpf_fanotify_fastpath_ops = {
+ .fp_handler = (void *)bpf_fp_handler,
+ .fp_init = (void *)bpf_fp_init,
+ .fp_free = (void *)bpf_fp_free,
+ .name = "_tmp_test_sub_tree",
+};
+
+char _license[] SEC("license") = "GPL";
--
2.43.5
On Thu, Nov 14, 2024 at 12:44 AM Song Liu <song@kernel.org> wrote: > > + > + if (bpf_is_subdir(dentry, v->dentry)) > + ret = FAN_FP_RET_SEND_TO_USERSPACE; > + else > + ret = FAN_FP_RET_SKIP_EVENT; It seems to me that all these patches and feature additions to fanotify, new kfuncs, etc are done just to do the above filtering by subdir ? If so, just hard code this logic as an extra flag to fanotify ? So it can filter all events by subdir. bpf programmability makes sense when it needs to express user space policy. Here it's just a filter by subdir. bpf hammer doesn't look like the right tool for this use case.
On Thu, Nov 14, 2024 at 9:14 PM Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote: > > On Thu, Nov 14, 2024 at 12:44 AM Song Liu <song@kernel.org> wrote: > > > > + > > + if (bpf_is_subdir(dentry, v->dentry)) > > + ret = FAN_FP_RET_SEND_TO_USERSPACE; > > + else > > + ret = FAN_FP_RET_SKIP_EVENT; > > It seems to me that all these patches and feature additions > to fanotify, new kfuncs, etc are done just to do the above > filtering by subdir ? > > If so, just hard code this logic as an extra flag to fanotify ? > So it can filter all events by subdir. > bpf programmability makes sense when it needs to express > user space policy. Here it's just a filter by subdir. > bpf hammer doesn't look like the right tool for this use case. Good question. Speaking as someone who has made several attempts to design efficient subtree filtering in fanotify, it is not as easy as it sounds. I recently implemented a method that could be used for "practical" subdir filtering in userspace, not before Jan has questioned if we should go directly to subtree filtering with bpf [1]. This is not the only filter that was proposed for fanotify, where bpf filter came as an alternative proposal [2], but subtree filtering is by far the most wanted filter. The problem with implementing a naive is_subtree() filter in fanotify is the unbounded cost to be paid by every user for every fs access when M such filters are installed deep in the fs tree. Making this more efficient then becomes a matter of trading of memory (inode/path cache size) and performance and depends on the size and depth of the watched filesystem. This engineering decision *is* the userspace policy that can be expressed by a bpf program. As you may know, Linux is lagging behind Win and MacOS w.r.t subtree filtering for fs events. MacOS/FreeBSD took the userspace approach with fseventsd [3]. If you Google "fseventsd", you will get results with "High CPU and Memory Usage" for as far as the browser can scroll. I hope the bpf-aided early subtree filtering technology would be able to reduce some of this overhead to facilitate a better engineering solution, but that remains to be proven... Thanks, Amir. [1] https://lore.kernel.org/linux-fsdevel/20220228140556.ae5rhgqsyzm5djbp@quack3.lan/ [2] https://lore.kernel.org/linux-fsdevel/20200828084603.GA7072@quack2.suse.cz/ [3] https://developer.apple.com/library/archive/documentation/Darwin/Conceptual/FSEvents_ProgGuide/TechnologyOverview/TechnologyOverview.html#//apple_ref/doc/uid/TP40005289-CH3-SW1
On Thu, Nov 14, 2024 at 11:26 PM Amir Goldstein <amir73il@gmail.com> wrote: > > On Thu, Nov 14, 2024 at 9:14 PM Alexei Starovoitov > <alexei.starovoitov@gmail.com> wrote: > > > > On Thu, Nov 14, 2024 at 12:44 AM Song Liu <song@kernel.org> wrote: > > > > > > + > > > + if (bpf_is_subdir(dentry, v->dentry)) > > > + ret = FAN_FP_RET_SEND_TO_USERSPACE; > > > + else > > > + ret = FAN_FP_RET_SKIP_EVENT; > > > > It seems to me that all these patches and feature additions > > to fanotify, new kfuncs, etc are done just to do the above > > filtering by subdir ? > > > > If so, just hard code this logic as an extra flag to fanotify ? > > So it can filter all events by subdir. > > bpf programmability makes sense when it needs to express > > user space policy. Here it's just a filter by subdir. > > bpf hammer doesn't look like the right tool for this use case. > > Good question. > > Speaking as someone who has made several attempts to design > efficient subtree filtering in fanotify, it is not as easy as it sounds. > > I recently implemented a method that could be used for "practical" > subdir filtering in userspace, not before Jan has questioned if we > should go directly to subtree filtering with bpf [1]. > > This is not the only filter that was proposed for fanotify, where bpf > filter came as an alternative proposal [2], but subtree filtering is by far > the most wanted filter. Interesting :) Thanks for the links. Long threads back then. Looks like bpf filtering was proposed 2 and 4 years ago and Song's current attempt is the first real prototype that actually implements what was discussed for so long? Cool. I guess it has legs then. > The problem with implementing a naive is_subtree() filter in fanotify > is the unbounded cost to be paid by every user for every fs access > when M such filters are installed deep in the fs tree. Agree that the concern is real. I just don't see how filtering in bpf vs filtering in the kernel is going to be any different. is_subdir() is fast, so either kernel or bpf prog calling it on every file_open doesn't seem like a big deal. Are you saying that 'naive is_subdir' would call is_subdir M times for every such filter ? I guess it can be optimized. When these M filters are installed the kernel can check whether they're subdirs of each other and filter a subset of M filters with a single is_subdir() call. Same logic can be in either bpf prog or in the kernel. > Making this more efficient then becomes a matter of trading of > memory (inode/path cache size) and performance and depends > on the size and depth of the watched filesystem. > This engineering decision *is* the userspace policy that can be > expressed by a bpf program. > > As you may know, Linux is lagging behind Win and MacOS w.r.t > subtree filtering for fs events. > > MacOS/FreeBSD took the userspace approach with fseventsd [3]. > If you Google "fseventsd", you will get results with "High CPU and > Memory Usage" for as far as the browser can scroll. Yeah. Fun. Looking at your 2 year old attempt it seems the key part was to make sure inodes are not pinned for filtering purpose? How would you call is_subdir() then if parent dentry is not dget() ? Or meaning of 'pinning' is different? > I hope the bpf-aided early subtree filtering technology would be > able to reduce some of this overhead to facilitate a better engineering > solution, but that remains to be proven... Sure. Let's explore this further. > Thanks, > Amir. > > [1] https://lore.kernel.org/linux-fsdevel/20220228140556.ae5rhgqsyzm5djbp@quack3.lan/ > [2] https://lore.kernel.org/linux-fsdevel/20200828084603.GA7072@quack2.suse.cz/ > [3] https://developer.apple.com/library/archive/documentation/Darwin/Conceptual/FSEvents_ProgGuide/TechnologyOverview/TechnologyOverview.html#//apple_ref/doc/uid/TP40005289-CH3-SW1
© 2016 - 2026 Red Hat, Inc.