Merge: net: IRQ suspension

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1588

JIRA: https://issues.redhat.com/browse/RHEL-77189

Tested using the selftest in the series. See the associated Jira ticket for details about the feature.

Signed-off-by: Antoine Tenart <atenart@redhat.com>

Approved-by: Davide Caratti <dcaratti@redhat.com>
Approved-by: Xin Long <lxin@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

Documentation/netlink/specs/netdev.yaml

@@ -267,6 +267,11 @@ attribute-sets:
              the end of a NAPI cycle. This may add receive latency in exchange
              for reducing the number of frames processed by the network stack.
         type: uint
+      -
+        name: irq-suspend-timeout
+        doc: The timeout, in nanoseconds, of how long to suspend irq
+             processing, if event polling finds events
+        type: uint
   -
     name: queue
     attributes:
@@ -657,6 +662,7 @@ operations:
             - pid
             - defer-hard-irqs
             - gro-flush-timeout
+            - irq-suspend-timeout
       dump:
         request:
           attributes:
@@ -708,6 +714,7 @@ operations:
             - id
             - defer-hard-irqs
             - gro-flush-timeout
+            - irq-suspend-timeout
 
 kernel-family:
   headers: [ "linux/list.h"]

Documentation/networking/napi.rst

@@ -192,6 +192,33 @@ is reused to control the delay of the timer, while
 ``napi_defer_hard_irqs`` controls the number of consecutive empty polls
 before NAPI gives up and goes back to using hardware IRQs.
 
+The above parameters can also be set on a per-NAPI basis using netlink via
+netdev-genl. When used with netlink and configured on a per-NAPI basis, the
+parameters mentioned above use hyphens instead of underscores:
+``gro-flush-timeout`` and ``napi-defer-hard-irqs``.
+
+Per-NAPI configuration can be done programmatically in a user application
+or by using a script included in the kernel source tree:
+``tools/net/ynl/cli.py``.
+
+For example, using the script:
+
+.. code-block:: bash
+
+  $ kernel-source/tools/net/ynl/cli.py \
+            --spec Documentation/netlink/specs/netdev.yaml \
+            --do napi-set \
+            --json='{"id": 345,
+                     "defer-hard-irqs": 111,
+                     "gro-flush-timeout": 11111}'
+
+Similarly, the parameter ``irq-suspend-timeout`` can be set using netlink
+via netdev-genl. There is no global sysfs parameter for this value.
+
+``irq-suspend-timeout`` is used to determine how long an application can
+completely suspend IRQs. It is used in combination with SO_PREFER_BUSY_POLL,
+which can be set on a per-epoll context basis with ``EPIOCSPARAMS`` ioctl.
+
 .. _poll:
 
 Busy polling
@@ -207,6 +234,46 @@ selected sockets or using the global ``net.core.busy_poll`` and
 ``net.core.busy_read`` sysctls. An io_uring API for NAPI busy polling
 also exists.
 
+epoll-based busy polling
+------------------------
+
+It is possible to trigger packet processing directly from calls to
+``epoll_wait``. In order to use this feature, a user application must ensure
+all file descriptors which are added to an epoll context have the same NAPI ID.
+
+If the application uses a dedicated acceptor thread, the application can obtain
+the NAPI ID of the incoming connection using SO_INCOMING_NAPI_ID and then
+distribute that file descriptor to a worker thread. The worker thread would add
+the file descriptor to its epoll context. This would ensure each worker thread
+has an epoll context with FDs that have the same NAPI ID.
+
+Alternatively, if the application uses SO_REUSEPORT, a bpf or ebpf program can
+be inserted to distribute incoming connections to threads such that each thread
+is only given incoming connections with the same NAPI ID. Care must be taken to
+carefully handle cases where a system may have multiple NICs.
+
+In order to enable busy polling, there are two choices:
+
+1. ``/proc/sys/net/core/busy_poll`` can be set with a time in useconds to busy
+   loop waiting for events. This is a system-wide setting and will cause all
+   epoll-based applications to busy poll when they call epoll_wait. This may
+   not be desirable as many applications may not have the need to busy poll.
+
+2. Applications using recent kernels can issue an ioctl on the epoll context
+   file descriptor to set (``EPIOCSPARAMS``) or get (``EPIOCGPARAMS``) ``struct
+   epoll_params``:, which user programs can define as follows:
+
+.. code-block:: c
+
+  struct epoll_params {
+      uint32_t busy_poll_usecs;
+      uint16_t busy_poll_budget;
+      uint8_t prefer_busy_poll;
+
+      /* pad the struct to a multiple of 64bits */
+      uint8_t __pad;
+  };
+
 IRQ mitigation
 ---------------
 
@@ -222,12 +289,111 @@ Such applications can pledge to the kernel that they will perform a busy
 polling operation periodically, and the driver should keep the device IRQs
 permanently masked. This mode is enabled by using the ``SO_PREFER_BUSY_POLL``
 socket option. To avoid system misbehavior the pledge is revoked
-if ``gro_flush_timeout`` passes without any busy poll call.
+if ``gro_flush_timeout`` passes without any busy poll call. For epoll-based
+busy polling applications, the ``prefer_busy_poll`` field of ``struct
+epoll_params`` can be set to 1 and the ``EPIOCSPARAMS`` ioctl can be issued to
+enable this mode. See the above section for more details.
 
 The NAPI budget for busy polling is lower than the default (which makes
 sense given the low latency intention of normal busy polling). This is
 not the case with IRQ mitigation, however, so the budget can be adjusted
-with the ``SO_BUSY_POLL_BUDGET`` socket option.
+with the ``SO_BUSY_POLL_BUDGET`` socket option. For epoll-based busy polling
+applications, the ``busy_poll_budget`` field can be adjusted to the desired value
+in ``struct epoll_params`` and set on a specific epoll context using the ``EPIOCSPARAMS``
+ioctl. See the above section for more details.
+
+It is important to note that choosing a large value for ``gro_flush_timeout``
+will defer IRQs to allow for better batch processing, but will induce latency
+when the system is not fully loaded. Choosing a small value for
+``gro_flush_timeout`` can cause interference of the user application which is
+attempting to busy poll by device IRQs and softirq processing. This value
+should be chosen carefully with these tradeoffs in mind. epoll-based busy
+polling applications may be able to mitigate how much user processing happens
+by choosing an appropriate value for ``maxevents``.
+
+Users may want to consider an alternate approach, IRQ suspension, to help deal
+with these tradeoffs.
+
+IRQ suspension
+--------------
+
+IRQ suspension is a mechanism wherein device IRQs are masked while epoll
+triggers NAPI packet processing.
+
+While application calls to epoll_wait successfully retrieve events, the kernel will
+defer the IRQ suspension timer. If the kernel does not retrieve any events
+while busy polling (for example, because network traffic levels subsided), IRQ
+suspension is disabled and the IRQ mitigation strategies described above are
+engaged.
+
+This allows users to balance CPU consumption with network processing
+efficiency.
+
+To use this mechanism:
+
+  1. The per-NAPI config parameter ``irq-suspend-timeout`` should be set to the
+     maximum time (in nanoseconds) the application can have its IRQs
+     suspended. This is done using netlink, as described above. This timeout
+     serves as a safety mechanism to restart IRQ driver interrupt processing if
+     the application has stalled. This value should be chosen so that it covers
+     the amount of time the user application needs to process data from its
+     call to epoll_wait, noting that applications can control how much data
+     they retrieve by setting ``max_events`` when calling epoll_wait.
+
+  2. The sysfs parameter or per-NAPI config parameters ``gro_flush_timeout``
+     and ``napi_defer_hard_irqs`` can be set to low values. They will be used
+     to defer IRQs after busy poll has found no data.
+
+  3. The ``prefer_busy_poll`` flag must be set to true. This can be done using
+     the ``EPIOCSPARAMS`` ioctl as described above.
+
+  4. The application uses epoll as described above to trigger NAPI packet
+     processing.
+
+As mentioned above, as long as subsequent calls to epoll_wait return events to
+userland, the ``irq-suspend-timeout`` is deferred and IRQs are disabled. This
+allows the application to process data without interference.
+
+Once a call to epoll_wait results in no events being found, IRQ suspension is
+automatically disabled and the ``gro_flush_timeout`` and
+``napi_defer_hard_irqs`` mitigation mechanisms take over.
+
+It is expected that ``irq-suspend-timeout`` will be set to a value much larger
+than ``gro_flush_timeout`` as ``irq-suspend-timeout`` should suspend IRQs for
+the duration of one userland processing cycle.
+
+While it is not stricly necessary to use ``napi_defer_hard_irqs`` and
+``gro_flush_timeout`` to use IRQ suspension, their use is strongly
+recommended.
+
+IRQ suspension causes the system to alternate between polling mode and
+irq-driven packet delivery. During busy periods, ``irq-suspend-timeout``
+overrides ``gro_flush_timeout`` and keeps the system busy polling, but when
+epoll finds no events, the setting of ``gro_flush_timeout`` and
+``napi_defer_hard_irqs`` determine the next step.
+
+There are essentially three possible loops for network processing and
+packet delivery:
+
+1) hardirq -> softirq -> napi poll; basic interrupt delivery
+2) timer -> softirq -> napi poll; deferred irq processing
+3) epoll -> busy-poll -> napi poll; busy looping
+
+Loop 2 can take control from Loop 1, if ``gro_flush_timeout`` and
+``napi_defer_hard_irqs`` are set.
+
+If ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` are set, Loops 2
+and 3 "wrestle" with each other for control.
+
+During busy periods, ``irq-suspend-timeout`` is used as timer in Loop 2,
+which essentially tilts network processing in favour of Loop 3.
+
+If ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` are not set, Loop 3
+cannot take control from Loop 1.
+
+Therefore, setting ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` is
+the recommended usage, because otherwise setting ``irq-suspend-timeout``
+might not have any discernible effect.
 
 .. _threaded:
 

fs/eventpoll.c

@@ -420,7 +420,9 @@ static bool busy_loop_ep_timeout(unsigned long start_time,
 
 static bool ep_busy_loop_on(struct eventpoll *ep)
 {
-	return !!READ_ONCE(ep->busy_poll_usecs) || net_busy_loop_on();
+	return !!READ_ONCE(ep->busy_poll_usecs) ||
+	       READ_ONCE(ep->prefer_busy_poll) ||
+	       net_busy_loop_on();
 }
 
 static bool ep_busy_loop_end(void *p, unsigned long start_time)
@@ -455,6 +457,8 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
 		 * it back in when we have moved a socket with a valid NAPI
 		 * ID onto the ready list.
 		 */
+		if (prefer_busy_poll)
+			napi_resume_irqs(napi_id);
 		ep->napi_id = 0;
 		return false;
 	}
@@ -538,6 +542,22 @@ static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
 	}
 }
 
+static void ep_suspend_napi_irqs(struct eventpoll *ep)
+{
+	unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+	if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll))
+		napi_suspend_irqs(napi_id);
+}
+
+static void ep_resume_napi_irqs(struct eventpoll *ep)
+{
+	unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+	if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll))
+		napi_resume_irqs(napi_id);
+}
+
 #else
 
 static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock)
@@ -555,6 +575,14 @@ static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
 	return -EOPNOTSUPP;
 }
 
+static void ep_suspend_napi_irqs(struct eventpoll *ep)
+{
+}
+
+static void ep_resume_napi_irqs(struct eventpoll *ep)
+{
+}
+
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
 /*
@@ -786,6 +814,7 @@ static bool ep_refcount_dec_and_test(struct eventpoll *ep)
 
 static void ep_free(struct eventpoll *ep)
 {
+	ep_resume_napi_irqs(ep);
 	mutex_destroy(&ep->mtx);
 	free_uid(ep->user);
 	wakeup_source_unregister(ep->ws);
@@ -2003,8 +2032,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 			 * trying again in search of more luck.
 			 */
 			res = ep_send_events(ep, events, maxevents);
-			if (res)
+			if (res) {
+				if (res > 0)
+					ep_suspend_napi_irqs(ep);
 				return res;
+			}
 		}
 
 		if (timed_out)

include/linux/netdevice.h

@@ -349,6 +349,7 @@ struct gro_list {
  */
 struct napi_config {
 	u64 gro_flush_timeout;
+	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	unsigned int napi_id;
 };
@@ -385,6 +386,7 @@ struct napi_struct {
 	struct hrtimer		timer;
 	struct task_struct	*thread;
 	unsigned long		gro_flush_timeout;
+	unsigned long		irq_suspend_timeout;
 	u32			defer_hard_irqs;
 	/* control-path-only fields follow */
 	struct list_head	dev_list;

include/net/busy_poll.h

@@ -52,6 +52,9 @@ void napi_busy_loop_rcu(unsigned int napi_id,
 			bool (*loop_end)(void *, unsigned long),
 			void *loop_end_arg, bool prefer_busy_poll, u16 budget);
 
+void napi_suspend_irqs(unsigned int napi_id);
+void napi_resume_irqs(unsigned int napi_id);
+
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
 {

include/uapi/linux/netdev.h

@@ -127,6 +127,7 @@ enum {
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)

net/core/dev.c

@@ -6595,6 +6595,43 @@ void napi_busy_loop(unsigned int napi_id,
 }
 EXPORT_SYMBOL(napi_busy_loop);
 
+void napi_suspend_irqs(unsigned int napi_id)
+{
+	struct napi_struct *napi;
+
+	rcu_read_lock();
+	napi = napi_by_id(napi_id);
+	if (napi) {
+		unsigned long timeout = napi_get_irq_suspend_timeout(napi);
+
+		if (timeout)
+			hrtimer_start(&napi->timer, ns_to_ktime(timeout),
+				      HRTIMER_MODE_REL_PINNED);
+	}
+	rcu_read_unlock();
+}
+
+void napi_resume_irqs(unsigned int napi_id)
+{
+	struct napi_struct *napi;
+
+	rcu_read_lock();
+	napi = napi_by_id(napi_id);
+	if (napi) {
+		/* If irq_suspend_timeout is set to 0 between the call to
+		 * napi_suspend_irqs and now, the original value still
+		 * determines the safety timeout as intended and napi_watchdog
+		 * will resume irq processing.
+		 */
+		if (napi_get_irq_suspend_timeout(napi)) {
+			local_bh_disable();
+			napi_schedule(napi);
+			local_bh_enable();
+		}
+	}
+	rcu_read_unlock();
+}
+
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
 static void __napi_hash_add_with_id(struct napi_struct *napi,
@@ -6760,6 +6797,7 @@ static void napi_restore_config(struct napi_struct *n)
 {
 	n->defer_hard_irqs = n->config->defer_hard_irqs;
 	n->gro_flush_timeout = n->config->gro_flush_timeout;
+	n->irq_suspend_timeout = n->config->irq_suspend_timeout;
 	/* a NAPI ID might be stored in the config, if so use it. if not, use
 	 * napi_hash_add to generate one for us. It will be saved to the config
 	 * in napi_disable.
@@ -6774,6 +6812,7 @@ static void napi_save_config(struct napi_struct *n)
 {
 	n->config->defer_hard_irqs = n->defer_hard_irqs;
 	n->config->gro_flush_timeout = n->gro_flush_timeout;
+	n->config->irq_suspend_timeout = n->irq_suspend_timeout;
 	n->config->napi_id = n->napi_id;
 	napi_hash_del(n);
 }