From: Hemant Agrawal <hemant.agrawal@nxp.com>
To: dev@dpdk.org
Cc: ferruh.yigit@amd.com, Gagandeep Singh <g.singh@nxp.com>, stable@dpdk.org
Subject: [PATCH v5 01/18] bus/dpaa: fix PFDRs leaks due to FQRNIs
Date: Tue, 1 Oct 2024 16:33:08 +0530 [thread overview]
Message-ID: <20241001110325.4173762-2-hemant.agrawal@nxp.com> (raw)
In-Reply-To: <20241001110325.4173762-1-hemant.agrawal@nxp.com>
From: Gagandeep Singh <g.singh@nxp.com>
When a Retire FQ command is executed on a FQ in the
Tentatively Scheduled or Parked states, in that case FQ
is retired immediately and a FQRNI (Frame Queue Retirement
Notification Immediate) message is generated. Software
must read this message from MR and consume it to free
the memory used by it.
Although it is not mentioned about which memory to be used
by FQRNIs in the RM but through experiments it is proven
that it can use PFDRs. So if these messages are allowed to
build up indefinitely then PFDR resources can become exhausted
and cause enqueues to stall. Therefore software must consume
these MR messages on a regular basis to avoid depleting
the available PFDR resources.
This is the PFDRs leak issue which user can experienace while
using the DPDK crypto driver and creating and destroying the
sessions multiple times. On a session destroy, DPDK calls the
qman_retire_fq() for each FQ used by the session, but it does
not handle the FQRNIs generated and allowed them to build up
indefinitely in MR.
This patch fixes this issue by consuming the FQRNIs received
from MR immediately after FQ retire by calling drain_mr_fqrni().
Please note that this drain_mr_fqrni() only look for
FQRNI type messages to consume. If there are other type of messages
like FQRN, FQRL, FQPN, ERN etc. also coming on MR then those
messages need to be handled separately.
Fixes: c47ff048b99a ("bus/dpaa: add QMAN driver core routines")
Cc: stable@dpdk.org
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
---
drivers/bus/dpaa/base/qbman/qman.c | 46 ++++++++++++++++--------------
1 file changed, 25 insertions(+), 21 deletions(-)
diff --git a/drivers/bus/dpaa/base/qbman/qman.c b/drivers/bus/dpaa/base/qbman/qman.c
index 301057723e..9c90ee25a6 100644
--- a/drivers/bus/dpaa/base/qbman/qman.c
+++ b/drivers/bus/dpaa/base/qbman/qman.c
@@ -292,10 +292,32 @@ static inline void qman_stop_dequeues_ex(struct qman_portal *p)
qm_dqrr_set_maxfill(&p->p, 0);
}
+static inline void qm_mr_pvb_update(struct qm_portal *portal)
+{
+ register struct qm_mr *mr = &portal->mr;
+ const struct qm_mr_entry *res = qm_cl(mr->ring, mr->pi);
+
+#ifdef RTE_LIBRTE_DPAA_HWDEBUG
+ DPAA_ASSERT(mr->pmode == qm_mr_pvb);
+#endif
+ /* when accessing 'verb', use __raw_readb() to ensure that compiler
+ * inlining doesn't try to optimise out "excess reads".
+ */
+ if ((__raw_readb(&res->ern.verb) & QM_MR_VERB_VBIT) == mr->vbit) {
+ mr->pi = (mr->pi + 1) & (QM_MR_SIZE - 1);
+ if (!mr->pi)
+ mr->vbit ^= QM_MR_VERB_VBIT;
+ mr->fill++;
+ res = MR_INC(res);
+ }
+ dcbit_ro(res);
+}
+
static int drain_mr_fqrni(struct qm_portal *p)
{
const struct qm_mr_entry *msg;
loop:
+ qm_mr_pvb_update(p);
msg = qm_mr_current(p);
if (!msg) {
/*
@@ -317,6 +339,7 @@ static int drain_mr_fqrni(struct qm_portal *p)
do {
now = mfatb();
} while ((then + 10000) > now);
+ qm_mr_pvb_update(p);
msg = qm_mr_current(p);
if (!msg)
return 0;
@@ -479,27 +502,6 @@ static inline int qm_mr_init(struct qm_portal *portal,
return 0;
}
-static inline void qm_mr_pvb_update(struct qm_portal *portal)
-{
- register struct qm_mr *mr = &portal->mr;
- const struct qm_mr_entry *res = qm_cl(mr->ring, mr->pi);
-
-#ifdef RTE_LIBRTE_DPAA_HWDEBUG
- DPAA_ASSERT(mr->pmode == qm_mr_pvb);
-#endif
- /* when accessing 'verb', use __raw_readb() to ensure that compiler
- * inlining doesn't try to optimise out "excess reads".
- */
- if ((__raw_readb(&res->ern.verb) & QM_MR_VERB_VBIT) == mr->vbit) {
- mr->pi = (mr->pi + 1) & (QM_MR_SIZE - 1);
- if (!mr->pi)
- mr->vbit ^= QM_MR_VERB_VBIT;
- mr->fill++;
- res = MR_INC(res);
- }
- dcbit_ro(res);
-}
-
struct qman_portal *
qman_init_portal(struct qman_portal *portal,
const struct qm_portal_config *c,
@@ -1794,6 +1796,8 @@ int qman_retire_fq(struct qman_fq *fq, u32 *flags)
}
out:
FQUNLOCK(fq);
+ /* Draining FQRNIs, if any */
+ drain_mr_fqrni(&p->p);
return rval;
}
--
2.25.1
next prev parent reply other threads:[~2024-10-01 11:03 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20240801105313.630280-1-hemant.agrawal@nxp.com>
2024-08-01 10:52 ` [PATCH 01/17] " Hemant Agrawal
2024-08-01 10:52 ` [PATCH 02/17] net/dpaa: fix typecasting ch ID to u32 Hemant Agrawal
2024-08-07 15:37 ` Ferruh Yigit
2024-08-01 10:52 ` [PATCH 03/17] bus/dpaa: fix VSP for 1G fm1-mac9 and 10 Hemant Agrawal
2024-08-07 15:38 ` Ferruh Yigit
2024-08-23 7:33 ` Hemant Agrawal
[not found] ` <20240823073240.3708320-1-hemant.agrawal@nxp.com>
2024-08-23 7:32 ` [PATCH v2 01/18] bus/dpaa: fix PFDRs leaks due to FQRNIs Hemant Agrawal
2024-08-23 7:32 ` [PATCH v2 02/18] net/dpaa: fix typecasting ch ID to u32 Hemant Agrawal
2024-08-23 7:32 ` [PATCH v2 03/18] bus/dpaa: fix VSP for 1G fm1-mac9 and 10 Hemant Agrawal
2024-08-23 7:32 ` [PATCH v2 04/18] bus/dpaa: fix the fman details status Hemant Agrawal
[not found] ` <20240930102946.3236998-1-hemant.agrawal@nxp.com>
2024-09-30 10:29 ` [PATCH v3 01/18] bus/dpaa: fix PFDRs leaks due to FQRNIs Hemant Agrawal
2024-09-30 10:29 ` [PATCH v3 02/18] net/dpaa: fix typecasting ch ID to u32 Hemant Agrawal
2024-09-30 10:29 ` [PATCH v3 03/18] bus/dpaa: fix VSP for 1G fm1-mac9 and 10 Hemant Agrawal
2024-09-30 10:29 ` [PATCH v3 04/18] bus/dpaa: fix the fman details status Hemant Agrawal
2024-09-30 10:29 ` [PATCH v3 18/18] net/dpaa: fix reallocate_mbuf handling Hemant Agrawal
[not found] ` <20240930121525.3452847-1-hemant.agrawal@nxp.com>
2024-09-30 12:15 ` [PATCH v4 01/18] bus/dpaa: fix PFDRs leaks due to FQRNIs Hemant Agrawal
2024-09-30 12:15 ` [PATCH v4 02/18] net/dpaa: fix typecasting ch ID to u32 Hemant Agrawal
2024-09-30 12:15 ` [PATCH v4 03/18] bus/dpaa: fix VSP for 1G fm1-mac9 and 10 Hemant Agrawal
2024-09-30 12:15 ` [PATCH v4 04/18] bus/dpaa: fix the fman details status Hemant Agrawal
2024-09-30 12:15 ` [PATCH v4 18/18] net/dpaa: fix reallocate_mbuf handling Hemant Agrawal
[not found] ` <20241001110325.4173762-1-hemant.agrawal@nxp.com>
2024-10-01 11:03 ` Hemant Agrawal [this message]
2024-10-01 11:03 ` [PATCH v5 02/18] net/dpaa: fix typecasting ch ID to u32 Hemant Agrawal
2024-10-01 11:03 ` [PATCH v5 03/18] bus/dpaa: fix VSP for 1G fm1-mac9 and 10 Hemant Agrawal
2024-10-01 11:03 ` [PATCH v5 04/18] bus/dpaa: fix the fman details status Hemant Agrawal
2024-10-01 11:03 ` [PATCH v5 18/18] net/dpaa: fix reallocate_mbuf handling Hemant Agrawal
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=20241001110325.4173762-2-hemant.agrawal@nxp.com \
--to=hemant.agrawal@nxp.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@amd.com \
--cc=g.singh@nxp.com \
--cc=stable@dpdk.org \
/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).