[PATCH v5 7/7] eal: keep per-lcore power intrinsics state in lcore variable

[Mattias Rönnblom]

Keep per-lcore power intrinsics state in a lcore variable to reduce
cache working set size and avoid any CPU next-line-prefetching causing
false sharing.

Signed-off-by: Mattias Rönnblom <mattias.ronnb...@ericsson.com>
Acked-by: Morten Brørup <m...@smartsharesystems.com>
Acked-by: Konstantin Ananyev <konstantin.anan...@huawei.com>
---
 lib/eal/x86/rte_power_intrinsics.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/lib/eal/x86/rte_power_intrinsics.c 
b/lib/eal/x86/rte_power_intrinsics.c
index 6d9b64240c..f4ba2c8ecb 100644
--- a/lib/eal/x86/rte_power_intrinsics.c
+++ b/lib/eal/x86/rte_power_intrinsics.c
@@ -6,6 +6,7 @@
 
 #include <rte_common.h>
 #include <rte_lcore.h>
+#include <rte_lcore_var.h>
 #include <rte_rtm.h>
 #include <rte_spinlock.h>
 
@@ -14,10 +15,14 @@
 /*
  * Per-lcore structure holding current status of C0.2 sleeps.
  */
-static alignas(RTE_CACHE_LINE_SIZE) struct power_wait_status {
+struct power_wait_status {
        rte_spinlock_t lock;
        volatile void *monitor_addr; /**< NULL if not currently sleeping */
-} wait_status[RTE_MAX_LCORE];
+};
+
+RTE_LCORE_VAR_HANDLE(struct power_wait_status, wait_status);
+
+RTE_LCORE_VAR_INIT(wait_status);
 
 /*
  * This function uses UMONITOR/UMWAIT instructions and will enter C0.2 state.
@@ -172,7 +177,7 @@ rte_power_monitor(const struct rte_power_monitor_cond *pmc,
        if (pmc->fn == NULL)
                return -EINVAL;
 
-       s = &wait_status[lcore_id];
+       s = RTE_LCORE_VAR_LCORE_VALUE(lcore_id, wait_status);
 
        /* update sleep address */
        rte_spinlock_lock(&s->lock);
@@ -264,7 +269,7 @@ rte_power_monitor_wakeup(const unsigned int lcore_id)
        if (lcore_id >= RTE_MAX_LCORE)
                return -EINVAL;
 
-       s = &wait_status[lcore_id];
+       s = RTE_LCORE_VAR_LCORE_VALUE(lcore_id, wait_status);
 
        /*
         * There is a race condition between sleep, wakeup and locking, but we
@@ -303,8 +308,8 @@ int
 rte_power_monitor_multi(const struct rte_power_monitor_cond pmc[],
                const uint32_t num, const uint64_t tsc_timestamp)
 {
-       const unsigned int lcore_id = rte_lcore_id();
-       struct power_wait_status *s = &wait_status[lcore_id];
+       struct power_wait_status *s = RTE_LCORE_VAR_VALUE(wait_status);
+
        uint32_t i, rc;
 
        /* check if supported */
-- 
2.34.1