* [PATCH v7 bpf-next 07/10] bpf: introduce BPF_RAW_TRACEPOINT
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
Introduce BPF_PROG_TYPE_RAW_TRACEPOINT bpf program type to access
kernel internal arguments of the tracepoints in their raw form.
>From bpf program point of view the access to the arguments look like:
struct bpf_raw_tracepoint_args {
__u64 args[0];
};
int bpf_prog(struct bpf_raw_tracepoint_args *ctx)
{
// program can read args[N] where N depends on tracepoint
// and statically verified at program load+attach time
}
kprobe+bpf infrastructure allows programs access function arguments.
This feature allows programs access raw tracepoint arguments.
Similar to proposed 'dynamic ftrace events' there are no abi guarantees
to what the tracepoints arguments are and what their meaning is.
The program needs to type cast args properly and use bpf_probe_read()
helper to access struct fields when argument is a pointer.
For every tracepoint __bpf_trace_##call function is prepared.
In assembler it looks like:
(gdb) disassemble __bpf_trace_xdp_exception
Dump of assembler code for function __bpf_trace_xdp_exception:
0xffffffff81132080 <+0>: mov %ecx,%ecx
0xffffffff81132082 <+2>: jmpq 0xffffffff811231f0 <bpf_trace_run3>
where
TRACE_EVENT(xdp_exception,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp, u32 act),
The above assembler snippet is casting 32-bit 'act' field into 'u64'
to pass into bpf_trace_run3(), while 'dev' and 'xdp' args are passed as-is.
All of ~500 of __bpf_trace_*() functions are only 5-10 byte long
and in total this approach adds 7k bytes to .text.
This approach gives the lowest possible overhead
while calling trace_xdp_exception() from kernel C code and
transitioning into bpf land.
Since tracepoint+bpf are used at speeds of 1M+ events per second
this is valuable optimization.
The new BPF_RAW_TRACEPOINT_OPEN sys_bpf command is introduced
that returns anon_inode FD of 'bpf-raw-tracepoint' object.
The user space looks like:
// load bpf prog with BPF_PROG_TYPE_RAW_TRACEPOINT type
prog_fd = bpf_prog_load(...);
// receive anon_inode fd for given bpf_raw_tracepoint with prog attached
raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);
Ctrl-C of tracing daemon or cmdline tool that uses this feature
will automatically detach bpf program, unload it and
unregister tracepoint probe.
On the kernel side the __bpf_raw_tp_map section of pointers to
tracepoint definition and to __bpf_trace_*() probe function is used
to find a tracepoint with "xdp_exception" name and
corresponding __bpf_trace_xdp_exception() probe function
which are passed to tracepoint_probe_register() to connect probe
with tracepoint.
Addition of bpf_raw_tracepoint doesn't interfere with ftrace and perf
tracepoint mechanisms. perf_event_open() can be used in parallel
on the same tracepoint.
Multiple bpf_raw_tracepoint_open("xdp_exception", prog_fd) are permitted.
Each with its own bpf program. The kernel will execute
all tracepoint probes and all attached bpf programs.
In the future bpf_raw_tracepoints can be extended with
query/introspection logic.
__bpf_raw_tp_map section logic was contributed by Steven Rostedt
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
include/asm-generic/vmlinux.lds.h | 10 +++
include/linux/bpf_types.h | 1 +
include/linux/trace_events.h | 42 +++++++++
include/linux/tracepoint-defs.h | 5 ++
include/trace/bpf_probe.h | 91 +++++++++++++++++++
include/trace/define_trace.h | 1 +
include/uapi/linux/bpf.h | 11 +++
kernel/bpf/syscall.c | 78 ++++++++++++++++
kernel/trace/bpf_trace.c | 183 ++++++++++++++++++++++++++++++++++++++
9 files changed, 422 insertions(+)
create mode 100644 include/trace/bpf_probe.h
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1ab0e520d6fc..8add3493a202 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -178,6 +178,15 @@
#define TRACE_SYSCALLS()
#endif
+#ifdef CONFIG_BPF_EVENTS
+#define BPF_RAW_TP() STRUCT_ALIGN(); \
+ VMLINUX_SYMBOL(__start__bpf_raw_tp) = .; \
+ KEEP(*(__bpf_raw_tp_map)) \
+ VMLINUX_SYMBOL(__stop__bpf_raw_tp) = .;
+#else
+#define BPF_RAW_TP()
+#endif
+
#ifdef CONFIG_SERIAL_EARLYCON
#define EARLYCON_TABLE() STRUCT_ALIGN(); \
VMLINUX_SYMBOL(__earlycon_table) = .; \
@@ -249,6 +258,7 @@
LIKELY_PROFILE() \
BRANCH_PROFILE() \
TRACE_PRINTKS() \
+ BPF_RAW_TP() \
TRACEPOINT_STR()
/*
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5e2e8a49fb21..6d7243bfb0ff 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -19,6 +19,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
#endif
#ifdef CONFIG_CGROUP_BPF
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 8a1442c4e513..b0357cd198b0 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -468,6 +468,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog);
void perf_event_detach_bpf_prog(struct perf_event *event);
int perf_event_query_prog_array(struct perf_event *event, void __user *info);
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
#else
static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
@@ -487,6 +490,18 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info)
{
return -EOPNOTSUPP;
}
+static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+{
+ return -EOPNOTSUPP;
+}
+static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+{
+ return -EOPNOTSUPP;
+}
+static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+{
+ return NULL;
+}
#endif
enum {
@@ -546,6 +561,33 @@ extern void ftrace_profile_free_filter(struct perf_event *event);
void perf_trace_buf_update(void *record, u16 type);
void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp);
+void bpf_trace_run1(struct bpf_prog *prog, u64 arg1);
+void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2);
+void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3);
+void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4);
+void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5);
+void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6);
+void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7);
+void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8);
+void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9);
+void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9, u64 arg10);
+void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9, u64 arg10, u64 arg11);
+void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12);
void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
struct trace_event_call *call, u64 count,
struct pt_regs *regs, struct hlist_head *head,
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index 39a283c61c51..35db8dd48c4c 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -36,4 +36,9 @@ struct tracepoint {
u32 num_args;
};
+struct bpf_raw_event_map {
+ struct tracepoint *tp;
+ void *bpf_func;
+};
+
#endif
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
new file mode 100644
index 000000000000..c374ed1f2eee
--- /dev/null
+++ b/include/trace/bpf_probe.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#undef TRACE_SYSTEM_VAR
+
+#ifdef CONFIG_BPF_EVENTS
+
+#undef __entry
+#define __entry entry
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field) \
+ ((void *)__entry + (__entry->__data_loc_##field & 0xffff))
+
+#undef __get_dynamic_array_len
+#define __get_dynamic_array_len(field) \
+ ((__entry->__data_loc_##field >> 16) & 0xffff)
+
+#undef __get_str
+#define __get_str(field) ((char *)__get_dynamic_array(field))
+
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
+#undef __perf_count
+#define __perf_count(c) (c)
+
+#undef __perf_task
+#define __perf_task(t) (t)
+
+/* cast any integer, pointer, or small struct to u64 */
+#define UINTTYPE(size) \
+ __typeof__(__builtin_choose_expr(size == 1, (u8)1, \
+ __builtin_choose_expr(size == 2, (u16)2, \
+ __builtin_choose_expr(size == 4, (u32)3, \
+ __builtin_choose_expr(size == 8, (u64)4, \
+ (void)5)))))
+#define __CAST_TO_U64(x) ({ \
+ typeof(x) __src = (x); \
+ UINTTYPE(sizeof(x)) __dst; \
+ memcpy(&__dst, &__src, sizeof(__dst)); \
+ (u64)__dst; })
+
+#define __CAST1(a,...) __CAST_TO_U64(a)
+#define __CAST2(a,...) __CAST_TO_U64(a), __CAST1(__VA_ARGS__)
+#define __CAST3(a,...) __CAST_TO_U64(a), __CAST2(__VA_ARGS__)
+#define __CAST4(a,...) __CAST_TO_U64(a), __CAST3(__VA_ARGS__)
+#define __CAST5(a,...) __CAST_TO_U64(a), __CAST4(__VA_ARGS__)
+#define __CAST6(a,...) __CAST_TO_U64(a), __CAST5(__VA_ARGS__)
+#define __CAST7(a,...) __CAST_TO_U64(a), __CAST6(__VA_ARGS__)
+#define __CAST8(a,...) __CAST_TO_U64(a), __CAST7(__VA_ARGS__)
+#define __CAST9(a,...) __CAST_TO_U64(a), __CAST8(__VA_ARGS__)
+#define __CAST10(a,...) __CAST_TO_U64(a), __CAST9(__VA_ARGS__)
+#define __CAST11(a,...) __CAST_TO_U64(a), __CAST10(__VA_ARGS__)
+#define __CAST12(a,...) __CAST_TO_U64(a), __CAST11(__VA_ARGS__)
+/* tracepoints with more than 12 arguments will hit build error */
+#define CAST_TO_U64(...) CONCATENATE(__CAST, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
+static notrace void \
+__bpf_trace_##call(void *__data, proto) \
+{ \
+ struct bpf_prog *prog = __data; \
+ CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args)); \
+}
+
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * bpf probe will fail to compile unless it too is updated.
+ */
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args) \
+static inline void bpf_test_probe_##call(void) \
+{ \
+ check_trace_callback_type_##call(__bpf_trace_##template); \
+} \
+static struct bpf_raw_event_map __used \
+ __attribute__((section("__bpf_raw_tp_map"))) \
+__bpf_trace_tp_map_##call = { \
+ .tp = &__tracepoint_##call, \
+ .bpf_func = (void *)__bpf_trace_##template, \
+};
+
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
+ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_BPF_EVENTS */
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index 96b22ace9ae7..5f8216bc261f 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -95,6 +95,7 @@
#ifdef TRACEPOINTS_ENABLED
#include <trace/trace_events.h>
#include <trace/perf.h>
+#include <trace/bpf_probe.h>
#endif
#undef TRACE_EVENT
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 18b7c510c511..1878201c2d77 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -94,6 +94,7 @@ enum bpf_cmd {
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
+ BPF_RAW_TRACEPOINT_OPEN,
};
enum bpf_map_type {
@@ -134,6 +135,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_RAW_TRACEPOINT,
};
enum bpf_attach_type {
@@ -344,6 +346,11 @@ union bpf_attr {
__aligned_u64 prog_ids;
__u32 prog_cnt;
} query;
+
+ struct {
+ __u64 name;
+ __u32 prog_fd;
+ } raw_tracepoint;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -1152,4 +1159,8 @@ struct bpf_cgroup_dev_ctx {
__u32 minor;
};
+struct bpf_raw_tracepoint_args {
+ __u64 args[0];
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3aeb4ea2a93a..1894537dcada 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1311,6 +1311,81 @@ static int bpf_obj_get(const union bpf_attr *attr)
attr->file_flags);
}
+struct bpf_raw_tracepoint {
+ struct bpf_raw_event_map *btp;
+ struct bpf_prog *prog;
+};
+
+static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
+{
+ struct bpf_raw_tracepoint *raw_tp = filp->private_data;
+
+ if (raw_tp->prog) {
+ bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
+ bpf_prog_put(raw_tp->prog);
+ }
+ kfree(raw_tp);
+ return 0;
+}
+
+static const struct file_operations bpf_raw_tp_fops = {
+ .release = bpf_raw_tracepoint_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
+};
+
+#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
+
+static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
+{
+ struct bpf_raw_tracepoint *raw_tp;
+ struct bpf_raw_event_map *btp;
+ struct bpf_prog *prog;
+ char tp_name[128];
+ int tp_fd, err;
+
+ if (strncpy_from_user(tp_name, u64_to_user_ptr(attr->raw_tracepoint.name),
+ sizeof(tp_name) - 1) < 0)
+ return -EFAULT;
+ tp_name[sizeof(tp_name) - 1] = 0;
+
+ btp = bpf_find_raw_tracepoint(tp_name);
+ if (!btp)
+ return -ENOENT;
+
+ raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
+ if (!raw_tp)
+ return -ENOMEM;
+ raw_tp->btp = btp;
+
+ prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
+ BPF_PROG_TYPE_RAW_TRACEPOINT);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto out_free_tp;
+ }
+
+ err = bpf_probe_register(raw_tp->btp, prog);
+ if (err)
+ goto out_put_prog;
+
+ raw_tp->prog = prog;
+ tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp,
+ O_CLOEXEC);
+ if (tp_fd < 0) {
+ bpf_probe_unregister(raw_tp->btp, prog);
+ err = tp_fd;
+ goto out_put_prog;
+ }
+ return tp_fd;
+
+out_put_prog:
+ bpf_prog_put(prog);
+out_free_tp:
+ kfree(raw_tp);
+ return err;
+}
+
#ifdef CONFIG_CGROUP_BPF
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
@@ -1921,6 +1996,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET_INFO_BY_FD:
err = bpf_obj_get_info_by_fd(&attr, uattr);
break;
+ case BPF_RAW_TRACEPOINT_OPEN:
+ err = bpf_raw_tracepoint_open(&attr);
+ break;
default:
err = -EINVAL;
break;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c634e093951f..7d0009e712f5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -723,6 +723,86 @@ const struct bpf_verifier_ops tracepoint_verifier_ops = {
const struct bpf_prog_ops tracepoint_prog_ops = {
};
+/*
+ * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
+ * to avoid potential recursive reuse issue when/if tracepoints are added
+ * inside bpf_*_event_output and/or bpf_get_stack_id
+ */
+static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
+ struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+ perf_fetch_caller_regs(regs);
+ return ____bpf_perf_event_output(regs, map, flags, data, size);
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
+ .func = bpf_perf_event_output_raw_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+};
+
+BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
+ struct bpf_map *, map, u64, flags)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+ perf_fetch_caller_regs(regs);
+ /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
+ return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+ flags, 0, 0);
+}
+
+static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
+ .func = bpf_get_stackid_raw_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *raw_tp_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_perf_event_output:
+ return &bpf_perf_event_output_proto_raw_tp;
+ case BPF_FUNC_get_stackid:
+ return &bpf_get_stackid_proto_raw_tp;
+ default:
+ return tracing_func_proto(func_id);
+ }
+}
+
+static bool raw_tp_prog_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ struct bpf_insn_access_aux *info)
+{
+ /* largest tracepoint in the kernel has 12 args */
+ if (off < 0 || off >= sizeof(__u64) * 12)
+ return false;
+ if (type != BPF_READ)
+ return false;
+ if (off % size != 0)
+ return false;
+ return true;
+}
+
+const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
+ .get_func_proto = raw_tp_prog_func_proto,
+ .is_valid_access = raw_tp_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops raw_tracepoint_prog_ops = {
+};
+
static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
@@ -896,3 +976,106 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
return ret;
}
+
+extern struct bpf_raw_event_map __start__bpf_raw_tp[];
+extern struct bpf_raw_event_map __stop__bpf_raw_tp[];
+
+struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+{
+ struct bpf_raw_event_map *btp = __start__bpf_raw_tp;
+
+ for (; btp < __stop__bpf_raw_tp; btp++) {
+ if (!strcmp(btp->tp->name, name))
+ return btp;
+ }
+ return NULL;
+}
+
+static __always_inline
+void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
+{
+ rcu_read_lock();
+ preempt_disable();
+ (void) BPF_PROG_RUN(prog, args);
+ preempt_enable();
+ rcu_read_unlock();
+}
+
+#define UNPACK(...) __VA_ARGS__
+#define REPEAT_1(FN, DL, X, ...) FN(X)
+#define REPEAT_2(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__)
+#define REPEAT_3(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__)
+#define REPEAT_4(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__)
+#define REPEAT_5(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__)
+#define REPEAT_6(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__)
+#define REPEAT_7(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__)
+#define REPEAT_8(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__)
+#define REPEAT_9(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__)
+#define REPEAT_10(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__)
+#define REPEAT_11(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__)
+#define REPEAT_12(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__)
+#define REPEAT(X, FN, DL, ...) REPEAT_##X(FN, DL, __VA_ARGS__)
+
+#define SARG(X) u64 arg##X
+#define COPY(X) args[X] = arg##X
+
+#define __DL_COM (,)
+#define __DL_SEM (;)
+
+#define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
+
+#define BPF_TRACE_DEFN_x(x) \
+ void bpf_trace_run##x(struct bpf_prog *prog, \
+ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \
+ { \
+ u64 args[x]; \
+ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \
+ __bpf_trace_run(prog, args); \
+ } \
+ EXPORT_SYMBOL_GPL(bpf_trace_run##x)
+BPF_TRACE_DEFN_x(1);
+BPF_TRACE_DEFN_x(2);
+BPF_TRACE_DEFN_x(3);
+BPF_TRACE_DEFN_x(4);
+BPF_TRACE_DEFN_x(5);
+BPF_TRACE_DEFN_x(6);
+BPF_TRACE_DEFN_x(7);
+BPF_TRACE_DEFN_x(8);
+BPF_TRACE_DEFN_x(9);
+BPF_TRACE_DEFN_x(10);
+BPF_TRACE_DEFN_x(11);
+BPF_TRACE_DEFN_x(12);
+
+static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+ struct tracepoint *tp = btp->tp;
+
+ /*
+ * check that program doesn't access arguments beyond what's
+ * available in this tracepoint
+ */
+ if (prog->aux->max_ctx_offset > tp->num_args * sizeof(u64))
+ return -EINVAL;
+
+ return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
+}
+
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+ int err;
+
+ mutex_lock(&bpf_event_mutex);
+ err = __bpf_probe_register(btp, prog);
+ mutex_unlock(&bpf_event_mutex);
+ return err;
+}
+
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+ int err;
+
+ mutex_lock(&bpf_event_mutex);
+ err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
+ mutex_unlock(&bpf_event_mutex);
+ return err;
+}
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 00/10] bpf, tracing: introduce bpf raw tracepoints
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
v6->v7:
- adopted Steven's bpf_raw_tp_map section approach to find tracepoint
and corresponding bpf probe function instead of kallsyms approach.
dropped kernel_tracepoint_find_by_name() patch
v5->v6:
- avoid changing semantics of for_each_kernel_tracepoint() function, instead
introduce kernel_tracepoint_find_by_name() helper
v4->v5:
- adopted Daniel's fancy REPEAT macro in bpf_trace.c in patch 7
v3->v4:
- adopted Linus's CAST_TO_U64 macro to cast any integer, pointer, or small
struct to u64. That nicely reduced the size of patch 1
v2->v3:
- with Linus's suggestion introduced generic COUNT_ARGS and CONCATENATE macros
(or rather moved them from apparmor)
that cleaned up patches 6 and 7
- added patch 4 to refactor trace_iwlwifi_dev_ucode_error() from 17 args to 4
Now any tracepoint with >12 args will have build error
v1->v2:
- simplified api by combing bpf_raw_tp_open(name) + bpf_attach(prog_fd) into
bpf_raw_tp_open(name, prog_fd) as suggested by Daniel.
That simplifies bpf_detach as well which is now simple close() of fd.
- fixed memory leak in error path which was spotted by Daniel.
- fixed bpf_get_stackid(), bpf_perf_event_output() called from raw tracepoints
- added more tests
- fixed allyesconfig build caught by buildbot
v1:
This patch set is a different way to address the pressing need to access
task_struct pointers in sched tracepoints from bpf programs.
The first approach simply added these pointers to sched tracepoints:
https://lkml.org/lkml/2017/12/14/753
which Peter nacked.
Few options were discussed and eventually the discussion converged on
doing bpf specific tracepoint_probe_register() probe functions.
Details here:
https://lkml.org/lkml/2017/12/20/929
Patch 1 is kernel wide cleanup of pass-struct-by-value into
pass-struct-by-reference into tracepoints.
Patches 2 and 3 are minor cleanups to address allyesconfig build
Patch 4 refactor trace_iwlwifi_dev_ucode_error from 17 to 4 args
Patch 5 introduces COUNT_ARGS macro
Patch 6 minor prep work to expose number of arguments passed
into tracepoints.
Patch 7 introduces BPF_RAW_TRACEPOINT api.
the auto-cleanup and multiple concurrent users are must have
features of tracing api. For bpf raw tracepoints it looks like:
// load bpf prog with BPF_PROG_TYPE_RAW_TRACEPOINT type
prog_fd = bpf_prog_load(...);
// receive anon_inode fd for given bpf_raw_tracepoint
// and attach bpf program to it
raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);
Ctrl-C of tracing daemon or cmdline tool will automatically
detach bpf program, unload it and unregister tracepoint probe.
More details in patch 7.
Patch 8 - trivial support in libbpf
Patches 9, 10 - user space tests
samples/bpf/test_overhead performance on 1 cpu:
tracepoint base kprobe+bpf tracepoint+bpf raw_tracepoint+bpf
task_rename 1.1M 769K 947K 1.0M
urandom_read 789K 697K 750K 755K
Alexei Starovoitov (10):
treewide: remove large struct-pass-by-value from tracepoint arguments
net/mediatek: disambiguate mt76 vs mt7601u trace events
net/mac802154: disambiguate mac80215 vs mac802154 trace events
net/wireless/iwlwifi: fix iwlwifi_dev_ucode_error tracepoint
macro: introduce COUNT_ARGS() macro
tracepoint: compute num_args at build time
bpf: introduce BPF_RAW_TRACEPOINT
libbpf: add bpf_raw_tracepoint_open helper
samples/bpf: raw tracepoint test
selftests/bpf: test for bpf_get_stackid() from raw tracepoints
drivers/infiniband/hw/hfi1/file_ops.c | 2 +-
drivers/infiniband/hw/hfi1/trace_ctxts.h | 12 +-
drivers/net/wireless/intel/iwlwifi/dvm/main.c | 7 +-
.../wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h | 39 ++---
drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c | 1 +
drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 7 +-
drivers/net/wireless/mediatek/mt7601u/trace.h | 6 +-
include/asm-generic/vmlinux.lds.h | 10 ++
include/linux/bpf_types.h | 1 +
include/linux/kernel.h | 7 +
include/linux/trace_events.h | 42 +++++
include/linux/tracepoint-defs.h | 6 +
include/linux/tracepoint.h | 12 +-
include/trace/bpf_probe.h | 91 ++++++++++
include/trace/define_trace.h | 15 +-
include/trace/events/f2fs.h | 2 +-
include/uapi/linux/bpf.h | 11 ++
kernel/bpf/syscall.c | 78 +++++++++
kernel/trace/bpf_trace.c | 183 +++++++++++++++++++++
net/mac802154/trace.h | 8 +-
net/wireless/trace.h | 2 +-
samples/bpf/Makefile | 1 +
samples/bpf/bpf_load.c | 14 ++
samples/bpf/test_overhead_raw_tp_kern.c | 17 ++
samples/bpf/test_overhead_user.c | 12 ++
security/apparmor/include/path.h | 7 +-
sound/firewire/amdtp-stream-trace.h | 2 +-
tools/include/uapi/linux/bpf.h | 11 ++
tools/lib/bpf/bpf.c | 11 ++
tools/lib/bpf/bpf.h | 1 +
tools/testing/selftests/bpf/test_progs.c | 91 +++++++---
31 files changed, 619 insertions(+), 90 deletions(-)
create mode 100644 include/trace/bpf_probe.h
create mode 100644 samples/bpf/test_overhead_raw_tp_kern.c
--
2.9.5
^ permalink raw reply
* [PATCH v7 bpf-next 01/10] treewide: remove large struct-pass-by-value from tracepoint arguments
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
- fix trace_hfi1_ctxt_info() to pass large struct by reference instead of by value
- convert 'type array[]' tracepoint arguments into 'type *array',
since compiler will warn that sizeof('type array[]') == sizeof('type *array')
and later should be used instead
The CAST_TO_U64 macro in the later patch will enforce that tracepoint
arguments can only be integers, pointers, or less than 8 byte structures.
Larger structures should be passed by reference.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
drivers/infiniband/hw/hfi1/file_ops.c | 2 +-
drivers/infiniband/hw/hfi1/trace_ctxts.h | 12 ++++++------
include/trace/events/f2fs.h | 2 +-
net/wireless/trace.h | 2 +-
sound/firewire/amdtp-stream-trace.h | 2 +-
5 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 41fafebe3b0d..da4aa1a95b11 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -1153,7 +1153,7 @@ static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len)
cinfo.sdma_ring_size = fd->cq->nentries;
cinfo.rcvegr_size = uctxt->egrbufs.rcvtid_size;
- trace_hfi1_ctxt_info(uctxt->dd, uctxt->ctxt, fd->subctxt, cinfo);
+ trace_hfi1_ctxt_info(uctxt->dd, uctxt->ctxt, fd->subctxt, &cinfo);
if (copy_to_user((void __user *)arg, &cinfo, len))
return -EFAULT;
diff --git a/drivers/infiniband/hw/hfi1/trace_ctxts.h b/drivers/infiniband/hw/hfi1/trace_ctxts.h
index 4eb4cc798035..e00c8a7d559c 100644
--- a/drivers/infiniband/hw/hfi1/trace_ctxts.h
+++ b/drivers/infiniband/hw/hfi1/trace_ctxts.h
@@ -106,7 +106,7 @@ TRACE_EVENT(hfi1_uctxtdata,
TRACE_EVENT(hfi1_ctxt_info,
TP_PROTO(struct hfi1_devdata *dd, unsigned int ctxt,
unsigned int subctxt,
- struct hfi1_ctxt_info cinfo),
+ struct hfi1_ctxt_info *cinfo),
TP_ARGS(dd, ctxt, subctxt, cinfo),
TP_STRUCT__entry(DD_DEV_ENTRY(dd)
__field(unsigned int, ctxt)
@@ -120,11 +120,11 @@ TRACE_EVENT(hfi1_ctxt_info,
TP_fast_assign(DD_DEV_ASSIGN(dd);
__entry->ctxt = ctxt;
__entry->subctxt = subctxt;
- __entry->egrtids = cinfo.egrtids;
- __entry->rcvhdrq_cnt = cinfo.rcvhdrq_cnt;
- __entry->rcvhdrq_size = cinfo.rcvhdrq_entsize;
- __entry->sdma_ring_size = cinfo.sdma_ring_size;
- __entry->rcvegr_size = cinfo.rcvegr_size;
+ __entry->egrtids = cinfo->egrtids;
+ __entry->rcvhdrq_cnt = cinfo->rcvhdrq_cnt;
+ __entry->rcvhdrq_size = cinfo->rcvhdrq_entsize;
+ __entry->sdma_ring_size = cinfo->sdma_ring_size;
+ __entry->rcvegr_size = cinfo->rcvegr_size;
),
TP_printk("[%s] ctxt %u:%u " CINFO_FMT,
__get_str(dev),
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 06c87f9f720c..795698925d20 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -491,7 +491,7 @@ DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node,
TRACE_EVENT(f2fs_truncate_partial_nodes,
- TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err),
+ TP_PROTO(struct inode *inode, nid_t *nid, int depth, int err),
TP_ARGS(inode, nid, depth, err),
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 5152938b358d..018c81fa72fb 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -3137,7 +3137,7 @@ TRACE_EVENT(rdev_start_radar_detection,
TRACE_EVENT(rdev_set_mcast_rate,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
- int mcast_rate[NUM_NL80211_BANDS]),
+ int *mcast_rate),
TP_ARGS(wiphy, netdev, mcast_rate),
TP_STRUCT__entry(
WIPHY_ENTRY
diff --git a/sound/firewire/amdtp-stream-trace.h b/sound/firewire/amdtp-stream-trace.h
index ea0d486652c8..54cdd4ffa9ce 100644
--- a/sound/firewire/amdtp-stream-trace.h
+++ b/sound/firewire/amdtp-stream-trace.h
@@ -14,7 +14,7 @@
#include <linux/tracepoint.h>
TRACE_EVENT(in_packet,
- TP_PROTO(const struct amdtp_stream *s, u32 cycles, u32 cip_header[2], unsigned int payload_length, unsigned int index),
+ TP_PROTO(const struct amdtp_stream *s, u32 cycles, u32 *cip_header, unsigned int payload_length, unsigned int index),
TP_ARGS(s, cycles, cip_header, payload_length, index),
TP_STRUCT__entry(
__field(unsigned int, second)
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 05/10] macro: introduce COUNT_ARGS() macro
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
move COUNT_ARGS() macro from apparmor to generic header and extend it
to count till twelve.
COUNT() was an alternative name for this logic, but it's used for
different purpose in many other places.
Similarly for CONCATENATE() macro.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/kernel.h | 7 +++++++
security/apparmor/include/path.h | 7 +------
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3fd291503576..293fa0677fba 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -919,6 +919,13 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
#define swap(a, b) \
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+/* This counts to 12. Any more, it will return 13th argument. */
+#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
+#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __CONCAT(a, b) a ## b
+#define CONCATENATE(a, b) __CONCAT(a, b)
+
/**
* container_of - cast a member of a structure out to the containing structure
* @ptr: the pointer to the member.
diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h
index 05fb3305671e..e042b994f2b8 100644
--- a/security/apparmor/include/path.h
+++ b/security/apparmor/include/path.h
@@ -43,15 +43,10 @@ struct aa_buffers {
DECLARE_PER_CPU(struct aa_buffers, aa_buffers);
-#define COUNT_ARGS(X...) COUNT_ARGS_HELPER(, ##X, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-#define COUNT_ARGS_HELPER(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, n, X...) n
-#define CONCAT(X, Y) X ## Y
-#define CONCAT_AFTER(X, Y) CONCAT(X, Y)
-
#define ASSIGN(FN, X, N) ((X) = FN(N))
#define EVAL1(FN, X) ASSIGN(FN, X, 0) /*X = FN(0)*/
#define EVAL2(FN, X, Y...) do { ASSIGN(FN, X, 1); EVAL1(FN, Y); } while (0)
-#define EVAL(FN, X...) CONCAT_AFTER(EVAL, COUNT_ARGS(X))(FN, X)
+#define EVAL(FN, X...) CONCATENATE(EVAL, COUNT_ARGS(X))(FN, X)
#define for_each_cpu_buffer(I) for ((I) = 0; (I) < MAX_PATH_BUFFERS; (I)++)
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 04/10] net/wireless/iwlwifi: fix iwlwifi_dev_ucode_error tracepoint
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
fix iwlwifi_dev_ucode_error tracepoint to pass pointer to a table
instead of all 17 arguments by value.
dvm/main.c and mvm/utils.c have 'struct iwl_error_event_table'
defined with very similar yet subtly different fields and offsets.
tracepoint is still common and using definition of 'struct iwl_error_event_table'
from dvm/commands.h while copying fields.
Long term this tracepoint probably should be split into two.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
drivers/net/wireless/intel/iwlwifi/dvm/main.c | 7 +---
.../wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h | 39 ++++++++++------------
drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c | 1 +
drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 7 +---
4 files changed, 21 insertions(+), 33 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index d11d72615de2..e68254e12764 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1651,12 +1651,7 @@ static void iwl_dump_nic_error_log(struct iwl_priv *priv)
priv->status, table.valid);
}
- trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
- table.data1, table.data2, table.line,
- table.blink2, table.ilink1, table.ilink2,
- table.bcon_time, table.gp1, table.gp2,
- table.gp3, table.ucode_ver, table.hw_ver,
- 0, table.brd_ver);
+ trace_iwlwifi_dev_ucode_error(trans->dev, &table, 0, table.brd_ver);
IWL_ERR(priv, "0x%08X | %-28s\n", table.error_id,
desc_lookup(table.error_id));
IWL_ERR(priv, "0x%08X | uPc\n", table.pc);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
index 9518a82f44c2..27e3e4e96aa2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
@@ -126,14 +126,11 @@ TRACE_EVENT(iwlwifi_dev_tx,
__entry->framelen, __entry->skbaddr)
);
+struct iwl_error_event_table;
TRACE_EVENT(iwlwifi_dev_ucode_error,
- TP_PROTO(const struct device *dev, u32 desc, u32 tsf_low,
- u32 data1, u32 data2, u32 line, u32 blink2, u32 ilink1,
- u32 ilink2, u32 bcon_time, u32 gp1, u32 gp2, u32 rev_type,
- u32 major, u32 minor, u32 hw_ver, u32 brd_ver),
- TP_ARGS(dev, desc, tsf_low, data1, data2, line,
- blink2, ilink1, ilink2, bcon_time, gp1, gp2,
- rev_type, major, minor, hw_ver, brd_ver),
+ TP_PROTO(const struct device *dev, const struct iwl_error_event_table *table,
+ u32 hw_ver, u32 brd_ver),
+ TP_ARGS(dev, table, hw_ver, brd_ver),
TP_STRUCT__entry(
DEV_ENTRY
__field(u32, desc)
@@ -155,20 +152,20 @@ TRACE_EVENT(iwlwifi_dev_ucode_error,
),
TP_fast_assign(
DEV_ASSIGN;
- __entry->desc = desc;
- __entry->tsf_low = tsf_low;
- __entry->data1 = data1;
- __entry->data2 = data2;
- __entry->line = line;
- __entry->blink2 = blink2;
- __entry->ilink1 = ilink1;
- __entry->ilink2 = ilink2;
- __entry->bcon_time = bcon_time;
- __entry->gp1 = gp1;
- __entry->gp2 = gp2;
- __entry->rev_type = rev_type;
- __entry->major = major;
- __entry->minor = minor;
+ __entry->desc = table->error_id;
+ __entry->tsf_low = table->tsf_low;
+ __entry->data1 = table->data1;
+ __entry->data2 = table->data2;
+ __entry->line = table->line;
+ __entry->blink2 = table->blink2;
+ __entry->ilink1 = table->ilink1;
+ __entry->ilink2 = table->ilink2;
+ __entry->bcon_time = table->bcon_time;
+ __entry->gp1 = table->gp1;
+ __entry->gp2 = table->gp2;
+ __entry->rev_type = table->gp3;
+ __entry->major = table->ucode_ver;
+ __entry->minor = table->hw_ver;
__entry->hw_ver = hw_ver;
__entry->brd_ver = brd_ver;
),
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
index 50510fb6ab8c..6aa719865a58 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
@@ -30,6 +30,7 @@
#ifndef __CHECKER__
#include "iwl-trans.h"
+#include "dvm/commands.h"
#define CREATE_TRACE_POINTS
#include "iwl-devtrace.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index d65e1db7c097..5442ead876eb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -549,12 +549,7 @@ static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u32 base)
IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
- trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
- table.data1, table.data2, table.data3,
- table.blink2, table.ilink1,
- table.ilink2, table.bcon_time, table.gp1,
- table.gp2, table.fw_rev_type, table.major,
- table.minor, table.hw_ver, table.brd_ver);
+ trace_iwlwifi_dev_ucode_error(trans->dev, &table, table.hw_ver, table.brd_ver);
IWL_ERR(mvm, "0x%08X | %-28s\n", table.error_id,
desc_lookup(table.error_id));
IWL_ERR(mvm, "0x%08X | trm_hw_status0\n", table.trm_hw_status0);
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 02/10] net/mediatek: disambiguate mt76 vs mt7601u trace events
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
two trace events defined with the same name and both unused.
They conflict in allyesconfig build. Rename one of them.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
drivers/net/wireless/mediatek/mt7601u/trace.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt7601u/trace.h b/drivers/net/wireless/mediatek/mt7601u/trace.h
index 289897300ef0..82c8898b9076 100644
--- a/drivers/net/wireless/mediatek/mt7601u/trace.h
+++ b/drivers/net/wireless/mediatek/mt7601u/trace.h
@@ -34,7 +34,7 @@
#define REG_PR_FMT "%04x=%08x"
#define REG_PR_ARG __entry->reg, __entry->val
-DECLARE_EVENT_CLASS(dev_reg_evt,
+DECLARE_EVENT_CLASS(dev_reg_evtu,
TP_PROTO(struct mt7601u_dev *dev, u32 reg, u32 val),
TP_ARGS(dev, reg, val),
TP_STRUCT__entry(
@@ -51,12 +51,12 @@ DECLARE_EVENT_CLASS(dev_reg_evt,
)
);
-DEFINE_EVENT(dev_reg_evt, reg_read,
+DEFINE_EVENT(dev_reg_evtu, reg_read,
TP_PROTO(struct mt7601u_dev *dev, u32 reg, u32 val),
TP_ARGS(dev, reg, val)
);
-DEFINE_EVENT(dev_reg_evt, reg_write,
+DEFINE_EVENT(dev_reg_evtu, reg_write,
TP_PROTO(struct mt7601u_dev *dev, u32 reg, u32 val),
TP_ARGS(dev, reg, val)
);
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 10/10] selftests/bpf: test for bpf_get_stackid() from raw tracepoints
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
similar to traditional traceopint test add bpf_get_stackid() test
from raw tracepoints
and reduce verbosity of existing stackmap test
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/bpf/test_progs.c | 91 ++++++++++++++++++++++++--------
1 file changed, 70 insertions(+), 21 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index e9df48b306df..faadbe233966 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -877,7 +877,7 @@ static void test_stacktrace_map()
err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
- goto out;
+ return;
/* Get the ID for the sched/sched_switch tracepoint */
snprintf(buf, sizeof(buf),
@@ -888,8 +888,7 @@ static void test_stacktrace_map()
bytes = read(efd, buf, sizeof(buf));
close(efd);
- if (CHECK(bytes <= 0 || bytes >= sizeof(buf),
- "read", "bytes %d errno %d\n", bytes, errno))
+ if (bytes <= 0 || bytes >= sizeof(buf))
goto close_prog;
/* Open the perf event and attach bpf progrram */
@@ -906,29 +905,24 @@ static void test_stacktrace_map()
goto close_prog;
err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
- err, errno))
- goto close_pmu;
+ if (err)
+ goto disable_pmu;
err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
- err, errno))
+ if (err)
goto disable_pmu;
/* find map fds */
control_map_fd = bpf_find_map(__func__, obj, "control_map");
- if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
- "err %d errno %d\n", err, errno))
+ if (control_map_fd < 0)
goto disable_pmu;
stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
- if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
- "err %d errno %d\n", err, errno))
+ if (stackid_hmap_fd < 0)
goto disable_pmu;
stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
- if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
- err, errno))
+ if (stackmap_fd < 0)
goto disable_pmu;
/* give some time for bpf program run */
@@ -945,24 +939,78 @@ static void test_stacktrace_map()
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
+ goto disable_pmu_noerr;
err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
"err %d errno %d\n", err, errno))
- ; /* fall through */
+ goto disable_pmu_noerr;
+ goto disable_pmu_noerr;
disable_pmu:
+ error_cnt++;
+disable_pmu_noerr:
ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-
-close_pmu:
close(pmu_fd);
-
close_prog:
bpf_object__close(obj);
+}
-out:
- return;
+static void test_stacktrace_map_raw_tp()
+{
+ int control_map_fd, stackid_hmap_fd, stackmap_fd;
+ const char *file = "./test_stacktrace_map.o";
+ int efd, err, prog_fd;
+ __u32 key, val, duration = 0;
+ struct bpf_object *obj;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+ return;
+
+ efd = bpf_raw_tracepoint_open("sched_switch", prog_fd);
+ if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+
+ /* find map fds */
+ control_map_fd = bpf_find_map(__func__, obj, "control_map");
+ if (control_map_fd < 0)
+ goto close_prog;
+
+ stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
+ if (stackid_hmap_fd < 0)
+ goto close_prog;
+
+ stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
+ if (stackmap_fd < 0)
+ goto close_prog;
+
+ /* give some time for bpf program run */
+ sleep(1);
+
+ /* disable stack trace collection */
+ key = 0;
+ val = 1;
+ bpf_map_update_elem(control_map_fd, &key, &val, 0);
+
+ /* for every element in stackid_hmap, we can find a corresponding one
+ * in stackmap, and vise versa.
+ */
+ err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
+ if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
+ "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
+ if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
+ "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ goto close_prog_noerr;
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
}
static int extract_build_id(char *build_id, size_t size)
@@ -1138,6 +1186,7 @@ int main(void)
test_tp_attach_query();
test_stacktrace_map();
test_stacktrace_build_id();
+ test_stacktrace_map_raw_tp();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 09/10] samples/bpf: raw tracepoint test
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
add empty raw_tracepoint bpf program to test overhead similar
to kprobe and traditional tracepoint tests
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
samples/bpf/Makefile | 1 +
samples/bpf/bpf_load.c | 14 ++++++++++++++
samples/bpf/test_overhead_raw_tp_kern.c | 17 +++++++++++++++++
samples/bpf/test_overhead_user.c | 12 ++++++++++++
4 files changed, 44 insertions(+)
create mode 100644 samples/bpf/test_overhead_raw_tp_kern.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 2c2a587e0942..4d6a6edd4bf6 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -119,6 +119,7 @@ always += offwaketime_kern.o
always += spintest_kern.o
always += map_perf_test_kern.o
always += test_overhead_tp_kern.o
+always += test_overhead_raw_tp_kern.o
always += test_overhead_kprobe_kern.o
always += parse_varlen.o parse_simple.o parse_ldabs.o
always += test_cgrp2_tc_kern.o
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b1a310c3ae89..bebe4188b4b3 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -61,6 +61,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
bool is_kprobe = strncmp(event, "kprobe/", 7) == 0;
bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0;
bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0;
+ bool is_raw_tracepoint = strncmp(event, "raw_tracepoint/", 15) == 0;
bool is_xdp = strncmp(event, "xdp", 3) == 0;
bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
@@ -85,6 +86,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
prog_type = BPF_PROG_TYPE_KPROBE;
} else if (is_tracepoint) {
prog_type = BPF_PROG_TYPE_TRACEPOINT;
+ } else if (is_raw_tracepoint) {
+ prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT;
} else if (is_xdp) {
prog_type = BPF_PROG_TYPE_XDP;
} else if (is_perf_event) {
@@ -131,6 +134,16 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
return populate_prog_array(event, fd);
}
+ if (is_raw_tracepoint) {
+ efd = bpf_raw_tracepoint_open(event + 15, fd);
+ if (efd < 0) {
+ printf("tracepoint %s %s\n", event + 15, strerror(errno));
+ return -1;
+ }
+ event_fd[prog_cnt - 1] = efd;
+ return 0;
+ }
+
if (is_kprobe || is_kretprobe) {
if (is_kprobe)
event += 7;
@@ -587,6 +600,7 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
if (memcmp(shname, "kprobe/", 7) == 0 ||
memcmp(shname, "kretprobe/", 10) == 0 ||
memcmp(shname, "tracepoint/", 11) == 0 ||
+ memcmp(shname, "raw_tracepoint/", 15) == 0 ||
memcmp(shname, "xdp", 3) == 0 ||
memcmp(shname, "perf_event", 10) == 0 ||
memcmp(shname, "socket", 6) == 0 ||
diff --git a/samples/bpf/test_overhead_raw_tp_kern.c b/samples/bpf/test_overhead_raw_tp_kern.c
new file mode 100644
index 000000000000..d2af8bc1c805
--- /dev/null
+++ b/samples/bpf/test_overhead_raw_tp_kern.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("raw_tracepoint/task_rename")
+int prog(struct bpf_raw_tracepoint_args *ctx)
+{
+ return 0;
+}
+
+SEC("raw_tracepoint/urandom_read")
+int prog2(struct bpf_raw_tracepoint_args *ctx)
+{
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c
index d291167fd3c7..e1d35e07a10e 100644
--- a/samples/bpf/test_overhead_user.c
+++ b/samples/bpf/test_overhead_user.c
@@ -158,5 +158,17 @@ int main(int argc, char **argv)
unload_progs();
}
+ if (test_flags & 0xC0) {
+ snprintf(filename, sizeof(filename),
+ "%s_raw_tp_kern.o", argv[0]);
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+ printf("w/RAW_TRACEPOINT\n");
+ run_perf_test(num_cpu, test_flags >> 6);
+ unload_progs();
+ }
+
return 0;
}
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 06/10] tracepoint: compute num_args at build time
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
compute number of arguments passed into tracepoint
at compile time and store it as part of 'struct tracepoint'.
The number is necessary to check safety of bpf program access that
is coming in subsequent patch.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
include/linux/tracepoint-defs.h | 1 +
include/linux/tracepoint.h | 12 ++++++------
include/trace/define_trace.h | 14 +++++++-------
3 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index 64ed7064f1fa..39a283c61c51 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -33,6 +33,7 @@ struct tracepoint {
int (*regfunc)(void);
void (*unregfunc)(void);
struct tracepoint_func __rcu *funcs;
+ u32 num_args;
};
#endif
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index c94f466d57ef..c92f4adbc0d7 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -230,18 +230,18 @@ extern void syscall_unregfunc(void);
* structures, so we create an array of pointers that will be used for iteration
* on the tracepoints.
*/
-#define DEFINE_TRACE_FN(name, reg, unreg) \
+#define DEFINE_TRACE_FN(name, reg, unreg, num_args) \
static const char __tpstrtab_##name[] \
__attribute__((section("__tracepoints_strings"))) = #name; \
struct tracepoint __tracepoint_##name \
__attribute__((section("__tracepoints"))) = \
- { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
+ { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL, num_args };\
static struct tracepoint * const __tracepoint_ptr_##name __used \
__attribute__((section("__tracepoints_ptrs"))) = \
&__tracepoint_##name;
-#define DEFINE_TRACE(name) \
- DEFINE_TRACE_FN(name, NULL, NULL);
+#define DEFINE_TRACE(name, num_args) \
+ DEFINE_TRACE_FN(name, NULL, NULL, num_args);
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \
EXPORT_SYMBOL_GPL(__tracepoint_##name)
@@ -275,8 +275,8 @@ extern void syscall_unregfunc(void);
return false; \
}
-#define DEFINE_TRACE_FN(name, reg, unreg)
-#define DEFINE_TRACE(name)
+#define DEFINE_TRACE_FN(name, reg, unreg, num_args)
+#define DEFINE_TRACE(name, num_args)
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
#define EXPORT_TRACEPOINT_SYMBOL(name)
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index d9e3d4aa3f6e..96b22ace9ae7 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -25,7 +25,7 @@
#undef TRACE_EVENT
#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef TRACE_EVENT_CONDITION
#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
@@ -39,24 +39,24 @@
#undef TRACE_EVENT_FN
#define TRACE_EVENT_FN(name, proto, args, tstruct, \
assign, print, reg, unreg) \
- DEFINE_TRACE_FN(name, reg, unreg)
+ DEFINE_TRACE_FN(name, reg, unreg, COUNT_ARGS(args))
#undef TRACE_EVENT_FN_COND
#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct, \
assign, print, reg, unreg) \
- DEFINE_TRACE_FN(name, reg, unreg)
+ DEFINE_TRACE_FN(name, reg, unreg, COUNT_ARGS(args))
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef DEFINE_EVENT_FN
#define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
- DEFINE_TRACE_FN(name, reg, unreg)
+ DEFINE_TRACE_FN(name, reg, unreg, COUNT_ARGS(args))
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef DEFINE_EVENT_CONDITION
#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
@@ -64,7 +64,7 @@
#undef DECLARE_TRACE
#define DECLARE_TRACE(name, proto, args) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef TRACE_INCLUDE
#undef __TRACE_INCLUDE
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 08/10] libbpf: add bpf_raw_tracepoint_open helper
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
add bpf_raw_tracepoint_open(const char *name, int prog_fd) api to libbpf
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/include/uapi/linux/bpf.h | 11 +++++++++++
tools/lib/bpf/bpf.c | 11 +++++++++++
tools/lib/bpf/bpf.h | 1 +
3 files changed, 23 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d245c41213ac..58060bec999d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -94,6 +94,7 @@ enum bpf_cmd {
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
+ BPF_RAW_TRACEPOINT_OPEN,
};
enum bpf_map_type {
@@ -134,6 +135,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_RAW_TRACEPOINT,
};
enum bpf_attach_type {
@@ -344,6 +346,11 @@ union bpf_attr {
__aligned_u64 prog_ids;
__u32 prog_cnt;
} query;
+
+ struct {
+ __u64 name;
+ __u32 prog_fd;
+ } raw_tracepoint;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -1151,4 +1158,8 @@ struct bpf_cgroup_dev_ctx {
__u32 minor;
};
+struct bpf_raw_tracepoint_args {
+ __u64 args[0];
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 592a58a2b681..e0500055f1a6 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -428,6 +428,17 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
return err;
}
+int bpf_raw_tracepoint_open(const char *name, int prog_fd)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.raw_tracepoint.name = ptr_to_u64(name);
+ attr.raw_tracepoint.prog_fd = prog_fd;
+
+ return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+}
+
int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
{
struct sockaddr_nl sa;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 8d18fb73d7fb..ee59342c6f42 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -79,4 +79,5 @@ int bpf_map_get_fd_by_id(__u32 id);
int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
__u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
+int bpf_raw_tracepoint_open(const char *name, int prog_fd);
#endif
--
2.9.5
^ permalink raw reply related
* [PATCH net-next] liquidio: Prioritize control messages
From: Felix Manlunas @ 2018-03-28 2:25 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, intiyaz.basha
From: Intiyaz Basha <intiyaz.basha@cavium.com>
During heavy tx traffic, control messages (sent by liquidio driver to NIC
firmware) sometimes do not get processed in a timely manner. Reason is:
the low-level metadata of control messages and that of egress network
packets indicate that they have the same priority.
Fix it by setting a higher priority for control messages through the new
ctrl_qpg field in the oct_txpciq struct. It is the NIC firmware that does
the actual setting of priority by writing to the new ctrl_qpg field; the
host driver treats that value as opaque and just assigns it to pki_ih3->qpg
Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/liquidio_common.h | 8 ++++++--
drivers/net/ethernet/cavium/liquidio/request_manager.c | 3 ++-
2 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 82a783d..75eea83 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -712,9 +712,13 @@ enum lio_phy_type {
u64 pkind:6;
u64 use_qpg:1;
u64 qpg:11;
- u64 reserved:30;
+ u64 reserved0:10;
+ u64 ctrl_qpg:11;
+ u64 reserved:9;
#else
- u64 reserved:30;
+ u64 reserved:9;
+ u64 ctrl_qpg:11;
+ u64 reserved0:10;
u64 qpg:11;
u64 use_qpg:1;
u64 pkind:6;
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 2766af0..b127035 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -628,7 +628,8 @@ static void check_db_timeout(struct work_struct *work)
pki_ih3->tag = LIO_CONTROL;
pki_ih3->tagtype = ATOMIC_TAG;
pki_ih3->qpg =
- oct->instr_queue[sc->iq_no]->txpciq.s.qpg;
+ oct->instr_queue[sc->iq_no]->txpciq.s.ctrl_qpg;
+
pki_ih3->pm = 0x7;
pki_ih3->sl = 8;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] ipv6: export ip6 fragments sysctl to unprivileged users
From: Eric Dumazet @ 2018-03-28 2:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet, Nikolay Borisov
IPv4 was changed in commit 52a773d645e9 ("net: Export ip fragment
sysctl to unprivileged users")
The only sysctl that is not per-netns is not used :
ip6frag_secret_interval
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Nikolay Borisov <kernel@kyup.com>
---
net/ipv6/reassembly.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index afbc000ad4f2912acd475246e2ff2368c1bbeacb..08a139f14d0f6fa8ca326088cce1144411e09bf5 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -650,10 +650,6 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
table[1].data = &net->ipv6.frags.low_thresh;
table[1].extra2 = &net->ipv6.frags.high_thresh;
table[2].data = &net->ipv6.frags.timeout;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[0].procname = NULL;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* Re: RFC on writel and writel_relaxed
From: Linus Torvalds @ 2018-03-28 2:51 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Alexander Duyck, Will Deacon, Sinan Kaya, Arnd Bergmann,
Jason Gunthorpe, David Laight, Oliver,
open list:LINUX FOR POWERPC (32-BIT AND 64-BIT),
linux-rdma@vger.kernel.org, Alexander Duyck, Paul E. McKenney,
netdev@vger.kernel.org
In-Reply-To: <1522198981.7364.81.camel@kernel.crashing.org>
On Tue, Mar 27, 2018 at 3:03 PM, Benjamin Herrenschmidt
<benh@kernel.crashing.org> wrote:
>
> The discussion at hand is about
>
> dma_buffer->foo = 1; /* WB */
> writel(KICK, DMA_KICK_REGISTER); /* UC */
Yes. That certainly is ordered on x86. In fact, afaik it's ordered
even if that writel() might be of type WC, because that only delays
writes, it doesn't move them earlier.
Whether people *do* that or not, I don't know. But I wouldn't be
surprised if they do.
So if it's a DMA buffer, it's "cached". And even cached accesses are
ordered wrt MMIO.
Basically, to get unordered writes on x86, you need to either use
explicitly nontemporal stores, or have a writecombining region with
back-to-back writes that actually combine.
And nobody really does that nontemporal store thing any more because
the hardware that cared pretty much doesn't exist any more. It was too
much pain. People use DMA and maybe an UC store for starting the DMA
(or possibly a WC buffer that gets multiple stores in ascending order
as a stream of commands).
Things like UC will force everything to be entirely ordered, but even
without UC, loads won't pass loads, and stores won't pass stores.
> Now it appears that this wasn't fully understood back then, and some
> people are now saying that x86 might not even provide that semantic
> always.
Oh, the above UC case is absoutely guaranteed.
And I think even if it's WC, the write to kick off the DMA is ordered
wrt the cached write.
On x86, I think you need barriers only if you do things like
- do two non-temporal stores and require them to be ordered: put a
sfence or mfence in between them.
- do two WC stores, and make sure they do not combine: put a sfence
or mfence between them.
- do a store, and a subsequent from a different address, and neither
of them is UC: put a mfence between them. But note that this is
literally just "load after store". A "store after load" doesn't need
one.
I think that's pretty much it.
For example, the "lfence" instruction is almost entirely pointless on
x86 - it was designed back in the time when people *thought* they
might re-order loads. But loads don't get re-ordered. At least Intel
seems to document that only non-temporal *stores* can get re-ordered
wrt each other.
End result: lfence is a historical oddity that can now be used to
guarantee that a previous load has finished, and that in turn meant
that it is now used in the Spectre mitigations. But it basically has
no real memory ordering meaning since nothing passes an earlier load
anyway, it's more of a pipeline thing.
But in the end, one question is just "how much do drivers actually
_rely_ on the x86 strong ordering?"
We so support "smp_wmb()" even though x86 has strong enough ordering
that just a barrier suffices. Somebody might just say "screw the x86
memory ordering, we're relaxed, and we'll fix up the drivers we care
about".
The only issue really is that 99.9% of all testing gets done on x86
unless you look at specific SoC drivers.
On ARM, for example, there is likely little reason to care about x86
memory ordering, because there is almost zero driver overlap between
x86 and ARM.
*Historically*, the reason for following the x86 IO ordering was
simply that a lot of architectures used the drivers that were
developed on x86. The alpha and powerpc workstations were *designed*
with the x86 IO bus (PCI, then PCIe) and to work with the devices that
came with it.
ARM? PCIe is almost irrelevant. For ARM servers, if they ever take
off, sure. But 99.99% of ARM is about their own SoC's, and so "x86
test coverage" is simply not an issue.
How much of an issue is it for Power? Maybe you decide it's not a big deal.
Then all the above is almost irrelevant.
Linus
^ permalink raw reply
* Re: [V9fs-developer] [PATCH] net/9p: fix potential refcnt problem of trans module
From: cgxu519 @ 2018-03-28 2:52 UTC (permalink / raw)
To: jiangyiwen
Cc: cgxu519@gmx.com, ericvh, rminnich, lucho, davem, v9fs-developer,
netdev
In-Reply-To: <5ABAF980.5060406@huawei.com>
在 2018年3月28日，上午10:10，jiangyiwen <jiangyiwen@huawei.com> 写道：
>
> On 2018/3/27 20:49, Chengguang Xu wrote:
>> When specifying trans_mod multiple times in a mount,
>> it may cause inaccurate refcount of trans module. Also,
>> in the error case of option parsing, we should put the
>> trans module if we have already got.
>>
>> Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
>> ---
>> net/9p/client.c | 5 ++++-
>> 1 file changed, 4 insertions(+), 1 deletion(-)
>>
>> diff --git a/net/9p/client.c b/net/9p/client.c
>> index b433aff..7ccfb4b 100644
>> --- a/net/9p/client.c
>> +++ b/net/9p/client.c
>> @@ -190,7 +190,9 @@ static int parse_opts(char *opts, struct p9_client *clnt)
>> p9_debug(P9_DEBUG_ERROR,
>> "problem allocating copy of trans arg\n");
>> goto free_and_return;
>> - }
>> + }
>> +
>> + v9fs_put_trans(clnt->trans_mod);
>
> I think this should return error if using multiple times
> in a mount.
Fail or retake are just different policies how to deal with this kind of situation,
most filesystems in kernel choose retaking new value, so we’d better keep consistence
with others unless there is a necessary reason.
Thanks,
Chengguang.
>
>> clnt->trans_mod = v9fs_get_trans_by_name(s);
>> if (clnt->trans_mod == NULL) {
>> pr_info("Could not find request transport: %s\n",
>> @@ -226,6 +228,7 @@ static int parse_opts(char *opts, struct p9_client *clnt)
>> }
>>
>> free_and_return:
>> + v9fs_put_trans(clnt->trans_mod);
>
> This looks good.
>
>> kfree(tmp_options);
>> return ret;
>> }
>>
>
>
^ permalink raw reply
* RE: [PATCH] net: fec: set dma_coherent_mask
From: Andy Duan @ 2018-03-28 3:04 UTC (permalink / raw)
To: Geert Uytterhoeven, Greg Ungerer; +Cc: netdev, Linux/m68k
In-Reply-To: <CAMuHMdW_ZmN9aptLoSK7JYLVaLyErkFyGU2sb2f564uCUeBh6w@mail.gmail.com>
From: Geert Uytterhoeven <geert@linux-m68k.org> Sent: 2018年3月27日 20:59
> Hi Greg,
>
> On Mon, Mar 26, 2018 at 3:36 PM, Greg Ungerer <gerg@linux-m68k.org> wrote:
> > As of commit 205e1b7f51e4 ("dma-mapping: warn when there is no
> > coherent_dma_mask") the Freescale FEC driver is issuing the following
> > warning on driver initialization on ColdFire systems:
> >
> > WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 0x40159e20
> > Modules linked in:
> > CPU: 0 PID: 1 Comm: swapper Not tainted 4.16.0-rc7-dirty #4 Stack from
> > 41833dd8:
> > 41833dd8 40259c53 40025534 40279e26 00000003 00000000
> 4004e514 41827000
> > 400255de 40244e42 00000204 40159e20 00000009 00000000
> 00000000 4024531d
> > 40159e20 40244e42 00000204 00000000 00000000 00000000
> 00000007 00000000
> > 00000000 40279e26 4028d040 40226576 4003ae88 40279e26
> 418273f6 41833ef8
> > 7fffffff 418273f2 41867028 4003c9a2 4180ac6c 00000004 41833f8c
> 4013e71c
> > 40279e1c 40279e26 40226c16 4013ced2 40279e26 40279e58
> 4028d040
> > 00000000 Call Trace:
> > [<40025534>] 0x40025534
> > [<4004e514>] 0x4004e514
> > [<400255de>] 0x400255de
> > [<40159e20>] 0x40159e20
> > [<40159e20>] 0x40159e20
> >
> > It is not fatal, the driver and the system continue to function normally.
> >
> > As per the warning the coherent_dma_mask is not set on this device.
> > There is nothing special about the DMA memory coherency on this
> > hardware so we can just set the mask to 32bits during probe.
> >
> > Signed-off-by: Greg Ungerer <gerg@linux-m68k.org>
>
> Thanks for your patch!
>
> > ---
> > drivers/net/ethernet/freescale/fec_main.c | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > Is this the best way to handle this problem?
> > Comments welcome...
> >
> > diff --git a/drivers/net/ethernet/freescale/fec_main.c
> > b/drivers/net/ethernet/freescale/fec_main.c
> > index d4604bc..3cb130a 100644
> > --- a/drivers/net/ethernet/freescale/fec_main.c
> > +++ b/drivers/net/ethernet/freescale/fec_main.c
> > @@ -2702,6 +2702,8 @@ static int fec_enet_alloc_queue(struct net_device
> *ndev)
> > int ret = 0;
> > struct fec_enet_priv_tx_q *txq;
> >
> > + dma_set_coherent_mask(&fep->pdev->dev, DMA_BIT_MASK(32));
> > +
> > for (i = 0; i < fep->num_tx_queues; i++) {
> > txq = kzalloc(sizeof(*txq), GFP_KERNEL);
> > if (!txq) {
>
> As per your other email, this does not trigger on iMX systems using DT.
> Hence I'm wondering if the Coldfire platform code shouldn't just do the same what
> drivers/of/device.c does, cfr.
> https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.s
> pinics.net%2Flists%2Flinux-m68k%2Fmsg10929.html&data=02%7C01%7Cfugan
> g.duan%40nxp.com%7C3db2dbadf1154965370608d593e294b2%7C686ea1d3
> bc2b4c6fa92cd99c5c301635%7C0%7C0%7C636577523756185995&sdata=bsO
> F%2BnSeXTP7C%2F55JLO3Pv8YybPahMaZDyqB16f9ySA%3D&reserved=0?
>
> Gr{oetje,eeting}s,
>
> Geert
>
It is better to use of_dma_configure(&pdev->dev, np), it iommu support, device also can allocate memory from 64bit space.
Andy
^ permalink raw reply
* Re: RFC on writel and writel_relaxed
From: Sinan Kaya @ 2018-03-28 3:24 UTC (permalink / raw)
To: Linus Torvalds, Benjamin Herrenschmidt
Cc: Alexander Duyck, Will Deacon, Arnd Bergmann, Jason Gunthorpe,
David Laight, Oliver,
open list:LINUX FOR POWERPC (32-BIT AND 64-BIT),
linux-rdma@vger.kernel.org, Alexander Duyck, Paul E. McKenney,
netdev@vger.kernel.org
In-Reply-To: <CA+55aFyTeuXPmC5-1JGh2ow-rf5wMA6Vcv0aeS_q0_EnptSK9Q@mail.gmail.com>
On 3/27/2018 10:51 PM, Linus Torvalds wrote:
>> The discussion at hand is about
>>
>> dma_buffer->foo = 1; /* WB */
>> writel(KICK, DMA_KICK_REGISTER); /* UC */
> Yes. That certainly is ordered on x86. In fact, afaik it's ordered
> even if that writel() might be of type WC, because that only delays
> writes, it doesn't move them earlier.
Now that we clarified x86 myth, Is this guaranteed on all architectures?
We keep getting IA64 exception example. Maybe, this is also corrected since
then.
Jose Abreu says "I don't know about x86 but arc architecture doesn't
have a wmb() in the writel() function (in some configs)".
As long as we have these exceptions, these wmb() in common drivers is not
going anywhere and relaxed-arches will continue paying performance penalty.
I see 15% performance loss on ARM64 servers using Intel i40e network
drivers and an XL710 adapter due to CPU keeping itself busy doing barriers
most of the time rather than real work because of sequences like this all over
the place.
dma_buffer->foo = 1; /* WB */
wmb()
writel(KICK, DMA_KICK_REGISTER); /* UC */
I posted several patches last week to remove duplicate barriers on ARM while
trying to make the code friendly with other architectures.
Basically changing it to
dma_buffer->foo = 1; /* WB */
wmb()
writel_relaxed(KICK, DMA_KICK_REGISTER); /* UC */
mmiowb()
This is a small step in the performance direction until we remove all exceptions.
https://www.spinics.net/lists/netdev/msg491842.html
https://www.spinics.net/lists/linux-rdma/msg62434.html
https://www.spinics.net/lists/arm-kernel/msg642336.html
Discussion started to move around the need for relaxed API on PPC and then
why wmb() question came up.
Sinan
--
Sinan Kaya
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.
^ permalink raw reply
* Re: [SPAMMY (6.9)]Re: [PATCH v13 net-next 02/12] ethtool: enable Inline TLS in HW
From: Atul Gupta @ 2018-03-28 3:36 UTC (permalink / raw)
To: Sabrina Dubroca
Cc: davem, herbert, davejwatson, sbrivio, linux-crypto, netdev,
werner, leedom, swise, indranil, ganeshgr
In-Reply-To: <20180327204420.GA18933@bistromath.localdomain>
On 3/28/2018 2:14 AM, Sabrina Dubroca wrote:
> 2018-03-27, 23:06:31 +0530, Atul Gupta wrote:
>> Ethtool option enables TLS record offload on HW, user
>> configures the feature for netdev capable of Inline TLS.
>> This allows user to define custom sk_prot for Inline TLS sock
>>
>> Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
>> Reviewed-by: Sabrina Dubroca <sdubroca@redhat.com>
> uh, what? I definitely didn't give my "Reviewed-by" for any of these
> patches. Please never do that again.
Sabrina,
I was not clear on protocol. I perhaps want to acknowledge the valuable feedback you
have provided. Will remove this. Thanks
>
^ permalink raw reply
* Re: [V9fs-developer] [PATCH] net/9p: fix potential refcnt problem of trans module
From: jiangyiwen @ 2018-03-28 3:38 UTC (permalink / raw)
To: cgxu519@gmx.com; +Cc: ericvh, rminnich, lucho, davem, v9fs-developer, netdev
In-Reply-To: <FFF9EE2E-713C-48C8-AA8D-9C54BEC2249A@gmx.com>
On 2018/3/28 10:52, cgxu519@gmx.com wrote:
> 在 2018年3月28日，上午10:10，jiangyiwen <jiangyiwen@huawei.com> 写道：
>>
>> On 2018/3/27 20:49, Chengguang Xu wrote:
>>> When specifying trans_mod multiple times in a mount,
>>> it may cause inaccurate refcount of trans module. Also,
>>> in the error case of option parsing, we should put the
>>> trans module if we have already got.
>>>
>>> Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
>>> ---
>>> net/9p/client.c | 5 ++++-
>>> 1 file changed, 4 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/net/9p/client.c b/net/9p/client.c
>>> index b433aff..7ccfb4b 100644
>>> --- a/net/9p/client.c
>>> +++ b/net/9p/client.c
>>> @@ -190,7 +190,9 @@ static int parse_opts(char *opts, struct p9_client *clnt)
>>> p9_debug(P9_DEBUG_ERROR,
>>> "problem allocating copy of trans arg\n");
>>> goto free_and_return;
>>> - }
>>> + }
>>> +
>>> + v9fs_put_trans(clnt->trans_mod);
>>
>> I think this should return error if using multiple times
>> in a mount.
>
> Fail or retake are just different policies how to deal with this kind of situation,
> most filesystems in kernel choose retaking new value, so we’d better keep consistence
> with others unless there is a necessary reason.
>
> Thanks,
> Chengguang.
>
Yes, you're right, most filesystems retake indeed the new value.
Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com>
>
>>
>>> clnt->trans_mod = v9fs_get_trans_by_name(s);
>>> if (clnt->trans_mod == NULL) {
>>> pr_info("Could not find request transport: %s\n",
>>> @@ -226,6 +228,7 @@ static int parse_opts(char *opts, struct p9_client *clnt)
>>> }
>>>
>>> free_and_return:
>>> + v9fs_put_trans(clnt->trans_mod);
>>
>> This looks good.
>>
>>> kfree(tmp_options);
>>> return ret;
>>> }
>>>
>>
>>
>
>
> .
>
^ permalink raw reply
* Re: [PATCH v13 net-next 08/12] crypto : chtls - CPL handler definition
From: Atul Gupta @ 2018-03-28 3:39 UTC (permalink / raw)
To: Stefano Brivio
Cc: davem, herbert, davejwatson, sd, linux-crypto, netdev, werner,
leedom, swise, indranil, ganeshgr
In-Reply-To: <20180327194206.36094fed@epycfail>
On 3/27/2018 11:12 PM, Stefano Brivio wrote:
> On Tue, 27 Mar 2018 23:06:37 +0530
> Atul Gupta <atul.gupta@chelsio.com> wrote:
>
>> Exchange messages with hardware to program the TLS session
>> CPL handlers for messages received from chip.
>>
>> Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
>> Signed-off-by: Michael Werner <werner@chelsio.com>
>> Reviewed-by: Sabrina Dubroca <sdubroca@redhat.com>
>> Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
> No, I haven't.
Stefano,
I was not clear on protocol for reviewed-by tag, I want to acknowledge the feedback
you have provided to code so far. Will remove this.
Thanks
Atul
>
^ permalink raw reply
* [PATCH v2 bpf-next 0/9] bpf: introduce cgroup-bpf bind, connect, post-bind hooks
From: Alexei Starovoitov @ 2018-03-28 3:41 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, kernel-team
v1->v2:
- support expected_attach_type at prog load time so that prog (incl.
context accesses and calls to helpers) can be validated with regard to
specific attach point it is supposed to be attached to.
Later, at attach time, attach type is checked so that it must be same as
at load time if it was provided
- reworked hooks to rely on expected_attach_type, and reduced number of new
prog types from 6 to just 1: BPF_PROG_TYPE_CGROUP_SOCK_ADDR
- reused BPF_PROG_TYPE_CGROUP_SOCK for sys_bind post-hooks
- add selftests for post-sys_bind hook
For our container management we've been using complicated and fragile setup
consisting of LD_PRELOAD wrapper intercepting bind and connect calls from
all containerized applications. Unfortunately it doesn't work for apps that
don't use glibc and changing all applications that run in the datacenter
is not possible due to 3rd party code and libraries (despite being
open source code) and sheer amount of legacy code that has to be rewritten
(we're rewriting what we can in parallel)
These applications are written without containers in mind and have
builtin assumptions about network services. Like an application X
expects to connect localhost:special_port and find service Y in there.
To move application X and service Y into two different containers
LD_PRELOAD approach is used to help one service connect to another
without rewriting them.
Moving these two applications into different L2 (netns) or L3 (vrf)
network isolation scopes doesn't help to solve the problem, since
applications need to see each other like they were running on
the host without containers.
So if app X and app Y would run in different netns something
would need to punch a connectivity hole in those namespaces.
That would be real layering violation (with corresponding
network debugging pains), since clean l2, l3 abstraction would
suddenly support something that breaks through the layers.
Instead we used LD_PRELOAD (and now bpf programs) at bind/connect
time to help applications discover and connect to each other.
All applications are running in init_nens and there are no vrfs.
After bind/connect the normal fib/neighbor core networking
logic works as it should always do and the whole system is
clean from network point of view and can be debugged with
standard tools.
We also considered resurrecting Hannes's afnetns work,
but all hierarchical namespace abstraction don't work due
to these builtin networking assumptions inside the apps.
To run an application inside cgroup container that was not written
with containers in mind we have to make an illusion of running
in non-containerized environment.
In some cases we remember the port and container id in the post-bind hook
in a bpf map and when some other task in a different container is trying
to connect to a service we need to know where this service is running.
It can be remote and can be local. Both client and service may or may not
be written with containers in mind and this sockaddr rewrite is providing
connectivity and load balancing feature.
BPF+cgroup looks to be the best solution for this problem.
Hence we introduce 3 hooks:
- at entry into sys_bind and sys_connect
to let bpf prog look and modify 'struct sockaddr' provided
by user space and fail bind/connect when appropriate
- post sys_bind after port is allocated
The approach works great and has zero overhead for anyone who doesn't
use it and very low overhead when deployed.
Different use case for this feature is to do low overhead firewall
that doesn't need to inspect all packets and works at bind/connect time.
Andrey Ignatov (9):
bpf: Check attach type at prog load time
libbpf: Support expected_attach_type at prog load
bpf: Hooks for sys_bind
selftests/bpf: Selftest for sys_bind hooks
net: Introduce __inet_bind() and __inet6_bind
bpf: Hooks for sys_connect
selftests/bpf: Selftest for sys_connect hooks
bpf: Post-hooks for sys_bind
selftests/bpf: Selftest for sys_bind post-hooks.
include/linux/bpf-cgroup.h | 68 ++-
include/linux/bpf.h | 5 +-
include/linux/bpf_types.h | 1 +
include/linux/filter.h | 11 +
include/net/inet_common.h | 2 +
include/net/ipv6.h | 2 +
include/net/sock.h | 3 +
include/net/udp.h | 1 +
include/uapi/linux/bpf.h | 51 ++-
kernel/bpf/cgroup.c | 39 +-
kernel/bpf/syscall.c | 102 ++++-
kernel/bpf/verifier.c | 7 +-
kernel/trace/bpf_trace.c | 21 +-
net/core/filter.c | 435 +++++++++++++++++--
net/ipv4/af_inet.c | 71 +++-
net/ipv4/tcp_ipv4.c | 16 +
net/ipv4/udp.c | 14 +
net/ipv6/af_inet6.c | 61 ++-
net/ipv6/tcp_ipv6.c | 16 +
net/ipv6/udp.c | 20 +
tools/include/uapi/linux/bpf.h | 51 ++-
tools/lib/bpf/bpf.c | 44 +-
tools/lib/bpf/bpf.h | 17 +-
tools/lib/bpf/libbpf.c | 113 +++--
tools/lib/bpf/libbpf.h | 8 +
tools/testing/selftests/bpf/Makefile | 10 +-
tools/testing/selftests/bpf/bpf_helpers.h | 2 +
tools/testing/selftests/bpf/connect4_prog.c | 45 ++
tools/testing/selftests/bpf/connect6_prog.c | 61 +++
tools/testing/selftests/bpf/test_sock.c | 479 +++++++++++++++++++++
tools/testing/selftests/bpf/test_sock_addr.c | 588 ++++++++++++++++++++++++++
tools/testing/selftests/bpf/test_sock_addr.sh | 57 +++
32 files changed, 2291 insertions(+), 130 deletions(-)
create mode 100644 tools/testing/selftests/bpf/connect4_prog.c
create mode 100644 tools/testing/selftests/bpf/connect6_prog.c
create mode 100644 tools/testing/selftests/bpf/test_sock.c
create mode 100644 tools/testing/selftests/bpf/test_sock_addr.c
create mode 100755 tools/testing/selftests/bpf/test_sock_addr.sh
--
2.9.5
^ permalink raw reply
* [PATCH v2 bpf-next 5/9] net: Introduce __inet_bind() and __inet6_bind
From: Alexei Starovoitov @ 2018-03-28 3:41 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, kernel-team
In-Reply-To: <20180328034140.291484-1-ast@kernel.org>
From: Andrey Ignatov <rdna@fb.com>
Refactor `bind()` code to make it ready to be called from BPF helper
function `bpf_bind()` (will be added soon). Implementation of
`inet_bind()` and `inet6_bind()` is separated into `__inet_bind()` and
`__inet6_bind()` correspondingly. These function can be used from both
`sk_prot->bind` and `bpf_bind()` contexts.
New functions have two additional arguments.
`force_bind_address_no_port` forces binding to IP only w/o checking
`inet_sock.bind_address_no_port` field. It'll allow to bind local end of
a connection to desired IP in `bpf_bind()` w/o changing
`bind_address_no_port` field of a socket. It's useful since `bpf_bind()`
can return an error and we'd need to restore original value of
`bind_address_no_port` in that case if we changed this before calling to
the helper.
`with_lock` specifies whether to lock socket when working with `struct
sk` or not. The argument is set to `true` for `sk_prot->bind`, i.e. old
behavior is preserved. But it will be set to `false` for `bpf_bind()`
use-case. The reason is all call-sites, where `bpf_bind()` will be
called, already hold that socket lock.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/net/inet_common.h | 2 ++
include/net/ipv6.h | 2 ++
net/ipv4/af_inet.c | 39 ++++++++++++++++++++++++---------------
net/ipv6/af_inet6.c | 37 ++++++++++++++++++++++++-------------
4 files changed, 52 insertions(+), 28 deletions(-)
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 500f81375200..384b90c62c0b 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -32,6 +32,8 @@ int inet_shutdown(struct socket *sock, int how);
int inet_listen(struct socket *sock, int backlog);
void inet_sock_destruct(struct sock *sk);
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+ bool force_bind_address_no_port, bool with_lock);
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
int peer);
int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 50a6f0ddb878..2e5fedc56e59 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1066,6 +1066,8 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
int inet6_release(struct socket *sock);
+int __inet6_bind(struct sock *sock, struct sockaddr *uaddr, int addr_len,
+ bool force_bind_address_no_port, bool with_lock);
int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
int peer);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 2dec266507dc..e203a39d6988 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -432,30 +432,37 @@ EXPORT_SYMBOL(inet_release);
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
- struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct sock *sk = sock->sk;
- struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
- unsigned short snum;
- int chk_addr_ret;
- u32 tb_id = RT_TABLE_LOCAL;
int err;
/* If the socket has its own bind function then use it. (RAW) */
if (sk->sk_prot->bind) {
- err = sk->sk_prot->bind(sk, uaddr, addr_len);
- goto out;
+ return sk->sk_prot->bind(sk, uaddr, addr_len);
}
- err = -EINVAL;
if (addr_len < sizeof(struct sockaddr_in))
- goto out;
+ return -EINVAL;
/* BPF prog is run before any checks are done so that if the prog
* changes context in a wrong way it will be caught.
*/
err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr);
if (err)
- goto out;
+ return err;
+
+ return __inet_bind(sk, uaddr, addr_len, false, true);
+}
+EXPORT_SYMBOL(inet_bind);
+
+int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+ bool force_bind_address_no_port, bool with_lock)
+{
+ struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
+ struct inet_sock *inet = inet_sk(sk);
+ struct net *net = sock_net(sk);
+ unsigned short snum;
+ int chk_addr_ret;
+ u32 tb_id = RT_TABLE_LOCAL;
+ int err;
if (addr->sin_family != AF_INET) {
/* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
@@ -499,7 +506,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
* would be illegal to use them (multicast/broadcast) in
* which case the sending device address is used.
*/
- lock_sock(sk);
+ if (with_lock)
+ lock_sock(sk);
/* Check these errors (active socket, double bind). */
err = -EINVAL;
@@ -511,7 +519,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
inet->inet_saddr = 0; /* Use device */
/* Make sure we are allowed to bind here. */
- if ((snum || !inet->bind_address_no_port) &&
+ if ((snum || !(inet->bind_address_no_port ||
+ force_bind_address_no_port)) &&
sk->sk_prot->get_port(sk, snum)) {
inet->inet_saddr = inet->inet_rcv_saddr = 0;
err = -EADDRINUSE;
@@ -528,11 +537,11 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
sk_dst_reset(sk);
err = 0;
out_release_sock:
- release_sock(sk);
+ if (with_lock)
+ release_sock(sk);
out:
return err;
}
-EXPORT_SYMBOL(inet_bind);
int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fa24e3f06ac6..13110bee5c14 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -277,15 +277,7 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
/* bind for INET6 API */
int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
- struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr;
struct sock *sk = sock->sk;
- struct inet_sock *inet = inet_sk(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
- struct net *net = sock_net(sk);
- __be32 v4addr = 0;
- unsigned short snum;
- bool saved_ipv6only;
- int addr_type = 0;
int err = 0;
/* If the socket has its own bind function then use it. */
@@ -302,11 +294,28 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (err)
return err;
+ return __inet6_bind(sk, uaddr, addr_len, false, true);
+}
+EXPORT_SYMBOL(inet6_bind);
+
+int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+ bool force_bind_address_no_port, bool with_lock)
+{
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr;
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct net *net = sock_net(sk);
+ __be32 v4addr = 0;
+ unsigned short snum;
+ bool saved_ipv6only;
+ int addr_type = 0;
+ int err = 0;
+
if (addr->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
addr_type = ipv6_addr_type(&addr->sin6_addr);
- if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM)
+ if ((addr_type & IPV6_ADDR_MULTICAST) && sk->sk_type == SOCK_STREAM)
return -EINVAL;
snum = ntohs(addr->sin6_port);
@@ -314,7 +323,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
!ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
return -EACCES;
- lock_sock(sk);
+ if (with_lock)
+ lock_sock(sk);
/* Check these errors (active socket, double bind). */
if (sk->sk_state != TCP_CLOSE || inet->inet_num) {
@@ -402,7 +412,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
sk->sk_ipv6only = 1;
/* Make sure we are allowed to bind here. */
- if ((snum || !inet->bind_address_no_port) &&
+ if ((snum || !(inet->bind_address_no_port ||
+ force_bind_address_no_port)) &&
sk->sk_prot->get_port(sk, snum)) {
sk->sk_ipv6only = saved_ipv6only;
inet_reset_saddr(sk);
@@ -418,13 +429,13 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
inet->inet_dport = 0;
inet->inet_daddr = 0;
out:
- release_sock(sk);
+ if (with_lock)
+ release_sock(sk);
return err;
out_unlock:
rcu_read_unlock();
goto out;
}
-EXPORT_SYMBOL(inet6_bind);
int inet6_release(struct socket *sock)
{
--
2.9.5
^ permalink raw reply related
* [PATCH v2 bpf-next 3/9] bpf: Hooks for sys_bind
From: Alexei Starovoitov @ 2018-03-28 3:41 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, kernel-team
In-Reply-To: <20180328034140.291484-1-ast@kernel.org>
From: Andrey Ignatov <rdna@fb.com>
== The problem ==
There is a use-case when all processes inside a cgroup should use one
single IP address on a host that has multiple IP configured. Those
processes should use the IP for both ingress and egress, for TCP and UDP
traffic. So TCP/UDP servers should be bound to that IP to accept
incoming connections on it, and TCP/UDP clients should make outgoing
connections from that IP. It should not require changing application
code since it's often not possible.
Currently it's solved by intercepting glibc wrappers around syscalls
such as `bind(2)` and `connect(2)`. It's done by a shared library that
is preloaded for every process in a cgroup so that whenever TCP/UDP
server calls `bind(2)`, the library replaces IP in sockaddr before
passing arguments to syscall. When application calls `connect(2)` the
library transparently binds the local end of connection to that IP
(`bind(2)` with `IP_BIND_ADDRESS_NO_PORT` to avoid performance penalty).
Shared library approach is fragile though, e.g.:
* some applications clear env vars (incl. `LD_PRELOAD`);
* `/etc/ld.so.preload` doesn't help since some applications are linked
with option `-z nodefaultlib`;
* other applications don't use glibc and there is nothing to intercept.
== The solution ==
The patch provides much more reliable in-kernel solution for the 1st
part of the problem: binding TCP/UDP servers on desired IP. It does not
depend on application environment and implementation details (whether
glibc is used or not).
It adds new eBPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` and
attach types `BPF_CGROUP_INET4_BIND` and `BPF_CGROUP_INET6_BIND`
(similar to already existing `BPF_CGROUP_INET_SOCK_CREATE`).
The new program type is intended to be used with sockets (`struct sock`)
in a cgroup and provided by user `struct sockaddr`. Pointers to both of
them are parts of the context passed to programs of newly added types.
The new attach types provides hooks in `bind(2)` system call for both
IPv4 and IPv6 so that one can write a program to override IP addresses
and ports user program tries to bind to and apply such a program for
whole cgroup.
== Implementation notes ==
[1]
Separate attach types for `AF_INET` and `AF_INET6` are added
intentionally to prevent reading/writing to offsets that don't make
sense for corresponding socket family. E.g. if user passes `sockaddr_in`
it doesn't make sense to read from / write to `user_ip6[]` context
fields.
[2]
The write access to `struct bpf_sock_addr_kern` is implemented using
special field as an additional "register".
There are just two registers in `sock_addr_convert_ctx_access`: `src`
with value to write and `dst` with pointer to context that can't be
changed not to break later instructions. But the fields, allowed to
write to, are not available directly and to access them address of
corresponding pointer has to be loaded first. To get additional register
the 1st not used by `src` and `dst` one is taken, its content is saved
to `bpf_sock_addr_kern.tmp_reg`, then the register is used to load
address of pointer field, and finally the register's content is restored
from the temporary field after writing `src` value.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf-cgroup.h | 21 ++++
include/linux/bpf_types.h | 1 +
include/linux/filter.h | 10 ++
include/uapi/linux/bpf.h | 23 +++++
kernel/bpf/cgroup.c | 36 +++++++
kernel/bpf/syscall.c | 36 +++++--
kernel/bpf/verifier.c | 1 +
net/core/filter.c | 232 +++++++++++++++++++++++++++++++++++++++++++++
net/ipv4/af_inet.c | 7 ++
net/ipv6/af_inet6.c | 7 ++
10 files changed, 366 insertions(+), 8 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 8a4566691c8f..67dc4a6471ad 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -6,6 +6,7 @@
#include <uapi/linux/bpf.h>
struct sock;
+struct sockaddr;
struct cgroup;
struct sk_buff;
struct bpf_sock_ops_kern;
@@ -63,6 +64,10 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
int __cgroup_bpf_run_filter_sk(struct sock *sk,
enum bpf_attach_type type);
+int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
+ struct sockaddr *uaddr,
+ enum bpf_attach_type type);
+
int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
struct bpf_sock_ops_kern *sock_ops,
enum bpf_attach_type type);
@@ -103,6 +108,20 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
__ret; \
})
+#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \
+ __ret; \
+})
+
+#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) \
+ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND)
+
+#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) \
+ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND)
+
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \
({ \
int __ret = 0; \
@@ -135,6 +154,8 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5e2e8a49fb21..ac2a3a2a082b 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -8,6 +8,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act)
BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr)
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout)
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout)
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5787280b1e88..9a172e131706 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1019,6 +1019,16 @@ static inline int bpf_tell_extensions(void)
return SKF_AD_MAX;
}
+struct bpf_sock_addr_kern {
+ struct sock *sk;
+ struct sockaddr *uaddr;
+ /* Temporary "register" to make indirect stores to nested structures
+ * defined above. We need three registers to make such a store, but
+ * only two (src and dst) are available at convert_ctx_access time
+ */
+ u64 tmp_reg;
+};
+
struct bpf_sock_ops_kern {
struct sock *sk;
u32 op;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dbc8a66b5d7e..6b249b0f3b19 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -134,6 +134,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
};
enum bpf_attach_type {
@@ -145,6 +146,8 @@ enum bpf_attach_type {
BPF_SK_SKB_STREAM_VERDICT,
BPF_CGROUP_DEVICE,
BPF_SK_MSG_VERDICT,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
__MAX_BPF_ATTACH_TYPE
};
@@ -1003,6 +1006,26 @@ struct bpf_map_info {
__u64 netns_ino;
} __attribute__((aligned(8)));
+/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
+ * by user and intended to be used by socket (e.g. to bind to, depends on
+ * attach attach type).
+ */
+struct bpf_sock_addr {
+ __u32 user_family; /* Allows 4-byte read, but no write. */
+ __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_port; /* Allows 4-byte read and write.
+ * Stored in network byte order
+ */
+ __u32 family; /* Allows 4-byte read, but no write */
+ __u32 type; /* Allows 4-byte read, but no write */
+ __u32 protocol; /* Allows 4-byte read, but no write */
+};
+
/* User bpf_sock_ops struct to access socket values and specify request ops
* and their replies.
* Some of this fields are in network (bigendian) byte order and may need
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 8730b24ed540..43171a0bb02b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -495,6 +495,42 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
/**
+ * __cgroup_bpf_run_filter_sock_addr() - Run a program on a sock and
+ * provided by user sockaddr
+ * @sk: sock struct that will use sockaddr
+ * @uaddr: sockaddr struct provided by user
+ * @type: The type of program to be exectuted
+ *
+ * socket is expected to be of type INET or INET6.
+ *
+ * This function will return %-EPERM if an attached program is found and
+ * returned value != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
+ struct sockaddr *uaddr,
+ enum bpf_attach_type type)
+{
+ struct bpf_sock_addr_kern ctx = {
+ .sk = sk,
+ .uaddr = uaddr,
+ };
+ struct cgroup *cgrp;
+ int ret;
+
+ /* Check socket family since not all sockets represent network
+ * endpoint (e.g. AF_UNIX).
+ */
+ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+ return 0;
+
+ cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
+
+ return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
+
+/**
* __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock
* @sk: socket to get cgroup from
* @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 508b36f12921..dca6cb665fa8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1175,19 +1175,29 @@ static int
bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type)
{
- /* There are currently no prog types that require specifying
- * attach_type at load time.
- */
- return 0;
+ switch (prog_type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ switch (expected_attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ default:
+ return 0;
+ }
}
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
- /* There are currently no prog types that require specifying
- * attach_type at load time.
- */
- return 0;
+ switch (prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+ default:
+ return 0;
+ }
}
/* last field in 'union bpf_attr' used by this command */
@@ -1404,6 +1414,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_INET_SOCK_CREATE:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ break;
case BPF_CGROUP_SOCK_OPS:
ptype = BPF_PROG_TYPE_SOCK_OPS;
break;
@@ -1466,6 +1480,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_CGROUP_INET_SOCK_CREATE:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ break;
case BPF_CGROUP_SOCK_OPS:
ptype = BPF_PROG_TYPE_SOCK_OPS;
break;
@@ -1515,6 +1533,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 10024323031d..5dd1dcb902bf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3887,6 +3887,7 @@ static int check_return_code(struct bpf_verifier_env *env)
switch (env->prog->type) {
case BPF_PROG_TYPE_CGROUP_SKB:
case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE:
break;
diff --git a/net/core/filter.c b/net/core/filter.c
index c18c826bebf9..5813eb8260e0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3664,6 +3664,20 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
static const struct bpf_func_proto *
+sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ /* inet and inet6 sockets are created in a process
+ * context so there is always a valid uid/gid
+ */
+ case BPF_FUNC_get_current_uid_gid:
+ return &bpf_get_current_uid_gid_proto;
+ default:
+ return bpf_base_func_proto(func_id);
+ }
+}
+
+static const struct bpf_func_proto *
sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
@@ -4145,6 +4159,69 @@ void bpf_warn_invalid_xdp_action(u32 act)
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
+static bool sock_addr_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ const int size_default = sizeof(__u32);
+
+ if (off < 0 || off >= sizeof(struct bpf_sock_addr))
+ return false;
+ if (off % size != 0)
+ return false;
+
+ /* Disallow access to IPv6 fields from IPv4 contex and vise
+ * versa.
+ */
+ switch (off) {
+ case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
+ switch (prog->expected_attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ break;
+ default:
+ return false;
+ }
+ break;
+ case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]):
+ switch (prog->expected_attach_type) {
+ case BPF_CGROUP_INET6_BIND:
+ break;
+ default:
+ return false;
+ }
+ break;
+ }
+
+ switch (off) {
+ case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
+ case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]):
+ /* Only narrow read access allowed for now. */
+ if (type == BPF_READ) {
+ bpf_ctx_record_field_size(info, size_default);
+ if (!bpf_ctx_narrow_access_ok(off, size, size_default))
+ return false;
+ } else {
+ if (size != size_default)
+ return false;
+ }
+ break;
+ case bpf_ctx_range(struct bpf_sock_addr, user_port):
+ if (size != size_default)
+ return false;
+ break;
+ default:
+ if (type == BPF_READ) {
+ if (size != size_default)
+ return false;
+ } else {
+ return false;
+ }
+ }
+
+ return true;
+}
+
static bool sock_ops_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
@@ -4689,6 +4766,152 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
return insn - insn_buf;
}
+/* SOCK_ADDR_LOAD_NESTED_FIELD() loads Nested Field S.F.NF where S is type of
+ * context Structure, F is Field in context structure that contains a pointer
+ * to Nested Structure of type NS that has the field NF.
+ *
+ * SIZE encodes the load size (BPF_B, BPF_H, etc). It's up to caller to make
+ * sure that SIZE is not greater than actual size of S.F.NF.
+ *
+ * If offset OFF is provided, the load happens from that offset relative to
+ * offset of NF.
+ */
+#define SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF) \
+ do { \
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), si->dst_reg, \
+ si->src_reg, offsetof(S, F)); \
+ *insn++ = BPF_LDX_MEM( \
+ SIZE, si->dst_reg, si->dst_reg, \
+ bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \
+ target_size) \
+ + OFF); \
+ } while (0)
+
+#define SOCK_ADDR_LOAD_NESTED_FIELD(S, NS, F, NF) \
+ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, \
+ BPF_FIELD_SIZEOF(NS, NF), 0)
+
+/* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to
+ * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation.
+ *
+ * It doesn't support SIZE argument though since narrow stores are not
+ * supported for now.
+ *
+ * In addition it uses Temporary Field TF (member of struct S) as the 3rd
+ * "register" since two registers available in convert_ctx_access are not
+ * enough: we can't override neither SRC, since it contains value to store, nor
+ * DST since it contains pointer to context that may be used by later
+ * instructions. But we need a temporary place to save pointer to nested
+ * structure whose field we want to store to.
+ */
+#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF, TF) \
+ do { \
+ int tmp_reg = BPF_REG_9; \
+ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \
+ --tmp_reg; \
+ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \
+ --tmp_reg; \
+ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, tmp_reg, \
+ offsetof(S, TF)); \
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \
+ si->dst_reg, offsetof(S, F)); \
+ *insn++ = BPF_STX_MEM( \
+ BPF_FIELD_SIZEOF(NS, NF), tmp_reg, si->src_reg, \
+ bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \
+ target_size) \
+ + OFF); \
+ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \
+ offsetof(S, TF)); \
+ } while (0)
+
+#define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF, \
+ TF) \
+ do { \
+ if (type == BPF_WRITE) { \
+ SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF, \
+ TF); \
+ } else { \
+ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( \
+ S, NS, F, NF, SIZE, OFF); \
+ } \
+ } while (0)
+
+#define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(S, NS, F, NF, TF) \
+ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( \
+ S, NS, F, NF, BPF_FIELD_SIZEOF(NS, NF), 0, TF)
+
+static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
+ const struct bpf_insn *si,
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog, u32 *target_size)
+{
+ struct bpf_insn *insn = insn_buf;
+ int off;
+
+ switch (si->off) {
+ case offsetof(struct bpf_sock_addr, user_family):
+ SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern,
+ struct sockaddr, uaddr, sa_family);
+ break;
+
+ case offsetof(struct bpf_sock_addr, user_ip4):
+ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
+ struct bpf_sock_addr_kern, struct sockaddr_in, uaddr,
+ sin_addr, BPF_SIZE(si->code), 0, tmp_reg);
+ break;
+
+ case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]):
+ off = si->off;
+ off -= offsetof(struct bpf_sock_addr, user_ip6[0]);
+ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
+ struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr,
+ sin6_addr.s6_addr32[0], BPF_SIZE(si->code), off,
+ tmp_reg);
+ break;
+
+ case offsetof(struct bpf_sock_addr, user_port):
+ /* To get port we need to know sa_family first and then treat
+ * sockaddr as either sockaddr_in or sockaddr_in6.
+ * Though we can simplify since port field has same offset and
+ * size in both structures.
+ * Here we check this invariant and use just one of the
+ * structures if it's true.
+ */
+ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) !=
+ offsetof(struct sockaddr_in6, sin6_port));
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sockaddr_in, sin_port) !=
+ FIELD_SIZEOF(struct sockaddr_in6, sin6_port));
+ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern,
+ struct sockaddr_in6, uaddr,
+ sin6_port, tmp_reg);
+ break;
+
+ case offsetof(struct bpf_sock_addr, family):
+ SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern,
+ struct sock, sk, sk_family);
+ break;
+
+ case offsetof(struct bpf_sock_addr, type):
+ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(
+ struct bpf_sock_addr_kern, struct sock, sk,
+ __sk_flags_offset, BPF_W, 0);
+ *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK);
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT);
+ break;
+
+ case offsetof(struct bpf_sock_addr, protocol):
+ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(
+ struct bpf_sock_addr_kern, struct sock, sk,
+ __sk_flags_offset, BPF_W, 0);
+ *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
+ SK_FL_PROTO_SHIFT);
+ break;
+ }
+
+ return insn - insn_buf;
+}
+
static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
@@ -5146,6 +5369,15 @@ const struct bpf_verifier_ops cg_sock_verifier_ops = {
const struct bpf_prog_ops cg_sock_prog_ops = {
};
+const struct bpf_verifier_ops cg_sock_addr_verifier_ops = {
+ .get_func_proto = sock_addr_func_proto,
+ .is_valid_access = sock_addr_is_valid_access,
+ .convert_ctx_access = sock_addr_convert_ctx_access,
+};
+
+const struct bpf_prog_ops cg_sock_addr_prog_ops = {
+};
+
const struct bpf_verifier_ops sock_ops_verifier_ops = {
.get_func_proto = sock_ops_func_proto,
.is_valid_access = sock_ops_is_valid_access,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e8c7fad8c329..2dec266507dc 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -450,6 +450,13 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (addr_len < sizeof(struct sockaddr_in))
goto out;
+ /* BPF prog is run before any checks are done so that if the prog
+ * changes context in a wrong way it will be caught.
+ */
+ err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr);
+ if (err)
+ goto out;
+
if (addr->sin_family != AF_INET) {
/* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
* only if s_addr is INADDR_ANY.
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index dbbe04018813..fa24e3f06ac6 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -295,6 +295,13 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
+ /* BPF prog is run before any checks are done so that if the prog
+ * changes context in a wrong way it will be caught.
+ */
+ err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr);
+ if (err)
+ return err;
+
if (addr->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
--
2.9.5
^ permalink raw reply related
* [PATCH v2 bpf-next 9/9] selftests/bpf: Selftest for sys_bind post-hooks.
From: Alexei Starovoitov @ 2018-03-28 3:41 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, kernel-team
In-Reply-To: <20180328034140.291484-1-ast@kernel.org>
From: Andrey Ignatov <rdna@fb.com>
Add selftest for attach types `BPF_CGROUP_INET4_POST_BIND` and
`BPF_CGROUP_INET6_POST_BIND`.
The main things tested are:
* prog load behaves as expected (valid/invalid accesses in prog);
* prog attach behaves as expected (load- vs attach-time attach types);
* `BPF_CGROUP_INET_SOCK_CREATE` can be attached in a backward compatible
way;
* post-hooks return expected result and errno.
Example:
# ./test_sock
Test case: bind4 load with invalid access: src_ip6 .. [PASS]
Test case: bind4 load with invalid access: mark .. [PASS]
Test case: bind6 load with invalid access: src_ip4 .. [PASS]
Test case: sock_create load with invalid access: src_port .. [PASS]
Test case: sock_create load w/o expected_attach_type (compat mode) ..
[PASS]
Test case: sock_create load w/ expected_attach_type .. [PASS]
Test case: attach type mismatch bind4 vs bind6 .. [PASS]
Test case: attach type mismatch bind6 vs bind4 .. [PASS]
Test case: attach type mismatch default vs bind4 .. [PASS]
Test case: attach type mismatch bind6 vs sock_create .. [PASS]
Test case: bind4 reject all .. [PASS]
Test case: bind6 reject all .. [PASS]
Test case: bind6 deny specific IP & port .. [PASS]
Test case: bind4 allow specific IP & port .. [PASS]
Test case: bind4 allow all .. [PASS]
Test case: bind6 allow all .. [PASS]
Summary: 16 PASSED, 0 FAILED
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/include/uapi/linux/bpf.h | 11 +
tools/testing/selftests/bpf/Makefile | 4 +-
tools/testing/selftests/bpf/test_sock.c | 479 ++++++++++++++++++++++++++++++++
3 files changed, 493 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_sock.c
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7a8314342e2d..bd9ad31c0ebc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -150,6 +150,8 @@ enum bpf_attach_type {
BPF_CGROUP_INET6_BIND,
BPF_CGROUP_INET4_CONNECT,
BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
__MAX_BPF_ATTACH_TYPE
};
@@ -940,6 +942,15 @@ struct bpf_sock {
__u32 protocol;
__u32 mark;
__u32 priority;
+ __u32 src_ip4; /* Allows 1,2,4-byte read.
+ * Stored in network byte order.
+ */
+ __u32 src_ip6[4]; /* Allows 1,2,4-byte read.
+ * Stored in network byte order.
+ */
+ __u32 src_port; /* Allows 4-byte read.
+ * Stored in host byte order
+ */
};
#define XDP_PACKET_HEADROOM 256
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c64d4ebc77ff..0a315ddabbf4 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,8 @@ urandom_read: urandom_read.c
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
- test_align test_verifier_log test_dev_cgroup test_tcpbpf_user test_sock_addr
+ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
+ test_sock test_sock_addr
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
@@ -52,6 +53,7 @@ $(TEST_GEN_PROGS): $(BPFOBJ)
$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+$(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
new file mode 100644
index 000000000000..73bb20cfb9b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -0,0 +1,479 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdio.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <linux/filter.h>
+
+#include <bpf/bpf.h>
+
+#include "cgroup_helpers.h"
+
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#define CG_PATH "/foo"
+#define MAX_INSNS 512
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+struct sock_test {
+ const char *descr;
+ /* BPF prog properties */
+ struct bpf_insn insns[MAX_INSNS];
+ enum bpf_attach_type expected_attach_type;
+ enum bpf_attach_type attach_type;
+ /* Socket properties */
+ int domain;
+ int type;
+ /* Endpoint to bind() to */
+ const char *ip;
+ unsigned short port;
+ /* Expected test result */
+ enum {
+ LOAD_REJECT,
+ ATTACH_REJECT,
+ BIND_REJECT,
+ SUCCESS,
+ } result;
+};
+
+static struct sock_test tests[] = {
+ {
+ "bind4 load with invalid access: src_ip6",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_ip6[0])),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET4_POST_BIND,
+ 0,
+ 0,
+ NULL,
+ 0,
+ LOAD_REJECT,
+ },
+ {
+ "bind4 load with invalid access: mark",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, mark)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET4_POST_BIND,
+ 0,
+ 0,
+ NULL,
+ 0,
+ LOAD_REJECT,
+ },
+ {
+ "bind6 load with invalid access: src_ip4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_ip4)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ 0,
+ 0,
+ NULL,
+ 0,
+ LOAD_REJECT,
+ },
+ {
+ "sock_create load with invalid access: src_port",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_port)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET_SOCK_CREATE,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ 0,
+ 0,
+ NULL,
+ 0,
+ LOAD_REJECT,
+ },
+ {
+ "sock_create load w/o expected_attach_type (compat mode)",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ 0,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ AF_INET,
+ SOCK_STREAM,
+ "127.0.0.1",
+ 8097,
+ SUCCESS,
+ },
+ {
+ "sock_create load w/ expected_attach_type",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET_SOCK_CREATE,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ AF_INET,
+ SOCK_STREAM,
+ "127.0.0.1",
+ 8097,
+ SUCCESS,
+ },
+ {
+ "attach type mismatch bind4 vs bind6",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ 0,
+ 0,
+ NULL,
+ 0,
+ ATTACH_REJECT,
+ },
+ {
+ "attach type mismatch bind6 vs bind4",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_INET4_POST_BIND,
+ 0,
+ 0,
+ NULL,
+ 0,
+ ATTACH_REJECT,
+ },
+ {
+ "attach type mismatch default vs bind4",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ 0,
+ BPF_CGROUP_INET4_POST_BIND,
+ 0,
+ 0,
+ NULL,
+ 0,
+ ATTACH_REJECT,
+ },
+ {
+ "attach type mismatch bind6 vs sock_create",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ 0,
+ 0,
+ NULL,
+ 0,
+ ATTACH_REJECT,
+ },
+ {
+ "bind4 reject all",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET4_POST_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ "0.0.0.0",
+ 0,
+ BIND_REJECT,
+ },
+ {
+ "bind6 reject all",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ AF_INET6,
+ SOCK_STREAM,
+ "::",
+ 0,
+ BIND_REJECT,
+ },
+ {
+ "bind6 deny specific IP & port",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+ /* if (ip == expected && port == expected) */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_ip6[3])),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x01000000, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_port)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2),
+
+ /* return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_A(1),
+
+ /* else return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ AF_INET6,
+ SOCK_STREAM,
+ "::1",
+ 8193,
+ BIND_REJECT,
+ },
+ {
+ "bind4 allow specific IP & port",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+ /* if (ip == expected && port == expected) */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_ip4)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x0100007F, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock, src_port)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2),
+
+ /* return ALLOW; */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_A(1),
+
+ /* else return DENY; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET4_POST_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ "127.0.0.1",
+ 4098,
+ SUCCESS,
+ },
+ {
+ "bind4 allow all",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET4_POST_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ "0.0.0.0",
+ 0,
+ SUCCESS,
+ },
+ {
+ "bind6 allow all",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ AF_INET6,
+ SOCK_STREAM,
+ "::",
+ 0,
+ SUCCESS,
+ },
+};
+
+static size_t probe_prog_length(const struct bpf_insn *fp)
+{
+ size_t len;
+
+ for (len = MAX_INSNS - 1; len > 0; --len)
+ if (fp[len].code != 0 || fp[len].imm != 0)
+ break;
+ return len + 1;
+}
+
+static int load_sock_prog(const struct bpf_insn *prog,
+ enum bpf_attach_type attach_type)
+{
+ struct bpf_load_program_attr attr;
+
+ memset(&attr, 0, sizeof(struct bpf_load_program_attr));
+ attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+ attr.expected_attach_type = attach_type;
+ attr.insns = prog;
+ attr.insns_cnt = probe_prog_length(attr.insns);
+ attr.license = "GPL";
+
+ return bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE);
+}
+
+static int attach_sock_prog(int cgfd, int progfd,
+ enum bpf_attach_type attach_type)
+{
+ return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE);
+}
+
+static int bind_sock(int domain, int type, const char *ip, unsigned short port)
+{
+ struct sockaddr_storage addr;
+ struct sockaddr_in6 *addr6;
+ struct sockaddr_in *addr4;
+ int sockfd = -1;
+ socklen_t len;
+ int err = 0;
+
+ sockfd = socket(domain, type, 0);
+ if (sockfd < 0)
+ goto err;
+
+ memset(&addr, 0, sizeof(addr));
+
+ if (domain == AF_INET) {
+ len = sizeof(struct sockaddr_in);
+ addr4 = (struct sockaddr_in *)&addr;
+ addr4->sin_family = domain;
+ addr4->sin_port = htons(port);
+ if (inet_pton(domain, ip, (void *)&addr4->sin_addr) != 1)
+ goto err;
+ } else if (domain == AF_INET6) {
+ len = sizeof(struct sockaddr_in6);
+ addr6 = (struct sockaddr_in6 *)&addr;
+ addr6->sin6_family = domain;
+ addr6->sin6_port = htons(port);
+ if (inet_pton(domain, ip, (void *)&addr6->sin6_addr) != 1)
+ goto err;
+ } else {
+ goto err;
+ }
+
+ if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(sockfd);
+ return err;
+}
+
+static int run_test_case(int cgfd, const struct sock_test *test)
+{
+ int progfd = -1;
+ int err = 0;
+
+ printf("Test case: %s .. ", test->descr);
+ progfd = load_sock_prog(test->insns, test->expected_attach_type);
+ if (progfd < 0) {
+ if (test->result == LOAD_REJECT)
+ goto out;
+ else
+ goto err;
+ }
+
+ if (attach_sock_prog(cgfd, progfd, test->attach_type) == -1) {
+ if (test->result == ATTACH_REJECT)
+ goto out;
+ else
+ goto err;
+ }
+
+ if (bind_sock(test->domain, test->type, test->ip, test->port) == -1) {
+ /* sys_bind() may fail for different reasons, errno has to be
+ * checked to confirm that BPF program rejected it.
+ */
+ if (test->result == BIND_REJECT && errno == EPERM)
+ goto out;
+ else
+ goto err;
+ }
+
+
+ if (test->result != SUCCESS)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ /* Detaching w/o checking return code: best effort attempt. */
+ if (progfd != -1)
+ bpf_prog_detach(cgfd, test->attach_type);
+ close(progfd);
+ printf("[%s]\n", err ? "FAIL" : "PASS");
+ return err;
+}
+
+static int run_tests(int cgfd)
+{
+ int passes = 0;
+ int fails = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+ if (run_test_case(cgfd, &tests[i]))
+ ++fails;
+ else
+ ++passes;
+ }
+ printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
+ return fails ? -1 : 0;
+}
+
+int main(int argc, char **argv)
+{
+ int cgfd = -1;
+ int err = 0;
+
+ if (setup_cgroup_environment())
+ goto err;
+
+ cgfd = create_and_get_cgroup(CG_PATH);
+ if (!cgfd)
+ goto err;
+
+ if (join_cgroup(CG_PATH))
+ goto err;
+
+ if (run_tests(cgfd))
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(cgfd);
+ cleanup_cgroup_environment();
+ return err;
+}
--
2.9.5
^ permalink raw reply related
* [PATCH v2 bpf-next 1/9] bpf: Check attach type at prog load time
From: Alexei Starovoitov @ 2018-03-28 3:41 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, kernel-team
In-Reply-To: <20180328034140.291484-1-ast@kernel.org>
From: Andrey Ignatov <rdna@fb.com>
== The problem ==
There are use-cases when a program of some type can be attached to
multiple attach points and those attach points must have different
permissions to access context or to call helpers.
E.g. context structure may have fields for both IPv4 and IPv6 but it
doesn't make sense to read from / write to IPv6 field when attach point
is somewhere in IPv4 stack.
Same applies to BPF-helpers: it may make sense to call some helper from
some attach point, but not from other for same prog type.
== The solution ==
Introduce `expected_attach_type` field in in `struct bpf_attr` for
`BPF_PROG_LOAD` command. If scenario described in "The problem" section
is the case for some prog type, the field will be checked twice:
1) At load time prog type is checked to see if attach type for it must
be known to validate program permissions correctly. Prog will be
rejected with EINVAL if it's the case and `expected_attach_type` is
not specified or has invalid value.
2) At attach time `attach_type` is compared with `expected_attach_type`,
if prog type requires to have one, and, if they differ, attach will
be rejected with EINVAL.
The `expected_attach_type` is now available as part of `struct bpf_prog`
in both `bpf_verifier_ops->is_valid_access()` and
`bpf_verifier_ops->get_func_proto()` () and can be used to check context
accesses and calls to helpers correspondingly.
Initially the idea was discussed by Alexei Starovoitov <ast@fb.com> and
Daniel Borkmann <daniel@iogearbox.net> here:
https://marc.info/?l=linux-netdev&m=152107378717201&w=2
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 5 ++++-
include/linux/filter.h | 1 +
include/uapi/linux/bpf.h | 5 +++++
kernel/bpf/cgroup.c | 3 ++-
kernel/bpf/syscall.c | 31 ++++++++++++++++++++++++++++++-
kernel/bpf/verifier.c | 6 +++---
kernel/trace/bpf_trace.c | 21 ++++++++++++++-------
net/core/filter.c | 39 +++++++++++++++++++++++++--------------
8 files changed, 84 insertions(+), 27 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 819229c80eca..95a7abd0ee92 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -208,12 +208,15 @@ struct bpf_prog_ops {
struct bpf_verifier_ops {
/* return eBPF function prototype for verification */
- const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+ const struct bpf_func_proto *
+ (*get_func_proto)(enum bpf_func_id func_id,
+ const struct bpf_prog *prog);
/* return true if 'size' wide access at offset 'off' within bpf_context
* with 'type' (read or write) is allowed
*/
bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
const struct bpf_prog *prog);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 109d05ccea9a..5787280b1e88 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -469,6 +469,7 @@ struct bpf_prog {
is_func:1, /* program is a bpf function */
kprobe_override:1; /* Do we override a kprobe? */
enum bpf_prog_type type; /* Type of BPF program */
+ enum bpf_attach_type expected_attach_type; /* For some prog types */
u32 len; /* Number of filter blocks */
u32 jited_len; /* Size of jited insns in bytes */
u8 tag[BPF_TAG_SIZE];
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 18b7c510c511..dbc8a66b5d7e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -294,6 +294,11 @@ union bpf_attr {
__u32 prog_flags;
char prog_name[BPF_OBJ_NAME_LEN];
__u32 prog_ifindex; /* ifindex of netdev to prep for */
+ /* For some prog types expected attach type must be known at
+ * load time to verify attach type specific parts of prog
+ * (context accesses, allowed helpers, etc).
+ */
+ __u32 expected_attach_type;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index c1c0b60d3f2f..8730b24ed540 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -545,7 +545,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
static const struct bpf_func_proto *
-cgroup_dev_func_proto(enum bpf_func_id func_id)
+cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@@ -566,6 +566,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id)
static bool cgroup_dev_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
const int size_default = sizeof(__u32);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 77d45bd9f507..508b36f12921 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1171,8 +1171,27 @@ struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
}
EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
+static int
+bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
+ enum bpf_attach_type expected_attach_type)
+{
+ /* There are currently no prog types that require specifying
+ * attach_type at load time.
+ */
+ return 0;
+}
+
+static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
+ enum bpf_attach_type attach_type)
+{
+ /* There are currently no prog types that require specifying
+ * attach_type at load time.
+ */
+ return 0;
+}
+
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD prog_ifindex
+#define BPF_PROG_LOAD_LAST_FIELD expected_attach_type
static int bpf_prog_load(union bpf_attr *attr)
{
@@ -1209,11 +1228,16 @@ static int bpf_prog_load(union bpf_attr *attr)
!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type))
+ return -EINVAL;
+
/* plain bpf_prog allocation */
prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
if (!prog)
return -ENOMEM;
+ prog->expected_attach_type = attr->expected_attach_type;
+
prog->aux->offload_requested = !!attr->prog_ifindex;
err = security_bpf_prog_alloc(prog->aux);
@@ -1399,6 +1423,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (IS_ERR(prog))
return PTR_ERR(prog);
+ if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) {
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
cgrp = cgroup_get_from_fd(attr->target_fd);
if (IS_ERR(cgrp)) {
bpf_prog_put(prog);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8acd2207e412..10024323031d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1323,7 +1323,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
};
if (env->ops->is_valid_access &&
- env->ops->is_valid_access(off, size, t, &info)) {
+ env->ops->is_valid_access(off, size, t, env->prog, &info)) {
/* A non zero info.ctx_field_size indicates that this field is a
* candidate for later verifier transformation to load the whole
* field and then apply a mask when accessed with a narrower
@@ -2349,7 +2349,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
}
if (env->ops->get_func_proto)
- fn = env->ops->get_func_proto(func_id);
+ fn = env->ops->get_func_proto(func_id, env->prog);
if (!fn) {
verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
func_id);
@@ -5572,7 +5572,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
insn = new_prog->insnsi + i + delta;
}
patch_call_imm:
- fn = env->ops->get_func_proto(insn->imm);
+ fn = env->ops->get_func_proto(insn->imm, env->prog);
/* all functions that have prototype and verifier allowed
* programs to call them, must be real in-kernel functions
*/
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7f9691c86b6e..bad52d33bba3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -524,7 +524,8 @@ static const struct bpf_func_proto bpf_probe_read_str_proto = {
.arg3_type = ARG_ANYTHING,
};
-static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *
+tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@@ -568,7 +569,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
}
}
-static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *
+kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_perf_event_output:
@@ -582,12 +584,13 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
return &bpf_override_return_proto;
#endif
default:
- return tracing_func_proto(func_id);
+ return tracing_func_proto(func_id, prog);
}
}
/* bpf+kprobe programs can access fields of 'struct pt_regs' */
static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (off < 0 || off >= sizeof(struct pt_regs))
@@ -661,7 +664,8 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
.arg3_type = ARG_ANYTHING,
};
-static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *
+tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_perf_event_output:
@@ -669,11 +673,12 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_get_stackid:
return &bpf_get_stackid_proto_tp;
default:
- return tracing_func_proto(func_id);
+ return tracing_func_proto(func_id, prog);
}
}
static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
@@ -721,7 +726,8 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
.arg3_type = ARG_CONST_SIZE,
};
-static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *
+pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_perf_event_output:
@@ -731,11 +737,12 @@ static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_perf_prog_read_value:
return &bpf_perf_prog_read_value_proto;
default:
- return tracing_func_proto(func_id);
+ return tracing_func_proto(func_id, prog);
}
}
static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
const int size_u64 = sizeof(u64);
diff --git a/net/core/filter.c b/net/core/filter.c
index 00c711c5f1a2..c18c826bebf9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3650,7 +3650,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
-sock_filter_func_proto(enum bpf_func_id func_id)
+sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
/* inet and inet6 sockets are created in a process
@@ -3664,7 +3664,7 @@ sock_filter_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
-sk_filter_func_proto(enum bpf_func_id func_id)
+sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_skb_load_bytes:
@@ -3679,7 +3679,7 @@ sk_filter_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
-tc_cls_act_func_proto(enum bpf_func_id func_id)
+tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_skb_store_bytes:
@@ -3746,7 +3746,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
-xdp_func_proto(enum bpf_func_id func_id)
+xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_perf_event_output:
@@ -3769,7 +3769,7 @@ xdp_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
-lwt_inout_func_proto(enum bpf_func_id func_id)
+lwt_inout_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_skb_load_bytes:
@@ -3796,7 +3796,7 @@ lwt_inout_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
- sock_ops_func_proto(enum bpf_func_id func_id)
+sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_setsockopt:
@@ -3812,7 +3812,8 @@ static const struct bpf_func_proto *
}
}
-static const struct bpf_func_proto *sk_msg_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *
+sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_msg_redirect_map:
@@ -3828,7 +3829,8 @@ static const struct bpf_func_proto *sk_msg_func_proto(enum bpf_func_id func_id)
}
}
-static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *
+sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_skb_store_bytes:
@@ -3853,7 +3855,7 @@ static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id)
}
static const struct bpf_func_proto *
-lwt_xmit_func_proto(enum bpf_func_id func_id)
+lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_skb_get_tunnel_key:
@@ -3883,11 +3885,12 @@ lwt_xmit_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_set_hash_invalid:
return &bpf_set_hash_invalid_proto;
default:
- return lwt_inout_func_proto(func_id);
+ return lwt_inout_func_proto(func_id, prog);
}
}
static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
const int size_default = sizeof(__u32);
@@ -3931,6 +3934,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
static bool sk_filter_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
switch (off) {
@@ -3951,11 +3955,12 @@ static bool sk_filter_is_valid_access(int off, int size,
}
}
- return bpf_skb_is_valid_access(off, size, type, info);
+ return bpf_skb_is_valid_access(off, size, type, prog, info);
}
static bool lwt_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
switch (off) {
@@ -3985,11 +3990,12 @@ static bool lwt_is_valid_access(int off, int size,
break;
}
- return bpf_skb_is_valid_access(off, size, type, info);
+ return bpf_skb_is_valid_access(off, size, type, prog, info);
}
static bool sock_filter_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (type == BPF_WRITE) {
@@ -4061,6 +4067,7 @@ static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
static bool tc_cls_act_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (type == BPF_WRITE) {
@@ -4090,7 +4097,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
return false;
}
- return bpf_skb_is_valid_access(off, size, type, info);
+ return bpf_skb_is_valid_access(off, size, type, prog, info);
}
static bool __is_valid_xdp_access(int off, int size)
@@ -4107,6 +4114,7 @@ static bool __is_valid_xdp_access(int off, int size)
static bool xdp_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (type == BPF_WRITE)
@@ -4139,6 +4147,7 @@ EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
static bool sock_ops_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
const int size_default = sizeof(__u32);
@@ -4185,6 +4194,7 @@ static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write,
static bool sk_skb_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
switch (off) {
@@ -4214,11 +4224,12 @@ static bool sk_skb_is_valid_access(int off, int size,
break;
}
- return bpf_skb_is_valid_access(off, size, type, info);
+ return bpf_skb_is_valid_access(off, size, type, prog, info);
}
static bool sk_msg_is_valid_access(int off, int size,
enum bpf_access_type type,
+ const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
if (type == BPF_WRITE)
--
2.9.5
^ permalink raw reply related
* [PATCH v2 bpf-next 4/9] selftests/bpf: Selftest for sys_bind hooks
From: Alexei Starovoitov @ 2018-03-28 3:41 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, kernel-team
In-Reply-To: <20180328034140.291484-1-ast@kernel.org>
From: Andrey Ignatov <rdna@fb.com>
Add selftest to work with bpf_sock_addr context from
`BPF_PROG_TYPE_CGROUP_SOCK_ADDR` programs.
Try to bind(2) on IP:port and apply:
* loads to make sure context can be read correctly, including narrow
loads (byte, half) for IP and full-size loads (word) for all fields;
* stores to those fields allowed by verifier.
All combination from IPv4/IPv6 and TCP/UDP are tested.
Both scenarios are tested:
* valid programs can be loaded and attached;
* invalid programs can be neither loaded nor attached.
Test passes when expected data can be read from context in the
BPF-program, and after the call to bind(2) socket is bound to IP:port
pair that was written by BPF-program to the context.
Example:
# ./test_sock_addr
Attached bind4 program.
Test case #1 (IPv4/TCP):
Requested: bind(192.168.1.254, 4040) ..
Actual: bind(127.0.0.1, 4444)
Test case #2 (IPv4/UDP):
Requested: bind(192.168.1.254, 4040) ..
Actual: bind(127.0.0.1, 4444)
Attached bind6 program.
Test case #3 (IPv6/TCP):
Requested: bind(face:b00c:1234:5678::abcd, 6060) ..
Actual: bind(::1, 6666)
Test case #4 (IPv6/UDP):
Requested: bind(face:b00c:1234:5678::abcd, 6060) ..
Actual: bind(::1, 6666)
### SUCCESS
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/include/uapi/linux/bpf.h | 23 ++
tools/lib/bpf/libbpf.c | 6 +
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/test_sock_addr.c | 486 +++++++++++++++++++++++++++
4 files changed, 517 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_sock_addr.c
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b44bcd7814ee..a8ec89065496 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -134,6 +134,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
};
enum bpf_attach_type {
@@ -145,6 +146,8 @@ enum bpf_attach_type {
BPF_SK_SKB_STREAM_VERDICT,
BPF_CGROUP_DEVICE,
BPF_SK_MSG_VERDICT,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
__MAX_BPF_ATTACH_TYPE
};
@@ -1002,6 +1005,26 @@ struct bpf_map_info {
__u64 netns_ino;
} __attribute__((aligned(8)));
+/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
+ * by user and intended to be used by socket (e.g. to bind to, depends on
+ * attach attach type).
+ */
+struct bpf_sock_addr {
+ __u32 user_family; /* Allows 4-byte read, but no write. */
+ __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_port; /* Allows 4-byte read and write.
+ * Stored in network byte order
+ */
+ __u32 family; /* Allows 4-byte read, but no write */
+ __u32 type; /* Allows 4-byte read, but no write */
+ __u32 protocol; /* Allows 4-byte read, but no write */
+};
+
/* User bpf_sock_ops struct to access socket values and specify request ops
* and their replies.
* Some of this fields are in network (bigendian) byte order and may need
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 48e3e743ebf7..d7ce8818982c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1859,6 +1859,9 @@ static void bpf_program__set_expected_attach_type(struct bpf_program *prog,
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0)
+#define BPF_SA_PROG_SEC(string, ptype) \
+ BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype)
+
static const struct {
const char *sec;
size_t len;
@@ -1882,10 +1885,13 @@ static const struct {
BPF_PROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS),
BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB),
BPF_PROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG),
+ BPF_SA_PROG_SEC("cgroup/bind4", BPF_CGROUP_INET4_BIND),
+ BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND),
};
#undef BPF_PROG_SEC
#undef BPF_PROG_SEC_FULL
+#undef BPF_SA_PROG_SEC
static int bpf_program__identify_section(struct bpf_program *prog)
{
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f35fb02bdf56..f4717c910874 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ urandom_read: urandom_read.c
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
- test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
+ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user test_sock_addr
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
@@ -51,6 +51,7 @@ $(TEST_GEN_PROGS): $(BPFOBJ)
$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+$(OUTPUT)/test_sock_addr: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
new file mode 100644
index 000000000000..a57e13a65e37
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <linux/filter.h>
+
+#include <bpf/bpf.h>
+
+#include "cgroup_helpers.h"
+
+#define CG_PATH "/foo"
+
+#define SERV4_IP "192.168.1.254"
+#define SERV4_REWRITE_IP "127.0.0.1"
+#define SERV4_PORT 4040
+#define SERV4_REWRITE_PORT 4444
+
+#define SERV6_IP "face:b00c:1234:5678::abcd"
+#define SERV6_REWRITE_IP "::1"
+#define SERV6_PORT 6060
+#define SERV6_REWRITE_PORT 6666
+
+#define INET_NTOP_BUF 40
+
+typedef int (*load_fn)(enum bpf_attach_type, const char *comment);
+typedef int (*info_fn)(int, struct sockaddr *, socklen_t *);
+
+struct program {
+ enum bpf_attach_type type;
+ load_fn loadfn;
+ int fd;
+ const char *name;
+ enum bpf_attach_type invalid_type;
+};
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int mk_sockaddr(int domain, const char *ip, unsigned short port,
+ struct sockaddr *addr, socklen_t addr_len)
+{
+ struct sockaddr_in6 *addr6;
+ struct sockaddr_in *addr4;
+
+ if (domain != AF_INET && domain != AF_INET6) {
+ log_err("Unsupported address family");
+ return -1;
+ }
+
+ memset(addr, 0, addr_len);
+
+ if (domain == AF_INET) {
+ if (addr_len < sizeof(struct sockaddr_in))
+ return -1;
+ addr4 = (struct sockaddr_in *)addr;
+ addr4->sin_family = domain;
+ addr4->sin_port = htons(port);
+ if (inet_pton(domain, ip, (void *)&addr4->sin_addr) != 1) {
+ log_err("Invalid IPv4: %s", ip);
+ return -1;
+ }
+ } else if (domain == AF_INET6) {
+ if (addr_len < sizeof(struct sockaddr_in6))
+ return -1;
+ addr6 = (struct sockaddr_in6 *)addr;
+ addr6->sin6_family = domain;
+ addr6->sin6_port = htons(port);
+ if (inet_pton(domain, ip, (void *)&addr6->sin6_addr) != 1) {
+ log_err("Invalid IPv6: %s", ip);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int load_insns(enum bpf_attach_type attach_type,
+ const struct bpf_insn *insns, size_t insns_cnt,
+ const char *comment)
+{
+ struct bpf_load_program_attr load_attr;
+ int ret;
+
+ memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
+ load_attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ load_attr.expected_attach_type = attach_type;
+ load_attr.insns = insns;
+ load_attr.insns_cnt = insns_cnt;
+ load_attr.license = "GPL";
+
+ ret = bpf_load_program_xattr(&load_attr, bpf_log_buf, BPF_LOG_BUF_SIZE);
+ if (ret < 0 && comment) {
+ log_err(">>> Loading %s program error.\n"
+ ">>> Output from verifier:\n%s\n-------\n",
+ comment, bpf_log_buf);
+ }
+
+ return ret;
+}
+
+/* [1] These testing programs try to read different context fields, including
+ * narrow loads of different sizes from user_ip4 and user_ip6, and write to
+ * those allowed to be overridden.
+ *
+ * [2] BPF_LD_IMM64 & BPF_JMP_REG are used below whenever there is a need to
+ * compare a register with unsigned 32bit integer. BPF_JMP_IMM can't be used
+ * in such cases since it accepts only _signed_ 32bit integer as IMM
+ * argument. Also note that BPF_LD_IMM64 contains 2 instructions what matters
+ * to count jumps properly.
+ */
+
+static int bind4_prog_load(enum bpf_attach_type attach_type,
+ const char *comment)
+{
+ union {
+ uint8_t u4_addr8[4];
+ uint16_t u4_addr16[2];
+ uint32_t u4_addr32;
+ } ip4;
+ struct sockaddr_in addr4_rw;
+
+ if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) {
+ log_err("Invalid IPv4: %s", SERV4_IP);
+ return -1;
+ }
+
+ if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
+ (struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1)
+ return -1;
+
+ /* See [1]. */
+ struct bpf_insn insns[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+ /* if (sk.family == AF_INET && */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, family)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 16),
+
+ /* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, type)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
+ BPF_JMP_A(1),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 12),
+
+ /* 1st_byte_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 10),
+
+ /* 1st_half_of_user_ip4 == expected && */
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 8),
+
+ /* whole_user_ip4 == expected) { */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+ BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4),
+
+ /* user_ip4 = addr4_rw.sin_addr */
+ BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_addr.s_addr),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+
+ /* user_port = addr4_rw.sin_port */
+ BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_port),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_port)),
+ /* } */
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ };
+
+ return load_insns(attach_type, insns,
+ sizeof(insns) / sizeof(struct bpf_insn), comment);
+}
+
+static int bind6_prog_load(enum bpf_attach_type attach_type,
+ const char *comment)
+{
+ struct sockaddr_in6 addr6_rw;
+ struct in6_addr ip6;
+
+ if (inet_pton(AF_INET6, SERV6_IP, (void *)&ip6) != 1) {
+ log_err("Invalid IPv6: %s", SERV6_IP);
+ return -1;
+ }
+
+ if (mk_sockaddr(AF_INET6, SERV6_REWRITE_IP, SERV6_REWRITE_PORT,
+ (struct sockaddr *)&addr6_rw, sizeof(addr6_rw)) == -1)
+ return -1;
+
+ /* See [1]. */
+ struct bpf_insn insns[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+ /* if (sk.family == AF_INET6 && */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, family)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18),
+
+ /* 5th_byte_of_user_ip6 == expected && */
+ BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip6[1])),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr[4], 16),
+
+ /* 3rd_half_of_user_ip6 == expected && */
+ BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip6[1])),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr16[2], 14),
+
+ /* last_word_of_user_ip6 == expected) { */
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+ offsetof(struct bpf_sock_addr, user_ip6[3])),
+ BPF_LD_IMM64(BPF_REG_8, ip6.s6_addr32[3]), /* See [2]. */
+ BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 10),
+
+
+#define STORE_IPV6_WORD(N) \
+ BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_addr.s6_addr32[N]), \
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \
+ offsetof(struct bpf_sock_addr, user_ip6[N]))
+
+ /* user_ip6 = addr6_rw.sin6_addr */
+ STORE_IPV6_WORD(0),
+ STORE_IPV6_WORD(1),
+ STORE_IPV6_WORD(2),
+ STORE_IPV6_WORD(3),
+
+ /* user_port = addr6_rw.sin6_port */
+ BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_port),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_port)),
+
+ /* } */
+
+ /* return 1 */
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ };
+
+ return load_insns(attach_type, insns,
+ sizeof(insns) / sizeof(struct bpf_insn), comment);
+}
+
+static void print_ip_port(int sockfd, info_fn fn, const char *fmt)
+{
+ char addr_buf[INET_NTOP_BUF];
+ struct sockaddr_storage addr;
+ struct sockaddr_in6 *addr6;
+ struct sockaddr_in *addr4;
+ socklen_t addr_len;
+ unsigned short port;
+ void *nip;
+
+ addr_len = sizeof(struct sockaddr_storage);
+ memset(&addr, 0, addr_len);
+
+ if (fn(sockfd, (struct sockaddr *)&addr, (socklen_t *)&addr_len) == 0) {
+ if (addr.ss_family == AF_INET) {
+ addr4 = (struct sockaddr_in *)&addr;
+ nip = (void *)&addr4->sin_addr;
+ port = ntohs(addr4->sin_port);
+ } else if (addr.ss_family == AF_INET6) {
+ addr6 = (struct sockaddr_in6 *)&addr;
+ nip = (void *)&addr6->sin6_addr;
+ port = ntohs(addr6->sin6_port);
+ } else {
+ return;
+ }
+ const char *addr_str =
+ inet_ntop(addr.ss_family, nip, addr_buf, INET_NTOP_BUF);
+ printf(fmt, addr_str ? addr_str : "??", port);
+ }
+}
+
+static void print_local_ip_port(int sockfd, const char *fmt)
+{
+ print_ip_port(sockfd, getsockname, fmt);
+}
+
+static int start_server(int type, const struct sockaddr_storage *addr,
+ socklen_t addr_len)
+{
+
+ int fd;
+
+ fd = socket(addr->ss_family, type, 0);
+ if (fd == -1) {
+ log_err("Failed to create server socket");
+ goto out;
+ }
+
+ if (bind(fd, (const struct sockaddr *)addr, addr_len) == -1) {
+ log_err("Failed to bind server socket");
+ goto close_out;
+ }
+
+ if (type == SOCK_STREAM) {
+ if (listen(fd, 128) == -1) {
+ log_err("Failed to listen on server socket");
+ goto close_out;
+ }
+ }
+
+ print_local_ip_port(fd, "\t Actual: bind(%s, %d)\n");
+
+ goto out;
+close_out:
+ close(fd);
+ fd = -1;
+out:
+ return fd;
+}
+
+static void print_test_case_num(int domain, int type)
+{
+ static int test_num;
+
+ printf("Test case #%d (%s/%s):\n", ++test_num,
+ (domain == AF_INET ? "IPv4" :
+ domain == AF_INET6 ? "IPv6" :
+ "unknown_domain"),
+ (type == SOCK_STREAM ? "TCP" :
+ type == SOCK_DGRAM ? "UDP" :
+ "unknown_type"));
+}
+
+static int run_test_case(int domain, int type, const char *ip,
+ unsigned short port)
+{
+ struct sockaddr_storage addr;
+ socklen_t addr_len = sizeof(addr);
+ int servfd = -1;
+ int err = 0;
+
+ print_test_case_num(domain, type);
+
+ if (mk_sockaddr(domain, ip, port, (struct sockaddr *)&addr,
+ addr_len) == -1)
+ return -1;
+
+ printf("\tRequested: bind(%s, %d) ..\n", ip, port);
+ servfd = start_server(type, &addr, addr_len);
+ if (servfd == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(servfd);
+ return err;
+}
+
+static void close_progs_fds(struct program *progs, size_t prog_cnt)
+{
+ size_t i;
+
+ for (i = 0; i < prog_cnt; ++i) {
+ close(progs[i].fd);
+ progs[i].fd = -1;
+ }
+}
+
+static int load_and_attach_progs(int cgfd, struct program *progs,
+ size_t prog_cnt)
+{
+ size_t i;
+
+ for (i = 0; i < prog_cnt; ++i) {
+ progs[i].fd = progs[i].loadfn(progs[i].invalid_type, NULL);
+ if (progs[i].fd != -1) {
+ log_err("Load with invalid type accepted for %s",
+ progs[i].name);
+ goto err;
+ }
+ progs[i].fd = progs[i].loadfn(progs[i].type, progs[i].name);
+ if (progs[i].fd == -1) {
+ log_err("Failed to load program %s", progs[i].name);
+ goto err;
+ }
+ if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].invalid_type,
+ BPF_F_ALLOW_OVERRIDE) != -1) {
+ log_err("Attach with invalid type accepted for %s",
+ progs[i].name);
+ goto err;
+ }
+ if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].type,
+ BPF_F_ALLOW_OVERRIDE) == -1) {
+ log_err("Failed to attach program %s", progs[i].name);
+ goto err;
+ }
+ printf("Attached %s program.\n", progs[i].name);
+ }
+
+ return 0;
+err:
+ close_progs_fds(progs, prog_cnt);
+ return -1;
+}
+
+static int run_domain_test(int domain, int cgfd, struct program *progs,
+ size_t prog_cnt, const char *ip, unsigned short port)
+{
+ int err = 0;
+
+ if (load_and_attach_progs(cgfd, progs, prog_cnt) == -1)
+ goto err;
+
+ if (run_test_case(domain, SOCK_STREAM, ip, port) == -1)
+ goto err;
+
+ if (run_test_case(domain, SOCK_DGRAM, ip, port) == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close_progs_fds(progs, prog_cnt);
+ return err;
+}
+
+static int run_test(void)
+{
+ size_t inet6_prog_cnt;
+ size_t inet_prog_cnt;
+ int cgfd = -1;
+ int err = 0;
+
+ struct program inet6_progs[] = {
+ {BPF_CGROUP_INET6_BIND, bind6_prog_load, -1, "bind6",
+ BPF_CGROUP_INET4_BIND},
+ };
+ inet6_prog_cnt = sizeof(inet6_progs) / sizeof(struct program);
+
+ struct program inet_progs[] = {
+ {BPF_CGROUP_INET4_BIND, bind4_prog_load, -1, "bind4",
+ BPF_CGROUP_INET6_BIND},
+ };
+ inet_prog_cnt = sizeof(inet_progs) / sizeof(struct program);
+
+ if (setup_cgroup_environment())
+ goto err;
+
+ cgfd = create_and_get_cgroup(CG_PATH);
+ if (!cgfd)
+ goto err;
+
+ if (join_cgroup(CG_PATH))
+ goto err;
+
+ if (run_domain_test(AF_INET, cgfd, inet_progs, inet_prog_cnt, SERV4_IP,
+ SERV4_PORT) == -1)
+ goto err;
+
+ if (run_domain_test(AF_INET6, cgfd, inet6_progs, inet6_prog_cnt,
+ SERV6_IP, SERV6_PORT) == -1)
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(cgfd);
+ cleanup_cgroup_environment();
+ printf(err ? "### FAIL\n" : "### SUCCESS\n");
+ return err;
+}
+
+int main(int argc, char **argv)
+{
+ return run_test();
+}
--
2.9.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox