bpf: Change syscall_nr type to int in struct syscall_tp_t

linux-rt-devel tree contains a patch (b1773eac3f29c ("sched: Add support
for lazy preemption")) that adds an extra member to struct trace_entry.
This causes the offset of args field in struct trace_event_raw_sys_enter
be different from the one in struct syscall_trace_enter:

struct trace_event_raw_sys_enter {
        struct trace_entry         ent;                  /*     0    12 */

        /* XXX last struct has 3 bytes of padding */
        /* XXX 4 bytes hole, try to pack */

        long int                   id;                   /*    16     8 */
        long unsigned int          args[6];              /*    24    48 */
        /* --- cacheline 1 boundary (64 bytes) was 8 bytes ago --- */
        char                       __data[];             /*    72     0 */

        /* size: 72, cachelines: 2, members: 4 */
        /* sum members: 68, holes: 1, sum holes: 4 */
        /* paddings: 1, sum paddings: 3 */
        /* last cacheline: 8 bytes */
};

struct syscall_trace_enter {
        struct trace_entry         ent;                  /*     0    12 */

        /* XXX last struct has 3 bytes of padding */

        int                        nr;                   /*    12     4 */
        long unsigned int          args[];               /*    16     0 */

        /* size: 16, cachelines: 1, members: 3 */
        /* paddings: 1, sum paddings: 3 */
        /* last cacheline: 16 bytes */
};

This, in turn, causes perf_event_set_bpf_prog() fail while running bpf
test_profiler testcase because max_ctx_offset is calculated based on the
former struct, while off on the latter:

  10488         if (is_tracepoint || is_syscall_tp) {
  10489                 int off = trace_event_get_offsets(event->tp_event);
  10490
  10491                 if (prog->aux->max_ctx_offset > off)
  10492                         return -EACCES;
  10493         }

What bpf program is actually getting is a pointer to struct
syscall_tp_t, defined in kernel/trace/trace_syscalls.c. This patch fixes
the problem by aligning struct syscall_tp_t with struct
syscall_trace_(enter|exit) and changing the tests to use these structs
to dereference context.

Signed-off-by: Artem Savkov <asavkov@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/bpf/20231013054219.172920-1-asavkov@redhat.com

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index de75340..9c581d6 100644 (file)
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -556,7 +556,7 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
 {
        struct syscall_tp_t {
                struct trace_entry ent;
-               unsigned long syscall_nr;
+               int syscall_nr;
                unsigned long args[SYSCALL_DEFINE_MAXARGS];
        } __aligned(8) param;
        int i;
@@ -661,7 +661,7 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
 {
        struct syscall_tp_t {
                struct trace_entry ent;
-               unsigned long syscall_nr;
+               int syscall_nr;
                unsigned long ret;
        } __aligned(8) param;
 

diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index f799d87..8970619 100644 (file)
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -609,7 +609,7 @@ out:
 }
 
 SEC("tracepoint/syscalls/sys_enter_kill")
-int tracepoint__syscalls__sys_enter_kill(struct trace_event_raw_sys_enter* ctx)
+int tracepoint__syscalls__sys_enter_kill(struct syscall_trace_enter* ctx)
 {
        struct bpf_func_stats_ctx stats_ctx;
 

diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c
index 4b8e37f..78b2393 100644 (file)
--- a/tools/testing/selftests/bpf/progs/test_vmlinux.c
+++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c
@@ -16,12 +16,12 @@ bool kprobe_called = false;
 bool fentry_called = false;
 
 SEC("tp/syscalls/sys_enter_nanosleep")
-int handle__tp(struct trace_event_raw_sys_enter *args)
+int handle__tp(struct syscall_trace_enter *args)
 {
        struct __kernel_timespec *ts;
        long tv_nsec;
 
-       if (args->id != __NR_nanosleep)
+       if (args->nr != __NR_nanosleep)
                return 0;
 
        ts = (void *)args->args[0];