summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorBjörn Töpel <bjorn.topel@intel.com>2020-11-30 19:51:57 +0100
committerDaniel Borkmann <daniel@iogearbox.net>2020-12-01 00:09:25 +0100
commit7c951cafc0cb2e575f1d58677b95ac387ac0a5bd (patch)
tree1d47f6c2fb6e3734d52c96a1f0abcf38e2c08cf5 /net/core
parent7fd3253a7de6a317a0683f83739479fb880bffc8 (diff)
net: Add SO_BUSY_POLL_BUDGET socket option
This option lets a user set a per socket NAPI budget for busy-polling. If the options is not set, it will use the default of 8. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/bpf/20201130185205.196029-3-bjorn.topel@gmail.com
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c21
-rw-r--r--net/core/sock.c10
2 files changed, 20 insertions, 11 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 6f8d2cffb7c5..7a1e5936c67f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6496,8 +6496,6 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
#if defined(CONFIG_NET_RX_BUSY_POLL)
-#define BUSY_POLL_BUDGET 8
-
static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
{
if (!skip_schedule) {
@@ -6517,7 +6515,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
clear_bit(NAPI_STATE_SCHED, &napi->state);
}
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll)
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
+ u16 budget)
{
bool skip_schedule = false;
unsigned long timeout;
@@ -6549,21 +6548,21 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
/* All we really want here is to re-enable device interrupts.
* Ideally, a new ndo_busy_poll_stop() could avoid another round.
*/
- rc = napi->poll(napi, BUSY_POLL_BUDGET);
+ rc = napi->poll(napi, budget);
/* We can't gro_normal_list() here, because napi->poll() might have
* rearmed the napi (napi_complete_done()) in which case it could
* already be running on another CPU.
*/
- trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+ trace_napi_poll(napi, rc, budget);
netpoll_poll_unlock(have_poll_lock);
- if (rc == BUSY_POLL_BUDGET)
+ if (rc == budget)
__busy_poll_stop(napi, skip_schedule);
local_bh_enable();
}
void napi_busy_loop(unsigned int napi_id,
bool (*loop_end)(void *, unsigned long),
- void *loop_end_arg, bool prefer_busy_poll)
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget)
{
unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6606,8 +6605,8 @@ restart:
have_poll_lock = netpoll_poll_lock(napi);
napi_poll = napi->poll;
}
- work = napi_poll(napi, BUSY_POLL_BUDGET);
- trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
+ work = napi_poll(napi, budget);
+ trace_napi_poll(napi, work, budget);
gro_normal_list(napi);
count:
if (work > 0)
@@ -6620,7 +6619,7 @@ count:
if (unlikely(need_resched())) {
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock, prefer_busy_poll);
+ busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
preempt_enable();
rcu_read_unlock();
cond_resched();
@@ -6631,7 +6630,7 @@ count:
cpu_relax();
}
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock, prefer_busy_poll);
+ busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
preempt_enable();
out:
rcu_read_unlock();
diff --git a/net/core/sock.c b/net/core/sock.c
index e05f2e52b5a8..d422a6808405 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1165,6 +1165,16 @@ set_sndbuf:
else
WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
break;
+ case SO_BUSY_POLL_BUDGET:
+ if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ } else {
+ if (val < 0 || val > U16_MAX)
+ ret = -EINVAL;
+ else
+ WRITE_ONCE(sk->sk_busy_poll_budget, val);
+ }
+ break;
#endif
case SO_MAX_PACING_RATE: