From: Lorenz Bauer lmb@cloudflare.com
stable inclusion from stable-v5.10.135 commit 6aad811b37eeeba902b14cc4ab698d2b37bb4fb9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5ZWFM
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 607b9cc92bd7208338d714a22b8082fe83bcb177 upstream.
Share the timing / signal interruption logic between different implementations of PROG_TEST_RUN. There is a change in behaviour as well. We check the loop exit condition before checking for pending signals. This resolves an edge case where a signal arrives during the last iteration. Instead of aborting with EINTR we return the successful result to user space.
Signed-off-by: Lorenz Bauer lmb@cloudflare.com Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/bpf/20210303101816.36774-2-lmb@cloudflare.com [dtcccc: fix conflicts in bpf_test_run()] Signed-off-by: Tianchen Ding dtcccc@linux.alibaba.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Conflicts: net/bpf/test_run.c Signed-off-by: Pu Lehui pulehui@huawei.com Reviewed-by: Kuohai Xu xukuohai@huawei.com Reviewed-by: Kuohai Xu xukuohai@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/bpf/test_run.c | 142 +++++++++++++++++++++++++-------------------- 1 file changed, 78 insertions(+), 64 deletions(-)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 141c39274066..5df75f12551e 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -16,16 +16,80 @@ #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h>
+struct bpf_test_timer { + enum { NO_PREEMPT, NO_MIGRATE } mode; + u32 i; + u64 time_start, time_spent; +}; + +static void bpf_test_timer_enter(struct bpf_test_timer *t) + __acquires(rcu) +{ + rcu_read_lock(); + if (t->mode == NO_PREEMPT) + preempt_disable(); + else + migrate_disable(); + + t->time_start = ktime_get_ns(); +} + +static void bpf_test_timer_leave(struct bpf_test_timer *t) + __releases(rcu) +{ + t->time_start = 0; + + if (t->mode == NO_PREEMPT) + preempt_enable(); + else + migrate_enable(); + rcu_read_unlock(); +} + +static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration) + __must_hold(rcu) +{ + t->i++; + if (t->i >= repeat) { + /* We're done. */ + t->time_spent += ktime_get_ns() - t->time_start; + do_div(t->time_spent, t->i); + *duration = t->time_spent > U32_MAX ? U32_MAX : (u32)t->time_spent; + *err = 0; + goto reset; + } + + if (signal_pending(current)) { + /* During iteration: we've been cancelled, abort. */ + *err = -EINTR; + goto reset; + } + + if (need_resched()) { + /* During iteration: we need to reschedule between runs. */ + t->time_spent += ktime_get_ns() - t->time_start; + bpf_test_timer_leave(t); + cond_resched(); + bpf_test_timer_enter(t); + } + + /* Do another round. */ + return true; + +reset: + t->i = 0; + return false; +} + static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { struct bpf_prog_array_item item = {.prog = prog}; struct bpf_run_ctx *old_ctx; struct bpf_cg_run_ctx run_ctx; + struct bpf_test_timer t = { NO_MIGRATE }; enum bpf_cgroup_storage_type stype; - u64 time_start, time_spent = 0; - int ret = 0; - u32 i; + int ret;
for_each_cgroup_storage_type(stype) { item.cgroup_storage[stype] = bpf_cgroup_storage_alloc(prog, stype); @@ -40,42 +104,17 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, if (!repeat) repeat = 1;
- rcu_read_lock(); - migrate_disable(); - time_start = ktime_get_ns(); + bpf_test_timer_enter(&t); old_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); - for (i = 0; i < repeat; i++) { + do { run_ctx.prog_item = &item; - if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = BPF_PROG_RUN(prog, ctx); - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (need_resched()) { - time_spent += ktime_get_ns() - time_start; - migrate_enable(); - rcu_read_unlock(); - - cond_resched(); - - rcu_read_lock(); - migrate_disable(); - time_start = ktime_get_ns(); - } - } + } while (bpf_test_timer_continue(&t, repeat, &ret, time)); bpf_reset_run_ctx(old_ctx); - time_spent += ktime_get_ns() - time_start; - migrate_enable(); - rcu_read_unlock(); - - do_div(time_spent, repeat); - *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + bpf_test_timer_leave(&t);
for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(item.cgroup_storage[stype]); @@ -692,18 +731,17 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { + struct bpf_test_timer t = { NO_PREEMPT }; u32 size = kattr->test.data_size_in; struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; struct bpf_flow_keys *user_ctx; struct bpf_flow_keys flow_keys; - u64 time_start, time_spent = 0; const struct ethhdr *eth; unsigned int flags = 0; u32 retval, duration; void *data; int ret; - u32 i;
if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; @@ -739,39 +777,15 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, ctx.data = data; ctx.data_end = (__u8 *)data + size;
- rcu_read_lock(); - preempt_disable(); - time_start = ktime_get_ns(); - for (i = 0; i < repeat; i++) { + bpf_test_timer_enter(&t); + do { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, size, flags); + } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); + bpf_test_timer_leave(&t);
- if (signal_pending(current)) { - preempt_enable(); - rcu_read_unlock(); - - ret = -EINTR; - goto out; - } - - if (need_resched()) { - time_spent += ktime_get_ns() - time_start; - preempt_enable(); - rcu_read_unlock(); - - cond_resched(); - - rcu_read_lock(); - preempt_disable(); - time_start = ktime_get_ns(); - } - } - time_spent += ktime_get_ns() - time_start; - preempt_enable(); - rcu_read_unlock(); - - do_div(time_spent, repeat); - duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + if (ret < 0) + goto out;
ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), retval, duration);