bpf: make jited programs visible in traces

Long standing issue with JITed programs is that stack traces from
function tracing check whether a given address is kernel code
through {__,}kernel_text_address(), which checks for code in core
kernel, modules and dynamically allocated ftrace trampolines. But
what is still missing is BPF JITed programs (interpreted programs
are not an issue as __bpf_prog_run() will be attributed to them),
thus when a stack trace is triggered, the code walking the stack
won't see any of the JITed ones. The same for address correlation
done from user space via reading /proc/kallsyms. This is read by
tools like perf, but the latter is also useful for permanent live
tracing with eBPF itself in combination with stack maps when other
eBPF types are part of the callchain. See offwaketime example on
dumping stack from a map.

This work tries to tackle that issue by making the addresses and
symbols known to the kernel. The lookup from *kernel_text_address()
is implemented through a latched RB tree that can be read under
RCU in fast-path that is also shared for symbol/size/offset lookup
for a specific given address in kallsyms. The slow-path iteration
through all symbols in the seq file done via RCU list, which holds
a tiny fraction of all exported ksyms, usually below 0.1 percent.
Function symbols are exported as bpf_prog_<tag>, in order to aide
debugging and attribution. This facility is currently enabled for
root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening
is active in any mode. The rationale behind this is that still a lot
of systems ship with world read permissions on kallsyms thus addresses
should not get suddenly exposed for them. If that situation gets
much better in future, we always have the option to change the
default on this. Likewise, unprivileged programs are not allowed
to add entries there either, but that is less of a concern as most
such programs types relevant in this context are for root-only anyway.
If enabled, call graphs and stack traces will then show a correct
attribution; one example is illustrated below, where the trace is
now visible in tooling such as perf script --kallsyms=/proc/kallsyms
and friends.

Before:

  7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux)
         f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so)

After:

  7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux)
  [...]
  7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux)
         f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so)

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 225 insertions, 0 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2831ba1e71c1..f45827e205d3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -28,6 +28,9 @@
 #include <linux/moduleloader.h>
 #include <linux/bpf.h>
 #include <linux/frame.h>
+#include <linux/rbtree_latch.h>
+#include <linux/kallsyms.h>
+#include <linux/rcupdate.h>
 
 #include <asm/unaligned.h>
 
@@ -95,6 +98,8 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 	fp->aux = aux;
 	fp->aux->prog = fp;
 
+	INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
+
 	return fp;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_alloc);
@@ -290,6 +295,206 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 }
 
 #ifdef CONFIG_BPF_JIT
+static __always_inline void
+bpf_get_prog_addr_region(const struct bpf_prog *prog,
+			 unsigned long *symbol_start,
+			 unsigned long *symbol_end)
+{
+	const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog);
+	unsigned long addr = (unsigned long)hdr;
+
+	WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));
+
+	*symbol_start = addr;
+	*symbol_end   = addr + hdr->pages * PAGE_SIZE;
+}
+
+static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+{
+	BUILD_BUG_ON(sizeof("bpf_prog_") +
+		     sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN);
+
+	sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
+	sym  = bin2hex(sym, prog->tag, sizeof(prog->tag));
+	*sym = 0;
+}
+
+static __always_inline unsigned long
+bpf_get_prog_addr_start(struct latch_tree_node *n)
+{
+	unsigned long symbol_start, symbol_end;
+	const struct bpf_prog_aux *aux;
+
+	aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
+	bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+
+	return symbol_start;
+}
+
+static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
+					  struct latch_tree_node *b)
+{
+	return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b);
+}
+
+static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
+{
+	unsigned long val = (unsigned long)key;
+	unsigned long symbol_start, symbol_end;
+	const struct bpf_prog_aux *aux;
+
+	aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
+	bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+
+	if (val < symbol_start)
+		return -1;
+	if (val >= symbol_end)
+		return  1;
+
+	return 0;
+}
+
+static const struct latch_tree_ops bpf_tree_ops = {
+	.less	= bpf_tree_less,
+	.comp	= bpf_tree_comp,
+};
+
+static DEFINE_SPINLOCK(bpf_lock);
+static LIST_HEAD(bpf_kallsyms);
+static struct latch_tree_root bpf_tree __cacheline_aligned;
+
+int bpf_jit_kallsyms __read_mostly;
+
+static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
+{
+	WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
+	list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms);
+	latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
+}
+
+static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux)
+{
+	if (list_empty(&aux->ksym_lnode))
+		return;
+
+	latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
+	list_del_rcu(&aux->ksym_lnode);
+}
+
+static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
+{
+	return fp->jited && !bpf_prog_was_classic(fp);
+}
+
+static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
+{
+	return list_empty(&fp->aux->ksym_lnode) ||
+	       fp->aux->ksym_lnode.prev == LIST_POISON2;
+}
+
+void bpf_prog_kallsyms_add(struct bpf_prog *fp)
+{
+	unsigned long flags;
+
+	if (!bpf_prog_kallsyms_candidate(fp) ||
+	    !capable(CAP_SYS_ADMIN))
+		return;
+
+	spin_lock_irqsave(&bpf_lock, flags);
+	bpf_prog_ksym_node_add(fp->aux);
+	spin_unlock_irqrestore(&bpf_lock, flags);
+}
+
+void bpf_prog_kallsyms_del(struct bpf_prog *fp)
+{
+	unsigned long flags;
+
+	if (!bpf_prog_kallsyms_candidate(fp))
+		return;
+
+	spin_lock_irqsave(&bpf_lock, flags);
+	bpf_prog_ksym_node_del(fp->aux);
+	spin_unlock_irqrestore(&bpf_lock, flags);
+}
+
+static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
+{
+	struct latch_tree_node *n;
+
+	if (!bpf_jit_kallsyms_enabled())
+		return NULL;
+
+	n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
+	return n ?
+	       container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
+	       NULL;
+}
+
+const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
+				 unsigned long *off, char *sym)
+{
+	unsigned long symbol_start, symbol_end;
+	struct bpf_prog *prog;
+	char *ret = NULL;
+
+	rcu_read_lock();
+	prog = bpf_prog_kallsyms_find(addr);
+	if (prog) {
+		bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end);
+		bpf_get_prog_name(prog, sym);
+
+		ret = sym;
+		if (size)
+			*size = symbol_end - symbol_start;
+		if (off)
+			*off  = addr - symbol_start;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+bool is_bpf_text_address(unsigned long addr)
+{
+	bool ret;
+
+	rcu_read_lock();
+	ret = bpf_prog_kallsyms_find(addr) != NULL;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		    char *sym)
+{
+	unsigned long symbol_start, symbol_end;
+	struct bpf_prog_aux *aux;
+	unsigned int it = 0;
+	int ret = -ERANGE;
+
+	if (!bpf_jit_kallsyms_enabled())
+		return ret;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) {
+		if (it++ != symnum)
+			continue;
+
+		bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+		bpf_get_prog_name(aux->prog, sym);
+
+		*value = symbol_start;
+		*type  = BPF_SYM_ELF_TYPE;
+
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 struct bpf_binary_header *
 bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 		     unsigned int alignment,
@@ -326,6 +531,24 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr)
 	module_memfree(hdr);
 }
 
+/* This symbol is only overridden by archs that have different
+ * requirements than the usual eBPF JITs, f.e. when they only
+ * implement cBPF JIT, do not set images read-only, etc.
+ */
+void __weak bpf_jit_free(struct bpf_prog *fp)
+{
+	if (fp->jited) {
+		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
+
+		bpf_jit_binary_unlock_ro(hdr);
+		bpf_jit_binary_free(hdr);
+
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
+	}
+
+	bpf_prog_unlock_free(fp);
+}
+
 int bpf_jit_harden __read_mostly;
 
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f74ca17af64a..461eb1e66a0f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -707,6 +707,7 @@ void bpf_prog_put(struct bpf_prog *prog)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
 		trace_bpf_prog_put_rcu(prog);
+		bpf_prog_kallsyms_del(prog);
 		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 	}
 }
@@ -903,6 +904,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 		/* failed to allocate fd */
 		goto free_used_maps;
 
+	bpf_prog_kallsyms_add(prog);
 	trace_bpf_prog_load(prog, err);
 	return err;