summaryrefslogtreecommitdiffstats
path: root/io_uring/sqpoll.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-08-07 13:11:27 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-08-07 13:11:27 +0000
commit34996e42f82bfd60bc2c191e5cae3c6ab233ec6c (patch)
tree62db60558cbf089714b48daeabca82bf2b20b20e /io_uring/sqpoll.c
parentAdding debian version 6.8.12-1. (diff)
downloadlinux-34996e42f82bfd60bc2c191e5cae3c6ab233ec6c.tar.xz
linux-34996e42f82bfd60bc2c191e5cae3c6ab233ec6c.zip
Merging upstream version 6.9.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'io_uring/sqpoll.c')
-rw-r--r--io_uring/sqpoll.c75
1 files changed, 71 insertions, 4 deletions
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 65b5dbe3c8..b3722e5275 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -15,9 +15,11 @@
#include <uapi/linux/io_uring.h>
#include "io_uring.h"
+#include "napi.h"
#include "sqpoll.h"
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
+#define IORING_TW_CAP_ENTRIES_VALUE 8
enum {
IO_SQ_THREAD_SHOULD_STOP = 0,
@@ -193,6 +195,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
ret = io_submit_sqes(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
+ if (io_napi(ctx))
+ ret += io_napi_sqpoll_busy_poll(ctx);
+
if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
wake_up(&ctx->sqo_sq_wait);
if (creds)
@@ -219,14 +224,62 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
}
+/*
+ * Run task_work, processing the retry_list first. The retry_list holds
+ * entries that we passed on in the previous run, if we had more task_work
+ * than we were asked to process. Newly queued task_work isn't run until the
+ * retry list has been fully processed.
+ */
+static unsigned int io_sq_tw(struct llist_node **retry_list, int max_entries)
+{
+ struct io_uring_task *tctx = current->io_uring;
+ unsigned int count = 0;
+
+ if (*retry_list) {
+ *retry_list = io_handle_tw_list(*retry_list, &count, max_entries);
+ if (count >= max_entries)
+ goto out;
+ max_entries -= count;
+ }
+ *retry_list = tctx_task_work_run(tctx, max_entries, &count);
+out:
+ if (task_work_pending(current))
+ task_work_run();
+ return count;
+}
+
+static bool io_sq_tw_pending(struct llist_node *retry_list)
+{
+ struct io_uring_task *tctx = current->io_uring;
+
+ return retry_list || !llist_empty(&tctx->task_list);
+}
+
+static void io_sq_update_worktime(struct io_sq_data *sqd, struct rusage *start)
+{
+ struct rusage end;
+
+ getrusage(current, RUSAGE_SELF, &end);
+ end.ru_stime.tv_sec -= start->ru_stime.tv_sec;
+ end.ru_stime.tv_usec -= start->ru_stime.tv_usec;
+
+ sqd->work_time += end.ru_stime.tv_usec + end.ru_stime.tv_sec * 1000000;
+}
+
static int io_sq_thread(void *data)
{
+ struct llist_node *retry_list = NULL;
struct io_sq_data *sqd = data;
struct io_ring_ctx *ctx;
+ struct rusage start;
unsigned long timeout = 0;
char buf[TASK_COMM_LEN];
DEFINE_WAIT(wait);
+ /* offload context creation failed, just exit */
+ if (!current->io_uring)
+ goto err_out;
+
snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
set_task_comm(current, buf);
@@ -240,6 +293,14 @@ static int io_sq_thread(void *data)
sqd->sq_cpu = raw_smp_processor_id();
}
+ /*
+ * Force audit context to get setup, in case we do prep side async
+ * operations that would trigger an audit call before any issue side
+ * audit has been done.
+ */
+ audit_uring_entry(IORING_OP_NOP);
+ audit_uring_exit(true, 0);
+
mutex_lock(&sqd->lock);
while (1) {
bool cap_entries, sqt_spin = false;
@@ -251,18 +312,21 @@ static int io_sq_thread(void *data)
}
cap_entries = !list_is_singular(&sqd->ctx_list);
+ getrusage(current, RUSAGE_SELF, &start);
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
int ret = __io_sq_thread(ctx, cap_entries);
if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
sqt_spin = true;
}
- if (io_run_task_work())
+ if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE))
sqt_spin = true;
if (sqt_spin || !time_after(jiffies, timeout)) {
- if (sqt_spin)
+ if (sqt_spin) {
+ io_sq_update_worktime(sqd, &start);
timeout = jiffies + sqd->sq_thread_idle;
+ }
if (unlikely(need_resched())) {
mutex_unlock(&sqd->lock);
cond_resched();
@@ -273,7 +337,7 @@ static int io_sq_thread(void *data)
}
prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
- if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
+ if (!io_sqd_events_pending(sqd) && !io_sq_tw_pending(retry_list)) {
bool needs_sched = true;
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -312,13 +376,16 @@ static int io_sq_thread(void *data)
timeout = jiffies + sqd->sq_thread_idle;
}
+ if (retry_list)
+ io_sq_tw(&retry_list, UINT_MAX);
+
io_uring_cancel_generic(true, sqd);
sqd->thread = NULL;
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
io_run_task_work();
mutex_unlock(&sqd->lock);
-
+err_out:
complete(&sqd->exited);
do_exit(0);
}