DPDK patches and discussions
 help / color / mirror / Atom feed
From: David Marchand <david.marchand@redhat.com>
To: dev@dpdk.org
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Subject: [PATCH 1/2] eal/linux: fix VFIO hotplug with multiprocess
Date: Mon, 16 Sep 2024 14:30:42 +0200	[thread overview]
Message-ID: <20240916123044.2692301-1-david.marchand@redhat.com> (raw)

At the moment, if VFIO is not available at DPDK init, it won't be
available unless a subsequent rte_vfio_enable() is done.

Yet, even if rte_vfio_enable() is called again in primary and secondary
processes, a secondary process will never get to know that VFIO has been
enabled in the primary process as the MP requests handler is only
registered in EAL init.

On the other hand, moving the MP requests handler registration earlier
in EAL init is ok, as secondary process are supposed to be waiting on
eal_mcfg_wait_complete() until the primary process calls
eal_mcfg_complete().

Move vfio_mp_sync_setup() in rte_vfio_enable().

Besides, rte_eal_vfio_setup() is useless and its name with a rte_ prefix
is ambiguous as it gives the impression it is an exported/public symbol.
Remove it and directly call rte_vfio_enable() where needed.

Signed-off-by: David Marchand <david.marchand@redhat.com>
---
 lib/eal/linux/eal.c      | 18 +-----------------
 lib/eal/linux/eal_vfio.c |  9 ++++++---
 2 files changed, 7 insertions(+), 20 deletions(-)

diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index d742cc98e2..54577b7718 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -867,16 +867,6 @@ rte_eal_iopl_init(void)
 	return 0;
 }
 
-#ifdef VFIO_PRESENT
-static int rte_eal_vfio_setup(void)
-{
-	if (rte_vfio_enable("vfio"))
-		return -1;
-
-	return 0;
-}
-#endif
-
 static void rte_eal_init_alert(const char *msg)
 {
 	fprintf(stderr, "EAL: FATAL: %s\n", msg);
@@ -1162,7 +1152,7 @@ rte_eal_init(int argc, char **argv)
 	}
 
 #ifdef VFIO_PRESENT
-	if (rte_eal_vfio_setup() < 0) {
+	if (rte_vfio_enable("vfio")) {
 		rte_eal_init_alert("Cannot init VFIO");
 		rte_errno = EAGAIN;
 		rte_atomic_store_explicit(&run_once, 0, rte_memory_order_relaxed);
@@ -1291,12 +1281,6 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
-#ifdef VFIO_PRESENT
-	/* Register mp action after probe() so that we got enough info */
-	if (rte_vfio_is_enabled("vfio") && vfio_mp_sync_setup() < 0)
-		return -1;
-#endif
-
 	/* initialize default service/lcore mappings and start running. Ignore
 	 * -ENOTSUP, as it indicates no service coremask passed to EAL.
 	 */
diff --git a/lib/eal/linux/eal_vfio.c b/lib/eal/linux/eal_vfio.c
index 4e69e72e3b..7132e24cba 100644
--- a/lib/eal/linux/eal_vfio.c
+++ b/lib/eal/linux/eal_vfio.c
@@ -1120,9 +1120,12 @@ rte_vfio_enable(const char *modname)
 	}
 
 	if (internal_conf->process_type == RTE_PROC_PRIMARY) {
-		/* open a new container */
-		default_vfio_cfg->vfio_container_fd =
-				rte_vfio_get_container_fd();
+		if (vfio_mp_sync_setup() == -1) {
+			default_vfio_cfg->vfio_container_fd = -1;
+		} else {
+			/* open a new container */
+			default_vfio_cfg->vfio_container_fd = rte_vfio_get_container_fd();
+		}
 	} else {
 		/* get the default container from the primary process */
 		default_vfio_cfg->vfio_container_fd =
-- 
2.46.0


             reply	other threads:[~2024-09-16 12:30 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-16 12:30 David Marchand [this message]
2024-09-16 12:30 ` [PATCH 2/2] bus/pci: enhance hotplug for VFIO bound devices David Marchand
2024-09-17  8:57   ` Maxime Coquelin
2024-09-17  8:20 ` [PATCH 1/2] eal/linux: fix VFIO hotplug with multiprocess Maxime Coquelin
2024-10-02 18:31   ` David Marchand
2024-10-03  8:25     ` Kevin Traynor
2024-10-14 18:58   ` David Marchand
2024-10-04 14:34 ` David Marchand

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=20240916123044.2692301-1-david.marchand@redhat.com \
    --to=david.marchand@redhat.com \
    --cc=anatoly.burakov@intel.com \
    --cc=dev@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).