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>

Documentation/sysctl/net.txt

@@ -54,6 +54,18 @@ Values :
 	1 - enable JIT hardening for unprivileged users only
 	2 - enable JIT hardening for all users
 
+bpf_jit_kallsyms
+----------------
+
+When Berkeley Packet Filter Just in Time compiler is enabled, then compiled
+images are unknown addresses to the kernel, meaning they neither show up in
+traces nor in /proc/kallsyms. This enables export of these addresses, which
+can be used for debugging/tracing. If bpf_jit_harden is enabled, this feature
+is disabled.
+Values :
+	0 - disable JIT kallsyms export (default value)
+	1 - enable JIT kallsyms export for privileged users only
+
 dev_weight
 --------------
 

arch/arm64/net/bpf_jit_comp.c

@@ -910,18 +910,3 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 					   tmp : orig_prog);
 	return prog;
 }
-
-void bpf_jit_free(struct bpf_prog *prog)
-{
-	unsigned long addr = (unsigned long)prog->bpf_func & PAGE_MASK;
-	struct bpf_binary_header *header = (void *)addr;
-
-	if (!prog->jited)
-		goto free_filter;
-
-	set_memory_rw(addr, header->pages);
-	bpf_jit_binary_free(header);
-
-free_filter:
-	bpf_prog_unlock_free(prog);
-}

arch/powerpc/net/bpf_jit_comp64.c

@@ -1064,6 +1064,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	return fp;
 }
 
+/* Overriding bpf_jit_free() as we don't set images read-only. */
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;

arch/s390/net/bpf_jit_comp.c

@@ -1339,21 +1339,3 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 					   tmp : orig_fp);
 	return fp;
 }
-
-/*
- * Free eBPF program
- */
-void bpf_jit_free(struct bpf_prog *fp)
-{
-	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
-	struct bpf_binary_header *header = (void *)addr;
-
-	if (!fp->jited)
-		goto free_filter;
-
-	set_memory_rw(addr, header->pages);
-	bpf_jit_binary_free(header);
-
-free_filter:
-	bpf_prog_unlock_free(fp);
-}

arch/x86/net/bpf_jit_comp.c

@@ -1180,18 +1180,3 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 					   tmp : orig_prog);
 	return prog;
 }
-
-void bpf_jit_free(struct bpf_prog *fp)
-{
-	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
-	struct bpf_binary_header *header = (void *)addr;
-
-	if (!fp->jited)
-		goto free_filter;
-
-	set_memory_rw(addr, header->pages);
-	bpf_jit_binary_free(header);
-
-free_filter:
-	bpf_prog_unlock_free(fp);
-}

include/linux/bpf.h

@@ -8,10 +8,12 @@
 #define _LINUX_BPF_H 1
 
 #include <uapi/linux/bpf.h>
+
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/percpu.h>
 #include <linux/err.h>
+#include <linux/rbtree_latch.h>
 
 struct perf_event;
 struct bpf_map;
@@ -177,6 +179,8 @@ struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
 	u32 max_ctx_offset;
+	struct latch_tree_node ksym_tnode;
+	struct list_head ksym_lnode;
 	const struct bpf_verifier_ops *ops;
 	struct bpf_map **used_maps;
 	struct bpf_prog *prog;

include/linux/filter.h

@@ -54,6 +54,12 @@ struct bpf_prog_aux;
 #define BPF_REG_AX		MAX_BPF_REG
 #define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)
 
+/* As per nm, we expose JITed images as text (code) section for
+ * kallsyms. That way, tools like perf can find it to match
+ * addresses.
+ */
+#define BPF_SYM_ELF_TYPE	't'
+
 /* BPF program can access up to 512 bytes of stack space. */
 #define MAX_BPF_STACK	512
 
@@ -555,6 +561,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
 	set_memory_rw((unsigned long)fp, fp->pages);
 }
+
+static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
+{
+	set_memory_rw((unsigned long)hdr, hdr->pages);
+}
 #else
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
@@ -563,8 +574,21 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
 }
+
+static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
+{
+}
 #endif /* CONFIG_DEBUG_SET_MODULE_RONX */
 
+static inline struct bpf_binary_header *
+bpf_jit_binary_hdr(const struct bpf_prog *fp)
+{
+	unsigned long real_start = (unsigned long)fp->bpf_func;
+	unsigned long addr = real_start & PAGE_MASK;
+
+	return (void *)addr;
+}
+
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
@@ -617,6 +641,7 @@ void bpf_warn_invalid_xdp_action(u32 act);
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
 extern int bpf_jit_harden;
+extern int bpf_jit_kallsyms;
 
 typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
 
@@ -651,6 +676,11 @@ static inline bool bpf_jit_is_ebpf(void)
 # endif
 }
 
+static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
+{
+	return fp->jited && bpf_jit_is_ebpf();
+}
+
 static inline bool bpf_jit_blinding_enabled(void)
 {
 	/* These are the prerequisites, should someone ever have the
@@ -668,11 +698,91 @@ static inline bool bpf_jit_blinding_enabled(void)
 
 	return true;
 }
-#else
+
+static inline bool bpf_jit_kallsyms_enabled(void)
+{
+	/* There are a couple of corner cases where kallsyms should
+	 * not be enabled f.e. on hardening.
+	 */
+	if (bpf_jit_harden)
+		return false;
+	if (!bpf_jit_kallsyms)
+		return false;
+	if (bpf_jit_kallsyms == 1)
+		return true;
+
+	return false;
+}
+
+const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
+				 unsigned long *off, char *sym);
+bool is_bpf_text_address(unsigned long addr);
+int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		    char *sym);
+
+static inline const char *
+bpf_address_lookup(unsigned long addr, unsigned long *size,
+		   unsigned long *off, char **modname, char *sym)
+{
+	const char *ret = __bpf_address_lookup(addr, size, off, sym);
+
+	if (ret && modname)
+		*modname = NULL;
+	return ret;
+}
+
+void bpf_prog_kallsyms_add(struct bpf_prog *fp);
+void bpf_prog_kallsyms_del(struct bpf_prog *fp);
+
+#else /* CONFIG_BPF_JIT */
+
+static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp)
+{
+	return false;
+}
+
 static inline void bpf_jit_free(struct bpf_prog *fp)
 {
 	bpf_prog_unlock_free(fp);
 }
+
+static inline bool bpf_jit_kallsyms_enabled(void)
+{
+	return false;
+}
+
+static inline const char *
+__bpf_address_lookup(unsigned long addr, unsigned long *size,
+		     unsigned long *off, char *sym)
+{
+	return NULL;
+}
+
+static inline bool is_bpf_text_address(unsigned long addr)
+{
+	return false;
+}
+
+static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value,
+				  char *type, char *sym)
+{
+	return -ERANGE;
+}
+
+static inline const char *
+bpf_address_lookup(unsigned long addr, unsigned long *size,
+		   unsigned long *off, char **modname, char *sym)
+{
+	return NULL;
+}
+
+static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp)
+{
+}
+
+static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)
+{
+}
 #endif /* CONFIG_BPF_JIT */
 
 #define BPF_ANC		BIT(15)