[dpdk-stable] [PATCH v2] eal: fix ctrl thread affinity with --lcores

[David Marchand]

The ctrl thread cpu affinity setting has been broken when using --lcores.

Using -l/-c options makes each lcore associated to a physical cpu in a 1:1
fashion.
On the contrary, when using --lcores, each lcore cpu affinity can be set
to a list of any online cpu on the system.

To handle both cases, each lcore cpu affinity is considered and removed
from the process startup cpu affinity.

Introduced macros to manipulate dpdk cpu sets in both Linux and FreeBSD.

Examples on a 8 cores Linux system:

$ cd /sys/fs/cgroup/cpuset/
$ mkdir dpdk
$ cd dpdk
$ echo 4-7 > cpuset.cpus
$ echo 0 > cpuset.mems
$ echo $$ > tasks

Before the fix:
$ ./master/app/testpmd --master-lcore 0 --lcores '(0,7)@(7,4,5)' \
 --no-huge --no-pci -m 512 -- -i --total-num-mbufs=2048

8427	cpu_list=4-5,7	testpmd
8428	cpu_list=4-6	eal-intr-thread
8429	cpu_list=4-6	rte_mp_handle
8430	cpu_list=4-5,7	lcore-slave-7

$ taskset -c 7 \
 ./master/app/testpmd --master-lcore 0 --lcores '(0,7)@(7,4,5)' \
 --no-huge --no-pci -m 512 -- -i --total-num-mbufs=2048

EAL: Detected 8 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Failed to create thread for interrupt handling
EAL: FATAL: Cannot init interrupt-handling thread
EAL: Cannot init interrupt-handling thread
PANIC in main():
Cannot init EAL

After the fix:
$ ./master/app/testpmd --master-lcore 0 --lcores '(0,7)@(7,4,5)' \
 --no-huge --no-pci -m 512 -- -i --total-num-mbufs=2048

15214	cpu_list=4-5,7	testpmd
15215	cpu_list=6	eal-intr-thread
15216	cpu_list=6	rte_mp_handle
15217	cpu_list=4-5,7	lcore-slave-7

$ taskset -c 7 \
 ./master/app/testpmd --master-lcore 0 --lcores '(0,7)@(7,4,5)' \
 --no-huge --no-pci -m 512 -- -i --total-num-mbufs=2048

15297	cpu_list=4-5,7	testpmd
15298	cpu_list=4-5,7	eal-intr-thread
15299	cpu_list=4-5,7	rte_mp_handle
15300	cpu_list=4-5,7	lcore-slave-7

Bugzilla ID: 322
Fixes: c3568ea37670 ("eal: restrict control threads to startup CPU affinity")
Cc: stable at dpdk.org

Reported-by: Johan Källström <johan.kallstrom at ericsson.com>
Signed-off-by: David Marchand <david.marchand at redhat.com>
---
Changelog since v1:
- fixed build issue with icc
- rewrote commit log
- added examples of what was broken

---
 lib/librte_eal/common/eal_common_options.c | 16 +++++++++-------
 lib/librte_eal/common/include/rte_lcore.h  | 29 +++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/lib/librte_eal/common/eal_common_options.c b/lib/librte_eal/common/eal_common_options.c
index 512d508..7b182b8 100644
--- a/lib/librte_eal/common/eal_common_options.c
+++ b/lib/librte_eal/common/eal_common_options.c
@@ -1452,11 +1452,11 @@ compute_ctrl_threads_cpuset(struct internal_config *internal_cfg)
 	unsigned int lcore_id;
 
 	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
-		if (eal_cpu_detected(lcore_id) &&
-				rte_lcore_has_role(lcore_id, ROLE_OFF)) {
-			CPU_SET(lcore_id, cpuset);
-		}
+		if (rte_lcore_has_role(lcore_id, ROLE_OFF))
+			continue;
+		RTE_CPU_OR(cpuset, cpuset, &lcore_config[lcore_id].cpuset);
 	}
+	RTE_CPU_NOT(cpuset, cpuset);
 
 	if (pthread_getaffinity_np(pthread_self(), sizeof(rte_cpuset_t),
 				&default_set))
@@ -1464,9 +1464,11 @@ compute_ctrl_threads_cpuset(struct internal_config *internal_cfg)
 
 	RTE_CPU_AND(cpuset, cpuset, &default_set);
 
-	/* if no detected CPU is off, use master core */
-	if (!CPU_COUNT(cpuset))
-		CPU_SET(rte_get_master_lcore(), cpuset);
+	/* if no remaining cpu, use master lcore cpu affinity */
+	if (!CPU_COUNT(cpuset)) {
+		memcpy(cpuset, &lcore_config[rte_get_master_lcore()].cpuset,
+			sizeof(*cpuset));
+	}
 }
 
 int
diff --git a/lib/librte_eal/common/include/rte_lcore.h b/lib/librte_eal/common/include/rte_lcore.h
index 411df30..c86f72e 100644
--- a/lib/librte_eal/common/include/rte_lcore.h
+++ b/lib/librte_eal/common/include/rte_lcore.h
@@ -25,6 +25,20 @@ extern "C" {
 #if defined(__linux__)
 typedef	cpu_set_t rte_cpuset_t;
 #define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
+#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
+#define RTE_CPU_FILL(set) do \
+{ \
+	unsigned int i; \
+	CPU_ZERO(set); \
+	for (i = 0; i < CPU_SETSIZE; i++) \
+		CPU_SET(i, set); \
+} while (0)
+#define RTE_CPU_NOT(dst, src) do \
+{ \
+	cpu_set_t tmp; \
+	RTE_CPU_FILL(&tmp); \
+	CPU_XOR(dst, &tmp, src); \
+} while (0)
 #elif defined(__FreeBSD__)
 #include <pthread_np.h>
 typedef cpuset_t rte_cpuset_t;
@@ -35,6 +49,21 @@ typedef cpuset_t rte_cpuset_t;
 	CPU_AND(&tmp, src2); \
 	CPU_COPY(&tmp, dst); \
 } while (0)
+#define RTE_CPU_OR(dst, src1, src2) do \
+{ \
+	cpuset_t tmp; \
+	CPU_COPY(src1, &tmp); \
+	CPU_OR(&tmp, src2); \
+	CPU_COPY(&tmp, dst); \
+} while (0)
+#define RTE_CPU_FILL(set) CPU_FILL(set)
+#define RTE_CPU_NOT(dst, src) do \
+{ \
+	cpuset_t tmp; \
+	CPU_FILL(&tmp); \
+	CPU_NAND(&tmp, src); \
+	CPU_COPY(&tmp, dst); \
+} while (0)
 #endif
 
 /**
-- 
1.8.3.1