Merge branch 'bpf-add-multi-uprobe-link'

Jiri Olsa says:

====================
bpf: Add multi uprobe link

hi,
this patchset is adding support to attach multiple uprobes and usdt probes
through new uprobe_multi link.

The current uprobe is attached through the perf event and attaching many
uprobes takes a lot of time because of that.

The main reason is that we need to install perf event for each probed function
and profile shows perf event installation (perf_install_in_context) as culprit.

The new uprobe_multi link just creates raw uprobes and attaches the bpf
program to them without perf event being involved.

In addition to being faster we also save file descriptors. For the current
uprobe attach we use extra perf event fd for each probed function. The new
link just need one fd that covers all the functions we are attaching to.

v7 changes:
  - fixed task release on error path and re-org the error
    path to be more straightforward [Yonghong]
  - re-organized uprobe_prog_run locking to follow general pattern
    and removed might_fault check as it's not needed in uprobe/task
    context [Yonghong]

There's support for bpftrace [2] and tetragon [1].

Also available at:
  https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  uprobe_multi

thanks,
jirka

[1] cilium/tetragon#936
[2] bpftrace/bpftrace@master...olsajiri:bpftrace:uprobe_multi
[3] https://lore.kernel.org/bpf/[email protected]/
---
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: Alexei Starovoitov

include/linux/trace_events.h

@@ -752,6 +752,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
 			    u64 *probe_offset, u64 *probe_addr);
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 #else
 static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
@@ -798,6 +799,11 @@ bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	return -EOPNOTSUPP;
 }
+static inline int
+bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 enum {

include/uapi/linux/bpf.h

@@ -1039,6 +1039,7 @@ enum bpf_attach_type {
 	BPF_NETFILTER,
 	BPF_TCX_INGRESS,
 	BPF_TCX_EGRESS,
+	BPF_TRACE_UPROBE_MULTI,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1057,6 +1058,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
 	BPF_LINK_TYPE_TCX = 11,
+	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1186,7 +1188,16 @@ enum bpf_perf_event_type {
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
-#define BPF_F_KPROBE_MULTI_RETURN	(1U << 0)
+enum {
+	BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.uprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
+ */
+enum {
+	BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+};
 
 /* link_create.netfilter.flags used in LINK_CREATE command for
  * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
@@ -1624,6 +1635,15 @@ union bpf_attr {
 				};
 				__u64		expected_revision;
 			} tcx;
+			struct {
+				__aligned_u64	path;
+				__aligned_u64	offsets;
+				__aligned_u64	ref_ctr_offsets;
+				__aligned_u64	cookies;
+				__u32		cnt;
+				__u32		flags;
+				__u32		pid;
+			} uprobe_multi;
 		};
 	} link_create;
 

kernel/bpf/syscall.c

@@ -2815,10 +2815,12 @@ static void bpf_link_free_id(int id)
 
 /* Clean up bpf_link and corresponding anon_inode file and FD. After
  * anon_inode is created, bpf_link can't be just kfree()'d due to deferred
- * anon_inode's release() call. This helper marksbpf_link as
+ * anon_inode's release() call. This helper marks bpf_link as
  * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt
  * is not decremented, it's the responsibility of a calling code that failed
  * to complete bpf_link initialization.
+ * This helper eventually calls link's dealloc callback, but does not call
+ * link's release callback.
  */
 void bpf_link_cleanup(struct bpf_link_primer *primer)
 {
@@ -3655,34 +3657,6 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	return fd;
 }
 
-static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
-					     enum bpf_attach_type attach_type)
-{
-	switch (prog->type) {
-	case BPF_PROG_TYPE_CGROUP_SOCK:
-	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
-	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
-	case BPF_PROG_TYPE_SK_LOOKUP:
-		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
-	case BPF_PROG_TYPE_CGROUP_SKB:
-		if (!capable(CAP_NET_ADMIN))
-			/* cg-skb progs can be loaded by unpriv user.
-			 * check permissions at attach time.
-			 */
-			return -EPERM;
-		return prog->enforce_expected_attach_type &&
-			prog->expected_attach_type != attach_type ?
-			-EINVAL : 0;
-	case BPF_PROG_TYPE_KPROBE:
-		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
-		    attach_type != BPF_TRACE_KPROBE_MULTI)
-			return -EINVAL;
-		return 0;
-	default:
-		return 0;
-	}
-}
-
 static enum bpf_prog_type
 attach_type_to_prog_type(enum bpf_attach_type attach_type)
 {
@@ -3749,6 +3723,62 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	}
 }
 
+static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
+					     enum bpf_attach_type attach_type)
+{
+	enum bpf_prog_type ptype;
+
+	switch (prog->type) {
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		if (!capable(CAP_NET_ADMIN))
+			/* cg-skb progs can be loaded by unpriv user.
+			 * check permissions at attach time.
+			 */
+			return -EPERM;
+		return prog->enforce_expected_attach_type &&
+			prog->expected_attach_type != attach_type ?
+			-EINVAL : 0;
+	case BPF_PROG_TYPE_EXT:
+		return 0;
+	case BPF_PROG_TYPE_NETFILTER:
+		if (attach_type != BPF_NETFILTER)
+			return -EINVAL;
+		return 0;
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_TRACEPOINT:
+		if (attach_type != BPF_PERF_EVENT)
+			return -EINVAL;
+		return 0;
+	case BPF_PROG_TYPE_KPROBE:
+		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
+		    attach_type != BPF_TRACE_KPROBE_MULTI)
+			return -EINVAL;
+		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
+		    attach_type != BPF_TRACE_UPROBE_MULTI)
+			return -EINVAL;
+		if (attach_type != BPF_PERF_EVENT &&
+		    attach_type != BPF_TRACE_KPROBE_MULTI &&
+		    attach_type != BPF_TRACE_UPROBE_MULTI)
+			return -EINVAL;
+		return 0;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		if (attach_type != BPF_TCX_INGRESS &&
+		    attach_type != BPF_TCX_EGRESS)
+			return -EINVAL;
+		return 0;
+	default:
+		ptype = attach_type_to_prog_type(attach_type);
+		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type)
+			return -EINVAL;
+		return 0;
+	}
+}
+
 #define BPF_PROG_ATTACH_LAST_FIELD expected_revision
 
 #define BPF_F_ATTACH_MASK_BASE	\
@@ -4852,10 +4882,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	return err;
 }
 
-#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies
+#define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid
 static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
-	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
 	int ret;
 
@@ -4874,45 +4903,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	if (ret)
 		goto out;
 
-	switch (prog->type) {
-	case BPF_PROG_TYPE_EXT:
-		break;
-	case BPF_PROG_TYPE_NETFILTER:
-		if (attr->link_create.attach_type != BPF_NETFILTER) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	case BPF_PROG_TYPE_PERF_EVENT:
-	case BPF_PROG_TYPE_TRACEPOINT:
-		if (attr->link_create.attach_type != BPF_PERF_EVENT) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	case BPF_PROG_TYPE_KPROBE:
-		if (attr->link_create.attach_type != BPF_PERF_EVENT &&
-		    attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	case BPF_PROG_TYPE_SCHED_CLS:
-		if (attr->link_create.attach_type != BPF_TCX_INGRESS &&
-		    attr->link_create.attach_type != BPF_TCX_EGRESS) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	default:
-		ptype = attach_type_to_prog_type(attr->link_create.attach_type);
-		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
-			ret = -EINVAL;
-			goto out;
-		}
-		break;
-	}
-
 	switch (prog->type) {
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -4969,8 +4959,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_KPROBE:
 		if (attr->link_create.attach_type == BPF_PERF_EVENT)
 			ret = bpf_perf_link_attach(attr, prog);
-		else
+		else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI)
 			ret = bpf_kprobe_multi_link_attach(attr, prog);
+		else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI)
+			ret = bpf_uprobe_multi_link_attach(attr, prog);
 		break;
 	default:
 		ret = -EINVAL;