Merge branch 'bpf: Add kprobe multi link'

Jiri Olsa says:

====================

hi,
this patchset adds new link type BPF_TRACE_KPROBE_MULTI that attaches
kprobe program through fprobe API [1] instroduced by Masami.

The fprobe API allows to attach probe on multiple functions at once very
fast, because it works on top of ftrace. On the other hand this limits
the probe point to the function entry or return.

With bpftrace support I see following attach speed:

  # perf stat --null -r 5 ./src/bpftrace -e 'kprobe:x* { } i:ms:1 { exit(); } '
  Attaching 2 probes...
  Attaching 3342 functions
  ...

  1.4960 +- 0.0285 seconds time elapsed  ( +-  1.91% )

v3 changes:
  - based on latest fprobe post from Masami [2]
  - add acks
  - add extra comment to kprobe_multi_link_handler wrt entry ip setup [Masami]
  - keep swap_words_64 static and swap values directly in
    bpf_kprobe_multi_cookie_swap [Andrii]
  - rearrange locking/migrate setup in kprobe_multi_link_prog_run [Andrii]
  - move uapi fields [Andrii]
  - add bpf_program__attach_kprobe_multi_opts function [Andrii]
  - many small test changes [Andrii]
  - added tests for bpf_program__attach_kprobe_multi_opts
  - make kallsyms_lookup_name check for empty string [Andrii]

v2 changes:
  - based on latest fprobe changes [1]
  - renaming the uapi interface to kprobe multi
  - adding support for sort_r to pass user pointer for swap functions
    and using that in cookie support to keep just single functions array
  - moving new link to kernel/trace/bpf_trace.c file
  - using single fprobe callback function for entry and exit
  - using kvzalloc, libbpf_ensure_mem functions
  - adding new k[ret]probe.multi sections instead of using current kprobe
  - used glob_match from test_progs.c, added '?' matching
  - move bpf_get_func_ip verifier inline change to seprate change
  - couple of other minor fixes

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

thanks,
jirka

[1] https://lore.kernel.org/bpf/164458044634.586276.3261555265565111183.stgit@devnote2/
[2] https://lore.kernel.org/bpf/164735281449.1084943.12438881786173547153.stgit@devnote2/
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 385 insertions, 8 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9beb585be5a6..cdaa1152436a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -32,6 +32,7 @@
 #include <linux/bpf-netns.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
+#include <linux/trace_events.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -3022,6 +3023,11 @@ out_put_file:
 	fput(perf_file);
 	return err;
 }
+#else
+static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_PERF_EVENTS */
 
 #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
@@ -4255,7 +4261,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
 	return -EINVAL;
 }
 
-#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
+#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies
 static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	enum bpf_prog_type ptype;
@@ -4279,7 +4285,6 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		ret = tracing_bpf_link_attach(attr, uattr, prog);
 		goto out;
 	case BPF_PROG_TYPE_PERF_EVENT:
-	case BPF_PROG_TYPE_KPROBE:
 	case BPF_PROG_TYPE_TRACEPOINT:
 		if (attr->link_create.attach_type != BPF_PERF_EVENT) {
 			ret = -EINVAL;
@@ -4287,6 +4292,14 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		}
 		ptype = prog->type;
 		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;
+		}
+		ptype = prog->type;
+		break;
 	default:
 		ptype = attach_type_to_prog_type(attr->link_create.attach_type);
 		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
@@ -4318,13 +4331,16 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		ret = bpf_xdp_link_attach(attr, prog);
 		break;
 #endif
-#ifdef CONFIG_PERF_EVENTS
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_TRACEPOINT:
-	case BPF_PROG_TYPE_KPROBE:
 		ret = bpf_perf_link_attach(attr, prog);
 		break;
-#endif
+	case BPF_PROG_TYPE_KPROBE:
+		if (attr->link_create.attach_type == BPF_PERF_EVENT)
+			ret = bpf_perf_link_attach(attr, prog);
+		else
+			ret = bpf_kprobe_multi_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cf92f9c01556..0287176bfe9a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13678,7 +13678,7 @@ patch_map_ops_generic:
 			continue;
 		}
 
-		/* Implement bpf_get_func_ip inline. */
+		/* Implement tracing bpf_get_func_ip inline. */
 		if (prog_type == BPF_PROG_TYPE_TRACING &&
 		    insn->imm == BPF_FUNC_get_func_ip) {
 			/* Load IP address from ctx - 16 */
@@ -13693,6 +13693,25 @@ patch_map_ops_generic:
 			continue;
 		}
 
+#ifdef CONFIG_X86
+		/* Implement kprobe_multi bpf_get_func_ip inline. */
+		if (prog_type == BPF_PROG_TYPE_KPROBE &&
+		    eatype == BPF_TRACE_KPROBE_MULTI &&
+		    insn->imm == BPF_FUNC_get_func_ip) {
+			/* Load IP address from ctx (struct pt_regs) ip */
+			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+						  offsetof(struct pt_regs, ip));
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
+			if (!new_prog)
+				return -ENOMEM;
+
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+#endif
+
 patch_call_imm:
 		fn = env->ops->get_func_proto(insn->imm, env->prog);
 		/* all functions that have prototype and verifier allowed
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 951c93216fc4..79f2eb617a62 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -212,6 +212,10 @@ unsigned long kallsyms_lookup_name(const char *name)
 	unsigned long i;
 	unsigned int off;
 
+	/* Skip the search for empty string. */
+	if (!*name)
+		return 0;
+
 	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
 		off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a2024ba32a20..9a7b6be655e4 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,9 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 #include <linux/bpf_lsm.h>
+#include <linux/fprobe.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -77,6 +80,7 @@ u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
 				  u64 flags, const struct btf **btf,
 				  s32 *btf_id);
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx, u64 ip);
 
 /**
  * trace_call_bpf - invoke BPF program
@@ -1036,6 +1040,31 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_func_ip_kprobe_multi, struct pt_regs *, regs)
+{
+	/* This helper call is inlined by verifier on x86. */
+	return instruction_pointer(regs);
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = {
+	.func		= bpf_get_func_ip_kprobe_multi,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs)
+{
+	return bpf_kprobe_multi_cookie(current->bpf_ctx, instruction_pointer(regs));
+}
+
+static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = {
+	.func		= bpf_get_attach_cookie_kprobe_multi,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx)
 {
 	struct bpf_trace_run_ctx *run_ctx;
@@ -1279,9 +1308,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_override_return_proto;
 #endif
 	case BPF_FUNC_get_func_ip:
-		return &bpf_get_func_ip_proto_kprobe;
+		return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
+			&bpf_get_func_ip_proto_kprobe_multi :
+			&bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
-		return &bpf_get_attach_cookie_proto_trace;
+		return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ?
+			&bpf_get_attach_cookie_proto_kmulti :
+			&bpf_get_attach_cookie_proto_trace;
 	default:
 		return bpf_tracing_func_proto(func_id, prog);
 	}
@@ -2181,3 +2214,308 @@ static int __init bpf_event_init(void)
 
 fs_initcall(bpf_event_init);
 #endif /* CONFIG_MODULES */
+
+#ifdef CONFIG_FPROBE
+struct bpf_kprobe_multi_link {
+	struct bpf_link link;
+	struct fprobe fp;
+	unsigned long *addrs;
+	/*
+	 * The run_ctx here is used to get struct bpf_kprobe_multi_link in
+	 * get_attach_cookie helper, so it can't be used to store data.
+	 */
+	struct bpf_run_ctx run_ctx;
+	u64 *cookies;
+	u32 cnt;
+};
+
+static void bpf_kprobe_multi_link_release(struct bpf_link *link)
+{
+	struct bpf_kprobe_multi_link *kmulti_link;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	unregister_fprobe(&kmulti_link->fp);
+}
+
+static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_kprobe_multi_link *kmulti_link;
+
+	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	kvfree(kmulti_link->addrs);
+	kvfree(kmulti_link->cookies);
+	kfree(kmulti_link);
+}
+
+static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
+	.release = bpf_kprobe_multi_link_release,
+	.dealloc = bpf_kprobe_multi_link_dealloc,
+};
+
+static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv)
+{
+	const struct bpf_kprobe_multi_link *link = priv;
+	unsigned long *addr_a = a, *addr_b = b;
+	u64 *cookie_a, *cookie_b;
+	unsigned long tmp1;
+	u64 tmp2;
+
+	cookie_a = link->cookies + (addr_a - link->addrs);
+	cookie_b = link->cookies + (addr_b - link->addrs);
+
+	/* swap addr_a/addr_b and cookie_a/cookie_b values */
+	tmp1 = *addr_a; *addr_a = *addr_b; *addr_b = tmp1;
+	tmp2 = *cookie_a; *cookie_a = *cookie_b; *cookie_b = tmp2;
+}
+
+static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b)
+{
+	const unsigned long *addr_a = a, *addr_b = b;
+
+	if (*addr_a == *addr_b)
+		return 0;
+	return *addr_a < *addr_b ? -1 : 1;
+}
+
+static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv)
+{
+	return __bpf_kprobe_multi_cookie_cmp(a, b);
+}
+
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx, u64 ip)
+{
+	struct bpf_kprobe_multi_link *link;
+	unsigned long *addr;
+	u64 *cookie;
+
+	if (WARN_ON_ONCE(!ctx))
+		return 0;
+	link = container_of(ctx, struct bpf_kprobe_multi_link, run_ctx);
+	if (!link->cookies)
+		return 0;
+	addr = bsearch(&ip, link->addrs, link->cnt, sizeof(ip),
+		       __bpf_kprobe_multi_cookie_cmp);
+	if (!addr)
+		return 0;
+	cookie = link->cookies + (addr - link->addrs);
+	return *cookie;
+}
+
+static int
+kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
+			   struct pt_regs *regs)
+{
+	struct bpf_run_ctx *old_run_ctx;
+	int err;
+
+	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+		err = 0;
+		goto out;
+	}
+
+	migrate_disable();
+	rcu_read_lock();
+	old_run_ctx = bpf_set_run_ctx(&link->run_ctx);
+	err = bpf_prog_run(link->link.prog, regs);
+	bpf_reset_run_ctx(old_run_ctx);
+	rcu_read_unlock();
+	migrate_enable();
+
+ out:
+	__this_cpu_dec(bpf_prog_active);
+	return err;
+}
+
+static void
+kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
+			  struct pt_regs *regs)
+{
+	unsigned long saved_ip = instruction_pointer(regs);
+	struct bpf_kprobe_multi_link *link;
+
+	/*
+	 * Because fprobe's regs->ip is set to the next instruction of
+	 * dynamic-ftrace instruction, correct entry ip must be set, so
+	 * that the bpf program can access entry address via regs as same
+	 * as kprobes.
+	 *
+	 * Both kprobe and kretprobe see the entry ip of traced function
+	 * as instruction pointer.
+	 */
+	instruction_pointer_set(regs, entry_ip);
+
+	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
+	kprobe_multi_link_prog_run(link, regs);
+
+	instruction_pointer_set(regs, saved_ip);
+}
+
+static int
+kprobe_multi_resolve_syms(const void *usyms, u32 cnt,
+			  unsigned long *addrs)
+{
+	unsigned long addr, size;
+	const char **syms;
+	int err = -ENOMEM;
+	unsigned int i;
+	char *func;
+
+	size = cnt * sizeof(*syms);
+	syms = kvzalloc(size, GFP_KERNEL);
+	if (!syms)
+		return -ENOMEM;
+
+	func = kmalloc(KSYM_NAME_LEN, GFP_KERNEL);
+	if (!func)
+		goto error;
+
+	if (copy_from_user(syms, usyms, size)) {
+		err = -EFAULT;
+		goto error;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		err = strncpy_from_user(func, syms[i], KSYM_NAME_LEN);
+		if (err == KSYM_NAME_LEN)
+			err = -E2BIG;
+		if (err < 0)
+			goto error;
+		err = -EINVAL;
+		addr = kallsyms_lookup_name(func);
+		if (!addr)
+			goto error;
+		if (!kallsyms_lookup_size_offset(addr, &size, NULL))
+			goto error;
+		addr = ftrace_location_range(addr, addr + size - 1);
+		if (!addr)
+			goto error;
+		addrs[i] = addr;
+	}
+
+	err = 0;
+error:
+	kvfree(syms);
+	kfree(func);
+	return err;
+}
+
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_kprobe_multi_link *link = NULL;
+	struct bpf_link_primer link_primer;
+	void __user *ucookies;
+	unsigned long *addrs;
+	u32 flags, cnt, size;
+	void __user *uaddrs;
+	u64 *cookies = NULL;
+	void __user *usyms;
+	int err;
+
+	/* no support for 32bit archs yet */
+	if (sizeof(u64) != sizeof(void *))
+		return -EOPNOTSUPP;
+
+	if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI)
+		return -EINVAL;
+
+	flags = attr->link_create.kprobe_multi.flags;
+	if (flags & ~BPF_F_KPROBE_MULTI_RETURN)
+		return -EINVAL;
+
+	uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs);
+	usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms);
+	if (!!uaddrs == !!usyms)
+		return -EINVAL;
+
+	cnt = attr->link_create.kprobe_multi.cnt;
+	if (!cnt)
+		return -EINVAL;
+
+	size = cnt * sizeof(*addrs);
+	addrs = kvmalloc(size, GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+
+	if (uaddrs) {
+		if (copy_from_user(addrs, uaddrs, size)) {
+			err = -EFAULT;
+			goto error;
+		}
+	} else {
+		err = kprobe_multi_resolve_syms(usyms, cnt, addrs);
+		if (err)
+			goto error;
+	}
+
+	ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
+	if (ucookies) {
+		cookies = kvmalloc(size, GFP_KERNEL);
+		if (!cookies) {
+			err = -ENOMEM;
+			goto error;
+		}
+		if (copy_from_user(cookies, ucookies, size)) {
+			err = -EFAULT;
+			goto error;
+		}
+	}
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI,
+		      &bpf_kprobe_multi_link_lops, prog);
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto error;
+
+	if (flags & BPF_F_KPROBE_MULTI_RETURN)
+		link->fp.exit_handler = kprobe_multi_link_handler;
+	else
+		link->fp.entry_handler = kprobe_multi_link_handler;
+
+	link->addrs = addrs;
+	link->cookies = cookies;
+	link->cnt = cnt;
+
+	if (cookies) {
+		/*
+		 * Sorting addresses will trigger sorting cookies as well
+		 * (check bpf_kprobe_multi_cookie_swap). This way we can
+		 * find cookie based on the address in bpf_get_attach_cookie
+		 * helper.
+		 */
+		sort_r(addrs, cnt, sizeof(*addrs),
+		       bpf_kprobe_multi_cookie_cmp,
+		       bpf_kprobe_multi_cookie_swap,
+		       link);
+	}
+
+	err = register_fprobe_ips(&link->fp, addrs, cnt);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		return err;
+	}
+
+	return bpf_link_settle(&link_primer);
+
+error:
+	kfree(link);
+	kvfree(addrs);
+	kvfree(cookies);
+	return err;
+}
+#else /* !CONFIG_FPROBE */
+int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
+static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx, u64 ip)
+{
+	return 0;
+}
+#endif