Merge branch 'bpf-override-return'

Josef Bacik says:

====================
This is the same as v8, just rebased onto the bpf tree.

v8->v9:
- rebased onto the bpf tree.

v7->v8:
- removed the _ASM_KPROBE_ERROR_INJECT since it was not needed.

v6->v7:
- moved the opt-in macro to bpf.h out of kprobes.h.

v5->v6:
- add BPF_ALLOW_ERROR_INJECTION() tagging for functions that will support this
  feature.  This way only functions that opt-in will be allowed to be
  overridden.
- added a btrfs patch to allow error injection for open_ctree() so that the bpf
  sample actually works.

v4->v5:
- disallow kprobe_override programs from being put in the prog map array so we
  don't tail call into something we didn't check.  This allows us to make the
  normal path still fast without a bunch of percpu operations.

v3->v4:
- fix a build error found by kbuild test bot (I didn't wait long enough
  apparently.)
- Added a warning message as per Daniels suggestion.

v2->v3:
- added a ->kprobe_override flag to bpf_prog.
- added some sanity checks to disallow attaching bpf progs that have
  ->kprobe_override set that aren't for ftrace kprobes.
- added the trace_kprobe_ftrace helper to check if the trace_event_call is a
  ftrace kprobe.
- renamed bpf_kprobe_state to bpf_kprobe_override, fixed it so we only read this
  value in the kprobe path, and thus only write to it if we're overriding or
  clearing the override.

v1->v2:
- moved things around to make sure that bpf_override_return could really only be
  used for an ftrace kprobe.
- killed the special return values from trace_call_bpf.
- renamed pc_modified to bpf_kprobe_state so bpf_override_return could tell if
  it was being called from an ftrace kprobe context.
- reworked the logic in kprobe_perf_func to take advantage of bpf_kprobe_state.
- updated the test as per Alexei's review.

- Original message -

A lot of our error paths are not well tested because we have no good way of
injecting errors generically.  Some subystems (block, memory) have ways to
inject errors, but they are random so it's hard to get reproduceable results.

With BPF we can add determinism to our error injection.  We can use kprobes and
other things to verify we are injecting errors at the exact case we are trying
to test.  This patch gives us the tool to actual do the error injection part.
It is very simple, we just set the return value of the pt_regs we're given to
whatever we provide, and then override the PC with a dummy function that simply
returns.

Right now this only works on x86, but it would be simple enough to expand to
other architectures.  Thanks,

Josef
====================

In patch "bpf: add a bpf_override_function helper" Alexei moved
"ifdef CONFIG_BPF_KPROBE_OVERRIDE" few lines to fail program loading
when kprobe_override is not available instead of failing at run-time.

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

7 files changed, 36 insertions, 2 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index ee8b707d9fa9..a2e8582d094a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -136,6 +136,15 @@
 #define KPROBE_BLACKLIST()
 #endif
 
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+#define ERROR_INJECT_LIST()	. = ALIGN(8);						\
+				VMLINUX_SYMBOL(__start_kprobe_error_inject_list) = .;	\
+				KEEP(*(_kprobe_error_inject_list))			\
+				VMLINUX_SYMBOL(__stop_kprobe_error_inject_list) = .;
+#else
+#define ERROR_INJECT_LIST()
+#endif
+
 #ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	. = ALIGN(8);					\
 			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
@@ -564,6 +573,7 @@
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
 	KPROBE_BLACKLIST()						\
+	ERROR_INJECT_LIST()						\
 	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
 	RESERVEDMEM_OF_TABLES()						\
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f812ac508e9f..93e15b9d80c7 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -580,4 +580,15 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto;
 void bpf_user_rnd_init_once(void);
 u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+#define BPF_ALLOW_ERROR_INJECTION(fname)				\
+static unsigned long __used						\
+	__attribute__((__section__("_kprobe_error_inject_list")))	\
+	_eil_addr_##fname = (unsigned long)fname;
+#else
+#define BPF_ALLOW_ERROR_INJECTION(fname)
+#endif
+#endif
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0062302e1285..5feb441d3dd9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -458,7 +458,8 @@ struct bpf_prog {
 				locked:1,	/* Program image locked? */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
-				dst_needed:1;	/* Do we need dst entry? */
+				dst_needed:1,	/* Do we need dst entry? */
+				kprobe_override:1; /* Do we override a kprobe? */
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	u32			len;		/* Number of filter blocks */
 	u32			jited_len;	/* Size of jited insns in bytes */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9440a2fc8893..963fd364f3d6 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -271,6 +271,7 @@ extern bool arch_kprobe_on_func_entry(unsigned long offset);
 extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
 
 extern bool within_kprobe_blacklist(unsigned long addr);
+extern bool within_kprobe_error_injection_list(unsigned long addr);
 
 struct kprobe_insn_cache {
 	struct mutex mutex;
diff --git a/include/linux/module.h b/include/linux/module.h
index c69b49abe877..548fa09fa806 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -475,6 +475,11 @@ struct module {
 	ctor_fn_t *ctors;
 	unsigned int num_ctors;
 #endif
+
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+	unsigned int num_kprobe_ei_funcs;
+	unsigned long *kprobe_ei_funcs;
+#endif
 } ____cacheline_aligned __randomize_layout;
 #ifndef MODULE_ARCH_INIT
 #define MODULE_ARCH_INIT {}
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index af44e7c2d577..5fea451f6e28 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -528,6 +528,7 @@ do {									\
 struct perf_event;
 
 DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+DECLARE_PER_CPU(int, bpf_kprobe_override);
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 80d62e88590c..595bda120cfb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -677,6 +677,10 @@ union bpf_attr {
  *     @buf: buf to fill
  *     @buf_size: size of the buf
  *     Return : 0 on success or negative error code
+ *
+ * int bpf_override_return(pt_regs, rc)
+ *	@pt_regs: pointer to struct pt_regs
+ *	@rc: the return value to set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -736,7 +740,8 @@ union bpf_attr {
 	FN(xdp_adjust_meta),		\
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
-	FN(getsockopt),
+	FN(getsockopt),			\
+	FN(override_return),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call