@@ -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);
@@ -2312,8 +2317,12 @@ 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");
@@ -2334,7 +2343,7 @@ static int __init mlx5_init(void)
if (err)
goto err_pci;
- return 0;
+ goto out;
err_pci:
mlx5_sf_driver_unregister();
@@ -2342,6 +2351,9 @@ 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;
}
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(-)