public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: "Håkon Bugge" <haakon.bugge@oracle.com>
To: linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
	netdev@vger.kernel.org, rds-devel@oss.oracle.com
Cc: "Jason Gunthorpe" <jgg@ziepe.ca>,
	"Leon Romanovsky" <leon@kernel.org>,
	"Saeed Mahameed" <saeedm@nvidia.com>,
	"Tariq Toukan" <tariqt@nvidia.com>,
	"David S . Miller" <davem@davemloft.net>,
	"Eric Dumazet" <edumazet@google.com>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"Paolo Abeni" <pabeni@redhat.com>, "Tejun Heo" <tj@kernel.org>,
	"Lai Jiangshan" <jiangshanlai@gmail.com>,
	"Allison Henderson" <allison.henderson@oracle.com>,
	"Manjunath Patil" <manjunath.b.patil@oracle.com>,
	"Mark Zhang" <markzhang@nvidia.com>,
	"Håkon Bugge" <haakon.bugge@oracle.com>,
	"Chuck Lever" <chuck.lever@oracle.com>,
	"Shiraz Saleem" <shiraz.saleem@intel.com>,
	"Yang Li" <yang.lee@linux.alibaba.com>
Subject: [PATCH v3 6/6] net/mlx5: Brute force GFP_NOIO
Date: Wed, 22 May 2024 15:54:43 +0200	[thread overview]
Message-ID: <20240522135444.1685642-12-haakon.bugge@oracle.com> (raw)
In-Reply-To: <20240522135444.1685642-1-haakon.bugge@oracle.com>

In mlx5_core_init(), we call memalloc_noio_{save,restore} in a parenthetic
fashion when enabled by the module parameter force_noio.

This in order to conditionally enable mlx5_core to work aligned with
I/O devices. Any work queued later on work-queues created during
module initialization will inherit the PF_MEMALLOC_{NOIO,NOFS}
flag(s), due to commit ("workqueue: Inherit NOIO and NOFS alloc
flags").

We do this in order to enable ULPs using the RDMA stack and the
mlx5_core driver to be used as a network block I/O device. This to
support a filesystem on top of a raw block device which uses said
ULP(s) and the RDMA stack as the network transport layer.

Under intense memory pressure, we get memory reclaims. Assume the
filesystem reclaims memory, goes to the raw block device, which calls
into the ULP in question, which calls the RDMA stack. Now, if regular
GFP_KERNEL allocations in ULP or the RDMA stack require reclaims to be
fulfilled, we end up in a circular dependency.

We break this circular dependency by:

1. Force all allocations in the ULP and the relevant RDMA stack to use
   GFP_NOIO, by means of a parenthetic use of
   memalloc_noio_{save,restore} on all relevant entry points.

2. Make sure work-queues inherits current->flags
   wrt. PF_MEMALLOC_{NOIO,NOFS}, such that work executed on the
   work-queue inherits the same flag(s).

Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6574c145dc1e2..66cef64a82c61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -48,6 +48,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/version.h>
 #include <net/devlink.h>
+#include <linux/sched/mm.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "fs_core.h"
@@ -87,6 +88,10 @@ static unsigned int prof_sel = MLX5_DEFAULT_PROF;
 module_param_named(prof_sel, prof_sel, uint, 0444);
 MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2");
 
+static bool mlx5_core_force_noio;
+module_param_named(force_noio, mlx5_core_force_noio, bool, 0444);
+MODULE_PARM_DESC(force_noio, "Force the use of GFP_NOIO (Y/N)");
+
 static u32 sw_owner_id[4];
 #define MAX_SW_VHCA_ID (BIT(__mlx5_bit_sz(cmd_hca_cap_2, sw_vhca_id)) - 1)
 static DEFINE_IDA(sw_vhca_ida);
@@ -2308,8 +2313,12 @@ static void mlx5_core_verify_params(void)
 
 static int __init mlx5_init(void)
 {
+	unsigned int noio_flags;
 	int err;
 
+	if (mlx5_core_force_noio)
+		noio_flags = memalloc_noio_save();
+
 	WARN_ONCE(strcmp(MLX5_ADEV_NAME, KBUILD_MODNAME),
 		  "mlx5_core name not in sync with kernel module name");
 
@@ -2330,7 +2339,7 @@ static int __init mlx5_init(void)
 	if (err)
 		goto err_pci;
 
-	return 0;
+	goto out;
 
 err_pci:
 	mlx5_sf_driver_unregister();
@@ -2338,6 +2347,9 @@ static int __init mlx5_init(void)
 	mlx5e_cleanup();
 err_debug:
 	mlx5_unregister_debugfs();
+out:
+	if (mlx5_core_force_noio)
+		memalloc_noio_restore(noio_flags);
 	return err;
 }
 
-- 
2.31.1


  parent reply	other threads:[~2024-05-22 13:55 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-22 13:54 [PATCH v3 0/6] rds: rdma: Add ability to force GFP_NOIO Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 1/6] Orabug_list: Drop 36459425 Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 1/6] workqueue: Inherit per-process allocation flags Håkon Bugge
2024-05-22 16:37   ` Tejun Heo
2024-05-22 13:54 ` [PATCH v3 2/6] ml: renaming metadata directory Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 2/6] rds: Brute force GFP_NOIO Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 3/6] ml: adjusting build metadata to reflect mainline Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 3/6] RDMA/cma: Brute force GFP_NOIO Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 4/6] ml: Remove revocation list Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 4/6] RDMA/cm: Brute force GFP_NOIO Håkon Bugge
2024-05-23  6:45   ` Naveen Mamindlapalli
2024-05-22 13:54 ` [PATCH v3 5/6] ml: Add ol_signing_keys.pem in certs dir Håkon Bugge
2024-05-22 13:54 ` [PATCH v3 5/6] RDMA/mlx5: Brute force GFP_NOIO Håkon Bugge
2024-05-22 13:54 ` Håkon Bugge [this message]
2024-05-22 13:54 ` [PATCH v3 6/6] workqueue: Inherit per-process allocation flags Håkon Bugge
2024-05-23  8:18 ` [PATCH v3 0/6] rds: rdma: Add ability to force GFP_NOIO Christoph Hellwig
2024-05-23 10:34   ` Haakon Bugge

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=20240522135444.1685642-12-haakon.bugge@oracle.com \
    --to=haakon.bugge@oracle.com \
    --cc=allison.henderson@oracle.com \
    --cc=chuck.lever@oracle.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=jgg@ziepe.ca \
    --cc=jiangshanlai@gmail.com \
    --cc=kuba@kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=manjunath.b.patil@oracle.com \
    --cc=markzhang@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=rds-devel@oss.oracle.com \
    --cc=saeedm@nvidia.com \
    --cc=shiraz.saleem@intel.com \
    --cc=tariqt@nvidia.com \
    --cc=tj@kernel.org \
    --cc=yang.lee@linux.alibaba.com \
    /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