Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

7ce4de1c · Linus Torvalds <[email protected]> · 2025-07-31 12:19:55 -07:00

Pull rdma updates from Jason Gunthorpe:

 - Various minor code cleanups and fixes for hns, iser, cxgb4, hfi1,
   rxe, erdma, mana_ib

 - Prefetch supprot for rxe ODP

 - Remove memory window support from hns as new device FW is no longer
   support it

 - Remove qib, it is very old and obsolete now, Cornelis wishes to
   restructure the hfi1/qib shared layer

 - Fix a race in destroying CQs where we can still end up with work
   running because the work is cancled before the driver stops
   triggering it

 - Improve interaction with namespaces:
     * Follow the devlink namespace for newly spawned RDMA devices
     * Create iopoib net devces in the parent IB device's namespace
     * Allow CAP_NET_RAW checks to pass in user namespaces

 - A new flow control scheme for IB MADs to try and avoid queue
   overflows in the network

 - Fix 2G message sizes in bnxt_re

 - Optimize mkey layout for mlx5 DMABUF

 - New "DMA Handle" concept to allow controlling PCI TPH and steering
   tags

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (71 commits)
  RDMA/siw: Change maintainer email address
  RDMA/mana_ib: add support of multiple ports
  RDMA/mlx5: Refactor optional counters steering code
  RDMA/mlx5: Add DMAH support for reg_user_mr/reg_user_dmabuf_mr
  IB: Extend UVERBS_METHOD_REG_MR to get DMAH
  RDMA/mlx5: Add DMAH object support
  RDMA/core: Introduce a DMAH object and its alloc/free APIs
  IB/core: Add UVERBS_METHOD_REG_MR on the MR object
  net/mlx5: Add support for device steering tag
  net/mlx5: Expose IFC bits for TPH
  PCI/TPH: Expose pcie_tph_get_st_table_size()
  RDMA/mlx5: Fix incorrect MKEY masking
  RDMA/mlx5: Fix returned type from _mlx5r_umr_zap_mkey()
  RDMA/mlx5: remove redundant check on err on return expression
  RDMA/mana_ib: add additional port counters
  RDMA/mana_ib: Fix DSCP value in modify QP
  RDMA/efa: Add CQ with external memory support
  RDMA/core: Add umem "is_contiguous" and "start_dma_addr" helpers
  RDMA/uverbs: Add a common way to create CQ with umem
  RDMA/mlx5: Optimize DMABUF mkey page size
  ...

Commit: 7ce4de1cdaf11c39b507008dfb5a4e59079d4e8a
Parents: 2c8c9aae · ee235923

Merge commit. Changes below are compared with the first parent: 2c8c9aae.

Changes

153 files changed · +2869 −49167

File	Status	Add	Del	Content
.mailmap	modified	+1	−0	View file
MAINTAINERS	modified	+1	−7	View file
drivers/infiniband/Kconfig	modified	+0	−1	View file
drivers/infiniband/core/Makefile	modified	+1	−0	View file
drivers/infiniband/core/cm.c	modified	+41	−6	View file
drivers/infiniband/core/counters.c	modified	+1	−1	View file
drivers/infiniband/core/cq.c	modified	+10	−2	View file
drivers/infiniband/core/device.c	modified	+45	−2	View file
drivers/infiniband/core/mad.c	modified	+362	−106	View file
drivers/infiniband/core/mad_priv.h	modified	+73	−3	View file
drivers/infiniband/core/mad_rmpp.c	modified	+24	−17	View file
drivers/infiniband/core/nldev.c	modified	+13	−11	View file
drivers/infiniband/core/rdma_core.c	modified	+29	−0	View file
drivers/infiniband/core/rdma_core.h	modified	+1	−0	View file
drivers/infiniband/core/restrack.c	modified	+2	−0	View file
drivers/infiniband/core/uverbs_cmd.c	modified	+7	−6	View file
drivers/infiniband/core/uverbs_std_types_cq.c	modified	+81	−6	View file
drivers/infiniband/core/uverbs_std_types_dmah.c	added	+145	−0	View file
drivers/infiniband/core/uverbs_std_types_mr.c	modified	+170	−2	View file
drivers/infiniband/core/uverbs_std_types_qp.c	modified	+1	−1	View file
drivers/infiniband/core/uverbs_uapi.c	modified	+1	−0	View file
drivers/infiniband/core/verbs.c	modified	+4	−1	View file
drivers/infiniband/hw/Makefile	modified	+0	−1	View file
drivers/infiniband/hw/bnxt_re/ib_verbs.c	modified	+9	−1	View file
drivers/infiniband/hw/bnxt_re/ib_verbs.h	modified	+2	−0	View file
drivers/infiniband/hw/bnxt_re/qplib_fp.c	modified	+14	−14	View file
drivers/infiniband/hw/bnxt_re/qplib_fp.h	modified	+3	−0	View file
drivers/infiniband/hw/bnxt_re/qplib_sp.c	modified	+1	−1	View file
drivers/infiniband/hw/bnxt_re/qplib_sp.h	modified	+1	−0	View file
drivers/infiniband/hw/cxgb4/device.c	modified	+1	−2	View file
drivers/infiniband/hw/cxgb4/iw_cxgb4.h	modified	+1	−0	View file
drivers/infiniband/hw/cxgb4/mem.c	modified	+5	−1	View file
drivers/infiniband/hw/efa/efa.h	modified	+5	−0	View file
drivers/infiniband/hw/efa/efa_admin_cmds_defs.h	modified	+16	−1	View file
drivers/infiniband/hw/efa/efa_com_cmd.c	modified	+35	−18	View file
drivers/infiniband/hw/efa/efa_com_cmd.h	modified	+10	−1	View file
drivers/infiniband/hw/efa/efa_main.c	modified	+1	−0	View file
drivers/infiniband/hw/efa/efa_verbs.c	modified	+77	−14	View file
drivers/infiniband/hw/erdma/erdma_verbs.c	modified	+7	−2	View file
drivers/infiniband/hw/erdma/erdma_verbs.h	modified	+2	−1	View file
drivers/infiniband/hw/hfi1/affinity.c	modified	+37	−59	View file
drivers/infiniband/hw/hns/hns_roce_device.h	modified	+2	−19	View file
drivers/infiniband/hw/hns/hns_roce_hem.c	modified	+5	−13	View file
drivers/infiniband/hw/hns/hns_roce_hw_v2.c	modified	+64	−70	View file
drivers/infiniband/hw/hns/hns_roce_hw_v2.h	modified	+7	−9	View file
drivers/infiniband/hw/hns/hns_roce_main.c	modified	+7	−25	View file
drivers/infiniband/hw/hns/hns_roce_mr.c	modified	+6	−114	View file
drivers/infiniband/hw/hns/hns_roce_qp.c	modified	+2	−2	View file
drivers/infiniband/hw/irdma/verbs.c	modified	+9	−0	View file
drivers/infiniband/hw/mana/counters.c	modified	+76	−2	View file
drivers/infiniband/hw/mana/counters.h	modified	+18	−0	View file
drivers/infiniband/hw/mana/device.c	modified	+66	−54	View file
drivers/infiniband/hw/mana/main.c	modified	+10	−3	View file
drivers/infiniband/hw/mana/mana_ib.h	modified	+30	−0	View file
drivers/infiniband/hw/mana/mr.c	modified	+8	−0	View file
drivers/infiniband/hw/mana/qp.c	modified	+1	−1	View file
drivers/infiniband/hw/mlx4/mlx4_ib.h	modified	+1	−0	View file
drivers/infiniband/hw/mlx4/mr.c	modified	+4	−0	View file
drivers/infiniband/hw/mlx5/Makefile	modified	+1	−0	View file
drivers/infiniband/hw/mlx5/counters.c	modified	+26	−4	View file
drivers/infiniband/hw/mlx5/counters.h	modified	+0	−13	View file
drivers/infiniband/hw/mlx5/cq.c	modified	+15	−4	View file
drivers/infiniband/hw/mlx5/devx.c	modified	+5	−1	View file
drivers/infiniband/hw/mlx5/dmah.c	added	+54	−0	View file
drivers/infiniband/hw/mlx5/dmah.h	added	+23	−0	View file
drivers/infiniband/hw/mlx5/fs.c	modified	+63	−58	View file
drivers/infiniband/hw/mlx5/fs.h	modified	+6	−2	View file
drivers/infiniband/hw/mlx5/ib_rep.c	modified	+2	−1	View file
drivers/infiniband/hw/mlx5/main.c	modified	+11	−2	View file
drivers/infiniband/hw/mlx5/mlx5_ib.h	modified	+75	−24	View file
drivers/infiniband/hw/mlx5/mr.c	modified	+92	−24	View file
drivers/infiniband/hw/mlx5/odp.c	modified	+25	−7	View file
drivers/infiniband/hw/mlx5/umr.c	modified	+279	−22	View file
drivers/infiniband/hw/mlx5/umr.h	modified	+12	−1	View file
drivers/infiniband/hw/mthca/mthca_provider.c	modified	+5	−1	View file
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c	modified	+5	−1	View file
drivers/infiniband/hw/ocrdma/ocrdma_verbs.h	modified	+2	−1	View file
drivers/infiniband/hw/qedr/verbs.c	modified	+5	−1	View file
drivers/infiniband/hw/qedr/verbs.h	modified	+2	−1	View file
drivers/infiniband/hw/qib/Kconfig	deleted	+0	−17	View before deletion
drivers/infiniband/hw/qib/Makefile	deleted	+0	−17	View before deletion
drivers/infiniband/hw/qib/qib.h	deleted	+0	−1492	View before deletion
drivers/infiniband/hw/qib/qib_6120_regs.h	deleted	+0	−977	View before deletion
drivers/infiniband/hw/qib/qib_7220.h	deleted	+0	−149	View before deletion
drivers/infiniband/hw/qib/qib_7220_regs.h	deleted	+0	−1496	View before deletion
drivers/infiniband/hw/qib/qib_7322_regs.h	deleted	+0	−3163	View before deletion
drivers/infiniband/hw/qib/qib_common.h	deleted	+0	−798	View before deletion
drivers/infiniband/hw/qib/qib_debugfs.c	deleted	+0	−274	View before deletion
drivers/infiniband/hw/qib/qib_debugfs.h	deleted	+0	−45	View before deletion
drivers/infiniband/hw/qib/qib_diag.c	deleted	+0	−906	View before deletion
drivers/infiniband/hw/qib/qib_driver.c	deleted	+0	−798	View before deletion
drivers/infiniband/hw/qib/qib_eeprom.c	deleted	+0	−271	View before deletion
drivers/infiniband/hw/qib/qib_file_ops.c	deleted	+0	−2401	View before deletion
drivers/infiniband/hw/qib/qib_fs.c	deleted	+0	−549	View before deletion
drivers/infiniband/hw/qib/qib_iba6120.c	deleted	+0	−3533	View before deletion
drivers/infiniband/hw/qib/qib_iba7220.c	deleted	+0	−4596	View before deletion
drivers/infiniband/hw/qib/qib_iba7322.c	deleted	+0	−8475	View before deletion
drivers/infiniband/hw/qib/qib_init.c	deleted	+0	−1782	View before deletion
drivers/infiniband/hw/qib/qib_intr.c	deleted	+0	−241	View before deletion
drivers/infiniband/hw/qib/qib_mad.c	deleted	+0	−2450	View before deletion
drivers/infiniband/hw/qib/qib_mad.h	deleted	+0	−300	View before deletion
drivers/infiniband/hw/qib/qib_pcie.c	deleted	+0	−598	View before deletion
drivers/infiniband/hw/qib/qib_pio_copy.c	deleted	+0	−64	View before deletion
drivers/infiniband/hw/qib/qib_qp.c	deleted	+0	−454	View before deletion
drivers/infiniband/hw/qib/qib_qsfp.c	deleted	+0	−549	View before deletion
drivers/infiniband/hw/qib/qib_qsfp.h	deleted	+0	−188	View before deletion
drivers/infiniband/hw/qib/qib_rc.c	deleted	+0	−2131	View before deletion
drivers/infiniband/hw/qib/qib_ruc.c	deleted	+0	−314	View before deletion
drivers/infiniband/hw/qib/qib_sd7220.c	deleted	+0	−1445	View before deletion
drivers/infiniband/hw/qib/qib_sdma.c	deleted	+0	−999	View before deletion
drivers/infiniband/hw/qib/qib_sysfs.c	deleted	+0	−731	View before deletion
drivers/infiniband/hw/qib/qib_twsi.c	deleted	+0	−502	View before deletion
drivers/infiniband/hw/qib/qib_tx.c	deleted	+0	−566	View before deletion
drivers/infiniband/hw/qib/qib_uc.c	deleted	+0	−521	View before deletion
drivers/infiniband/hw/qib/qib_ud.c	deleted	+0	−583	View before deletion
drivers/infiniband/hw/qib/qib_user_pages.c	deleted	+0	−137	View before deletion
drivers/infiniband/hw/qib/qib_user_sdma.c	deleted	+0	−1470	View before deletion
drivers/infiniband/hw/qib/qib_user_sdma.h	deleted	+0	−52	View before deletion
drivers/infiniband/hw/qib/qib_verbs.c	deleted	+0	−1705	View before deletion
drivers/infiniband/hw/qib/qib_verbs.h	deleted	+0	−398	View before deletion
drivers/infiniband/hw/qib/qib_wc_ppc64.c	deleted	+0	−62	View before deletion
drivers/infiniband/hw/qib/qib_wc_x86_64.c	deleted	+0	−150	View before deletion
drivers/infiniband/hw/usnic/usnic_ib_verbs.c	modified	+4	−0	View file
drivers/infiniband/hw/usnic/usnic_ib_verbs.h	modified	+1	−0	View file
drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c	modified	+5	−0	View file
drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h	modified	+1	−0	View file
drivers/infiniband/sw/rdmavt/mr.c	modified	+5	−0	View file
drivers/infiniband/sw/rdmavt/mr.h	modified	+1	−0	View file
drivers/infiniband/sw/rdmavt/vt.c	modified	+1	−1	View file
drivers/infiniband/sw/rxe/rxe.c	modified	+7	−0	View file
drivers/infiniband/sw/rxe/rxe_loc.h	modified	+12	−0	View file
drivers/infiniband/sw/rxe/rxe_odp.c	modified	+175	−17	View file
drivers/infiniband/sw/rxe/rxe_verbs.c	modified	+4	−0	View file
drivers/infiniband/sw/siw/siw_qp_tx.c	modified	+16	−6	View file
drivers/infiniband/sw/siw/siw_verbs.c	modified	+6	−1	View file
drivers/infiniband/sw/siw/siw_verbs.h	modified	+2	−1	View file
drivers/infiniband/ulp/ipoib/ipoib_main.c	modified	+2	−0	View file
drivers/infiniband/ulp/iser/iscsi_iser.c	modified	+1	−5	View file
drivers/net/ethernet/mellanox/mlx5/core/Makefile	modified	+5	−0	View file
drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h	modified	+0	−5	View file
drivers/net/ethernet/mellanox/mlx5/core/lib/st.c	added	+164	−0	View file
drivers/net/ethernet/mellanox/mlx5/core/main.c	modified	+2	−0	View file
drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h	modified	+9	−0	View file
drivers/pci/tph.c	modified	+6	−5	View file
include/linux/cpumask.h	modified	+12	−0	View file
include/linux/mlx5/driver.h	modified	+25	−0	View file
include/linux/mlx5/mlx5_ifc.h	modified	+12	−2	View file
include/linux/pci-tph.h	modified	+1	−0	View file
include/rdma/ib_umem.h	modified	+21	−4	View file
include/rdma/ib_verbs.h	modified	+63	−2	View file
include/rdma/restrack.h	modified	+4	−0	View file
include/uapi/rdma/efa-abi.h	modified	+2	−1	View file
include/uapi/rdma/ib_user_ioctl_cmds.h	modified	+36	−0	View file

Only the first 600 diff lines are shown. Download the complete patch.

.mailmap

View file

diff --git a/.mailmap b/.mailmap
index 4bb3a7f..b1f0edf 100644
--- a/.mailmap
+++ b/.mailmap
@@ -138,6 +138,7 @@ Benjamin Poirier <[email protected]> <[email protected]>
 Benjamin Tissoires <[email protected]> <[email protected]>
 Benjamin Tissoires <[email protected]> <[email protected]>
 Benno Lossin <[email protected]> <[email protected]>
+Bernard Metzler <[email protected]> <[email protected]>
 Bingwu Zhang <[email protected]> <[email protected]>
 Bingwu Zhang <[email protected]> <[email protected]>
 Bjorn Andersson <[email protected]> <[email protected]>

MAINTAINERS

View file

diff --git a/MAINTAINERS b/MAINTAINERS
index 1e52309..59af2f0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20370,12 +20370,6 @@ S:	Maintained
 F:	drivers/firmware/qemu_fw_cfg.c
 F:	include/uapi/linux/qemu_fw_cfg.h
 
-QIB DRIVER
-M:	Dennis Dalessandro <[email protected]>
-L:	[email protected]
-S:	Supported
-F:	drivers/infiniband/hw/qib/
-
 QLOGIC QL41xxx FCOE DRIVER
 M:	Saurav Kashyap <[email protected]>
 M:	Javed Hasan <[email protected]>
@@ -23222,7 +23216,7 @@ S:	Maintained
 F:	drivers/leds/leds-net48xx.c
 
 SOFT-IWARP DRIVER (siw)
-M:	Bernard Metzler <[email protected]>
+M:	Bernard Metzler <[email protected]>
 L:	[email protected]
 S:	Supported
 F:	drivers/infiniband/sw/siw/

drivers/infiniband/Kconfig

View file

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index a5827d1..3a394cd 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -92,7 +92,6 @@ source "drivers/infiniband/hw/mlx5/Kconfig"
 source "drivers/infiniband/hw/mthca/Kconfig"
 source "drivers/infiniband/hw/ocrdma/Kconfig"
 source "drivers/infiniband/hw/qedr/Kconfig"
-source "drivers/infiniband/hw/qib/Kconfig"
 source "drivers/infiniband/hw/usnic/Kconfig"
 source "drivers/infiniband/hw/vmw_pvrdma/Kconfig"
 source "drivers/infiniband/sw/rdmavt/Kconfig"

drivers/infiniband/core/Makefile

View file

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index d49ded7..f483e0c 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -33,6 +33,7 @@ ib_umad-y :=			user_mad.o
 ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
 				rdma_core.o uverbs_std_types.o uverbs_ioctl.o \
 				uverbs_std_types_cq.o \
+				uverbs_std_types_dmah.o \
 				uverbs_std_types_flow_action.o uverbs_std_types_dm.o \
 				uverbs_std_types_mr.o uverbs_std_types_counters.o \
 				uverbs_uapi.o uverbs_std_types_device.o \

drivers/infiniband/core/cm.c

View file

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 8670e58..92678e4 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -161,6 +161,7 @@ struct cm_counter_attribute {
 struct cm_port {
 	struct cm_device *cm_dev;
 	struct ib_mad_agent *mad_agent;
+	struct ib_mad_agent *rep_agent;
 	u32 port_num;
 	atomic_long_t counters[CM_COUNTER_GROUPS][CM_ATTR_COUNT];
 };
@@ -274,7 +275,8 @@ static inline void cm_deref_id(struct cm_id_private *cm_id_priv)
 		complete(&cm_id_priv->comp);
 }
 
-static struct ib_mad_send_buf *cm_alloc_msg(struct cm_id_private *cm_id_priv)
+static struct ib_mad_send_buf *
+cm_alloc_msg_agent(struct cm_id_private *cm_id_priv, bool rep_agent)
 {
 	struct ib_mad_agent *mad_agent;
 	struct ib_mad_send_buf *m;
@@ -286,7 +288,8 @@ static struct ib_mad_send_buf *cm_alloc_msg(struct cm_id_private *cm_id_priv)
 		return ERR_PTR(-EINVAL);
 
 	read_lock(&cm_id_priv->av.port->cm_dev->mad_agent_lock);
-	mad_agent = cm_id_priv->av.port->mad_agent;
+	mad_agent = rep_agent ? cm_id_priv->av.port->rep_agent :
+				cm_id_priv->av.port->mad_agent;
 	if (!mad_agent) {
 		m = ERR_PTR(-EINVAL);
 		goto out;
@@ -315,6 +318,11 @@ out:
 	return m;
 }
 
+static struct ib_mad_send_buf *cm_alloc_msg(struct cm_id_private *cm_id_priv)
+{
+	return cm_alloc_msg_agent(cm_id_priv, false);
+}
+
 static void cm_free_msg(struct ib_mad_send_buf *msg)
 {
 	if (msg->ah)
@@ -323,13 +331,14 @@ static void cm_free_msg(struct ib_mad_send_buf *msg)
 }
 
 static struct ib_mad_send_buf *
-cm_alloc_priv_msg(struct cm_id_private *cm_id_priv, enum ib_cm_state state)
+cm_alloc_priv_msg_rep(struct cm_id_private *cm_id_priv, enum ib_cm_state state,
+		      bool rep_agent)
 {
 	struct ib_mad_send_buf *msg;
 
 	lockdep_assert_held(&cm_id_priv->lock);
 
-	msg = cm_alloc_msg(cm_id_priv);
+	msg = cm_alloc_msg_agent(cm_id_priv, rep_agent);
 	if (IS_ERR(msg))
 		return msg;
 
@@ -344,6 +353,12 @@ cm_alloc_priv_msg(struct cm_id_private *cm_id_priv, enum ib_cm_state state)
 	return msg;
 }
 
+static struct ib_mad_send_buf *
+cm_alloc_priv_msg(struct cm_id_private *cm_id_priv, enum ib_cm_state state)
+{
+	return cm_alloc_priv_msg_rep(cm_id_priv, state, false);
+}
+
 static void cm_free_priv_msg(struct ib_mad_send_buf *msg)
 {
 	struct cm_id_private *cm_id_priv = msg->context[0];
@@ -2295,7 +2310,7 @@ int ib_send_cm_rep(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	msg = cm_alloc_priv_msg(cm_id_priv, IB_CM_REP_SENT);
+	msg = cm_alloc_priv_msg_rep(cm_id_priv, IB_CM_REP_SENT, true);
 	if (IS_ERR(msg)) {
 		ret = PTR_ERR(msg);
 		goto out;
@@ -4380,9 +4395,22 @@ static int cm_add_one(struct ib_device *ib_device)
 			goto error2;
 		}
 
+		port->rep_agent = ib_register_mad_agent(ib_device, i,
+							IB_QPT_GSI,
+							NULL,
+							0,
+							cm_send_handler,
+							NULL,
+							port,
+							0);
+		if (IS_ERR(port->rep_agent)) {
+			ret = PTR_ERR(port->rep_agent);
+			goto error3;
+		}
+
 		ret = ib_modify_port(ib_device, i, 0, &port_modify);
 		if (ret)
-			goto error3;
+			goto error4;
 
 		count++;
 	}
@@ -4397,6 +4425,8 @@ static int cm_add_one(struct ib_device *ib_device)
 	write_unlock_irqrestore(&cm.device_lock, flags);
 	return 0;
 
+error4:
+	ib_unregister_mad_agent(port->rep_agent);
 error3:
 	ib_unregister_mad_agent(port->mad_agent);
 error2:
@@ -4410,6 +4440,7 @@ error1:
 
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
+		ib_unregister_mad_agent(port->rep_agent);
 		ib_unregister_mad_agent(port->mad_agent);
 		ib_port_unregister_client_groups(ib_device, i,
 						 cm_counter_groups);
@@ -4439,12 +4470,14 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 
 	rdma_for_each_port (ib_device, i) {
 		struct ib_mad_agent *mad_agent;
+		struct ib_mad_agent *rep_agent;
 
 		if (!rdma_cap_ib_cm(ib_device, i))
 			continue;
 
 		port = cm_dev->port[i-1];
 		mad_agent = port->mad_agent;
+		rep_agent = port->rep_agent;
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
 		/*
 		 * We flush the queue here after the going_down set, this
@@ -4458,8 +4491,10 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 		 */
 		write_lock(&cm_dev->mad_agent_lock);
 		port->mad_agent = NULL;
+		port->rep_agent = NULL;
 		write_unlock(&cm_dev->mad_agent_lock);
 		ib_unregister_mad_agent(mad_agent);
+		ib_unregister_mad_agent(rep_agent);
 		ib_port_unregister_client_groups(ib_device, i,
 						 cm_counter_groups);
 	}

drivers/infiniband/core/counters.c

View file

diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index e6ec7b7..c3aa6d7 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -461,7 +461,7 @@ static struct ib_qp *rdma_counter_get_qp(struct ib_device *dev, u32 qp_num)
 		return NULL;
 
 	qp = container_of(res, struct ib_qp, res);
-	if (qp->qp_type == IB_QPT_RAW_PACKET && !capable(CAP_NET_RAW))
+	if (qp->qp_type == IB_QPT_RAW_PACKET && !rdma_dev_has_raw_cap(dev))
 		goto err;
 
 	return qp;

drivers/infiniband/core/cq.c

View file

diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index a70876a..584537c 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -317,13 +317,18 @@ EXPORT_SYMBOL(__ib_alloc_cq_any);
  */
 void ib_free_cq(struct ib_cq *cq)
 {
-	int ret;
+	int ret = 0;
 
 	if (WARN_ON_ONCE(atomic_read(&cq->usecnt)))
 		return;
 	if (WARN_ON_ONCE(cq->cqe_used))
 		return;
 
+	if (cq->device->ops.pre_destroy_cq) {
+		ret = cq->device->ops.pre_destroy_cq(cq);
+		WARN_ONCE(ret, "Disable of kernel CQ shouldn't fail");
+	}
+
 	switch (cq->poll_ctx) {
 	case IB_POLL_DIRECT:
 		break;
@@ -340,7 +345,10 @@ void ib_free_cq(struct ib_cq *cq)
 
 	rdma_dim_destroy(cq);
 	trace_cq_free(cq);
-	ret = cq->device->ops.destroy_cq(cq, NULL);
+	if (cq->device->ops.post_destroy_cq)
+		cq->device->ops.post_destroy_cq(cq);
+	else
+		ret = cq->device->ops.destroy_cq(cq, NULL);
 	WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
 	rdma_restrack_del(&cq->res);
 	kfree(cq->wc);

drivers/infiniband/core/device.c

View file

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index d426338..3145cb3 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -145,6 +145,33 @@ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net)
 }
 EXPORT_SYMBOL(rdma_dev_access_netns);
 
+/**
+ * rdma_dev_has_raw_cap() - Returns whether a specified rdma device has
+ *			    CAP_NET_RAW capability or not.
+ *
+ * @dev:	Pointer to rdma device whose capability to be checked
+ *
+ * Returns true if a rdma device's owning user namespace has CAP_NET_RAW
+ * capability, otherwise false. When rdma subsystem is in legacy shared network,
+ * namespace mode, the default net namespace is considered.
+ */
+bool rdma_dev_has_raw_cap(const struct ib_device *dev)
+{
+	const struct net *net;
+
+	/* Network namespace is the resource whose user namespace
+	 * to be considered. When in shared mode, there is no reliable
+	 * network namespace resource, so consider the default net namespace.
+	 */
+	if (ib_devices_shared_netns)
+		net = &init_net;
+	else
+		net = read_pnet(&dev->coredev.rdma_net);
+
+	return ns_capable(net->user_ns, CAP_NET_RAW);
+}
+EXPORT_SYMBOL(rdma_dev_has_raw_cap);
+
 /*
  * xarray has this behavior where it won't iterate over NULL values stored in
  * allocated arrays.  So we need our own iterator to see all values stored in
@@ -557,6 +584,8 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
 /**
  * _ib_alloc_device - allocate an IB device struct
  * @size:size of structure to allocate
+ * @net: network namespace device should be located in, namespace
+ *       must stay valid until ib_register_device() is completed.
  *
  * Low-level drivers should use ib_alloc_device() to allocate &struct
  * ib_device.  @size is the size of the structure to be allocated,
@@ -564,7 +593,7 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
  * ib_dealloc_device() must be used to free structures allocated with
  * ib_alloc_device().
  */
-struct ib_device *_ib_alloc_device(size_t size)
+struct ib_device *_ib_alloc_device(size_t size, struct net *net)
 {
 	struct ib_device *device;
 	unsigned int i;
@@ -581,7 +610,15 @@ struct ib_device *_ib_alloc_device(size_t size)
 		return NULL;
 	}
 
-	rdma_init_coredev(&device->coredev, device, &init_net);
+	/* ib_devices_shared_netns can't change while we have active namespaces
+	 * in the system which means either init_net is passed or the user has
+	 * no idea what they are doing.
+	 *
+	 * To avoid breaking backward compatibility, when in shared mode,
+	 * force to init the device in the init_net.
+	 */
+	net = ib_devices_shared_netns ? &init_net : net;
+	rdma_init_coredev(&device->coredev, device, net);
 
 	INIT_LIST_HEAD(&device->event_handler_list);
 	spin_lock_init(&device->qp_open_list_lock);
@@ -2671,6 +2708,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, add_sub_dev);
 	SET_DEVICE_OP(dev_ops, advise_mr);
 	SET_DEVICE_OP(dev_ops, alloc_dm);
+	SET_DEVICE_OP(dev_ops, alloc_dmah);
 	SET_DEVICE_OP(dev_ops, alloc_hw_device_stats);
 	SET_DEVICE_OP(dev_ops, alloc_hw_port_stats);
 	SET_DEVICE_OP(dev_ops, alloc_mr);
@@ -2691,6 +2729,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, create_ah);
 	SET_DEVICE_OP(dev_ops, create_counters);
 	SET_DEVICE_OP(dev_ops, create_cq);
+	SET_DEVICE_OP(dev_ops, create_cq_umem);
 	SET_DEVICE_OP(dev_ops, create_flow);
 	SET_DEVICE_OP(dev_ops, create_qp);
 	SET_DEVICE_OP(dev_ops, create_rwq_ind_table);
@@ -2698,6 +2737,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, create_user_ah);
 	SET_DEVICE_OP(dev_ops, create_wq);
 	SET_DEVICE_OP(dev_ops, dealloc_dm);
+	SET_DEVICE_OP(dev_ops, dealloc_dmah);
 	SET_DEVICE_OP(dev_ops, dealloc_driver);
 	SET_DEVICE_OP(dev_ops, dealloc_mw);
 	SET_DEVICE_OP(dev_ops, dealloc_pd);
@@ -2763,8 +2803,10 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, modify_srq);
 	SET_DEVICE_OP(dev_ops, modify_wq);
 	SET_DEVICE_OP(dev_ops, peek_cq);
+	SET_DEVICE_OP(dev_ops, pre_destroy_cq);
 	SET_DEVICE_OP(dev_ops, poll_cq);
 	SET_DEVICE_OP(dev_ops, port_groups);
+	SET_DEVICE_OP(dev_ops, post_destroy_cq);
 	SET_DEVICE_OP(dev_ops, post_recv);
 	SET_DEVICE_OP(dev_ops, post_send);
 	SET_DEVICE_OP(dev_ops, post_srq_recv);
@@ -2793,6 +2835,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_ah);
 	SET_OBJ_SIZE(dev_ops, ib_counters);
 	SET_OBJ_SIZE(dev_ops, ib_cq);
+	SET_OBJ_SIZE(dev_ops, ib_dmah);
 	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
 	SET_OBJ_SIZE(dev_ops, ib_qp);

drivers/infiniband/core/mad.c

View file

diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 73f3a0b..8f26bfb 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -210,6 +210,29 @@ int ib_response_mad(const struct ib_mad_hdr *hdr)
 }
 EXPORT_SYMBOL(ib_response_mad);
 
+#define SOL_FC_MAX_DEFAULT_FRAC 4
+#define SOL_FC_MAX_SA_FRAC 32
+
+static int get_sol_fc_max_outstanding(struct ib_mad_reg_req *mad_reg_req)
+{
+	if (!mad_reg_req)
+		/* Send only agent */
+		return mad_recvq_size / SOL_FC_MAX_DEFAULT_FRAC;
+
+	switch (mad_reg_req->mgmt_class) {
+	case IB_MGMT_CLASS_CM:
+		return mad_recvq_size / SOL_FC_MAX_DEFAULT_FRAC;
+	case IB_MGMT_CLASS_SUBN_ADM:
+		return mad_recvq_size / SOL_FC_MAX_SA_FRAC;
+	case IB_MGMT_CLASS_SUBN_LID_ROUTED:
+	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
+		return min(mad_recvq_size, IB_MAD_QP_RECV_SIZE) /
+		       SOL_FC_MAX_DEFAULT_FRAC;
+	default:
+		return 0;
+	}
+}
+
 /*
  * ib_register_mad_agent - Register to send/receive MADs
  *
@@ -391,13 +414,17 @@ struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
 	spin_lock_init(&mad_agent_priv->lock);
 	INIT_LIST_HEAD(&mad_agent_priv->send_list);
 	INIT_LIST_HEAD(&mad_agent_priv->wait_list);
-	INIT_LIST_HEAD(&mad_agent_priv->done_list);
 	INIT_LIST_HEAD(&mad_agent_priv->rmpp_list);
+	INIT_LIST_HEAD(&mad_agent_priv->backlog_list);
 	INIT_DELAYED_WORK(&mad_agent_priv->timed_work, timeout_sends);
 	INIT_LIST_HEAD(&mad_agent_priv->local_list);
 	INIT_WORK(&mad_agent_priv->local_work, local_completions);
 	refcount_set(&mad_agent_priv->refcount, 1);
 	init_completion(&mad_agent_priv->comp);
+	mad_agent_priv->sol_fc_send_count = 0;
+	mad_agent_priv->sol_fc_wait_count = 0;
+	mad_agent_priv->sol_fc_max =
+		recv_handler ? get_sol_fc_max_outstanding(mad_reg_req) : 0;
 
 	ret2 = ib_mad_agent_security_setup(&mad_agent_priv->agent, qp_type);
 	if (ret2) {
@@ -1055,6 +1082,180 @@ int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr)
 	return ret;
 }
 
+static void handle_queued_state(struct ib_mad_send_wr_private *mad_send_wr,
+		       struct ib_mad_agent_private *mad_agent_priv)
+{
+	if (mad_send_wr->state == IB_MAD_STATE_WAIT_RESP) {
+		mad_agent_priv->sol_fc_wait_count--;
+		list_move_tail(&mad_send_wr->agent_list,
+			       &mad_agent_priv->backlog_list);
+	} else {
+		expect_mad_state(mad_send_wr, IB_MAD_STATE_INIT);
+		list_add_tail(&mad_send_wr->agent_list,
+			      &mad_agent_priv->backlog_list);
+	}
+}
+
+static void handle_send_state(struct ib_mad_send_wr_private *mad_send_wr,
+		       struct ib_mad_agent_private *mad_agent_priv)
+{
+	if (mad_send_wr->state == IB_MAD_STATE_INIT) {
+		list_add_tail(&mad_send_wr->agent_list,
+			      &mad_agent_priv->send_list);
+	} else {
+		expect_mad_state2(mad_send_wr, IB_MAD_STATE_WAIT_RESP,
+				  IB_MAD_STATE_QUEUED);
+		list_move_tail(&mad_send_wr->agent_list,
+			       &mad_agent_priv->send_list);
+	}
+
+	if (mad_send_wr->is_solicited_fc) {
+		if (mad_send_wr->state == IB_MAD_STATE_WAIT_RESP)
+			mad_agent_priv->sol_fc_wait_count--;
+		mad_agent_priv->sol_fc_send_count++;
+	}
+}
+
+static void handle_wait_state(struct ib_mad_send_wr_private *mad_send_wr,
+		       struct ib_mad_agent_private *mad_agent_priv)
+{
+	struct ib_mad_send_wr_private *temp_mad_send_wr;
+	struct list_head *list_item;
+	unsigned long delay;
+
+	expect_mad_state3(mad_send_wr, IB_MAD_STATE_SEND_START,
+			  IB_MAD_STATE_WAIT_RESP, IB_MAD_STATE_CANCELED);
+	if (mad_send_wr->state == IB_MAD_STATE_SEND_START &&
+	    mad_send_wr->is_solicited_fc) {
+		mad_agent_priv->sol_fc_send_count--;
+		mad_agent_priv->sol_fc_wait_count++;
+	}
+
+	list_del_init(&mad_send_wr->agent_list);
+	delay = mad_send_wr->timeout;
+	mad_send_wr->timeout += jiffies;
+
+	if (delay) {
+		list_for_each_prev(list_item,
+				   &mad_agent_priv->wait_list) {
+			temp_mad_send_wr = list_entry(
+				list_item,
+				struct ib_mad_send_wr_private,
+				agent_list);
+			if (time_after(mad_send_wr->timeout,
+				       temp_mad_send_wr->timeout))
+				break;
+		}
+	} else {
+		list_item = &mad_agent_priv->wait_list;
+	}
+
+	list_add(&mad_send_wr->agent_list, list_item);
+}
+
+static void handle_early_resp_state(struct ib_mad_send_wr_private *mad_send_wr,
+			    struct ib_mad_agent_private *mad_agent_priv)
+{
+	expect_mad_state(mad_send_wr, IB_MAD_STATE_SEND_START);
+	mad_agent_priv->sol_fc_send_count -= mad_send_wr->is_solicited_fc;
+}
+
+static void handle_canceled_state(struct ib_mad_send_wr_private *mad_send_wr,
+			 struct ib_mad_agent_private *mad_agent_priv)
+{
+	not_expect_mad_state(mad_send_wr, IB_MAD_STATE_DONE);
+	if (mad_send_wr->is_solicited_fc) {
+		if (mad_send_wr->state == IB_MAD_STATE_SEND_START)
+			mad_agent_priv->sol_fc_send_count--;
+		else if (mad_send_wr->state == IB_MAD_STATE_WAIT_RESP)
+			mad_agent_priv->sol_fc_wait_count--;
+	}
+}
+
+static void handle_done_state(struct ib_mad_send_wr_private *mad_send_wr,
+		       struct ib_mad_agent_private *mad_agent_priv)
+{
+	if (mad_send_wr->is_solicited_fc) {
+		if (mad_send_wr->state == IB_MAD_STATE_SEND_START)
+			mad_agent_priv->sol_fc_send_count--;
+		else if (mad_send_wr->state == IB_MAD_STATE_WAIT_RESP)
+			mad_agent_priv->sol_fc_wait_count--;
+	}
+
+	list_del_init(&mad_send_wr->agent_list);
+}
+
+void change_mad_state(struct ib_mad_send_wr_private *mad_send_wr,
+			     enum ib_mad_state new_state)
+{
+	struct ib_mad_agent_private *mad_agent_priv =
+		mad_send_wr->mad_agent_priv;
+
+	switch (new_state) {
+	case IB_MAD_STATE_INIT:
+		break;
+	case IB_MAD_STATE_QUEUED:
+		handle_queued_state(mad_send_wr, mad_agent_priv);
+		break;
+	case IB_MAD_STATE_SEND_START:
+		handle_send_state(mad_send_wr, mad_agent_priv);
+		break;
+	case IB_MAD_STATE_WAIT_RESP:
+		handle_wait_state(mad_send_wr, mad_agent_priv);
+		if (mad_send_wr->state == IB_MAD_STATE_CANCELED)
+			return;
+		break;
+	case IB_MAD_STATE_EARLY_RESP:
+		handle_early_resp_state(mad_send_wr, mad_agent_priv);
+		break;
+	case IB_MAD_STATE_CANCELED:
+		handle_canceled_state(mad_send_wr, mad_agent_priv);
+		break;
+	case IB_MAD_STATE_DONE:
+		handle_done_state(mad_send_wr, mad_agent_priv);
+		break;
+	}
+
+	mad_send_wr->state = new_state;
+}
+
+static bool is_solicited_fc_mad(struct ib_mad_send_wr_private *mad_send_wr)
+{
+	struct ib_rmpp_mad *rmpp_mad;
+	u8 mgmt_class;
+
+	if (!mad_send_wr->timeout)
+		return 0;
+
+	rmpp_mad = mad_send_wr->send_buf.mad;
+	if (mad_send_wr->mad_agent_priv->agent.rmpp_version &&
+	    (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE))
+		return 0;
+
+	mgmt_class =
+		((struct ib_mad_hdr *)mad_send_wr->send_buf.mad)->mgmt_class;
+	return mgmt_class == IB_MGMT_CLASS_CM ||
+	       mgmt_class == IB_MGMT_CLASS_SUBN_ADM ||
+	       mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
+	       mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE;
+}
+
+static bool mad_is_for_backlog(struct ib_mad_send_wr_private *mad_send_wr)
+{
+	struct ib_mad_agent_private *mad_agent_priv =
+		mad_send_wr->mad_agent_priv;
+
+	if (!mad_send_wr->is_solicited_fc || !mad_agent_priv->sol_fc_max)
+		return false;
+