DPDK patches and discussions
 help / color / mirror / Atom feed
From: Feifei Wang <feifei.wang2@arm.com>
To: David Hunt <david.hunt@intel.com>
Cc: dev@dpdk.org, david.marchand@redhat.com, thomas@monjalon.net,
	stephen@networkplumber.org, nd@arm.com,
	Feifei Wang <feifei.wang2@arm.com>,
	Ruifeng Wang <ruifeng.wang@arm.com>
Subject: [PATCH v4 3/4] power: add power monitor support check
Date: Fri, 11 Nov 2022 18:20:38 +0800	[thread overview]
Message-ID: <20221111102039.3567666-4-feifei.wang2@arm.com> (raw)
In-Reply-To: <20221111102039.3567666-1-feifei.wang2@arm.com>

On ARM, WFE instruction, which is used to power monitor, has no timeout
wake-up mechanism, and if users want to exit power monitor actively, the
main lcore is needed to send SEV instruction to wake up other lcores.

So it is necessary to ensure the main lcore does not enter the
power-monitor state. To solve this, main core support check on ARM is
added.

Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
 lib/power/rte_power_pmd_mgmt.c | 12 ++++++++++++
 lib/power/rte_power_pmd_mgmt.h |  1 +
 2 files changed, 13 insertions(+)

diff --git a/lib/power/rte_power_pmd_mgmt.c b/lib/power/rte_power_pmd_mgmt.c
index ca1840387c..3f3478b2c1 100644
--- a/lib/power/rte_power_pmd_mgmt.c
+++ b/lib/power/rte_power_pmd_mgmt.c
@@ -490,6 +490,18 @@ rte_power_ethdev_pmgmt_queue_enable(unsigned int lcore_id, uint16_t port_id,
 	rte_rx_callback_fn clb;
 	int ret;
 
+#if defined(RTE_ARCH_ARM64)
+	/* Ensure the main lcore does not enter the power-monitor state,
+	 * so that it can be used to wake up other lcores on ARM.
+	 * This is due to WFE instruction has no timeout wake-up mechanism,
+	 * and if users want to exit actively, the main lcore is needed
+	 * to send SEV instruction to wake up other lcores.
+	 */
+	if (lcore_id == rte_get_main_lcore() &&
+			mode == RTE_POWER_MGMT_TYPE_MONITOR)
+		return EPERM;
+#endif
+
 	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL);
 
 	if (queue_id >= RTE_MAX_QUEUES_PER_PORT || lcore_id >= RTE_MAX_LCORE) {
diff --git a/lib/power/rte_power_pmd_mgmt.h b/lib/power/rte_power_pmd_mgmt.h
index 7ae6ef2d32..b1a0989b88 100644
--- a/lib/power/rte_power_pmd_mgmt.h
+++ b/lib/power/rte_power_pmd_mgmt.h
@@ -52,6 +52,7 @@ enum rte_power_pmd_mgmt_type {
  *   The power management scheme to use for specified Rx queue.
  * @return
  *   0 on success
+ *   EPERM main core cannot be supported on ARM
  *   <0 on error
  */
 __rte_experimental
-- 
2.25.1


  parent reply	other threads:[~2022-11-11 10:21 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-25  6:42 [PATCH v1 0/3] Enable PMD power management on Arm Feifei Wang
2022-08-25  6:42 ` [PATCH v1 1/3] eal: add 8 bits case for wait scheme Feifei Wang
2022-08-25  6:42 ` [PATCH v1 2/3] eal: add power mgmt support on Arm Feifei Wang
2022-08-25  6:42 ` [PATCH v1 3/3] examples/l3fwd-power: enable PMD power mgmt " Feifei Wang
2022-08-29 12:48   ` Hunt, David
2022-10-03  7:12     ` David Marchand
2022-10-11  7:56       ` 回复: " Feifei Wang
2022-10-20 20:41         ` Thomas Monjalon
2022-10-27  9:38           ` 回复: " Feifei Wang
2022-10-20 22:09   ` Stephen Hemminger
2022-10-27  9:43     ` 回复: " Feifei Wang
2022-11-07  7:04 ` [PATCH v2 0/3] Enable PMD power management " Feifei Wang
2022-11-07  7:04   ` [PATCH v2 1/3] eal: add 8 bits case for wait scheme Feifei Wang
2022-11-07  7:04   ` [PATCH v2 2/3] eal: add power mgmt support on Arm Feifei Wang
2022-11-07  7:04   ` [PATCH v2 3/3] examples/l3fwd-power: enable PMD power monitor " Feifei Wang
2022-11-07 16:01     ` Stephen Hemminger
2022-11-08  3:25       ` 回复: " Feifei Wang
2022-11-11  7:26 ` [PATCH v3 0/3] Enable PMD power management " Feifei Wang
2022-11-11  7:26   ` [PATCH v3 1/3] eal: add 8 bits case for wait scheme Feifei Wang
2022-11-11  7:26   ` [PATCH v3 2/3] eal: add power mgmt support on Arm Feifei Wang
2022-11-11  7:26   ` [PATCH v3 3/3] examples/l3fwd-power: enable PMD power monitor " Feifei Wang
2022-11-11  8:22     ` Thomas Monjalon
2022-11-11 10:21       ` 回复: " Feifei Wang
2022-11-11 10:20 ` [PATCH v4 0/4] Enable PMD power management " Feifei Wang
2022-11-11 10:20   ` [PATCH v4 1/4] eal: add 8 bits case for wait scheme Feifei Wang
2022-11-11 10:20   ` [PATCH v4 2/4] eal: add power mgmt support on Arm Feifei Wang
2022-11-11 10:20   ` Feifei Wang [this message]
2022-11-11 10:20   ` [PATCH v4 4/4] examples/l3fwd-power: add power monitor wake up API Feifei Wang
2022-12-14  8:14 ` [PATCH v5 0/2] Enable PMD power management on Arm Feifei Wang
2022-12-14  8:14   ` [PATCH v5 1/2] eal: add 8 bits case for wait scheme Feifei Wang
2022-12-14  8:14   ` [PATCH v5 2/2] eal: add power mgmt support on Arm Feifei Wang
2023-02-17 16:23     ` Stephen Hemminger
2023-02-20  1:56       ` 回复: " Feifei Wang
2023-02-17  8:26   ` 回复: [PATCH v5 0/2] Enable PMD power management " Feifei Wang
2023-02-20  8:51 ` [PATCH v6 " Feifei Wang
2023-02-20  8:51   ` [PATCH v6 1/2] eal: add 8 bits case for wait scheme Feifei Wang
2023-02-20  8:51   ` [PATCH v6 2/2] eal: add power mgmt support on Arm Feifei Wang
2023-02-20 12:07   ` [PATCH v6 0/2] Enable PMD power management " David Marchand
2023-02-21  2:37     ` 回复: " Feifei Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221111102039.3567666-4-feifei.wang2@arm.com \
    --to=feifei.wang2@arm.com \
    --cc=david.hunt@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=nd@arm.com \
    --cc=ruifeng.wang@arm.com \
    --cc=stephen@networkplumber.org \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).