Merge branch 'BPF-directed-error-injection'

Josef Bacik says:

====================
Add the ability to do BPF directed error injection

I'm sending this through Dave since it'll conflict with other BPF changes in his
tree, but since it touches tracing as well Dave would like a review from
somebody on the tracing side.

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,
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/Kconfig

@@ -196,6 +196,9 @@ config HAVE_OPTPROBES
 config HAVE_KPROBES_ON_FTRACE
 	bool
 
+config HAVE_KPROBE_OVERRIDE
+	bool
+
 config HAVE_NMI
 	bool
 

arch/x86/Kconfig

@@ -153,6 +153,7 @@ config X86
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
+	select HAVE_KPROBE_OVERRIDE
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH			if X86_64

arch/x86/include/asm/kprobes.h

@@ -67,6 +67,10 @@ extern const int kretprobe_blacklist_size;
 void arch_remove_kprobe(struct kprobe *p);
 asmlinkage void kretprobe_trampoline(void);
 
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs);
+#endif
+
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */

arch/x86/include/asm/ptrace.h

@@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->ax;
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->ax = rc;
+}
+
 /*
  * user_mode(regs) determines whether a register set came from user
  * mode.  On x86_32, this is true if V8086 mode was enabled OR if the

arch/x86/kernel/kprobes/ftrace.c

@@ -97,3 +97,17 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p)
 	p->ainsn.boostable = false;
 	return 0;
 }
+
+asmlinkage void override_func(void);
+asm(
+	".type override_func, @function\n"
+	"override_func:\n"
+	"	ret\n"
+	".size override_func, .-override_func\n"
+);
+
+void arch_ftrace_kprobe_override_function(struct pt_regs *regs)
+{
+	regs->ip = (unsigned long)&override_func;
+}
+NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function);

include/linux/filter.h

@@ -459,7 +459,8 @@ 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? */
 	kmemcheck_bitfield_end(meta);
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	u32			len;		/* Number of filter blocks */

include/linux/trace_events.h

@@ -523,6 +523,7 @@ 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);

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

kernel/bpf/core.c

@@ -1326,6 +1326,9 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)
 {
+	if (fp->kprobe_override)
+		return false;
+
 	if (!array->owner_prog_type) {
 		/* There's no owner yet where we could check for
 		 * compatibility.

kernel/bpf/verifier.c

@@ -4357,6 +4357,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			prog->dst_needed = 1;
 		if (insn->imm == BPF_FUNC_get_prandom_u32)
 			bpf_user_rnd_init_once();
+		if (insn->imm == BPF_FUNC_override_return)
+			prog->kprobe_override = 1;
 		if (insn->imm == BPF_FUNC_tail_call) {
 			/* If we tail call into other programs, we
 			 * cannot make any assumptions since they can

kernel/events/core.c

@@ -8171,6 +8171,13 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 		return -EINVAL;
 	}
 
+	/* Kprobe override only works for kprobes, not uprobes. */
+	if (prog->kprobe_override &&
+	    !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) {
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
 	if (is_tracepoint || is_syscall_tp) {
 		int off = trace_event_get_offsets(event->tp_event);
 

kernel/trace/Kconfig

@@ -518,6 +518,17 @@ config FUNCTION_PROFILER
 
 	  If in doubt, say N.
 
+config BPF_KPROBE_OVERRIDE
+	bool "Enable BPF programs to override a kprobed function"
+	depends on BPF_EVENTS
+	depends on KPROBES_ON_FTRACE
+	depends on HAVE_KPROBE_OVERRIDE
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	default n
+	help
+	 Allows BPF to override the execution of a probed function and
+	 set a different return value.  This is used for error injection.
+
 config FTRACE_MCOUNT_RECORD
 	def_bool y
 	depends on DYNAMIC_FTRACE

kernel/trace/bpf_trace.c

@@ -13,6 +13,10 @@
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
+#include <linux/kprobes.h>
+#include <asm/kprobes.h>
+
+#include "trace_probe.h"
 #include "trace.h"
 
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
@@ -76,6 +80,29 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 }
 EXPORT_SYMBOL_GPL(trace_call_bpf);
 
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
+{
+	__this_cpu_write(bpf_kprobe_override, 1);
+	regs_set_return_value(regs, rc);
+	arch_ftrace_kprobe_override_function(regs);
+	return 0;
+}
+#else
+BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
+{
+	return -EINVAL;
+}
+#endif
+
+static const struct bpf_func_proto bpf_override_return_proto = {
+	.func		= bpf_override_return,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
 {
 	int ret;
@@ -551,6 +578,10 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_perf_event_read_value:
 		return &bpf_perf_event_read_value_proto;
+	case BPF_FUNC_override_return:
+		pr_warn_ratelimited("%s[%d] is installing a program with bpf_override_return helper that may cause unexpected behavior!",
+				    current->comm, task_pid_nr(current));
+		return &bpf_override_return_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -766,6 +797,10 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
 	struct bpf_prog_array *new_array;
 	int ret = -EEXIST;
 
+	/* Kprobe override only works for ftrace based kprobes. */
+	if (prog->kprobe_override && !trace_kprobe_ftrace(event->tp_event))
+		return -EINVAL;
+
 	mutex_lock(&bpf_event_mutex);
 
 	if (event->prog)

kernel/trace/trace_kprobe.c

@@ -42,6 +42,7 @@ struct trace_kprobe {
 	(offsetof(struct trace_kprobe, tp.args) +	\
 	(sizeof(struct probe_arg) * (n)))
 
+DEFINE_PER_CPU(int, bpf_kprobe_override);
 
 static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
 {
@@ -87,6 +88,12 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
 	return nhit;
 }
 
+int trace_kprobe_ftrace(struct trace_event_call *call)
+{
+	struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
+	return kprobe_ftrace(&tk->rp.kp);
+}
+
 static int register_kprobe_event(struct trace_kprobe *tk);
 static int unregister_kprobe_event(struct trace_kprobe *tk);
 
@@ -1170,7 +1177,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call)
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
-static void
+static int
 kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct trace_event_call *call = &tk->tp.call;
@@ -1179,12 +1186,29 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	int size, __size, dsize;
 	int rctx;
 
-	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
-		return;
+	if (bpf_prog_array_valid(call)) {
+		int ret;
+
+		ret = trace_call_bpf(call, regs);
+
+		/*
+		 * We need to check and see if we modified the pc of the
+		 * pt_regs, and if so clear the kprobe and return 1 so that we
+		 * don't do the instruction skipping.  Also reset our state so
+		 * we are clean the next pass through.
+		 */
+		if (__this_cpu_read(bpf_kprobe_override)) {
+			__this_cpu_write(bpf_kprobe_override, 0);
+			reset_current_kprobe();
+			return 1;
+		}
+		if (!ret)
+			return 0;
+	}
 
 	head = this_cpu_ptr(call->perf_events);
 	if (hlist_empty(head))
-		return;
+		return 0;
 
 	dsize = __get_data_size(&tk->tp, regs);
 	__size = sizeof(*entry) + tk->tp.size + dsize;
@@ -1193,13 +1217,14 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 	entry = perf_trace_buf_alloc(size, NULL, &rctx);
 	if (!entry)
-		return;
+		return 0;
 
 	entry->ip = (unsigned long)tk->rp.kp.addr;
 	memset(&entry[1], 0, dsize);
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL, NULL);
+	return 0;
 }
 NOKPROBE_SYMBOL(kprobe_perf_func);
 
@@ -1275,6 +1300,7 @@ static int kprobe_register(struct trace_event_call *event,
 static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
+	int ret = 0;
 
 	raw_cpu_inc(*tk->nhit);
 
@@ -1282,9 +1308,9 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
 	if (tk->tp.flags & TP_FLAG_PROFILE)
-		kprobe_perf_func(tk, regs);
+		ret = kprobe_perf_func(tk, regs);
 #endif
-	return 0;	/* We don't tweek kernel, so just return 0 */
+	return ret;
 }
 NOKPROBE_SYMBOL(kprobe_dispatcher);
 

kernel/trace/trace_probe.h

@@ -253,6 +253,7 @@ struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
 struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
+int trace_kprobe_ftrace(struct trace_event_call *call);
 #else
 /* uprobes do not support symbol fetch methods */
 #define fetch_symbol_u8			NULL
@@ -278,6 +279,11 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
+
+static inline int trace_kprobe_ftrace(struct trace_event_call *call)
+{
+	return 0;
+}
 #endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {

samples/bpf/Makefile

@@ -15,6 +15,7 @@ hostprogs-y += tracex3
 hostprogs-y += tracex4
 hostprogs-y += tracex5
 hostprogs-y += tracex6
+hostprogs-y += tracex7
 hostprogs-y += test_probe_write_user
 hostprogs-y += trace_output
 hostprogs-y += lathist
@@ -61,6 +62,7 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
 tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
 tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
 tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o
 load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
 test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
 trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
@@ -104,6 +106,7 @@ always += tracex3_kern.o
 always += tracex4_kern.o
 always += tracex5_kern.o
 always += tracex6_kern.o
+always += tracex7_kern.o
 always += sock_flags_kern.o
 always += test_probe_write_user_kern.o
 always += trace_output_kern.o
@@ -158,6 +161,7 @@ HOSTLOADLIBES_tracex3 += -lelf
 HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
 HOSTLOADLIBES_tracex6 += -lelf
+HOSTLOADLIBES_tracex7 += -lelf
 HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
 HOSTLOADLIBES_load_sock_ops += -lelf
 HOSTLOADLIBES_test_probe_write_user += -lelf

samples/bpf/test_override_return.sh

+#!/bin/bash
+
+rm -f testfile.img
+dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
+DEVICE=$(losetup --show -f testfile.img)
+mkfs.btrfs -f $DEVICE
+mkdir tmpmnt
+./tracex7 $DEVICE
+if [ $? -eq 0 ]
+then
+	echo "SUCCESS!"
+else
+	echo "FAILED!"
+fi
+losetup -d $DEVICE

samples/bpf/tracex7_kern.c

+#include <uapi/linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+SEC("kprobe/open_ctree")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	unsigned long rc = -12;
+
+	bpf_override_return(ctx, rc);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

samples/bpf/tracex7_user.c

+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <unistd.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+int main(int argc, char **argv)
+{
+	FILE *f;
+	char filename[256];
+	char command[256];
+	int ret;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	snprintf(command, 256, "mount %s tmpmnt/", argv[1]);
+	f = popen(command, "r");
+	ret = pclose(f);
+
+	return ret ? 0 : 1;
+}

tools/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

tools/testing/selftests/bpf/bpf_helpers.h

@@ -82,7 +82,8 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
 static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
 				       unsigned int buf_size) =
 	(void *) BPF_FUNC_perf_prog_read_value;
-
+static int (*bpf_override_return)(void *ctx, unsigned long rc) =
+	(void *) BPF_FUNC_override_return;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions