[PATCH] net: mana: add msix index sharing between EQs

2023-12-08 Thread Konstantin Taranov 
From: Konstantin Taranov 

This patch allows to assign and poll more than 1 EQ on the same msix index.
It is achieved by introducing a list of attached EQs in each IRQ context.
This patch export symbols for creating EQs from other MANA kernel modules.

Signed-off-by: Konstantin Taranov 
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 55 ++-
 .../net/ethernet/microsoft/mana/hw_channel.c  |  1 +
 drivers/net/ethernet/microsoft/mana/mana_en.c |  1 +
 include/net/mana/gdma.h   |  4 +-
 4 files changed, 45 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c 
b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6367de0..82a4534 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -401,6 +401,9 @@ static void mana_gd_process_eq_events(void *arg)
u32 head, num_eqe;
int i;
 
+   if (eq->id == INVALID_QUEUE_ID)
+   return;
+
gc = eq->gdma_dev->gdma_context;
 
num_eqe = eq->queue_size / GDMA_EQE_SIZE;
@@ -414,8 +417,12 @@ static void mana_gd_process_eq_events(void *arg)
 
old_bits = (eq->head / num_eqe - 1) & GDMA_EQE_OWNER_MASK;
/* No more entries */
-   if (owner_bits == old_bits)
+   if (owner_bits == old_bits) {
+   /* return here without ringing the doorbell */
+   if (i == 0)
+   return;
break;
+   }
 
new_bits = (eq->head / num_eqe) & GDMA_EQE_OWNER_MASK;
if (owner_bits != new_bits) {
@@ -457,12 +464,16 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
 
spin_lock_irqsave(&r->lock, flags);
 
-   msi_index = find_first_zero_bit(r->map, r->size);
+   if (queue->eq.msix_index == INVALID_PCI_MSIX_INDEX)
+   queue->eq.msix_index = find_first_zero_bit(r->map, r->size);
+
+   msi_index = queue->eq.msix_index;
+
if (msi_index >= r->size || msi_index >= gc->num_msix_usable) {
err = -ENOSPC;
+   queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
} else {
bitmap_set(r->map, msi_index, 1);
-   queue->eq.msix_index = msi_index;
}
 
spin_unlock_irqrestore(&r->lock, flags);
@@ -476,9 +487,7 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
 
gic = &gc->irq_contexts[msi_index];
 
-   WARN_ON(gic->handler || gic->arg);
-
-   gic->arg = queue;
+   list_add_rcu(&queue->entry, &gic->eq_list);
 
gic->handler = mana_gd_process_eq_events;
 
@@ -493,6 +502,7 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
struct gdma_resource *r;
unsigned int msix_index;
unsigned long flags;
+   struct gdma_queue *eq;
 
gc = gd->gdma_context;
r = &gc->msix_resource;
@@ -502,12 +512,19 @@ static void mana_gd_deregiser_irq(struct gdma_queue 
*queue)
if (WARN_ON(msix_index >= gc->num_msix_usable))
return;
 
-   gic = &gc->irq_contexts[msix_index];
-   gic->handler = NULL;
-   gic->arg = NULL;
-
spin_lock_irqsave(&r->lock, flags);
-   bitmap_clear(r->map, msix_index, 1);
+   gic = &gc->irq_contexts[msix_index];
+   list_for_each_entry_rcu(eq, &gic->eq_list, entry) {
+   if (queue == eq) {
+   list_del_rcu(&eq->entry);
+   synchronize_rcu();
+   break;
+   }
+   }
+   if (list_empty(&gic->eq_list)) {
+   gic->handler = NULL;
+   bitmap_clear(r->map, msix_index, 1);
+   }
spin_unlock_irqrestore(&r->lock, flags);
 
queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
@@ -587,7 +604,8 @@ static int mana_gd_create_eq(struct gdma_dev *gd,
u32 log2_num_entries;
int err;
 
-   queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+   queue->eq.msix_index = spec->eq.msix_index;
+   queue->id = INVALID_QUEUE_ID;
 
log2_num_entries = ilog2(queue->queue_size / GDMA_EQE_SIZE);
 
@@ -819,6 +837,7 @@ free_q:
kfree(queue);
return err;
 }
+EXPORT_SYMBOL_NS(mana_gd_create_mana_eq, NET_MANA);
 
 int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
  const struct gdma_queue_spec *spec,
@@ -895,6 +914,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct 
gdma_queue *queue)
mana_gd_free_memory(gmi);
kfree(queue);
 }
+EXPORT_SYMBOL_NS(mana_gd_destroy_queue, NET_MANA);
 
 int mana_gd_verify_vf_version(struct pci_dev *pdev)
 {
@@ -1217,9 +1237,14 @@ int mana_gd_poll_cq(struct gdma_q

[PATCH for-next v2] net: mana: add msix index sharing between EQs

2023-12-13 Thread Konstantin Taranov 
From: Konstantin Taranov 

This patch allows to assign and poll more than one EQ on the same
msix index.
It is achieved by introducing a list of attached EQs in each IRQ context.
It also removes the existing msix_index map that tried to ensure that there
is only one EQ at each msix_index.
This patch exports symbols for creating EQs from other MANA kernel modules.

Signed-off-by: Konstantin Taranov 
---
V1 -> V2: removed msix_index map and improved thread-safety of rcu lists
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 76 +--
 .../net/ethernet/microsoft/mana/hw_channel.c  |  1 +
 drivers/net/ethernet/microsoft/mana/mana_en.c |  1 +
 include/net/mana/gdma.h   |  7 +-
 4 files changed, 43 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c 
b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6367de0..a686301 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -414,8 +414,12 @@ static void mana_gd_process_eq_events(void *arg)
 
old_bits = (eq->head / num_eqe - 1) & GDMA_EQE_OWNER_MASK;
/* No more entries */
-   if (owner_bits == old_bits)
+   if (owner_bits == old_bits) {
+   /* return here without ringing the doorbell */
+   if (i == 0)
+   return;
break;
+   }
 
new_bits = (eq->head / num_eqe) & GDMA_EQE_OWNER_MASK;
if (owner_bits != new_bits) {
@@ -445,42 +449,29 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
struct gdma_dev *gd = queue->gdma_dev;
struct gdma_irq_context *gic;
struct gdma_context *gc;
-   struct gdma_resource *r;
unsigned int msi_index;
unsigned long flags;
struct device *dev;
int err = 0;
 
gc = gd->gdma_context;
-   r = &gc->msix_resource;
dev = gc->dev;
+   msi_index = spec->eq.msix_index;
 
-   spin_lock_irqsave(&r->lock, flags);
-
-   msi_index = find_first_zero_bit(r->map, r->size);
-   if (msi_index >= r->size || msi_index >= gc->num_msix_usable) {
+   if (msi_index >= gc->num_msix_usable) {
err = -ENOSPC;
-   } else {
-   bitmap_set(r->map, msi_index, 1);
-   queue->eq.msix_index = msi_index;
-   }
-
-   spin_unlock_irqrestore(&r->lock, flags);
-
-   if (err) {
-   dev_err(dev, "Register IRQ err:%d, msi:%u rsize:%u, nMSI:%u",
-   err, msi_index, r->size, gc->num_msix_usable);
+   dev_err(dev, "Register IRQ err:%d, msi:%u nMSI:%u",
+   err, msi_index, gc->num_msix_usable);
 
return err;
}
 
+   queue->eq.msix_index = msi_index;
gic = &gc->irq_contexts[msi_index];
 
-   WARN_ON(gic->handler || gic->arg);
-
-   gic->arg = queue;
-
-   gic->handler = mana_gd_process_eq_events;
+   spin_lock_irqsave(&gic->lock, flags);
+   list_add_rcu(&queue->entry, &gic->eq_list);
+   spin_unlock_irqrestore(&gic->lock, flags);
 
return 0;
 }
@@ -490,12 +481,11 @@ static void mana_gd_deregiser_irq(struct gdma_queue 
*queue)
struct gdma_dev *gd = queue->gdma_dev;
struct gdma_irq_context *gic;
struct gdma_context *gc;
-   struct gdma_resource *r;
unsigned int msix_index;
unsigned long flags;
+   struct gdma_queue *eq;
 
gc = gd->gdma_context;
-   r = &gc->msix_resource;
 
/* At most num_online_cpus() + 1 interrupts are used. */
msix_index = queue->eq.msix_index;
@@ -503,14 +493,17 @@ static void mana_gd_deregiser_irq(struct gdma_queue 
*queue)
return;
 
gic = &gc->irq_contexts[msix_index];
-   gic->handler = NULL;
-   gic->arg = NULL;
-
-   spin_lock_irqsave(&r->lock, flags);
-   bitmap_clear(r->map, msix_index, 1);
-   spin_unlock_irqrestore(&r->lock, flags);
+   spin_lock_irqsave(&gic->lock, flags);
+   list_for_each_entry_rcu(eq, &gic->eq_list, entry) {
+   if (queue == eq) {
+   list_del_rcu(&eq->entry);
+   break;
+   }
+   }
+   spin_unlock_irqrestore(&gic->lock, flags);
 
queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+   synchronize_rcu();
 }
 
 int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
@@ -588,6 +581,7 @@ static int mana_gd_create_eq(struct gdma_dev *gd,
int err;
 
queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+   queue->id = INVALID_QUEUE_ID;

RE: [PATCH] net: mana: Fix possible double free in error handling path

2024-06-24 Thread Konstantin Taranov 
> > - kfree(madev);
> I think you can just avoid using add_fail and keep/retain rest of init_fail, 
> idx_fail
> conditions in old way right?

I do agree with Sai. I think the patch can be just:
@@ -2797,7 +2797,8 @@ static int add_adev(struct gdma_dev *gd)
ret = auxiliary_device_init(adev);
if (ret)
goto init_fail;
-
+   /* madev is owned by the auxiliary device */
+   madev = NULL;
ret = auxiliary_device_add(adev);
if (ret)
goto add_fail;


- Konstantin

RE: [PATCH v2] net: mana: Fix possible double free in error handling path

2024-06-25 Thread Konstantin Taranov 
> When auxiliary_device_add() returns error and then calls
> auxiliary_device_uninit(), callback function adev_release calls kfree(madev).
> We shouldn't call kfree(madev) again in the error handling path. Set 'madev'
> to NULL.
> 
> Signed-off-by: Ma Ke 
> ---
> Changes in v2:
> - streamlined the patch according suggestions;
> - revised the description.
> ---
>  drivers/net/ethernet/microsoft/mana/mana_en.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c
> b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index d087cf954f75..608ad31a9702 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -2798,6 +2798,8 @@ static int add_adev(struct gdma_dev *gd)
> if (ret)
> goto init_fail;
> 
> +   /* madev is owned by the auxiliary device */
> +   madev = NULL;
> ret = auxiliary_device_add(adev);
> if (ret)
> goto add_fail;
> --
> 2.25.1

Reviewed-by: Konstantin Taranov

RE: [PATCH v2] net: mana: Fix possible double free in error handling path

2024-06-25 Thread Konstantin Taranov 

> When auxiliary_device_add() returns error and then calls
> auxiliary_device_uninit(), callback function adev_release calls kfree(madev).
> We shouldn't call kfree(madev) again in the error handling path. Set 'madev'
> to NULL.
> 
> Signed-off-by: Ma Ke 
> ---
> Changes in v2:
> - streamlined the patch according suggestions;
> - revised the description.

The change is ok, but the commit message is missing a "Fixes" tag/line.
- Konstantin

[PATCH rdma-next 02/13] RDMA/mana_ib: implement get_dma_mr

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Implement allocation of DMA-mapped memory regions.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/device.c |  1 +
 drivers/infiniband/hw/mana/mr.c | 36 +
 include/net/mana/gdma.h |  5 
 3 files changed, 42 insertions(+)

diff --git a/drivers/infiniband/hw/mana/device.c 
b/drivers/infiniband/hw/mana/device.c
index 7ac0191..215dbce 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -32,6 +32,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
.destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table,
.destroy_wq = mana_ib_destroy_wq,
.disassociate_ucontext = mana_ib_disassociate_ucontext,
+   .get_dma_mr = mana_ib_get_dma_mr,
.get_link_layer = mana_ib_get_link_layer,
.get_port_immutable = mana_ib_get_port_immutable,
.mmap = mana_ib_mmap,
diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c
index 887b09d..3a047f8 100644
--- a/drivers/infiniband/hw/mana/mr.c
+++ b/drivers/infiniband/hw/mana/mr.c
@@ -8,6 +8,8 @@
 #define VALID_MR_FLAGS 
\
(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ)
 
+#define VALID_DMA_MR_FLAGS (IB_ACCESS_LOCAL_WRITE)
+
 static enum gdma_mr_access_flags
 mana_ib_verbs_to_gdma_access_flags(int access_flags)
 {
@@ -39,6 +41,8 @@ static int mana_ib_gd_create_mr(struct mana_ib_dev *dev, 
struct mana_ib_mr *mr,
req.mr_type = mr_params->mr_type;
 
switch (mr_params->mr_type) {
+   case GDMA_MR_TYPE_GPA:
+   break;
case GDMA_MR_TYPE_GVA:
req.gva.dma_region_handle = mr_params->gva.dma_region_handle;
req.gva.virtual_address = mr_params->gva.virtual_address;
@@ -169,6 +173,38 @@ err_free:
return ERR_PTR(err);
 }
 
+struct ib_mr *mana_ib_get_dma_mr(struct ib_pd *ibpd, int access_flags)
+{
+   struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+   struct gdma_create_mr_params mr_params = {};
+   struct ib_device *ibdev = ibpd->device;
+   struct mana_ib_dev *dev;
+   struct mana_ib_mr *mr;
+   int err;
+
+   dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+   if (access_flags & ~VALID_DMA_MR_FLAGS)
+   return ERR_PTR(-EINVAL);
+
+   mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+   if (!mr)
+   return ERR_PTR(-ENOMEM);
+
+   mr_params.pd_handle = pd->pd_handle;
+   mr_params.mr_type = GDMA_MR_TYPE_GPA;
+
+   err = mana_ib_gd_create_mr(dev, mr, &mr_params);
+   if (err)
+   goto err_free;
+
+   return &mr->ibmr;
+
+err_free:
+   kfree(mr);
+   return ERR_PTR(err);
+}
+
 int mana_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 {
struct mana_ib_mr *mr = container_of(ibmr, struct mana_ib_mr, ibmr);
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 03e1b25..a94b04e 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -801,6 +801,11 @@ struct gdma_destory_pd_resp {
 };/* HW DATA */
 
 enum gdma_mr_type {
+   /*
+* Guest Physical Address - MRs of this type allow access
+* to any DMA-mapped memory using bus-logical address
+*/
+   GDMA_MR_TYPE_GPA = 1,
/* Guest Virtual Address - MRs of this type allow access
 * to memory mapped by PTEs associated with this MR using a virtual
 * address that is set up in the MST
-- 
2.43.0

[PATCH rdma-next 00/13] RDMA/mana_ib: Enable CM for mana_ib

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

This patch series enables GSI QPs and CM on mana_ib. 

Konstantin Taranov (13):
  RDMA/mana_ib: Allow registration of DMA-mapped memory in PDs
  RDMA/mana_ib: implement get_dma_mr
  RDMA/mana_ib: helpers to allocate kernel queues
  RDMA/mana_ib: create kernel-level CQs
  RDMA/mana_ib: Create and destroy UD/GSI QP
  RDMA/mana_ib: UD/GSI QP creation for kernel
  RDMA/mana_ib: create/destroy AH
  net/mana: fix warning in the writer of client oob
  RDMA/mana_ib: UD/GSI work requests
  RDMA/mana_ib: implement req_notify_cq
  RDMA/mana_ib: extend mana QP table
  RDMA/mana_ib: polling of CQs for GSI/UD
  RDMA/mana_ib: indicate CM support

 drivers/infiniband/hw/mana/Makefile   |   2 +-
 drivers/infiniband/hw/mana/ah.c   |  58 +
 drivers/infiniband/hw/mana/cq.c   | 227 ++--
 drivers/infiniband/hw/mana/device.c   |  18 +-
 drivers/infiniband/hw/mana/main.c |  95 ++-
 drivers/infiniband/hw/mana/mana_ib.h  | 157 ++-
 drivers/infiniband/hw/mana/mr.c   |  36 +++
 drivers/infiniband/hw/mana/qp.c   | 245 +-
 drivers/infiniband/hw/mana/shadow_queue.h | 115 
 drivers/infiniband/hw/mana/wr.c   | 168 
 .../net/ethernet/microsoft/mana/gdma_main.c   |   7 +-
 include/net/mana/gdma.h   |   6 +
 12 files changed, 1096 insertions(+), 38 deletions(-)
 create mode 100644 drivers/infiniband/hw/mana/ah.c
 create mode 100644 drivers/infiniband/hw/mana/shadow_queue.h
 create mode 100644 drivers/infiniband/hw/mana/wr.c

-- 
2.43.0

[PATCH rdma-next 07/13] RDMA/mana_ib: create/destroy AH

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Implement create and destroy AH for kernel.

In mana_ib, AV is passed as an sge in WQE.
Allocate DMA memory and write an AV there.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/Makefile  |  2 +-
 drivers/infiniband/hw/mana/ah.c  | 58 
 drivers/infiniband/hw/mana/device.c  | 13 ++-
 drivers/infiniband/hw/mana/mana_ib.h | 30 ++
 4 files changed, 101 insertions(+), 2 deletions(-)
 create mode 100644 drivers/infiniband/hw/mana/ah.c

diff --git a/drivers/infiniband/hw/mana/Makefile 
b/drivers/infiniband/hw/mana/Makefile
index 88655fe..6e56f77 100644
--- a/drivers/infiniband/hw/mana/Makefile
+++ b/drivers/infiniband/hw/mana/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o
 
-mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o
+mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o ah.o
diff --git a/drivers/infiniband/hw/mana/ah.c b/drivers/infiniband/hw/mana/ah.c
new file mode 100644
index 000..f56952e
--- /dev/null
+++ b/drivers/infiniband/hw/mana/ah.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+int mana_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *attr,
+ struct ib_udata *udata)
+{
+   struct mana_ib_dev *mdev = container_of(ibah->device, struct 
mana_ib_dev, ib_dev);
+   struct mana_ib_ah *ah = container_of(ibah, struct mana_ib_ah, ibah);
+   struct rdma_ah_attr *ah_attr = attr->ah_attr;
+   const struct ib_global_route *grh;
+   enum rdma_network_type ntype;
+
+   if (ah_attr->type != RDMA_AH_ATTR_TYPE_ROCE ||
+   !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH))
+   return -EINVAL;
+
+   if (udata)
+   return -EINVAL;
+
+   ah->av = dma_pool_zalloc(mdev->av_pool, GFP_ATOMIC, &ah->dma_handle);
+   if (!ah->av)
+   return -ENOMEM;
+
+   grh = rdma_ah_read_grh(ah_attr);
+   ntype = rdma_gid_attr_network_type(grh->sgid_attr);
+
+   copy_in_reverse(ah->av->dest_mac, ah_attr->roce.dmac, ETH_ALEN);
+   ah->av->udp_src_port = rdma_flow_label_to_udp_sport(grh->flow_label);
+   ah->av->hop_limit = grh->hop_limit;
+   ah->av->dscp = (grh->traffic_class >> 2) & 0x3f;
+   ah->av->is_ipv6 = (ntype == RDMA_NETWORK_IPV6);
+
+   if (ah->av->is_ipv6) {
+   copy_in_reverse(ah->av->dest_ip, grh->dgid.raw, 16);
+   copy_in_reverse(ah->av->src_ip, grh->sgid_attr->gid.raw, 16);
+   } else {
+   ah->av->dest_ip[10] = 0xFF;
+   ah->av->dest_ip[11] = 0xFF;
+   copy_in_reverse(&ah->av->dest_ip[12], &grh->dgid.raw[12], 4);
+   copy_in_reverse(&ah->av->src_ip[12], 
&grh->sgid_attr->gid.raw[12], 4);
+   }
+
+   return 0;
+}
+
+int mana_ib_destroy_ah(struct ib_ah *ibah, u32 flags)
+{
+   struct mana_ib_dev *mdev = container_of(ibah->device, struct 
mana_ib_dev, ib_dev);
+   struct mana_ib_ah *ah = container_of(ibah, struct mana_ib_ah, ibah);
+
+   dma_pool_free(mdev->av_pool, ah->av, ah->dma_handle);
+
+   return 0;
+}
diff --git a/drivers/infiniband/hw/mana/device.c 
b/drivers/infiniband/hw/mana/device.c
index 215dbce..d534ef1 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -19,6 +19,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
.add_gid = mana_ib_gd_add_gid,
.alloc_pd = mana_ib_alloc_pd,
.alloc_ucontext = mana_ib_alloc_ucontext,
+   .create_ah = mana_ib_create_ah,
.create_cq = mana_ib_create_cq,
.create_qp = mana_ib_create_qp,
.create_rwq_ind_table = mana_ib_create_rwq_ind_table,
@@ -27,6 +28,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
.dealloc_ucontext = mana_ib_dealloc_ucontext,
.del_gid = mana_ib_gd_del_gid,
.dereg_mr = mana_ib_dereg_mr,
+   .destroy_ah = mana_ib_destroy_ah,
.destroy_cq = mana_ib_destroy_cq,
.destroy_qp = mana_ib_destroy_qp,
.destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table,
@@ -44,6 +46,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
.query_port = mana_ib_query_port,
.reg_user_mr = mana_ib_reg_user_mr,
 
+   INIT_RDMA_OBJ_SIZE(ib_ah, mana_ib_ah, ibah),
INIT_RDMA_OBJ_SIZE(ib_cq, mana_ib_cq, ibcq),
INIT_RDMA_OBJ_SIZE(ib_pd, mana_ib_pd, ibpd),
INIT_RDMA_OBJ_SIZE(ib_qp, mana_ib_qp, ibqp),
@@ -135,15 +138,22 @@ static int mana_ib_probe(struct auxiliary_device *adev,
goto destroy_rnic;
}
 
+   dev->av_pool = dma_pool_create("mana_ib_a

[PATCH rdma-next 03/13] RDMA/mana_ib: helpers to allocate kernel queues

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Introduce helpers to allocate queues for kernel-level use.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/main.c | 23 +++
 drivers/infiniband/hw/mana/mana_ib.h  |  3 +++
 .../net/ethernet/microsoft/mana/gdma_main.c   |  1 +
 3 files changed, 27 insertions(+)

diff --git a/drivers/infiniband/hw/mana/main.c 
b/drivers/infiniband/hw/mana/main.c
index 45b251b..f2f6bb3 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -240,6 +240,27 @@ void mana_ib_dealloc_ucontext(struct ib_ucontext 
*ibcontext)
ibdev_dbg(ibdev, "Failed to destroy doorbell page %d\n", ret);
 }
 
+int mana_ib_create_kernel_queue(struct mana_ib_dev *mdev, u32 size, enum 
gdma_queue_type type,
+   struct mana_ib_queue *queue)
+{
+   struct gdma_context *gc = mdev_to_gc(mdev);
+   struct gdma_queue_spec spec = {};
+   int err;
+
+   queue->id = INVALID_QUEUE_ID;
+   queue->gdma_region = GDMA_INVALID_DMA_REGION;
+   spec.type = type;
+   spec.monitor_avl_buf = false;
+   spec.queue_size = size;
+   err = mana_gd_create_mana_wq_cq(&gc->mana_ib, &spec, &queue->kmem);
+   if (err)
+   return err;
+   /* take ownership into mana_ib from mana */
+   queue->gdma_region = queue->kmem->mem_info.dma_region_handle;
+   queue->kmem->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION;
+   return 0;
+}
+
 int mana_ib_create_queue(struct mana_ib_dev *mdev, u64 addr, u32 size,
 struct mana_ib_queue *queue)
 {
@@ -279,6 +300,8 @@ void mana_ib_destroy_queue(struct mana_ib_dev *mdev, struct 
mana_ib_queue *queue
 */
mana_ib_gd_destroy_dma_region(mdev, queue->gdma_region);
ib_umem_release(queue->umem);
+   if (queue->kmem)
+   mana_gd_destroy_queue(mdev_to_gc(mdev), queue->kmem);
 }
 
 static int
diff --git a/drivers/infiniband/hw/mana/mana_ib.h 
b/drivers/infiniband/hw/mana/mana_ib.h
index b53a5b4..79ebd95 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -52,6 +52,7 @@ struct mana_ib_adapter_caps {
 
 struct mana_ib_queue {
struct ib_umem *umem;
+   struct gdma_queue *kmem;
u64 gdma_region;
u64 id;
 };
@@ -388,6 +389,8 @@ int mana_ib_create_dma_region(struct mana_ib_dev *dev, 
struct ib_umem *umem,
 int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev,
  mana_handle_t gdma_region);
 
+int mana_ib_create_kernel_queue(struct mana_ib_dev *mdev, u32 size, enum 
gdma_queue_type type,
+   struct mana_ib_queue *queue);
 int mana_ib_create_queue(struct mana_ib_dev *mdev, u64 addr, u32 size,
 struct mana_ib_queue *queue);
 void mana_ib_destroy_queue(struct mana_ib_dev *mdev, struct mana_ib_queue 
*queue);
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c 
b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index e97af7a..3cb0543 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -867,6 +867,7 @@ free_q:
kfree(queue);
return err;
 }
+EXPORT_SYMBOL_NS(mana_gd_create_mana_wq_cq, NET_MANA);
 
 void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)
 {
-- 
2.43.0

[PATCH rdma-next 01/13] RDMA/mana_ib: Allow registration of DMA-mapped memory in PDs

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Allow the HW to register DMA-mapped memory for kernel-level PDs.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/main.c | 3 +++
 include/net/mana/gdma.h   | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/infiniband/hw/mana/main.c 
b/drivers/infiniband/hw/mana/main.c
index 67c2d43..45b251b 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -82,6 +82,9 @@ int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata 
*udata)
mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_PD, sizeof(req),
 sizeof(resp));
 
+   if (!udata)
+   flags |= GDMA_PD_FLAG_ALLOW_GPA_MR;
+
req.flags = flags;
err = mana_gd_send_request(gc, sizeof(req), &req,
   sizeof(resp), &resp);
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 90f5665..03e1b25 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -775,6 +775,7 @@ struct gdma_destroy_dma_region_req {
 
 enum gdma_pd_flags {
GDMA_PD_FLAG_INVALID = 0,
+   GDMA_PD_FLAG_ALLOW_GPA_MR = 1,
 };
 
 struct gdma_create_pd_req {
-- 
2.43.0

[PATCH rdma-next 08/13] net/mana: fix warning in the writer of client oob

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Do not warn on missing pad_data when oob is in sgl.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c 
b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3cb0543..a8a9cd7 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1042,7 +1042,7 @@ static u32 mana_gd_write_client_oob(const struct 
gdma_wqe_request *wqe_req,
header->inline_oob_size_div4 = client_oob_size / sizeof(u32);
 
if (oob_in_sgl) {
-   WARN_ON_ONCE(!pad_data || wqe_req->num_sge < 2);
+   WARN_ON_ONCE(wqe_req->num_sge < 2);
 
header->client_oob_in_sgl = 1;
 
-- 
2.43.0

[PATCH rdma-next 05/13] RDMA/mana_ib: Create and destroy UD/GSI QP

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Implement HW requests to create and destroy UD/GSI QPs.
An UD/GSI QP has send and receive queues.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/main.c| 58 
 drivers/infiniband/hw/mana/mana_ib.h | 49 +++
 2 files changed, 107 insertions(+)

diff --git a/drivers/infiniband/hw/mana/main.c 
b/drivers/infiniband/hw/mana/main.c
index f2f6bb3..b0c55cb 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -1013,3 +1013,61 @@ int mana_ib_gd_destroy_rc_qp(struct mana_ib_dev *mdev, 
struct mana_ib_qp *qp)
}
return 0;
 }
+
+int mana_ib_gd_create_ud_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp,
+   struct ib_qp_init_attr *attr, u32 doorbell, u32 
type)
+{
+   struct mana_ib_cq *send_cq = container_of(qp->ibqp.send_cq, struct 
mana_ib_cq, ibcq);
+   struct mana_ib_cq *recv_cq = container_of(qp->ibqp.recv_cq, struct 
mana_ib_cq, ibcq);
+   struct mana_ib_pd *pd = container_of(qp->ibqp.pd, struct mana_ib_pd, 
ibpd);
+   struct gdma_context *gc = mdev_to_gc(mdev);
+   struct mana_rnic_create_udqp_resp resp = {};
+   struct mana_rnic_create_udqp_req req = {};
+   int err, i;
+
+   mana_gd_init_req_hdr(&req.hdr, MANA_IB_CREATE_UD_QP, sizeof(req), 
sizeof(resp));
+   req.hdr.dev_id = gc->mana_ib.dev_id;
+   req.adapter = mdev->adapter_handle;
+   req.pd_handle = pd->pd_handle;
+   req.send_cq_handle = send_cq->cq_handle;
+   req.recv_cq_handle = recv_cq->cq_handle;
+   for (i = 0; i < MANA_UD_QUEUE_TYPE_MAX; i++)
+   req.dma_region[i] = qp->ud_qp.queues[i].gdma_region;
+   req.doorbell_page = doorbell;
+   req.max_send_wr = attr->cap.max_send_wr;
+   req.max_recv_wr = attr->cap.max_recv_wr;
+   req.max_send_sge = attr->cap.max_send_sge;
+   req.max_recv_sge = attr->cap.max_recv_sge;
+   req.qp_type = type;
+   err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+   if (err) {
+   ibdev_err(&mdev->ib_dev, "Failed to create ud qp err %d", err);
+   return err;
+   }
+   qp->qp_handle = resp.qp_handle;
+   for (i = 0; i < MANA_UD_QUEUE_TYPE_MAX; i++) {
+   qp->ud_qp.queues[i].id = resp.queue_ids[i];
+   /* The GDMA regions are now owned by the RNIC QP handle */
+   qp->ud_qp.queues[i].gdma_region = GDMA_INVALID_DMA_REGION;
+   }
+   return 0;
+}
+
+int mana_ib_gd_destroy_ud_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp)
+{
+   struct mana_rnic_destroy_udqp_resp resp = {0};
+   struct mana_rnic_destroy_udqp_req req = {0};
+   struct gdma_context *gc = mdev_to_gc(mdev);
+   int err;
+
+   mana_gd_init_req_hdr(&req.hdr, MANA_IB_DESTROY_UD_QP, sizeof(req), 
sizeof(resp));
+   req.hdr.dev_id = gc->mana_ib.dev_id;
+   req.adapter = mdev->adapter_handle;
+   req.qp_handle = qp->qp_handle;
+   err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+   if (err) {
+   ibdev_err(&mdev->ib_dev, "Failed to destroy ud qp err %d", err);
+   return err;
+   }
+   return 0;
+}
diff --git a/drivers/infiniband/hw/mana/mana_ib.h 
b/drivers/infiniband/hw/mana/mana_ib.h
index 79ebd95..5e470f1 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -115,6 +115,17 @@ struct mana_ib_rc_qp {
struct mana_ib_queue queues[MANA_RC_QUEUE_TYPE_MAX];
 };
 
+enum mana_ud_queue_type {
+   MANA_UD_SEND_QUEUE = 0,
+   MANA_UD_RECV_QUEUE,
+   MANA_UD_QUEUE_TYPE_MAX,
+};
+
+struct mana_ib_ud_qp {
+   struct mana_ib_queue queues[MANA_UD_QUEUE_TYPE_MAX];
+   u32 sq_psn;
+};
+
 struct mana_ib_qp {
struct ib_qp ibqp;
 
@@ -122,6 +133,7 @@ struct mana_ib_qp {
union {
struct mana_ib_queue raw_sq;
struct mana_ib_rc_qp rc_qp;
+   struct mana_ib_ud_qp ud_qp;
};
 
/* The port on the IB device, starting with 1 */
@@ -146,6 +158,8 @@ enum mana_ib_command_code {
MANA_IB_DESTROY_ADAPTER = 0x30003,
MANA_IB_CONFIG_IP_ADDR  = 0x30004,
MANA_IB_CONFIG_MAC_ADDR = 0x30005,
+   MANA_IB_CREATE_UD_QP= 0x30006,
+   MANA_IB_DESTROY_UD_QP   = 0x30007,
MANA_IB_CREATE_CQ   = 0x30008,
MANA_IB_DESTROY_CQ  = 0x30009,
MANA_IB_CREATE_RC_QP= 0x3000a,
@@ -297,6 +311,37 @@ struct mana_rnic_destroy_rc_qp_resp {
struct gdma_resp_hdr hdr;
 }; /* HW Data */
 
+struct mana_rnic_create_udqp_req {
+   struct gdma_req_hdr hdr;
+   mana_handle_t adapter;
+   mana_handle_t pd_handle;
+   mana_handle_t send_cq_handle;
+   mana_handle_t recv_cq_handle

[PATCH rdma-next 11/13] RDMA/mana_ib: extend mana QP table

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Enable mana QP table to store UD/GSI QPs.
For send queues, set the most significant bit to one,
as send and receive WQs can have the same ID in mana.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/main.c|  2 +-
 drivers/infiniband/hw/mana/mana_ib.h |  8 ++-
 drivers/infiniband/hw/mana/qp.c  | 78 ++--
 3 files changed, 83 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/mana/main.c 
b/drivers/infiniband/hw/mana/main.c
index b0c55cb..114e391 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -704,7 +704,7 @@ mana_ib_event_handler(void *ctx, struct gdma_queue *q, 
struct gdma_event *event)
switch (event->type) {
case GDMA_EQE_RNIC_QP_FATAL:
qpn = event->details[0];
-   qp = mana_get_qp_ref(mdev, qpn);
+   qp = mana_get_qp_ref(mdev, qpn, false);
if (!qp)
break;
if (qp->ibqp.event_handler) {
diff --git a/drivers/infiniband/hw/mana/mana_ib.h 
b/drivers/infiniband/hw/mana/mana_ib.h
index bd34ad6..5e4ca55 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -23,6 +23,9 @@
 /* MANA doesn't have any limit for MR size */
 #define MANA_IB_MAX_MR_SIZEU64_MAX
 
+/* Send queue ID mask */
+#define MANA_SENDQ_MASKBIT(31)
+
 /*
  * The hardware limit of number of MRs is greater than maximum number of MRs
  * that can possibly represent in 24 bits
@@ -438,11 +441,14 @@ static inline struct gdma_context *mdev_to_gc(struct 
mana_ib_dev *mdev)
 }
 
 static inline struct mana_ib_qp *mana_get_qp_ref(struct mana_ib_dev *mdev,
-uint32_t qid)
+u32 qid, bool is_sq)
 {
struct mana_ib_qp *qp;
unsigned long flag;
 
+   if (is_sq)
+   qid |= MANA_SENDQ_MASK;
+
xa_lock_irqsave(&mdev->qp_table_wq, flag);
qp = xa_load(&mdev->qp_table_wq, qid);
if (qp)
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 051ea03..2528046 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -444,18 +444,82 @@ static enum gdma_queue_type mana_ib_queue_type(struct 
ib_qp_init_attr *attr, u32
return type;
 }
 
+static int mana_table_store_rc_qp(struct mana_ib_dev *mdev, struct mana_ib_qp 
*qp)
+{
+   return xa_insert_irq(&mdev->qp_table_wq, qp->ibqp.qp_num, qp,
+GFP_KERNEL);
+}
+
+static void mana_table_remove_rc_qp(struct mana_ib_dev *mdev, struct 
mana_ib_qp *qp)
+{
+   xa_erase_irq(&mdev->qp_table_wq, qp->ibqp.qp_num);
+}
+
+static int mana_table_store_ud_qp(struct mana_ib_dev *mdev, struct mana_ib_qp 
*qp)
+{
+   u32 qids = qp->ud_qp.queues[MANA_UD_SEND_QUEUE].id | MANA_SENDQ_MASK;
+   u32 qidr = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].id;
+   int err;
+
+   err = xa_insert_irq(&mdev->qp_table_wq, qids, qp, GFP_KERNEL);
+   if (err)
+   return err;
+
+   err = xa_insert_irq(&mdev->qp_table_wq, qidr, qp, GFP_KERNEL);
+   if (err)
+   goto remove_sq;
+
+   return 0;
+
+remove_sq:
+   xa_erase_irq(&mdev->qp_table_wq, qids);
+   return err;
+}
+
+static void mana_table_remove_ud_qp(struct mana_ib_dev *mdev, struct 
mana_ib_qp *qp)
+{
+   u32 qids = qp->ud_qp.queues[MANA_UD_SEND_QUEUE].id | MANA_SENDQ_MASK;
+   u32 qidr = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].id;
+
+   xa_erase_irq(&mdev->qp_table_wq, qids);
+   xa_erase_irq(&mdev->qp_table_wq, qidr);
+}
+
 static int mana_table_store_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp)
 {
refcount_set(&qp->refcount, 1);
init_completion(&qp->free);
-   return xa_insert_irq(&mdev->qp_table_wq, qp->ibqp.qp_num, qp,
-GFP_KERNEL);
+
+   switch (qp->ibqp.qp_type) {
+   case IB_QPT_RC:
+   return mana_table_store_rc_qp(mdev, qp);
+   case IB_QPT_UD:
+   case IB_QPT_GSI:
+   return mana_table_store_ud_qp(mdev, qp);
+   default:
+   ibdev_dbg(&mdev->ib_dev, "Unknown QP type for storing in mana 
table, %d\n",
+ qp->ibqp.qp_type);
+   }
+
+   return -EINVAL;
 }
 
 static void mana_table_remove_qp(struct mana_ib_dev *mdev,
 struct mana_ib_qp *qp)
 {
-   xa_erase_irq(&mdev->qp_table_wq, qp->ibqp.qp_num);
+   switch (qp->ibqp.qp_type) {
+   case IB_QPT_RC:
+   mana_table_remove_rc_qp(mdev, qp);
+   break;
+   case IB_QPT_UD:
+   case IB_QPT_GSI:
+   mana_table_remove_ud_qp(mdev, qp);
+

[PATCH rdma-next 10/13] RDMA/mana_ib: implement req_notify_cq

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Arm a CQ when req_notify_cq is called.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/cq.c | 12 
 drivers/infiniband/hw/mana/device.c |  1 +
 drivers/infiniband/hw/mana/mana_ib.h|  2 ++
 drivers/net/ethernet/microsoft/mana/gdma_main.c |  1 +
 4 files changed, 16 insertions(+)

diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index d26d82d..82f1462 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -168,3 +168,15 @@ void mana_ib_remove_cq_cb(struct mana_ib_dev *mdev, struct 
mana_ib_cq *cq)
kfree(gc->cq_table[cq->queue.id]);
gc->cq_table[cq->queue.id] = NULL;
 }
+
+int mana_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
+{
+   struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
+   struct gdma_queue *gdma_cq = cq->queue.kmem;
+
+   if (!gdma_cq)
+   return -EINVAL;
+
+   mana_gd_ring_cq(gdma_cq, SET_ARM_BIT);
+   return 0;
+}
diff --git a/drivers/infiniband/hw/mana/device.c 
b/drivers/infiniband/hw/mana/device.c
index 1da86c3..63e12c3 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -47,6 +47,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
.query_pkey = mana_ib_query_pkey,
.query_port = mana_ib_query_port,
.reg_user_mr = mana_ib_reg_user_mr,
+   .req_notify_cq = mana_ib_arm_cq,
 
INIT_RDMA_OBJ_SIZE(ib_ah, mana_ib_ah, ibah),
INIT_RDMA_OBJ_SIZE(ib_cq, mana_ib_cq, ibcq),
diff --git a/drivers/infiniband/hw/mana/mana_ib.h 
b/drivers/infiniband/hw/mana/mana_ib.h
index 6265c39..bd34ad6 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -595,4 +595,6 @@ int mana_ib_post_recv(struct ib_qp *ibqp, const struct 
ib_recv_wr *wr,
  const struct ib_recv_wr **bad_wr);
 int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
  const struct ib_send_wr **bad_wr);
+
+int mana_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 #endif
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c 
b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 409e4e8..823f7e7 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -344,6 +344,7 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, cq->type, cq->id,
  head, arm_bit);
 }
+EXPORT_SYMBOL_NS(mana_gd_ring_cq, NET_MANA);
 
 static void mana_gd_process_eqe(struct gdma_queue *eq)
 {
-- 
2.43.0

[PATCH rdma-next 13/13] RDMA/mana_ib: indicate CM support

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Set max_mad_size and IB_PORT_CM_SUP capability
to enable connection manager.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/main.c | 9 +++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mana/main.c 
b/drivers/infiniband/hw/mana/main.c
index 114e391..ae1fb69 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -561,8 +561,10 @@ int mana_ib_get_port_immutable(struct ib_device *ibdev, 
u32 port_num,
immutable->pkey_tbl_len = attr.pkey_tbl_len;
immutable->gid_tbl_len = attr.gid_tbl_len;
immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET;
-   if (port_num == 1)
+   if (port_num == 1) {
immutable->core_cap_flags |= RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+   immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+   }
 
return 0;
 }
@@ -621,8 +623,11 @@ int mana_ib_query_port(struct ib_device *ibdev, u32 port,
props->active_width = IB_WIDTH_4X;
props->active_speed = IB_SPEED_EDR;
props->pkey_tbl_len = 1;
-   if (port == 1)
+   if (port == 1) {
props->gid_tbl_len = 16;
+   props->port_cap_flags = IB_PORT_CM_SUP;
+   props->ip_gids = true;
+   }
 
return 0;
 }
-- 
2.43.0

[PATCH rdma-next 04/13] RDMA/mana_ib: create kernel-level CQs

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Implement creation of CQs for the kernel.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/cq.c | 80 +
 1 file changed, 52 insertions(+), 28 deletions(-)

diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index f04a679..d26d82d 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -15,42 +15,57 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct 
ib_cq_init_attr *attr,
struct ib_device *ibdev = ibcq->device;
struct mana_ib_create_cq ucmd = {};
struct mana_ib_dev *mdev;
+   struct gdma_context *gc;
bool is_rnic_cq;
u32 doorbell;
+   u32 buf_size;
int err;
 
mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+   gc = mdev_to_gc(mdev);
 
cq->comp_vector = attr->comp_vector % ibdev->num_comp_vectors;
cq->cq_handle = INVALID_MANA_HANDLE;
 
-   if (udata->inlen < offsetof(struct mana_ib_create_cq, flags))
-   return -EINVAL;
+   if (udata) {
+   if (udata->inlen < offsetof(struct mana_ib_create_cq, flags))
+   return -EINVAL;
 
-   err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
-   if (err) {
-   ibdev_dbg(ibdev,
- "Failed to copy from udata for create cq, %d\n", err);
-   return err;
-   }
+   err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), 
udata->inlen));
+   if (err) {
+   ibdev_dbg(ibdev, "Failed to copy from udata for create 
cq, %d\n", err);
+   return err;
+   }
 
-   is_rnic_cq = !!(ucmd.flags & MANA_IB_CREATE_RNIC_CQ);
+   is_rnic_cq = !!(ucmd.flags & MANA_IB_CREATE_RNIC_CQ);
 
-   if (!is_rnic_cq && attr->cqe > mdev->adapter_caps.max_qp_wr) {
-   ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
-   return -EINVAL;
-   }
+   if (!is_rnic_cq && attr->cqe > mdev->adapter_caps.max_qp_wr) {
+   ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
+   return -EINVAL;
+   }
 
-   cq->cqe = attr->cqe;
-   err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe * 
COMP_ENTRY_SIZE, &cq->queue);
-   if (err) {
-   ibdev_dbg(ibdev, "Failed to create queue for create cq, %d\n", 
err);
-   return err;
-   }
+   cq->cqe = attr->cqe;
+   err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe * 
COMP_ENTRY_SIZE,
+  &cq->queue);
+   if (err) {
+   ibdev_dbg(ibdev, "Failed to create queue for create cq, 
%d\n", err);
+   return err;
+   }
 
-   mana_ucontext = rdma_udata_to_drv_context(udata, struct 
mana_ib_ucontext,
- ibucontext);
-   doorbell = mana_ucontext->doorbell;
+   mana_ucontext = rdma_udata_to_drv_context(udata, struct 
mana_ib_ucontext,
+ ibucontext);
+   doorbell = mana_ucontext->doorbell;
+   } else {
+   is_rnic_cq = true;
+   buf_size = MANA_PAGE_ALIGN(roundup_pow_of_two(attr->cqe * 
COMP_ENTRY_SIZE));
+   cq->cqe = buf_size / COMP_ENTRY_SIZE;
+   err = mana_ib_create_kernel_queue(mdev, buf_size, GDMA_CQ, 
&cq->queue);
+   if (err) {
+   ibdev_dbg(ibdev, "Failed to create kernel queue for 
create cq, %d\n", err);
+   return err;
+   }
+   doorbell = gc->mana_ib.doorbell;
+   }
 
if (is_rnic_cq) {
err = mana_ib_gd_create_cq(mdev, cq, doorbell);
@@ -66,11 +81,13 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct 
ib_cq_init_attr *attr,
}
}
 
-   resp.cqid = cq->queue.id;
-   err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen));
-   if (err) {
-   ibdev_dbg(&mdev->ib_dev, "Failed to copy to udata, %d\n", err);
-   goto err_remove_cq_cb;
+   if (udata) {
+   resp.cqid = cq->queue.id;
+   err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), 
udata->outlen));
+   if (err) {
+   ibdev_dbg(&mdev->ib_dev, "Failed to copy to udata, 
%d\n", err);
+   goto err_remove_cq_cb;
+   }
}
 
return 0;
@@ -122,7 +139

[PATCH rdma-next 06/13] RDMA/mana_ib: UD/GSI QP creation for kernel

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Implement UD/GSI QPs for the kernel.
Allow create/modify/destroy for such QPs.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/qp.c | 115 
 1 file changed, 115 insertions(+)

diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 73d67c8..fea45be 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -398,6 +398,52 @@ err_free_vport:
return err;
 }
 
+static u32 mana_ib_wqe_size(u32 sge, u32 oob_size)
+{
+   u32 wqe_size = sge * sizeof(struct gdma_sge) + sizeof(struct gdma_wqe) 
+ oob_size;
+
+   return ALIGN(wqe_size, GDMA_WQE_BU_SIZE);
+}
+
+static u32 mana_ib_queue_size(struct ib_qp_init_attr *attr, u32 queue_type)
+{
+   u32 queue_size;
+
+   switch (attr->qp_type) {
+   case IB_QPT_UD:
+   case IB_QPT_GSI:
+   if (queue_type == MANA_UD_SEND_QUEUE)
+   queue_size = attr->cap.max_send_wr *
+   mana_ib_wqe_size(attr->cap.max_send_sge, 
INLINE_OOB_LARGE_SIZE);
+   else
+   queue_size = attr->cap.max_recv_wr *
+   mana_ib_wqe_size(attr->cap.max_recv_sge, 
INLINE_OOB_SMALL_SIZE);
+   break;
+   default:
+   return 0;
+   }
+
+   return MANA_PAGE_ALIGN(roundup_pow_of_two(queue_size));
+}
+
+static enum gdma_queue_type mana_ib_queue_type(struct ib_qp_init_attr *attr, 
u32 queue_type)
+{
+   enum gdma_queue_type type;
+
+   switch (attr->qp_type) {
+   case IB_QPT_UD:
+   case IB_QPT_GSI:
+   if (queue_type == MANA_UD_SEND_QUEUE)
+   type = GDMA_SQ;
+   else
+   type = GDMA_RQ;
+   break;
+   default:
+   type = GDMA_INVALID_QUEUE;
+   }
+   return type;
+}
+
 static int mana_table_store_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp)
 {
refcount_set(&qp->refcount, 1);
@@ -490,6 +536,51 @@ destroy_queues:
return err;
 }
 
+static int mana_ib_create_ud_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
+   struct ib_qp_init_attr *attr, struct ib_udata 
*udata)
+{
+   struct mana_ib_dev *mdev = container_of(ibpd->device, struct 
mana_ib_dev, ib_dev);
+   struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp);
+   struct gdma_context *gc = mdev_to_gc(mdev);
+   u32 doorbell, queue_size;
+   int i, err;
+
+   if (udata) {
+   ibdev_dbg(&mdev->ib_dev, "User-level UD QPs are not supported, 
%d\n", err);
+   return -EINVAL;
+   }
+
+   for (i = 0; i < MANA_UD_QUEUE_TYPE_MAX; ++i) {
+   queue_size = mana_ib_queue_size(attr, i);
+   err = mana_ib_create_kernel_queue(mdev, queue_size, 
mana_ib_queue_type(attr, i),
+ &qp->ud_qp.queues[i]);
+   if (err) {
+   ibdev_err(&mdev->ib_dev, "Failed to create queue %d, 
err %d\n",
+ i, err);
+   goto destroy_queues;
+   }
+   }
+   doorbell = gc->mana_ib.doorbell;
+
+   err = mana_ib_gd_create_ud_qp(mdev, qp, attr, doorbell, attr->qp_type);
+   if (err) {
+   ibdev_err(&mdev->ib_dev, "Failed to create ud qp  %d\n", err);
+   goto destroy_queues;
+   }
+   qp->ibqp.qp_num = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].id;
+   qp->port = attr->port_num;
+
+   for (i = 0; i < MANA_UD_QUEUE_TYPE_MAX; ++i)
+   qp->ud_qp.queues[i].kmem->id = qp->ud_qp.queues[i].id;
+
+   return 0;
+
+destroy_queues:
+   while (i-- > 0)
+   mana_ib_destroy_queue(mdev, &qp->ud_qp.queues[i]);
+   return err;
+}
+
 int mana_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attr,
  struct ib_udata *udata)
 {
@@ -503,6 +594,9 @@ int mana_ib_create_qp(struct ib_qp *ibqp, struct 
ib_qp_init_attr *attr,
return mana_ib_create_qp_raw(ibqp, ibqp->pd, attr, udata);
case IB_QPT_RC:
return mana_ib_create_rc_qp(ibqp, ibqp->pd, attr, udata);
+   case IB_QPT_UD:
+   case IB_QPT_GSI:
+   return mana_ib_create_ud_qp(ibqp, ibqp->pd, attr, udata);
default:
ibdev_dbg(ibqp->device, "Creating QP type %u not supported\n",
  attr->qp_type);
@@ -579,6 +673,8 @@ int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr 
*attr,
 {
switch (ibqp->qp_type) {
case IB_QPT_RC:
+   case IB_QPT_UD:
+   case IB_QPT_GSI:
return mana_ib_gd_modify_qp(ibqp, attr, attr_mask, udata);
defa

[PATCH rdma-next 09/13] RDMA/mana_ib: UD/GSI work requests

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Implement post send and post recv for UD/GSI QPs.
Add information about posted requests into shadow queues.

Co-developed-by: Shiraz Saleem 
Signed-off-by: Shiraz Saleem 
Signed-off-by: Konstantin Taranov 
---
 drivers/infiniband/hw/mana/Makefile   |   2 +-
 drivers/infiniband/hw/mana/device.c   |   2 +
 drivers/infiniband/hw/mana/mana_ib.h  |  33 
 drivers/infiniband/hw/mana/qp.c   |  21 ++-
 drivers/infiniband/hw/mana/shadow_queue.h | 115 
 drivers/infiniband/hw/mana/wr.c   | 168 ++
 .../net/ethernet/microsoft/mana/gdma_main.c   |   2 +
 7 files changed, 341 insertions(+), 2 deletions(-)
 create mode 100644 drivers/infiniband/hw/mana/shadow_queue.h
 create mode 100644 drivers/infiniband/hw/mana/wr.c

diff --git a/drivers/infiniband/hw/mana/Makefile 
b/drivers/infiniband/hw/mana/Makefile
index 6e56f77..79426e7 100644
--- a/drivers/infiniband/hw/mana/Makefile
+++ b/drivers/infiniband/hw/mana/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o
 
-mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o ah.o
+mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o ah.o wr.o
diff --git a/drivers/infiniband/hw/mana/device.c 
b/drivers/infiniband/hw/mana/device.c
index d534ef1..1da86c3 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -40,6 +40,8 @@ static const struct ib_device_ops mana_ib_dev_ops = {
.mmap = mana_ib_mmap,
.modify_qp = mana_ib_modify_qp,
.modify_wq = mana_ib_modify_wq,
+   .post_recv = mana_ib_post_recv,
+   .post_send = mana_ib_post_send,
.query_device = mana_ib_query_device,
.query_gid = mana_ib_query_gid,
.query_pkey = mana_ib_query_pkey,
diff --git a/drivers/infiniband/hw/mana/mana_ib.h 
b/drivers/infiniband/hw/mana/mana_ib.h
index 7b079d8..6265c39 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -14,6 +14,7 @@
 #include 
 
 #include 
+#include "shadow_queue.h"
 
 #define PAGE_SZ_BM 
\
(SZ_4K | SZ_8K | SZ_16K | SZ_32K | SZ_64K | SZ_128K | SZ_256K |\
@@ -165,6 +166,9 @@ struct mana_ib_qp {
/* The port on the IB device, starting with 1 */
u32 port;
 
+   struct shadow_queue shadow_rq;
+   struct shadow_queue shadow_sq;
+
refcount_t  refcount;
struct completion   free;
 };
@@ -404,6 +408,30 @@ struct mana_rnic_set_qp_state_resp {
struct gdma_resp_hdr hdr;
 }; /* HW Data */
 
+enum WQE_OPCODE_TYPES {
+   WQE_TYPE_UD_SEND = 0,
+   WQE_TYPE_UD_RECV = 8,
+}; /* HW DATA */
+
+struct rdma_send_oob {
+   u32 wqe_type: 5;
+   u32 fence   : 1;
+   u32 signaled: 1;
+   u32 solicited   : 1;
+   u32 psn : 24;
+
+   u32 ssn_or_rqpn : 24;
+   u32 reserved1   : 8;
+   union {
+   struct {
+   u32 remote_qkey;
+   u32 immediate;
+   u32 reserved1;
+   u32 reserved2;
+   } ud_send;
+   };
+}; /* HW DATA */
+
 static inline struct gdma_context *mdev_to_gc(struct mana_ib_dev *mdev)
 {
return mdev->gdma_dev->gdma_context;
@@ -562,4 +590,9 @@ int mana_ib_gd_destroy_ud_qp(struct mana_ib_dev *mdev, 
struct mana_ib_qp *qp);
 int mana_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
  struct ib_udata *udata);
 int mana_ib_destroy_ah(struct ib_ah *ah, u32 flags);
+
+int mana_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
+ const struct ib_recv_wr **bad_wr);
+int mana_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
+ const struct ib_send_wr **bad_wr);
 #endif
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index fea45be..051ea03 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -562,10 +562,23 @@ static int mana_ib_create_ud_qp(struct ib_qp *ibqp, 
struct ib_pd *ibpd,
}
doorbell = gc->mana_ib.doorbell;
 
+   err = create_shadow_queue(&qp->shadow_rq, attr->cap.max_recv_wr,
+ sizeof(struct ud_rq_shadow_wqe));
+   if (err) {
+   ibdev_err(&mdev->ib_dev, "Failed to create shadow rq err %d\n", 
err);
+   goto destroy_queues;
+   }
+   err = create_shadow_queue(&qp->shadow_sq, attr->cap.max_send_wr,
+ sizeof(struct ud_sq_shadow_wqe));
+   if (err) {
+   ibdev_err(&mdev->ib_dev, "Failed to create shadow sq err %d\n", 
err);
+   goto destroy_shadow_queues;
+   }
+
err = mana_ib_gd_create_ud_qp(mdev, qp, attr, doo

[PATCH rdma-next 12/13] RDMA/mana_ib: polling of CQs for GSI/UD

2025-01-20 Thread Konstantin Taranov 
From: Konstantin Taranov 

Add polling for the kernel CQs.
Process completion events for UD/GSI QPs.

Signed-off-by: Konstantin Taranov 
Reviewed-by: Shiraz Saleem 
---
 drivers/infiniband/hw/mana/cq.c   | 135 ++
 drivers/infiniband/hw/mana/device.c   |   1 +
 drivers/infiniband/hw/mana/mana_ib.h  |  32 +
 drivers/infiniband/hw/mana/qp.c   |  33 +
 .../net/ethernet/microsoft/mana/gdma_main.c   |   1 +
 5 files changed, 202 insertions(+)

diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index 82f1462..5c325ef 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -90,6 +90,10 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct 
ib_cq_init_attr *attr,
}
}
 
+   spin_lock_init(&cq->cq_lock);
+   INIT_LIST_HEAD(&cq->list_send_qp);
+   INIT_LIST_HEAD(&cq->list_recv_qp);
+
return 0;
 
 err_remove_cq_cb:
@@ -180,3 +184,134 @@ int mana_ib_arm_cq(struct ib_cq *ibcq, enum 
ib_cq_notify_flags flags)
mana_gd_ring_cq(gdma_cq, SET_ARM_BIT);
return 0;
 }
+
+static inline void handle_ud_sq_cqe(struct mana_ib_qp *qp, struct gdma_comp 
*cqe)
+{
+   struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
+   struct gdma_queue *wq = qp->ud_qp.queues[MANA_UD_SEND_QUEUE].kmem;
+   struct ud_sq_shadow_wqe *shadow_wqe;
+
+   shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_sq);
+   if (!shadow_wqe)
+   return;
+
+   shadow_wqe->header.error_code = rdma_cqe->ud_send.vendor_error;
+
+   wq->tail += shadow_wqe->header.posted_wqe_size;
+   shadow_queue_advance_next_to_complete(&qp->shadow_sq);
+}
+
+static inline void handle_ud_rq_cqe(struct mana_ib_qp *qp, struct gdma_comp 
*cqe)
+{
+   struct mana_rdma_cqe *rdma_cqe = (struct mana_rdma_cqe *)cqe->cqe_data;
+   struct gdma_queue *wq = qp->ud_qp.queues[MANA_UD_RECV_QUEUE].kmem;
+   struct ud_rq_shadow_wqe *shadow_wqe;
+
+   shadow_wqe = shadow_queue_get_next_to_complete(&qp->shadow_rq);
+   if (!shadow_wqe)
+   return;
+
+   shadow_wqe->byte_len = rdma_cqe->ud_recv.msg_len;
+   shadow_wqe->src_qpn = rdma_cqe->ud_recv.src_qpn;
+   shadow_wqe->header.error_code = IB_WC_SUCCESS;
+
+   wq->tail += shadow_wqe->header.posted_wqe_size;
+   shadow_queue_advance_next_to_complete(&qp->shadow_rq);
+}
+
+static void mana_handle_cqe(struct mana_ib_dev *mdev, struct gdma_comp *cqe)
+{
+   struct mana_ib_qp *qp = mana_get_qp_ref(mdev, cqe->wq_num, cqe->is_sq);
+
+   if (!qp)
+   return;
+
+   if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_UD) {
+   if (cqe->is_sq)
+   handle_ud_sq_cqe(qp, cqe);
+   else
+   handle_ud_rq_cqe(qp, cqe);
+   }
+
+   mana_put_qp_ref(qp);
+}
+
+static void fill_verbs_from_shadow_wqe(struct mana_ib_qp *qp, struct ib_wc *wc,
+  const struct shadow_wqe_header 
*shadow_wqe)
+{
+   const struct ud_rq_shadow_wqe *ud_wqe = (const struct ud_rq_shadow_wqe 
*)shadow_wqe;
+
+   wc->wr_id = shadow_wqe->wr_id;
+   wc->status = shadow_wqe->error_code;
+   wc->opcode = shadow_wqe->opcode;
+   wc->vendor_err = shadow_wqe->error_code;
+   wc->wc_flags = 0;
+   wc->qp = &qp->ibqp;
+   wc->pkey_index = 0;
+
+   if (shadow_wqe->opcode == IB_WC_RECV) {
+   wc->byte_len = ud_wqe->byte_len;
+   wc->src_qp = ud_wqe->src_qpn;
+   wc->wc_flags |= IB_WC_GRH;
+   }
+}
+
+static int mana_process_completions(struct mana_ib_cq *cq, int nwc, struct 
ib_wc *wc)
+{
+   struct shadow_wqe_header *shadow_wqe;
+   struct mana_ib_qp *qp;
+   int wc_index = 0;
+
+   /* process send shadow queue completions  */
+   list_for_each_entry(qp, &cq->list_send_qp, cq_send_list) {
+   while ((shadow_wqe = 
shadow_queue_get_next_to_consume(&qp->shadow_sq))
+   != NULL) {
+   if (wc_index >= nwc)
+   goto out;
+
+   fill_verbs_from_shadow_wqe(qp, &wc[wc_index], 
shadow_wqe);
+   shadow_queue_advance_consumer(&qp->shadow_sq);
+   wc_index++;
+   }
+   }
+
+   /* process recv shadow queue completions */
+   list_for_each_entry(qp, &cq->list_recv_qp, cq_recv_list) {
+   while ((shadow_wqe = 
shadow_queue_get_next_to_consume(&qp->shadow_rq))
+   != NULL) {
+   if (wc_index >= nwc)
+   goto out;
+
+

RE: [PATCH rdma-next 04/13] RDMA/mana_ib: create kernel-level CQs

2025-01-28 Thread Konstantin Taranov 
> Subject: RE: [PATCH rdma-next 04/13] RDMA/mana_ib: create kernel-level
> CQs
> 
> > Subject: [PATCH rdma-next 04/13] RDMA/mana_ib: create kernel-level CQs
> >
> > From: Konstantin Taranov 
> >
> > Implement creation of CQs for the kernel.
> >
> > Signed-off-by: Konstantin Taranov 
> > Reviewed-by: Shiraz Saleem 
> > ---
> >  drivers/infiniband/hw/mana/cq.c | 80
> > +
> >  1 file changed, 52 insertions(+), 28 deletions(-)
> >
> > diff --git a/drivers/infiniband/hw/mana/cq.c
> > b/drivers/infiniband/hw/mana/cq.c index f04a679..d26d82d 100644
> > --- a/drivers/infiniband/hw/mana/cq.c
> > +++ b/drivers/infiniband/hw/mana/cq.c
> > @@ -15,42 +15,57 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const
> > struct ib_cq_init_attr *attr,
> > struct ib_device *ibdev = ibcq->device;
> > struct mana_ib_create_cq ucmd = {};
> > struct mana_ib_dev *mdev;
> > +   struct gdma_context *gc;
> > bool is_rnic_cq;
> > u32 doorbell;
> > +   u32 buf_size;
> > int err;
> >
> > mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
> > +   gc = mdev_to_gc(mdev);
> >
> > cq->comp_vector = attr->comp_vector % ibdev->num_comp_vectors;
> > cq->cq_handle = INVALID_MANA_HANDLE;
> >
> > -   if (udata->inlen < offsetof(struct mana_ib_create_cq, flags))
> > -   return -EINVAL;
> > +   if (udata) {
> > +   if (udata->inlen < offsetof(struct mana_ib_create_cq, flags))
> > +   return -EINVAL;
> >
> > -   err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-
> > >inlen));
> > -   if (err) {
> > -   ibdev_dbg(ibdev,
> > - "Failed to copy from udata for create cq, %d\n", err);
> > -   return err;
> > -   }
> > +   err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd),
> > udata->inlen));
> > +   if (err) {
> > +   ibdev_dbg(ibdev, "Failed to copy from udata for create
> > cq, %d\n", err);
> > +   return err;
> > +   }
> >
> > -   is_rnic_cq = !!(ucmd.flags & MANA_IB_CREATE_RNIC_CQ);
> > +   is_rnic_cq = !!(ucmd.flags & MANA_IB_CREATE_RNIC_CQ);
> >
> > -   if (!is_rnic_cq && attr->cqe > mdev->adapter_caps.max_qp_wr) {
> > -   ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
> > -   return -EINVAL;
> > -   }
> > +   if (!is_rnic_cq && attr->cqe > mdev-
> >adapter_caps.max_qp_wr)
> > {
> > +   ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr-
> >cqe);
> > +   return -EINVAL;
> > +   }
> >
> > -   cq->cqe = attr->cqe;
> > -   err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe *
> > COMP_ENTRY_SIZE, &cq->queue);
> > -   if (err) {
> > -   ibdev_dbg(ibdev, "Failed to create queue for create cq, %d\n",
> > err);
> > -   return err;
> > -   }
> > +   cq->cqe = attr->cqe;
> > +   err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe *
> > COMP_ENTRY_SIZE,
> > +  &cq->queue);
> > +   if (err) {
> > +   ibdev_dbg(ibdev, "Failed to create queue for create
> > cq, %d\n", err);
> > +   return err;
> > +   }
> >
> > -   mana_ucontext = rdma_udata_to_drv_context(udata, struct
> > mana_ib_ucontext,
> > - ibucontext);
> > -   doorbell = mana_ucontext->doorbell;
> > +   mana_ucontext = rdma_udata_to_drv_context(udata, struct
> > mana_ib_ucontext,
> > + ibucontext);
> > +   doorbell = mana_ucontext->doorbell;
> > +   } else {
> > +   is_rnic_cq = true;
> > +   buf_size = MANA_PAGE_ALIGN(roundup_pow_of_two(attr-
> >cqe
> > * COMP_ENTRY_SIZE));
> > +   cq->cqe = buf_size / COMP_ENTRY_SIZE;
> > +   err = mana_ib_create_kernel_queue(mdev, buf_size,
> GDMA_CQ,
> > &cq->queue);
> > +   if (err) {
> > +   ibdev_dbg(ibdev, "Failed to create kernel queue for
> > create cq, %d\n", err);
> > +   return err;
> > +   }
>