dpdk: Support running PMD threads on any core.

Previously in OVS, a PMD thread running on cpu X used lcore X.
This assumption limited OVS to run PMD threads on physical cpu <
RTE_MAX_LCORE.

DPDK 20.08 introduced a new API that associates a non-EAL thread to a free
lcore. This new API does not change the thread characteristics (like CPU
affinity) and let OVS run its PMD threads on any cpu regardless of
RTE_MAX_LCORE.

The DPDK multiprocess feature is not compatible with this new API and is
disabled.

DPDK still limits the number of lcores to RTE_MAX_LCORE (128 on x86_64)
which should be enough for OVS pmd threads (hopefully).

DPDK lcore/OVS pmd threads mapping are logged at threads when trying to
attach a OVS PMD thread, and when detaching.
A new command is added to help get DPDK point of view of the DPDK lcores
at any time:

$ ovs-appctl dpdk/lcore-list
lcore 0, socket 0, role RTE, cpuset 0
lcore 1, socket 0, role NON_EAL, cpuset 1
lcore 2, socket 0, role NON_EAL, cpuset 15

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Kevin Traynor <ktraynor@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>

7 files changed, 71 insertions, 12 deletions

diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst
index 70b64881a..81f236d3b 100644
--- a/Documentation/howto/dpdk.rst
+++ b/Documentation/howto/dpdk.rst
@@ -402,6 +402,11 @@ Supported actions for hardware offload are:
 - Clone/output (tnl_push and output) for encapsulating over a tunnel.
 - Tunnel pop, for packets received on physical ports.
 
+Multiprocess
+------------
+
+This DPDK feature is not supported and disabled during OVS initialization.
+
 Further Reading
 ---------------
 
diff --git a/NEWS b/NEWS
index aaaa038b8..afef81b40 100644
--- a/NEWS
+++ b/NEWS
@@ -17,6 +17,8 @@ Post-v2.16.0
      * Add hardware offload support for GRE flows (experimental).
        Available only if DPDK experimantal APIs enabled during the build.
      * Add support for DPDK 21.11.
+     * Forbid use of DPDK multiprocess feature.
+     * Add support for running threads on cores >= RTE_MAX_LCORE.
    - Python:
      * For SSL support, the use of the pyOpenSSL library has been replaced
        with the native 'ssl' module.
diff --git a/lib/dpdk-stub.c b/lib/dpdk-stub.c
index c332c217c..3eee1f485 100644
--- a/lib/dpdk-stub.c
+++ b/lib/dpdk-stub.c
@@ -38,10 +38,15 @@ dpdk_init(const struct smap *ovs_other_config)
     }
 }
 
+bool
+dpdk_attach_thread(unsigned cpu OVS_UNUSED)
+{
+    return false;
+}
+
 void
-dpdk_set_lcore_id(unsigned cpu OVS_UNUSED)
+dpdk_detach_thread(void)
 {
-    /* Nothing */
 }
 
 const char *
diff --git a/lib/dpdk-unixctl.man b/lib/dpdk-unixctl.man
index a0d1fa2ea..5bac80638 100644
--- a/lib/dpdk-unixctl.man
+++ b/lib/dpdk-unixctl.man
@@ -1,5 +1,8 @@
 .SS "DPDK COMMANDS"
 These commands manage DPDK components.
+.IP "\fBdpdk/lcore-list\fR"
+Lists the DPDK lcores and their cpu affinity.
+When RTE_MAX_LCORE lcores are registered, some OVS PMD threads won't appear.
 .IP "\fBdpdk/log-list\fR"
 Lists all DPDK components that emit logs and their logging levels.
 .IP "\fBdpdk/log-set\fR [\fIspec\fR]"
diff --git a/lib/dpdk.c b/lib/dpdk.c
index 38f142017..6886fbd9d 100644
--- a/lib/dpdk.c
+++ b/lib/dpdk.c
@@ -35,6 +35,7 @@
 #include "netdev-offload-provider.h"
 #include "openvswitch/dynamic-string.h"
 #include "openvswitch/vlog.h"
+#include "ovs-atomic.h"
 #include "ovs-numa.h"
 #include "smap.h"
 #include "svec.h"
@@ -50,10 +51,11 @@ static char *vhost_sock_dir = NULL;   /* Location of vhost-user sockets */
 static bool vhost_iommu_enabled = false; /* Status of vHost IOMMU support */
 static bool vhost_postcopy_enabled = false; /* Status of vHost POSTCOPY
                                              * support. */
-static bool dpdk_initialized = false; /* Indicates successful initialization
-                                       * of DPDK. */
 static bool per_port_memory = false; /* Status of per port memory support */
 
+/* Indicates successful initialization of DPDK. */
+static atomic_bool dpdk_initialized = ATOMIC_VAR_INIT(false);
+
 static int
 process_vhost_flags(char *flag, const char *default_val, int size,
                     const struct smap *ovs_other_config,
@@ -477,6 +479,12 @@ dpdk_init__(const struct smap *ovs_other_config)
         return false;
     }
 
+    if (!rte_mp_disable()) {
+        VLOG_EMER("Could not disable multiprocess, DPDK won't be available.");
+        rte_eal_cleanup();
+        return false;
+    }
+
     if (VLOG_IS_DBG_ENABLED()) {
         size_t size;
         char *response = NULL;
@@ -496,6 +504,8 @@ dpdk_init__(const struct smap *ovs_other_config)
         }
     }
 
+    unixctl_command_register("dpdk/lcore-list", "", 0, 0,
+                             dpdk_unixctl_mem_stream, rte_lcore_dump);
     unixctl_command_register("dpdk/log-list", "", 0, 0,
                              dpdk_unixctl_mem_stream, rte_log_dump);
     unixctl_command_register("dpdk/log-set", "{level | pattern:level}", 0,
@@ -545,7 +555,7 @@ dpdk_init(const struct smap *ovs_other_config)
     } else {
         VLOG_INFO_ONCE("DPDK Disabled - Use other_config:dpdk-init to enable");
     }
-    dpdk_initialized = enabled;
+    atomic_store_relaxed(&dpdk_initialized, enabled);
 }
 
 const char *
@@ -575,15 +585,40 @@ dpdk_per_port_memory(void)
 bool
 dpdk_available(void)
 {
-    return dpdk_initialized;
+    bool initialized;
+
+    atomic_read_relaxed(&dpdk_initialized, &initialized);
+    return initialized;
 }
 
-void
-dpdk_set_lcore_id(unsigned cpu)
+bool
+dpdk_attach_thread(unsigned cpu)
 {
     /* NON_PMD_CORE_ID is reserved for use by non pmd threads. */
     ovs_assert(cpu != NON_PMD_CORE_ID);
-    RTE_PER_LCORE(_lcore_id) = cpu;
+
+    if (!dpdk_available()) {
+        return false;
+    }
+
+    if (rte_thread_register() < 0) {
+        VLOG_WARN("DPDK max threads count has been reached. "
+                  "PMD thread performance may be impacted.");
+        return false;
+    }
+
+    VLOG_INFO("PMD thread uses DPDK lcore %u.", rte_lcore_id());
+    return true;
+}
+
+void
+dpdk_detach_thread(void)
+{
+    unsigned int lcore_id;
+
+    lcore_id = rte_lcore_id();
+    rte_thread_unregister();
+    VLOG_INFO("PMD thread released DPDK lcore %u.", lcore_id);
 }
 
 void
@@ -596,7 +631,7 @@ void
 dpdk_status(const struct ovsrec_open_vswitch *cfg)
 {
     if (cfg) {
-        ovsrec_open_vswitch_set_dpdk_initialized(cfg, dpdk_initialized);
+        ovsrec_open_vswitch_set_dpdk_initialized(cfg, dpdk_available());
         ovsrec_open_vswitch_set_dpdk_version(cfg, rte_version());
     }
 }
diff --git a/lib/dpdk.h b/lib/dpdk.h
index 2eb1aedbb..64ebca47d 100644
--- a/lib/dpdk.h
+++ b/lib/dpdk.h
@@ -36,7 +36,8 @@ struct smap;
 struct ovsrec_open_vswitch;
 
 void dpdk_init(const struct smap *ovs_other_config);
-void dpdk_set_lcore_id(unsigned cpu);
+bool dpdk_attach_thread(unsigned cpu);
+void dpdk_detach_thread(void);
 const char *dpdk_get_vhost_sock_dir(void);
 bool dpdk_vhost_iommu_enabled(void);
 bool dpdk_vhost_postcopy_enabled(void);
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index 1efeab622..649c700cb 100644
--- a/lib/dpif-netdev.c
+++ b/lib/dpif-netdev.c
@@ -6390,6 +6390,7 @@ pmd_thread_main(void *f_)
     unsigned int lc = 0;
     struct polled_queue *poll_list;
     bool wait_for_reload = false;
+    bool dpdk_attached;
     bool reload_tx_qid;
     bool exiting;
     bool reload;
@@ -6402,7 +6403,7 @@ pmd_thread_main(void *f_)
     /* Stores the pmd thread's 'pmd' to 'per_pmd_key'. */
     ovsthread_setspecific(pmd->dp->per_pmd_key, pmd);
     ovs_numa_thread_setaffinity_core(pmd->core_id);
-    dpdk_set_lcore_id(pmd->core_id);
+    dpdk_attached = dpdk_attach_thread(pmd->core_id);
     poll_cnt = pmd_load_queues_and_ports(pmd, &poll_list);
     dfc_cache_init(&pmd->flow_cache);
     pmd_alloc_static_tx_qid(pmd);
@@ -6410,6 +6411,10 @@ pmd_thread_main(void *f_)
 reload:
     atomic_count_init(&pmd->pmd_overloaded, 0);
 
+    if (!dpdk_attached) {
+        dpdk_attached = dpdk_attach_thread(pmd->core_id);
+    }
+
     /* List port/core affinity */
     for (i = 0; i < poll_cnt; i++) {
        VLOG_DBG("Core %d processing port \'%s\' with queue-id %d\n",
@@ -6546,6 +6551,9 @@ reload:
     dfc_cache_uninit(&pmd->flow_cache);
     free(poll_list);
     pmd_free_cached_ports(pmd);
+    if (dpdk_attached) {
+        dpdk_detach_thread();
+    }
     return NULL;
 }