+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Thomas Lamprecht <t.lamprecht@proxmox.com>
-Date: Sat, 7 Jan 2023 13:48:41 +0100
-Subject: [PATCH] Revert "RDMA/irdma: Report the correct link speed"
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-seem to cause a regression with some NICs:
-https://lore.kernel.org/netdev/CAK8fFZ6A_Gphw_3-QMGKEFQk=sfCw1Qmq0TVZK3rtAi7vb621A@mail.gmail.com/
-
-This reverts commit e8553504e366c8a47d1f6156c30d6eb9778cda13.
-
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
----
- drivers/infiniband/hw/irdma/verbs.c | 35 ++++++++++++++++++++++++++---
- 1 file changed, 32 insertions(+), 3 deletions(-)
-
-diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
-index f6973ea55eda..132fe91bb799 100644
---- a/drivers/infiniband/hw/irdma/verbs.c
-+++ b/drivers/infiniband/hw/irdma/verbs.c
-@@ -63,6 +63,36 @@ static int irdma_query_device(struct ib_device *ibdev,
- return 0;
- }
-
-+/**
-+ * irdma_get_eth_speed_and_width - Get IB port speed and width from netdev speed
-+ * @link_speed: netdev phy link speed
-+ * @active_speed: IB port speed
-+ * @active_width: IB port width
-+ */
-+static void irdma_get_eth_speed_and_width(u32 link_speed, u16 *active_speed,
-+ u8 *active_width)
-+{
-+ if (link_speed <= SPEED_1000) {
-+ *active_width = IB_WIDTH_1X;
-+ *active_speed = IB_SPEED_SDR;
-+ } else if (link_speed <= SPEED_10000) {
-+ *active_width = IB_WIDTH_1X;
-+ *active_speed = IB_SPEED_FDR10;
-+ } else if (link_speed <= SPEED_20000) {
-+ *active_width = IB_WIDTH_4X;
-+ *active_speed = IB_SPEED_DDR;
-+ } else if (link_speed <= SPEED_25000) {
-+ *active_width = IB_WIDTH_1X;
-+ *active_speed = IB_SPEED_EDR;
-+ } else if (link_speed <= SPEED_40000) {
-+ *active_width = IB_WIDTH_4X;
-+ *active_speed = IB_SPEED_FDR10;
-+ } else {
-+ *active_width = IB_WIDTH_4X;
-+ *active_speed = IB_SPEED_EDR;
-+ }
-+}
-+
- /**
- * irdma_query_port - get port attributes
- * @ibdev: device pointer from stack
-@@ -90,9 +120,8 @@ static int irdma_query_port(struct ib_device *ibdev, u32 port,
- props->state = IB_PORT_DOWN;
- props->phys_state = IB_PORT_PHYS_STATE_DISABLED;
- }
--
-- ib_get_eth_speed(ibdev, port, &props->active_speed,
-- &props->active_width);
-+ irdma_get_eth_speed_and_width(SPEED_100000, &props->active_speed,
-+ &props->active_width);
-
- if (rdma_protocol_roce(ibdev, 1)) {
- props->gid_tbl_len = 32;
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Dave Ertman <david.m.ertman@intel.com>
+Date: Fri, 10 Mar 2023 11:48:33 -0800
+Subject: [PATCH] ice: avoid bonding causing auxiliary plug/unplug under RTNL
+ lock
+
+RDMA is not supported in ice on a PF that has been added to a bonded
+interface. To enforce this, when an interface enters a bond, we unplug
+the auxiliary device that supports RDMA functionality. This unplug
+currently happens in the context of handling the netdev bonding event.
+This event is sent to the ice driver under RTNL context. This is causing
+a deadlock where the RDMA driver is waiting for the RTNL lock to complete
+the removal.
+
+Defer the unplugging/re-plugging of the auxiliary device to the service
+task so that it is not performed under the RTNL lock context.
+
+Cc: stable@vger.kernel.org # 6.1.x
+Reported-by: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
+Link: https://lore.kernel.org/netdev/CAK8fFZ6A_Gphw_3-QMGKEFQk=sfCw1Qmq0TVZK3rtAi7vb621A@mail.gmail.com/
+Fixes: 5cb1ebdbc434 ("ice: Fix race condition during interface enslave")
+Fixes: 4eace75e0853 ("RDMA/irdma: Report the correct link speed")
+Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
+Tested-by: Arpana Arland <arpanax.arland@intel.com> (A Contingent worker at Intel)
+Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
+Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
+Link: https://lore.kernel.org/r/20230310194833.3074601-1-anthony.l.nguyen@intel.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ drivers/net/ethernet/intel/ice/ice.h | 14 +++++---------
+ drivers/net/ethernet/intel/ice/ice_main.c | 19 ++++++++-----------
+ 2 files changed, 13 insertions(+), 20 deletions(-)
+
+diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
+index 713069f809ec..3cad5e6b2ad1 100644
+--- a/drivers/net/ethernet/intel/ice/ice.h
++++ b/drivers/net/ethernet/intel/ice/ice.h
+@@ -506,6 +506,7 @@ enum ice_pf_flags {
+ ICE_FLAG_VF_VLAN_PRUNING,
+ ICE_FLAG_LINK_LENIENT_MODE_ENA,
+ ICE_FLAG_PLUG_AUX_DEV,
++ ICE_FLAG_UNPLUG_AUX_DEV,
+ ICE_FLAG_MTU_CHANGED,
+ ICE_FLAG_GNSS, /* GNSS successfully initialized */
+ ICE_PF_FLAGS_NBITS /* must be last */
+@@ -950,16 +951,11 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf)
+ */
+ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
+ {
+- /* We can directly unplug aux device here only if the flag bit
+- * ICE_FLAG_PLUG_AUX_DEV is not set because ice_unplug_aux_dev()
+- * could race with ice_plug_aux_dev() called from
+- * ice_service_task(). In this case we only clear that bit now and
+- * aux device will be unplugged later once ice_plug_aux_device()
+- * called from ice_service_task() finishes (see ice_service_task()).
++ /* defer unplug to service task to avoid RTNL lock and
++ * clear PLUG bit so that pending plugs don't interfere
+ */
+- if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags))
+- ice_unplug_aux_dev(pf);
+-
++ clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags);
++ set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags);
+ clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+ }
+ #endif /* _ICE_H_ */
+diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
+index 381146282439..56155a04cc0c 100644
+--- a/drivers/net/ethernet/intel/ice/ice_main.c
++++ b/drivers/net/ethernet/intel/ice/ice_main.c
+@@ -2316,18 +2316,15 @@ static void ice_service_task(struct work_struct *work)
+ }
+ }
+
+- if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) {
+- /* Plug aux device per request */
+- ice_plug_aux_dev(pf);
++ /* unplug aux dev per request, if an unplug request came in
++ * while processing a plug request, this will handle it
++ */
++ if (test_and_clear_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags))
++ ice_unplug_aux_dev(pf);
+
+- /* Mark plugging as done but check whether unplug was
+- * requested during ice_plug_aux_dev() call
+- * (e.g. from ice_clear_rdma_cap()) and if so then
+- * plug aux device.
+- */
+- if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags))
+- ice_unplug_aux_dev(pf);
+- }
++ /* Plug aux device per request */
++ if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags))
++ ice_plug_aux_dev(pf);
+
+ if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) {
+ struct iidc_event *event;
projects / pve-kernel.git / commitdiff