Introduce Microsoft Azure Network Adapter (MANA) RDMA driver
Subsystems (5)
PATCH v8 1/12 net: mana: Add support for auxiliary device
In reply to [email protected]From: Long Li <[email protected]>
In preparation for supporting MANA RDMA driver, add support for auxiliary device in the Ethernet driver. The RDMA device is modeled as an auxiliary device to the Ethernet device.
---
Change log:
v3: define mana_adev_idx_alloc and mana_adev_idx_free as static
v7: fix a bug that may assign a negative value to adev->id
drivers/net/ethernet/microsoft/Kconfig | 1 + drivers/net/ethernet/microsoft/mana/gdma.h | 2 + .../ethernet/microsoft/mana/mana_auxiliary.h | 10 +++ drivers/net/ethernet/microsoft/mana/mana_en.c | 83 ++++++++++++++++++- 4 files changed, 95 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/microsoft/mana/mana_auxiliary.h
drivers/net/ethernet/microsoft/Kconfig +1 -0
@@ -19,6 +19,7 @@ config MICROSOFT_MANA tristate "Microsoft Azure Network Adapter (MANA) support" depends on PCI_MSI && X86_64 depends on PCI_HYPERV + select AUXILIARY_BUS help This driver supports Microsoft Azure Network Adapter (MANA). So far, the driver is only supported on X86_64.
drivers/net/ethernet/microsoft/mana/gdma.h +2 -0
@@ -204,6 +204,8 @@ struct gdma_dev {/* GDMA driver specific pointer */ void *driver_data; + +struct auxiliary_device *adev; };#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE
drivers/net/ethernet/microsoft/mana/mana_auxiliary.h new file +10 -0
@@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022, Microsoft Corporation. */ + +#include "mana.h" +#include <linux/auxiliary_bus.h> + +struct mana_adev { +struct auxiliary_device adev; +struct gdma_dev *mdev; +};
drivers/net/ethernet/microsoft/mana/mana_en.c +82 -1
113 lines not on this page · raw message
Signature · 1 line
2.17.1
v8 cover Introduce Microsoft Azure Network Adapter (MANA) RDMA driver
From: Long Li <[email protected]>
This patchset implements a RDMA driver for Microsoft Azure Network Adapter (MANA). In MANA, the RDMA device is modeled as an auxiliary device to the Ethernet device.
The first 11 patches modify the MANA Ethernet driver to support RDMA driver. The last patch implementes the RDMA driver.
The user-mode of the driver is being reviewed at:
https://github.com/linux-rdma/rdma-core/pull/1177
Ajay Sharma (3):
net: mana: Set the DMA device max segment size
net: mana: Define and process GDMA response code
GDMA_STATUS_MORE_ENTRIES
net: mana: Define data structures for protection domain and memory
registration
Long Li (9):
net: mana: Add support for auxiliary device
net: mana: Record the physical address for doorbell page region
net: mana: Handle vport sharing between devices
net: mana: Export Work Queue functions for use by RDMA driver
net: mana: Record port number in netdev
net: mana: Move header files to a common location
net: mana: Define max values for SGL entries
net: mana: Define data structures for allocating doorbell page from
GDMA
RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
MAINTAINERS | 10 +
drivers/infiniband/Kconfig | 1 +
drivers/infiniband/hw/Makefile | 1 +
drivers/infiniband/hw/mana/Kconfig | 10 +
drivers/infiniband/hw/mana/Makefile | 4 +
drivers/infiniband/hw/mana/cq.c | 79 +++
drivers/infiniband/hw/mana/device.c | 117 ++++
drivers/infiniband/hw/mana/main.c | 507 ++++++++++++++++++
drivers/infiniband/hw/mana/mana_ib.h | 156 ++++++
drivers/infiniband/hw/mana/mr.c | 197 +++++++
drivers/infiniband/hw/mana/qp.c | 506 +++++++++++++++++
drivers/infiniband/hw/mana/wq.c | 115 ++++
drivers/net/ethernet/microsoft/Kconfig | 1 +
.../net/ethernet/microsoft/mana/gdma_main.c | 40 +-
.../net/ethernet/microsoft/mana/hw_channel.c | 6 +-
.../net/ethernet/microsoft/mana/mana_bpf.c | 2 +-
drivers/net/ethernet/microsoft/mana/mana_en.c | 175 +++++-
.../ethernet/microsoft/mana/mana_ethtool.c | 2 +-
.../net/ethernet/microsoft/mana/shm_channel.c | 2 +-
.../microsoft => include/net}/mana/gdma.h | 158 +++++-
.../net}/mana/hw_channel.h | 0
.../microsoft => include/net}/mana/mana.h | 23 +-
include/net/mana/mana_auxiliary.h | 10 +
.../net}/mana/shm_channel.h | 0
include/uapi/rdma/ib_user_ioctl_verbs.h | 1 +
include/uapi/rdma/mana-abi.h | 66 +++
26 files changed, 2144 insertions(+), 45 deletions(-)
create mode 100644 drivers/infiniband/hw/mana/Kconfig
create mode 100644 drivers/infiniband/hw/mana/Makefile
create mode 100644 drivers/infiniband/hw/mana/cq.c
create mode 100644 drivers/infiniband/hw/mana/device.c
create mode 100644 drivers/infiniband/hw/mana/main.c
create mode 100644 drivers/infiniband/hw/mana/mana_ib.h
create mode 100644 drivers/infiniband/hw/mana/mr.c
create mode 100644 drivers/infiniband/hw/mana/qp.c
create mode 100644 drivers/infiniband/hw/mana/wq.c
rename {drivers/net/ethernet/microsoft => include/net}/mana/gdma.h (80%)
rename {drivers/net/ethernet/microsoft => include/net}/mana/hw_channel.h (100%)
rename {drivers/net/ethernet/microsoft => include/net}/mana/mana.h (95%)
create mode 100644 include/net/mana/mana_auxiliary.h
rename {drivers/net/ethernet/microsoft => include/net}/mana/shm_channel.h (100%)
create mode 100644 include/uapi/rdma/mana-abi.hSignature · 1 line
2.17.1
PATCH v8 3/12 net: mana: Handle vport sharing between devices
From: Long Li <[email protected]>
For outgoing packets, the PF requires the VF to configure the vport with corresponding protection domain and doorbell ID for the kernel or user context. The vport can't be shared between different contexts.
Implement the logic to exclusively take over the vport by either the Ethernet device or RDMA device.
---
Change log:
v2: use refcount instead of directly using atomic variables
v4: change to mutex to avoid possible race with refcount
v5: add detailed comments explaining vport sharing, use EXPORT_SYMBOL_NS
v6: rebased to rdma-next
drivers/net/ethernet/microsoft/mana/mana.h | 7 +++ drivers/net/ethernet/microsoft/mana/mana_en.c | 53 ++++++++++++++++++- 2 files changed, 58 insertions(+), 2 deletions(-)
drivers/net/ethernet/microsoft/mana/mana.h +7 -0
@@ -380,6 +380,10 @@ struct mana_port_context {mana_handle_t port_handle;mana_handle_t pf_filter_handle; +/* Mutex for sharing access to vport_use_count */ +struct mutex vport_mutex; +int vport_use_count; +u16 port_idx;bool port_is_up;
@@ -631,4 +635,7 @@ struct mana_tx_package { struct gdma_posted_wqe_info wqe_info; }; +int mana_cfg_vport (struct mana_port_context *apc,u32 protection_dom_id, +u32 doorbell_pg_id); +void mana_uncfg_vport (struct mana_port_context *apc);#endif /* _MANA_H */
drivers/net/ethernet/microsoft/mana/mana_en.c +51 -2
91 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v8 2/12 net: mana: Record the physical address for doorbell page region
In reply to [email protected]From: Long Li <[email protected]>
For supporting RDMA device with multiple user contexts with their individual doorbell pages, record the start address of doorbell page region for use by the RDMA driver to allocate user context doorbell IDs.
---
Change log:
v6: rebased to rdma-next
drivers/net/ethernet/microsoft/mana/gdma.h | 2 ++ drivers/net/ethernet/microsoft/mana/gdma_main.c | 4 ++++ 2 files changed, 6 insertions(+)
drivers/net/ethernet/microsoft/mana/gdma.h +2 -0
@@ -351,9 +351,11 @@ struct gdma_context {u32 test_event_eq_id;bool is_pf; +phys_addr_t bar0_pa;void __iomem *bar0_va;void __iomem *shm_base;void __iomem *db_page_base; +phys_addr_t phys_db_page_base;u32 db_page_size;/* Shared memory chanenl (used to bootstrap HWC) */
drivers/net/ethernet/microsoft/mana/gdma_main.c +4 -0
@@ -44,6 +44,9 @@ static void mana_gd_init_vf_regs(struct pci_dev *pdev) gc->db_page_base = gc->bar0_va +mana_gd_r64 (gc,GDMA_REG_DB_PAGE_OFFSET ); + gc->phys_db_page_base = gc->bar0_pa + +mana_gd_r64 (gc,GDMA_REG_DB_PAGE_OFFSET ); + gc->shm_base = gc->bar0_va +mana_gd_r64 (gc,GDMA_REG_SHM_OFFSET ); }
@@ -1367,6 +1370,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)mutex_init (&gc->eq_test_event_mutex);pci_set_drvdata (pdev, gc); + gc->bar0_pa =pci_resource_start (pdev,0 ); bar0_va =pci_iomap (pdev, bar,0 );if (!bar0_va)
Signature · 1 line
2.17.1
PATCH v8 6/12 net: mana: Record port number in netdev
In reply to [email protected]From: Long Li <[email protected]>
The port number is useful for user-mode application to identify this net device based on port index. Set to the correct value in ndev.
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/ethernet/microsoft/mana/mana_en.c +1 -0
@@ -2133,6 +2133,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->max_mtu = ndev->mtu; ndev->min_mtu = ndev->mtu; ndev->needed_headroom =MANA_HEADROOM ; + ndev->dev_port = port_idx;SET_NETDEV_DEV (ndev, gc->dev);netif_carrier_off (ndev);
Signature · 1 line
2.17.1
PATCH v8 7/12 net: mana: Move header files to a common location
In reply to [email protected]From: Long Li <[email protected]>
In preparation to add MANA RDMA driver, move all the required header files to a common location for use by both Ethernet and RDMA drivers.
---
Change log:
v2: Move headers to include/net/mana, instead of include/linux/mana
MAINTAINERS | 1 +
drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +-
drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 ++--
drivers/net/ethernet/microsoft/mana/mana_bpf.c | 2 +-
drivers/net/ethernet/microsoft/mana/mana_en.c | 4 ++--
drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 2 +-
drivers/net/ethernet/microsoft/mana/shm_channel.c | 2 +-
{drivers/net/ethernet/microsoft => include/net}/mana/gdma.h | 0
.../net/ethernet/microsoft => include/net}/mana/hw_channel.h | 0
{drivers/net/ethernet/microsoft => include/net}/mana/mana.h | 0
.../ethernet/microsoft => include/net}/mana/mana_auxiliary.h | 0
.../net/ethernet/microsoft => include/net}/mana/shm_channel.h | 0
12 files changed, 9 insertions(+), 8 deletions(-)
rename {drivers/net/ethernet/microsoft => include/net}/mana/gdma.h (100%)
rename {drivers/net/ethernet/microsoft => include/net}/mana/hw_channel.h (100%)
rename {drivers/net/ethernet/microsoft => include/net}/mana/mana.h (100%)
rename {drivers/net/ethernet/microsoft => include/net}/mana/mana_auxiliary.h (100%)
rename {drivers/net/ethernet/microsoft => include/net}/mana/shm_channel.h (100%)MAINTAINERS +1 -0
@@ -9457,6 +9457,7 @@ F: include/asm-generic/hyperv-tlfs.h F: include/asm-generic/mshyperv.h F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h +F: include/net/mana F: include/uapi/linux/hyperv.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/
drivers/net/ethernet/microsoft/mana/gdma_main.c +1 -1
@@ -6,7 +6,7 @@#include <linux/utsname.h> #include <linux/version.h> -#include "mana.h" +#include <net/mana/mana.h> static u32 mana_gd_r32 (struct gdma_context *g,u64 offset) {
drivers/net/ethernet/microsoft/mana/hw_channel.c +2 -2
@@ -1,8 +1,8 @@// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Copyright (c) 2021, Microsoft Corporation. */ -#include "gdma.h" -#include "hw_channel.h" +#include <net/mana/gdma.h> +#include <net/mana/hw_channel.h> static int mana_hwc_get_msg_index (struct hw_channel_context *hwc,u16 *msg_id) {
drivers/net/ethernet/microsoft/mana/mana_bpf.c +1 -1
@@ -8,7 +8,7 @@#include <linux/bpf_trace.h> #include <net/xdp.h> -#include "mana.h" +#include <net/mana/mana.h> void mana_xdp_tx (struct sk_buff *skb,struct net_device *ndev) {
drivers/net/ethernet/microsoft/mana/mana_en.c +2 -2
@@ -12,8 +12,8 @@#include <net/checksum.h> #include <net/ip6_checksum.h> -#include "mana.h" -#include "mana_auxiliary.h" +#include <net/mana/mana.h> +#include <net/mana/mana_auxiliary.h> static DEFINE_IDA (mana_adev_ida);
drivers/net/ethernet/microsoft/mana/mana_ethtool.c +1 -1
@@ -5,7 +5,7 @@#include <linux/etherdevice.h> #include <linux/ethtool.h> -#include "mana.h" +#include <net/mana/mana.h> static const struct { char name[ETH_GSTRING_LEN];
drivers/net/ethernet/microsoft/mana/shm_channel.c +1 -1
@@ -6,7 +6,7 @@#include <linux/io.h> #include <linux/mm.h> -#include "shm_channel.h" +#include <net/mana/shm_channel.h> #define PAGE_FRAME_L48_WIDTH_BYTES 6#define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8)
include/net/mana/gdma.h renamed from drivers/net/ethernet/microsoft/mana/gdma.h +0 -0
include/net/mana/hw_channel.h renamed from drivers/net/ethernet/microsoft/mana/hw_channel.h +0 -0
include/net/mana/mana.h renamed from drivers/net/ethernet/microsoft/mana/mana.h +0 -0
include/net/mana/mana_auxiliary.h renamed from drivers/net/ethernet/microsoft/mana/mana_auxiliary.h +0 -0
include/net/mana/shm_channel.h renamed from drivers/net/ethernet/microsoft/mana/shm_channel.h +0 -0
Signature · 1 line
2.17.1
PATCH v8 9/12 net: mana: Define and process GDMA response code GDMA_STATUS_MORE_ENTRIES
In reply to [email protected]From: Ajay Sharma <[email protected]>
When doing memory registration, the PF may respond with GDMA_STATUS_MORE_ENTRIES to indicate a follow request is needed. This is not an error and should be processed as expected.
--- drivers/net/ethernet/microsoft/mana/hw_channel.c | 2 +- include/net/mana/gdma.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/microsoft/mana/hw_channel.c +1 -1
@@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } -if (ctx->status_code) { +if (ctx->status_code && ctx->status_code !=GDMA_STATUS_MORE_ENTRIES ) {dev_err (hwc->dev,"HWC: Failed hw_channel req: 0x%x\n" , ctx->status_code); err = -EPROTO ;
include/net/mana/gdma.h +2 -0
@@ -9,6 +9,8 @@#include "shm_channel.h" +#define GDMA_STATUS_MORE_ENTRIES 0x00000105 +/* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. */
Signature · 1 line
2.17.1
PATCH v8 10/12 net: mana: Define data structures for allocating doorbell page from GDMA
In reply to [email protected]From: Long Li <[email protected]>
The RDMA device needs to allocate doorbell pages for each user context. Define the GDMA data structures for use by the RDMA driver.
---
Change log:
v4: use EXPORT_SYMBOL_NS
v7: move mana_gd_allocate_doorbell_page() and mana_gd_destroy_doorbell_page() to the RDMA driver
v8: remove extra line in header file
include/net/mana/gdma.h | 25 +++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
include/net/mana/gdma.h +24 -0
@@ -24,11 +24,15 @@ enum gdma_request_type {GDMA_GENERATE_TEST_EQE =10 ,GDMA_CREATE_QUEUE =12 ,GDMA_DISABLE_QUEUE =13 , +GDMA_ALLOCATE_RESOURCE_RANGE =22 , +GDMA_DESTROY_RESOURCE_RANGE =24 ,GDMA_CREATE_DMA_REGION =25 ,GDMA_DMA_REGION_ADD_PAGES =26 , GDMA_DESTROY_DMA_REGION = 27, }; +#define GDMA_RESOURCE_DOORBELL_PAGE 27 +enum gdma_queue_type {GDMA_INVALID_QUEUE , GDMA_SQ,
@@ -587,6 +591,26 @@ struct gdma_register_device_resp {u32 db_id; };/* HW DATA */ +struct gdma_allocate_resource_range_req { +struct gdma_req_hdr hdr; +u32 resource_type; +u32 num_resources; +u32 alignment; +u32 allocated_resources; +}; + +struct gdma_allocate_resource_range_resp { +struct gdma_resp_hdr hdr; +u32 allocated_resources; +}; + +struct gdma_destroy_resource_range_req { +struct gdma_req_hdr hdr; +u32 resource_type; +u32 num_resources; +u32 allocated_resources; +}; +/* GDMA_CREATE_QUEUE */ struct gdma_create_queue_req {struct gdma_req_hdr hdr;
Signature · 1 line
2.17.1
PATCH v8 8/12 net: mana: Define max values for SGL entries
In reply to [email protected]From: Long Li <[email protected]>
The number of maximum SGl entries should be computed from the maximum WQE size for the intended queue type and the corresponding OOB data size. This guarantees the hardware queue can successfully queue requests up to the queue depth exposed to the upper layer.
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- include/net/mana/gdma.h | 7 +++++++ include/net/mana/mana.h | 4 +--- 3 files changed, 9 insertions(+), 4 deletions(-)
drivers/net/ethernet/microsoft/mana/mana_en.c +1 -1
@@ -189,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit =0 ; pkg.wqe_req.num_sge =1 +skb_shinfo (skb)->nr_frags; -WARN_ON_ONCE (pkg.wqe_req.num_sge >30 ); +WARN_ON_ONCE (pkg.wqe_req.num_sge >MAX_TX_WQE_SGL_ENTRIES );if (pkg.wqe_req.num_sge <=ARRAY_SIZE (pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array;
include/net/mana/gdma.h +7 -0
@@ -427,6 +427,13 @@ struct gdma_wqe {#define MAX_TX_WQE_SIZE 512#define MAX_RX_WQE_SIZE 256 +#define MAX_TX_WQE_SGL_ENTRIES ((GDMA_MAX_SQE_SIZE - \ + sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \ + sizeof(struct gdma_sge)) + +#define MAX_RX_WQE_SGL_ENTRIES ((GDMA_MAX_RQE_SIZE - \ + sizeof(struct gdma_sge)) / sizeof(struct gdma_sge)) +struct gdma_cqe {u32 cqe_data[GDMA_COMP_DATA_SIZE /4 ];
include/net/mana/mana.h +1 -3
@@ -265,8 +265,6 @@ struct mana_cq {int budget; }; -#define GDMA_MAX_RQE_SGES 15 -struct mana_recv_buf_oob {/* A valid GDMA work request representing the data buffer. */ struct gdma_wqe_request wqe_req;
@@ -276,7 +274,7 @@ struct mana_recv_buf_oob {/* SGL of the buffer going to be sent has part of the work request. */ u32 num_sge; -struct gdma_sge sgl[GDMA_MAX_RQE_SGES ]; +struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES ];/* Required to store the result of mana_gd_post_work_request. * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the
Signature · 1 line
2.17.1
PATCH v8 11/12 net: mana: Define data structures for protection domain and memory registration
In reply to [email protected]From: Ajay Sharma <[email protected]>
The MANA hardware support protection domain and memory registration for use in RDMA environment. Add those definitions and expose them for use by the RDMA driver.
---
Change log:
v3: format/coding style changes
v5: remove unused code dealing with kernel-mode MR
.../net/ethernet/microsoft/mana/gdma_main.c | 27 ++-- drivers/net/ethernet/microsoft/mana/mana_en.c | 18 +-- include/net/mana/gdma.h | 121 +++++++++++++++++- 3 files changed, 143 insertions(+), 23 deletions(-)
drivers/net/ethernet/microsoft/mana/gdma_main.c +17 -10
@@ -198,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, req.type = queue->type; req.pdid = queue->gdma_dev->pdid; req.doolbell_id = queue->gdma_dev->doorbell; - req.gdma_region = queue->mem_info.gdma_region; + req.gdma_region = queue->mem_info.dma_region_handle; req.queue_size = queue->queue_size; req.log2_throttle_limit = queue->eq.log2_throttle_limit; req.eq_pci_msix_index = queue->eq.msix_index;
@@ -212,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, queue->id = resp.queue_index; queue->eq.disable_needed = true; - queue->mem_info.gdma_region =GDMA_INVALID_DMA_REGION ; + queue->mem_info.dma_region_handle =GDMA_INVALID_DMA_REGION ;return 0 ; }
@@ -666,24 +666,30 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd,return err; } -static void mana_gd_destroy_dma_region (struct gdma_context *gc,u64 gdma_region) +int mana_gd_destroy_dma_region (struct gdma_context *gc, +gdma_obj_handle_t dma_region_handle) {struct gdma_destroy_dma_region_req req = {};struct gdma_general_resp resp = {};int err; -if (gdma_region ==GDMA_INVALID_DMA_REGION ) -return ; +if (dma_region_handle ==GDMA_INVALID_DMA_REGION ) +return 0 ;mana_gd_init_req_hdr (&req.hdr,GDMA_DESTROY_DMA_REGION ,sizeof (req),sizeof (resp)); - req.gdma_region = gdma_region; + req.dma_region_handle = dma_region_handle; err =mana_gd_send_request (gc,sizeof (req), &req,sizeof (resp), &resp); -if (err || resp.hdr.status) +if (err || resp.hdr.status) {dev_err (gc->dev,"Failed to destroy DMA region: %d, 0x%x\n" , err, resp.hdr.status); +return -EPROTO ; + } + +return 0 ; } +EXPORT_SYMBOL_NS (mana_gd_destroy_dma_region,NET_MANA );static int mana_gd_create_dma_region (struct gdma_dev *gd,struct gdma_mem_info *gmi)
@@ -728,14 +734,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd,if (err) goto out; -if (resp.hdr.status || resp.gdma_region ==GDMA_INVALID_DMA_REGION ) { +if (resp.hdr.status || + resp.dma_region_handle ==GDMA_INVALID_DMA_REGION ) {dev_err (gc->dev,"Failed to create DMA region: 0x%x\n" , resp.hdr.status); err = -EPROTO ; goto out; } - gmi->gdma_region = resp.gdma_region; + gmi->dma_region_handle = resp.dma_region_handle; out:kfree (req);return err;
@@ -858,7 +865,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)return ; } -mana_gd_destroy_dma_region (gc, gmi->gdma_region); +mana_gd_destroy_dma_region (gc, gmi->dma_region_handle);mana_gd_free_memory (gmi);kfree (queue); }
drivers/net/ethernet/microsoft/mana/mana_en.c +10 -8
@@ -1523,10 +1523,10 @@ static int mana_create_txq(struct mana_port_context *apc,memset (&wq_spec,0 ,sizeof (wq_spec));memset (&cq_spec,0 ,sizeof (cq_spec)); - wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region; + wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle; wq_spec.queue_size = txq->gdma_sq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id =0 ; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
@@ -1541,8 +1541,10 @@ static int mana_create_txq(struct mana_port_context *apc, txq->gdma_sq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - txq->gdma_sq->mem_info.gdma_region =GDMA_INVALID_DMA_REGION ; - cq->gdma_cq->mem_info.gdma_region =GDMA_INVALID_DMA_REGION ; + txq->gdma_sq->mem_info.dma_region_handle = +GDMA_INVALID_DMA_REGION ; + cq->gdma_cq->mem_info.dma_region_handle = +GDMA_INVALID_DMA_REGION ; txq->gdma_txq_id = txq->gdma_sq->id;
@@ -1753,10 +1755,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,memset (&wq_spec,0 ,sizeof (wq_spec));memset (&cq_spec,0 ,sizeof (cq_spec)); - wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region; + wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle; wq_spec.queue_size = rxq->gdma_rq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id =0 ; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
@@ -1769,8 +1771,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, rxq->gdma_rq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - rxq->gdma_rq->mem_info.gdma_region =GDMA_INVALID_DMA_REGION ; - cq->gdma_cq->mem_info.gdma_region =GDMA_INVALID_DMA_REGION ; + rxq->gdma_rq->mem_info.dma_region_handle =GDMA_INVALID_DMA_REGION ; + cq->gdma_cq->mem_info.dma_region_handle =GDMA_INVALID_DMA_REGION ; rxq->gdma_id = rxq->gdma_rq->id; cq->gdma_id = cq->gdma_cq->id;
include/net/mana/gdma.h +116 -5
175 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v8 12/12 RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to [email protected]From: Long Li <[email protected]>
Add a RDMA VF driver for Microsoft Azure Network Adapter (MANA).
---
Change log:
v2:
Changed coding sytles/formats
Checked undersize for udata length
Changed all logging to use ibdev_xxx()
Avoided page array copy when doing MR
Sorted driver ops
Fixed warnings reported by kernel test robot <[email protected]>
v3:
More coding sytle/format changes
v4:
Process error on hardware vport configuration
v5:
Change licenses to GPL-2.0-only
Fix error handling in mana_ib_gd_create_dma_region()
v6:
rebased to rdma-next
removed redundant initialization to return value in mana_ib_probe() added missing tabs at the end of mana_ib_gd_create_dma_region()
v7:
move mana_gd_destroy_doorbell_page() and mana_gd_allocate_doorbell_page() from GDMA to this driver use ib_umem_find_best_pgsz() for finding page size for registering dma regions with hardware fix a bug that may double free mana_ind_table in mana_ib_create_qp_rss()
add Ajay Sharma <[email protected]> to maintainer list
add details to description in drivers/infiniband/hw/mana/Kconfig
change multiple lines comments to use RDMA style from NETDEV style
change mana_ib_dev_ops to static
use module_auxiliary_driver() in place of module_init and module_exit
move all user-triggerable error messages to debug messages
check for ind_tbl_size overflow in mana_ib_create_qp_rss()
v8:
instead of EFAULT, use return code from ib_copy_from_udata() fix the race condition on mana_cfg_vport()
use return code from mana_gd_allocate_doorbell_page() simplify error handling code in mana_ib_gd_create_dma_region() use U64_MAX in place of ((u64)(~(0ULL)))
remove confusing debug output on vport steering failure fix uninitialized cleanup index i in mana_ib_create_qp_rss()
MAINTAINERS | 9 + drivers/infiniband/Kconfig | 1 + drivers/infiniband/hw/Makefile | 1 + drivers/infiniband/hw/mana/Kconfig | 10 + drivers/infiniband/hw/mana/Makefile | 4 + drivers/infiniband/hw/mana/cq.c | 79 ++++ drivers/infiniband/hw/mana/device.c | 117 ++++++ drivers/infiniband/hw/mana/main.c | 507 ++++++++++++++++++++++++ drivers/infiniband/hw/mana/mana_ib.h | 156 ++++++++ drivers/infiniband/hw/mana/mr.c | 197 +++++++++ drivers/infiniband/hw/mana/qp.c | 506 +++++++++++++++++++++++ drivers/infiniband/hw/mana/wq.c | 115 ++++++ include/net/mana/mana.h | 3 + include/uapi/rdma/ib_user_ioctl_verbs.h | 1 + include/uapi/rdma/mana-abi.h | 66 +++ 15 files changed, 1772 insertions(+) create mode 100644 drivers/infiniband/hw/mana/Kconfig create mode 100644 drivers/infiniband/hw/mana/Makefile create mode 100644 drivers/infiniband/hw/mana/cq.c create mode 100644 drivers/infiniband/hw/mana/device.c create mode 100644 drivers/infiniband/hw/mana/main.c create mode 100644 drivers/infiniband/hw/mana/mana_ib.h create mode 100644 drivers/infiniband/hw/mana/mr.c create mode 100644 drivers/infiniband/hw/mana/qp.c create mode 100644 drivers/infiniband/hw/mana/wq.c create mode 100644 include/uapi/rdma/mana-abi.h
MAINTAINERS +9 -0
@@ -13506,6 +13506,15 @@ F: drivers/scsi/smartpqi/smartpqi*.[ch] F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h +MICROSOFT MANA RDMA DRIVER +M: Long Li <[email protected]> +M: Ajay Sharma <[email protected]> +L: [email protected] +S: Supported +F: drivers/infiniband/hw/mana/ +F: include/net/mana +F: include/uapi/rdma/mana-abi.h + MICROSOFT SURFACE AGGREGATOR TABLET-MODE SWITCH M: Maximilian Luz <[email protected]> L: [email protected]
drivers/infiniband/Kconfig +1 -0
@@ -85,6 +85,7 @@ source "drivers/infiniband/hw/erdma/Kconfig" source "drivers/infiniband/hw/hfi1/Kconfig" source "drivers/infiniband/hw/hns/Kconfig" source "drivers/infiniband/hw/irdma/Kconfig" +source "drivers/infiniband/hw/mana/Kconfig" source "drivers/infiniband/hw/mlx4/Kconfig" source "drivers/infiniband/hw/mlx5/Kconfig" source "drivers/infiniband/hw/mthca/Kconfig"
drivers/infiniband/hw/Makefile +1 -0
@@ -4,6 +4,7 @@ obj-$(CONFIG_INFINIBAND_QIB) += qib/ obj-$(CONFIG_INFINIBAND_CXGB4) += cxgb4/ obj-$(CONFIG_INFINIBAND_EFA) += efa/ obj-$(CONFIG_INFINIBAND_IRDMA) += irdma/ +obj-$(CONFIG_MANA_INFINIBAND) += mana/ obj-$(CONFIG_MLX4_INFINIBAND) += mlx4/ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5/ obj-$(CONFIG_INFINIBAND_OCRDMA) += ocrdma/
drivers/infiniband/hw/mana/Kconfig new file +10 -0
@@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +config MANA_INFINIBAND + tristate "Microsoft Azure Network Adapter support" + depends on NETDEVICES && ETHERNET && PCI && MICROSOFT_MANA + help + This driver provides low-level RDMA support for Microsoft Azure + Network Adapter (MANA). MANA supports RDMA features that can be used + for workloads (e.g. DPDK, MPI etc) that uses RDMA verbs to directly + access hardware from user-mode processes in Microsoft Azure cloud + environment.
drivers/infiniband/hw/mana/Makefile new file +4 -0
@@ -0,0 +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
drivers/infiniband/hw/mana/cq.c new file +79 -0
79 lines not on this page · raw message
drivers/infiniband/hw/mana/device.c new file +117 -0
117 lines not on this page · raw message
drivers/infiniband/hw/mana/main.c new file +507 -0
507 lines not on this page · raw message
drivers/infiniband/hw/mana/mana_ib.h new file +156 -0
156 lines not on this page · raw message
drivers/infiniband/hw/mana/mr.c new file +197 -0
197 lines not on this page · raw message
drivers/infiniband/hw/mana/qp.c new file +506 -0
506 lines not on this page · raw message
drivers/infiniband/hw/mana/wq.c new file +115 -0
115 lines not on this page · raw message
include/net/mana/mana.h +3 -0
@@ -412,6 +412,9 @@ int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);extern const struct ethtool_ops mana_ethtool_ops; +/* A CQ can be created not associated with any EQ */ +#define GDMA_CQ_NO_EQ 0xffff +struct mana_obj_spec {u32 queue_index;u64 gdma_region;
include/uapi/rdma/ib_user_ioctl_verbs.h +1 -0
@@ -251,6 +251,7 @@ enum rdma_driver_id {RDMA_DRIVER_EFA ,RDMA_DRIVER_SIW ,RDMA_DRIVER_ERDMA , + RDMA_DRIVER_MANA, }; enum ib_uverbs_gid_type {
include/uapi/rdma/mana-abi.h new file +66 -0
66 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v8 4/12 net: mana: Set the DMA device max segment size
In reply to [email protected]From: Ajay Sharma <[email protected]>
MANA hardware doesn't have any restrictions on the DMA segment size, set it to the max allowed value.
---
Change log:
v2: Use the max allowed value as the hardware doesn't have any limit
drivers/net/ethernet/microsoft/mana/gdma_main.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/net/ethernet/microsoft/mana/gdma_main.c +6 -0
@@ -1363,6 +1363,12 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)if (err) goto release_region; + err =dma_set_max_seg_size (&pdev->dev,UINT_MAX ); +if (err) { +dev_err (&pdev->dev,"Failed to set dma device segment size\n" ); + goto release_region; + } + err = -ENOMEM ; gc =vzalloc (sizeof (*gc));if (!gc)
Signature · 1 line
2.17.1
PATCH v8 5/12 net: mana: Export Work Queue functions for use by RDMA driver
In reply to [email protected]From: Long Li <[email protected]>
RDMA device may need to create Ethernet device queues for use by Queue Pair type RAW. This allows a user-mode context accesses Ethernet hardware queues. Export the supporting functions for use by the RDMA driver.
---
Change log:
v3: format/coding style changes
v5: remove unused defintions, use EXPORT_SYMBOL_NS, rearrange some defintions to a later patch in the series
drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 + drivers/net/ethernet/microsoft/mana/mana.h | 9 +++++++++ drivers/net/ethernet/microsoft/mana/mana_en.c | 16 +++++++++------- 3 files changed, 19 insertions(+), 7 deletions(-)
drivers/net/ethernet/microsoft/mana/gdma_main.c +1 -0
@@ -152,6 +152,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,return mana_hwc_send_request (hwc, req_len, req, resp_len, resp); } +EXPORT_SYMBOL_NS (mana_gd_send_request,NET_MANA );int mana_gd_alloc_memory (struct gdma_context *gc,unsigned int length,struct gdma_mem_info *gmi)
drivers/net/ethernet/microsoft/mana/mana.h +9 -0
@@ -635,6 +635,15 @@ struct mana_tx_package {struct gdma_posted_wqe_info wqe_info; }; +int mana_create_wq_obj (struct mana_port_context *apc, +mana_handle_t vport, +u32 wq_type,struct mana_obj_spec *wq_spec, +struct mana_obj_spec *cq_spec, +mana_handle_t *wq_obj); + +void mana_destroy_wq_obj (struct mana_port_context *apc,u32 wq_type, +mana_handle_t wq_obj); +int mana_cfg_vport (struct mana_port_context *apc,u32 protection_dom_id,u32 doorbell_pg_id);void mana_uncfg_vport (struct mana_port_context *apc);
drivers/net/ethernet/microsoft/mana/mana_en.c +9 -7
@@ -792,11 +792,11 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,return err; } -static int mana_create_wq_obj (struct mana_port_context *apc, -mana_handle_t vport, -u32 wq_type,struct mana_obj_spec *wq_spec, -struct mana_obj_spec *cq_spec, -mana_handle_t *wq_obj) +int mana_create_wq_obj (struct mana_port_context *apc, +mana_handle_t vport, +u32 wq_type,struct mana_obj_spec *wq_spec, +struct mana_obj_spec *cq_spec, +mana_handle_t *wq_obj) {struct mana_create_wqobj_resp resp = {};struct mana_create_wqobj_req req = {};
@@ -845,9 +845,10 @@ static int mana_create_wq_obj(struct mana_port_context *apc, out:return err; } +EXPORT_SYMBOL_NS (mana_create_wq_obj,NET_MANA ); -static void mana_destroy_wq_obj (struct mana_port_context *apc,u32 wq_type, -mana_handle_t wq_obj) +void mana_destroy_wq_obj (struct mana_port_context *apc,u32 wq_type, +mana_handle_t wq_obj) {struct mana_destroy_wqobj_resp resp = {};struct mana_destroy_wqobj_req req = {};
@@ -872,6 +873,7 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,netdev_err (ndev,"Failed to destroy WQ object: %d, 0x%x\n" , err, resp.hdr.status); } +EXPORT_SYMBOL_NS (mana_destroy_wq_obj,NET_MANA );static void mana_destroy_eq (struct mana_context *ac) {
Signature · 1 line
2.17.1
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to [email protected]Quoted 874 lines
-----Original Message-----
From: [email protected] <[email protected]>
Sent: Thursday, 20 October 2022 00:24
To: K. Y. Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Stephen Hemminger <[email protected]>; Wei Liu <[email protected]>; Dexuan Cui <[email protected]>; David S. Miller <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jason Gunthorpe <[email protected]>; Leon Romanovsky <[email protected]>; [email protected]; [email protected]; Ajay Sharma <[email protected]>
Cc: [email protected]; [email protected]; linux- [email protected]; [email protected]; Long Li <[email protected]>
Subject: [EXTERNAL] [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network AdapterFrom: Long Li <[email protected]>
Add a RDMA VF driver for Microsoft Azure Network Adapter (MANA).
Co-developed-by Ajay Sharma <[email protected]>Signed-off-by Ajay Sharma <[email protected]>Reviewed-by Dexuan Cui <[email protected]>Signed-off-by Long Li <[email protected]>---
Change log:
v2:
Changed coding sytles/formats
Checked undersize for udata length
Changed all logging to useibdev_xxx()
Avoided page array copy when doing MR
Sorted driver ops
Fixed warnings reported by kernel test robot <[email protected]>v3:
More coding sytle/format changesv4:
Process error on hardware vport configurationv5:
Change licenses to GPL-2.0-only
Fix error handling inmana_ib_gd_create_dma_region()v6:
rebased to rdma-next
removed redundant initialization to return value inmana_ib_probe()added missing tabs at the end ofmana_ib_gd_create_dma_region()v7:
movemana_gd_destroy_doorbell_page()andmana_gd_allocate_doorbell_page()from GDMA to this driver
useib_umem_find_best_pgsz()for finding page size for registering dma regions with hardware
fix a bug that may double freemana_ind_tableinmana_ib_create_qp_rss()add Ajay Sharma <[email protected]> to maintainer list add details to description indrivers/infiniband/hw/mana/Kconfigchange multiple lines comments to use RDMA style from NETDEV style changemana_ib_dev_opsto static
usemodule_auxiliary_driver()in place ofmodule_initandmodule_exitmove all user-triggerable error messages to debug messages check forind_tbl_sizeoverflow inmana_ib_create_qp_rss()v8:
instead of EFAULT, use return code fromib_copy_from_udata()fix the race condition onmana_cfg_vport()
use return code frommana_gd_allocate_doorbell_page()simplify error handling code inmana_ib_gd_create_dma_region()useU64_MAXin place of ((u64)(~(0ULL)))
remove confusing debug output on vport steering failure fix uninitialized cleanup index i inmana_ib_create_qp_rss()MAINTAINERS | 9 + drivers/infiniband/Kconfig | 1 + drivers/infiniband/hw/Makefile | 1 + drivers/infiniband/hw/mana/Kconfig | 10 + drivers/infiniband/hw/mana/Makefile | 4 + drivers/infiniband/hw/mana/cq.c | 79 ++++ drivers/infiniband/hw/mana/device.c | 117 ++++++ drivers/infiniband/hw/mana/main.c | 507 ++++++++++++++++++++++++ drivers/infiniband/hw/mana/mana_ib.h | 156 ++++++++ drivers/infiniband/hw/mana/mr.c | 197 +++++++++ drivers/infiniband/hw/mana/qp.c | 506 +++++++++++++++++++++++ drivers/infiniband/hw/mana/wq.c | 115 ++++++ include/net/mana/mana.h | 3 + include/uapi/rdma/ib_user_ioctl_verbs.h | 1 + include/uapi/rdma/mana-abi.h | 66 +++ 15 files changed, 1772 insertions(+) create mode 100644 drivers/infiniband/hw/mana/Kconfig create mode 100644 drivers/infiniband/hw/mana/Makefile create mode 100644 drivers/infiniband/hw/mana/cq.c create mode 100644 drivers/infiniband/hw/mana/device.c create mode 100644 drivers/infiniband/hw/mana/main.c create mode 100644 drivers/infiniband/hw/mana/mana_ib.h create mode 100644 drivers/infiniband/hw/mana/mr.c create mode 100644 drivers/infiniband/hw/mana/qp.c create mode 100644 drivers/infiniband/hw/mana/wq.c create mode 100644 include/uapi/rdma/mana-abi.hMAINTAINERS +9
-0@@ -13506,6 +13506,15 @@ F: drivers/scsi/smartpqi/smartpqi*.[ch] F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h +MICROSOFT MANA RDMA DRIVER +M: Long Li <[email protected]> +M: Ajay Sharma <[email protected]> +L: [email protected] +S: Supported +F: drivers/infiniband/hw/mana/ +F: include/net/mana +F: include/uapi/rdma/mana-abi.h + MICROSOFT SURFACE AGGREGATOR TABLET-MODE SWITCH M: Maximilian Luz <[email protected]> L: [email protected]drivers/infiniband/Kconfig +1
-0@@ -85,6 +85,7 @@ source "drivers/infiniband/hw/erdma/Kconfig" source "drivers/infiniband/hw/hfi1/Kconfig" source "drivers/infiniband/hw/hns/Kconfig" source "drivers/infiniband/hw/irdma/Kconfig" +source "drivers/infiniband/hw/mana/Kconfig" source "drivers/infiniband/hw/mlx4/Kconfig" source "drivers/infiniband/hw/mlx5/Kconfig" source "drivers/infiniband/hw/mthca/Kconfig"drivers/infiniband/hw/Makefile +1
-0@@ -4,6 +4,7 @@ obj-$(CONFIG_INFINIBAND_QIB) += qib/ obj-$(CONFIG_INFINIBAND_CXGB4) += cxgb4/ obj-$(CONFIG_INFINIBAND_EFA) += efa/ obj-$(CONFIG_INFINIBAND_IRDMA) += irdma/ +obj-$(CONFIG_MANA_INFINIBAND) += mana/ obj-$(CONFIG_MLX4_INFINIBAND) += mlx4/ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5/ obj-$(CONFIG_INFINIBAND_OCRDMA) += ocrdma/drivers/infiniband/hw/mana/Kconfig new file +7
-0@@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +config MANA_INFINIBAND + tristate "Microsoft Azure Network Adapter support" + depends on NETDEVICES && ETHERNET && PCI && MICROSOFT_MANA + help + This driver provides low-level RDMA support for Microsoft Azure + Network Adapter (MANA). MANA supports RDMA features that can beused
drivers/infiniband/hw/mana/Kconfig new file +3
-0+ for workloads (e.g. DPDK, MPI etc) that uses RDMA verbs to directly + access hardware from user-mode processes in Microsoft Azure cloud + environment.drivers/infiniband/hw/mana/Makefile new file +4
-0@@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o + +mana_ib-y := device.o main.o wq.o qp.o cq.o mr.odrivers/infiniband/hw/mana/cq.c new file +8
-0@@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr*attr,
drivers/infiniband/hw/mana/cq.c new file +14
-0+ struct ib_udata *udata) +{ + struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq); +struct ib_device *ibdev = ibcq->device; +struct mana_ib_create_cq ucmd = {}; +struct mana_ib_dev *mdev; +int err; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + +if (udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/cq.c new file +13
-0+if (err) { +ibdev_dbg (ibdev, +"Failed to copy from udata for create cq, %d\n" , err); +return err; + } + +if (attr->cqe >MAX_SEND_BUFFERS_PER_QUEUE ) { +ibdev_dbg (ibdev,"CQE %d exceeding limit\n" , attr->cqe); +return -EINVAL ; + } + + cq->cqe = attr->cqe; + cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, cq->cqe *
COMP_ENTRY_SIZE,drivers/infiniband/hw/mana/cq.c new file +22
-0+ IB_ACCESS_LOCAL_WRITE); +if (IS_ERR (cq->umem)) { + err =PTR_ERR (cq->umem); +ibdev_dbg (ibdev,"Failed to get umem for create cq, err %d\n" , + err); +return err; + } + + err =mana_ib_gd_create_dma_region (mdev, cq->umem, &cq->gdma_region); +if (err) { +ibdev_dbg (ibdev, +"Failed to create dma region for create cq, %d\n" , + err); + goto err_release_umem; + } + +ibdev_dbg (ibdev, +"mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n" , + err, cq->gdma_region); + +/* +* The CQ ID is not known at this time. The ID is generated at
create_qpdrivers/infiniband/hw/mana/cq.c new file +22
-0+*/ + +return 0 ; + +err_release_umem: +ib_umem_release (cq->umem); +return err; +} + +int mana_ib_destroy_cq (struct ib_cq *ibcq,struct ib_udata *udata) +{ + struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq); +struct ib_device *ibdev = ibcq->device; +struct mana_ib_dev *mdev; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + +mana_ib_gd_destroy_dma_region (mdev, cq->gdma_region); +ib_umem_release (cq->umem); + +return 0 ; +}drivers/infiniband/hw/mana/device.c new file +117
-0@@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" +#include <net/mana/mana_auxiliary.h> + +MODULE_DESCRIPTION ("Microsoft Azure Network Adapter IB driver" ); +MODULE_LICENSE ("GPL" ); +MODULE_IMPORT_NS (NET_MANA ); + +static const struct ib_device_ops mana_ib_dev_ops = { + .owner =THIS_MODULE , + .driver_id =RDMA_DRIVER_MANA , + .uverbs_abi_ver =MANA_IB_UVERBS_ABI_VERSION , + + .alloc_pd = mana_ib_alloc_pd, + .alloc_ucontext = mana_ib_alloc_ucontext, + .create_cq = mana_ib_create_cq, + .create_qp = mana_ib_create_qp, + .create_rwq_ind_table = mana_ib_create_rwq_ind_table, + .create_wq = mana_ib_create_wq, + .dealloc_pd = mana_ib_dealloc_pd, + .dealloc_ucontext = mana_ib_dealloc_ucontext, + .dereg_mr = mana_ib_dereg_mr, + .destroy_cq = mana_ib_destroy_cq, + .destroy_qp = mana_ib_destroy_qp, + .destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table, + .destroy_wq = mana_ib_destroy_wq, + .disassociate_ucontext = mana_ib_disassociate_ucontext, + .get_port_immutable = mana_ib_get_port_immutable, + .mmap = mana_ib_mmap, + .modify_qp = mana_ib_modify_qp, + .modify_wq = mana_ib_modify_wq, + .query_device = mana_ib_query_device, + .query_gid = mana_ib_query_gid, + .query_port = mana_ib_query_port, + .reg_user_mr = mana_ib_reg_user_mr, + +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), +INIT_RDMA_OBJ_SIZE (ib_ucontext, mana_ib_ucontext, ibucontext), +INIT_RDMA_OBJ_SIZE (ib_rwq_ind_table, mana_ib_rwq_ind_table, + ib_ind_table), +}; + +static int mana_ib_probe (struct auxiliary_device *adev, +const struct auxiliary_device_id *id) +{ + struct mana_adev *madev = container_of(adev, struct mana_adev, adev); +struct gdma_dev *mdev = madev->mdev; +struct mana_context *mc; +struct mana_ib_dev *dev; +int ret; + + mc = mdev->driver_data; + + dev =ib_alloc_device (mana_ib_dev, ib_dev); +if (!dev) +return -ENOMEM ; + +ib_set_device_ops (&dev->ib_dev, &mana_ib_dev_ops); + + dev->ib_dev.phys_port_cnt = mc->num_ports; + +ibdev_dbg (&dev->ib_dev,"mdev=%p id=%d num_ports=%d\n" , mdev, + mdev->dev_id.as_uint32, dev->ib_dev.phys_port_cnt); + + dev->gdma_dev = mdev; + dev->ib_dev.node_type =RDMA_NODE_IB_CA ; + +/* +* num_comp_vectors needs to set to the max MSIX index +* when interrupts and event queues are implemented +*/ + dev->ib_dev.num_comp_vectors =1 ; + dev->ib_dev.dev.parent = mdev->gdma_context->dev; + + ret =ib_register_device (&dev->ib_dev,"mana_%d" , + mdev->gdma_context->dev); +if (ret) { +ib_dealloc_device (&dev->ib_dev); +return ret; + } + +dev_set_drvdata (&adev->dev, dev); + +return 0 ; +} + +static void mana_ib_remove (struct auxiliary_device *adev) +{ +struct mana_ib_dev *dev =dev_get_drvdata (&adev->dev); + +ib_unregister_device (&dev->ib_dev); +ib_dealloc_device (&dev->ib_dev); +} + +static const struct auxiliary_device_id mana_id_table[] = { + { + .name ="mana.rdma" , + }, + {}, +}; + +MODULE_DEVICE_TABLE (auxiliary, mana_id_table); + +static struct auxiliary_driver mana_driver = { + .name ="rdma" , + .probe = mana_ib_probe, + .remove = mana_ib_remove, + .id_table = mana_id_table, +}; + +module_auxiliary_driver (mana_driver);drivers/infiniband/hw/mana/main.c new file +31
-0@@ -0,0 +1,507 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +void mana_ib_uncfg_vport (struct mana_ib_dev *dev,struct mana_ib_pd *pd, +u32 port) +{ +struct gdma_dev *gd = dev->gdma_dev; +struct mana_port_context *mpc; +struct net_device *ndev; +struct mana_context *mc; + + mc = gd->driver_data; + ndev = mc->ports[port]; + mpc =netdev_priv (ndev); + +mutex_lock (&pd->vport_mutex); + + pd->vport_use_count--; +WARN_ON (pd->vport_use_count <0 ); + +if (!pd->vport_use_count) +mana_uncfg_vport (mpc); + +mutex_unlock (&pd->vport_mutex); +} + +int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct mana_ib_pd*pd,
drivers/infiniband/hw/mana/main.c new file +129
-0+ u32 doorbell_id) +{ +struct gdma_dev *mdev = dev->gdma_dev; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +int err; + + mc = mdev->driver_data; + ndev = mc->ports[port]; + mpc =netdev_priv (ndev); + +mutex_lock (&pd->vport_mutex); + + pd->vport_use_count++; +if (pd->vport_use_count >1 ) { +ibdev_dbg (&dev->ib_dev, +"Skip as this PD is already configured vport\n" ); +mutex_unlock (&pd->vport_mutex); +return 0 ; + } + + err =mana_cfg_vport (mpc, pd->pdn, doorbell_id); +if (err) { + pd->vport_use_count--; +mutex_unlock (&pd->vport_mutex); + +ibdev_dbg (&dev->ib_dev,"Failed to configure vPort %d\n" , err); +return err; + } + +mutex_unlock (&pd->vport_mutex); + + pd->tx_shortform_allowed = mpc->tx_shortform_allowed; + pd->tx_vp_offset = mpc->tx_vp_offset; + +ibdev_dbg (&dev->ib_dev,"vport handle %llx pdid %x doorbell_id %x\n" , + mpc->port_handle, pd->pdn, doorbell_id); + +return 0 ; +} + +int mana_ib_alloc_pd (struct ib_pd *ibpd,struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd); +struct ib_device *ibdev = ibpd->device; +struct gdma_create_pd_resp resp = {}; +struct gdma_create_pd_req req = {}; +enum gdma_pd_flags flags =0 ; +struct mana_ib_dev *dev; +struct gdma_dev *mdev; +int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + mdev = dev->gdma_dev; + +mana_gd_init_req_hdr (&req.hdr,GDMA_CREATE_PD ,sizeof (req), +sizeof (resp)); + + req.flags = flags; + err =mana_gd_send_request (mdev->gdma_context,sizeof (req), &req, +sizeof (resp), &resp); + +if (err || resp.hdr.status) { +ibdev_dbg (&dev->ib_dev, +"Failed to get pd_id err %d status %u\n" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ; + +return err; + } + + pd->pd_handle = resp.pd_handle; + pd->pdn = resp.pd_id; +ibdev_dbg (&dev->ib_dev,"pd_handle 0x%llx pd_id %d\n" , + pd->pd_handle, pd->pdn); + +mutex_init (&pd->vport_mutex); + pd->vport_use_count =0 ; +return 0 ; +} + +int mana_ib_dealloc_pd (struct ib_pd *ibpd,struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd); +struct ib_device *ibdev = ibpd->device; +struct gdma_destory_pd_resp resp = {}; +struct gdma_destroy_pd_req req = {}; +struct mana_ib_dev *dev; +struct gdma_dev *mdev; +int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + mdev = dev->gdma_dev; + +mana_gd_init_req_hdr (&req.hdr,GDMA_DESTROY_PD ,sizeof (req), +sizeof (resp)); + + req.pd_handle = pd->pd_handle; + err =mana_gd_send_request (mdev->gdma_context,sizeof (req), &req, +sizeof (resp), &resp); + +if (err || resp.hdr.status) { +ibdev_dbg (&dev->ib_dev, +"Failed to destroy pd_handle 0x%llx err %d status %u" , + pd->pd_handle, err, resp.hdr.status); +if (!err) + err = -EPROTO ; + } + +return err; +} + +static int mana_gd_destroy_doorbell_page (struct gdma_context *gc, +int doorbell_page) +{ +struct gdma_destroy_resource_range_req req = {}; +struct gdma_resp_hdr resp = {}; +int err; + +mana_gd_init_req_hdr (&req.hdr,GDMA_DESTROY_RESOURCE_RANGE , +sizeof (req),sizeof (resp)); + + req.resource_type =GDMA_RESOURCE_DOORBELL_PAGE ; + req.num_resources =1 ; + req.allocated_resources = doorbell_page; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/main.c new file +28
-0+if (err || resp.status) { +dev_err (gc->dev, +"Failed to destroy doorbell page: ret %d, 0x%x\n" , + err, resp.status); +return err ?: -EPROTO ; + } + +return 0 ; +} + +static int mana_gd_allocate_doorbell_page (struct gdma_context *gc, +int *doorbell_page) +{ +struct gdma_allocate_resource_range_req req = {}; +struct gdma_allocate_resource_range_resp resp = {}; +int err; + +mana_gd_init_req_hdr (&req.hdr,GDMA_ALLOCATE_RESOURCE_RANGE , +sizeof (req),sizeof (resp)); + + req.resource_type =GDMA_RESOURCE_DOORBELL_PAGE ; + req.num_resources =1 ; + req.alignment =1 ; + +/* Have GDMA start searching from 0 */ + req.allocated_resources =0 ; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/main.c new file +60
-0+if (err || resp.hdr.status) { +dev_err (gc->dev, +"Failed to allocate doorbell page: ret %d, 0x%x\n" , + err, resp.hdr.status); +return err ?: -EPROTO ; + } + + *doorbell_page = resp.allocated_resources; + +return 0 ; +} + +int mana_ib_alloc_ucontext (struct ib_ucontext *ibcontext, +struct ib_udata *udata) +{ +struct mana_ib_ucontext *ucontext = + container_of(ibcontext, struct mana_ib_ucontext, ibucontext); +struct ib_device *ibdev = ibcontext->device; +struct mana_ib_dev *mdev; +struct gdma_context *gc; +struct gdma_dev *dev; +int doorbell_page; +int ret; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + dev = mdev->gdma_dev; + gc = dev->gdma_context; + +/* Allocate a doorbell page index */ + ret =mana_gd_allocate_doorbell_page (gc, &doorbell_page); +if (ret) { +ibdev_dbg (ibdev,"Failed to allocate doorbell page %d\n" , ret); +return ret; + } + +ibdev_dbg (ibdev,"Doorbell page allocated %d\n" , doorbell_page); + + ucontext->doorbell = doorbell_page; + +return 0 ; +} + +void mana_ib_dealloc_ucontext (struct ib_ucontext *ibcontext) +{ +struct mana_ib_ucontext *mana_ucontext = + container_of(ibcontext, struct mana_ib_ucontext, ibucontext); +struct ib_device *ibdev = ibcontext->device; +struct mana_ib_dev *mdev; +struct gdma_context *gc; +int ret; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + gc = mdev->gdma_dev->gdma_context; + + ret =mana_gd_destroy_doorbell_page (gc, mana_ucontext->doorbell); +if (ret) +ibdev_dbg (ibdev,"Failed to destroy doorbell page %d\n" , ret); +} + +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem*umem,
drivers/infiniband/hw/mana/main.c new file +156
-0+ mana_handle_t *gdma_region) +{ +struct gdma_dma_region_add_pages_req *add_req =NULL ; +struct gdma_create_dma_region_resp create_resp = {}; +struct gdma_create_dma_region_req *create_req; +size_t num_pages_cur, num_pages_to_handle; +unsigned int create_req_msg_size; +struct hw_channel_context *hwc; +struct ib_block_iter biter; +size_t max_pgs_create_cmd; +struct gdma_context *gc; +size_t num_pages_total; +struct gdma_dev *mdev; +unsigned long page_sz; +void *request_buf; +unsigned int i; +int err; + + mdev = dev->gdma_dev; + gc = mdev->gdma_context; + hwc = gc->hwc.driver_data; + +/* Hardware requires dma region to align to chosen page size */ + page_sz =ib_umem_find_best_pgsz (umem,PAGE_SZ_BM ,0 ); +if (!page_sz) { +ibdev_dbg (&dev->ib_dev,"failed to find page size.\n" ); +return -ENOMEM ; + } + num_pages_total =ib_umem_num_dma_blocks (umem, page_sz); + + max_pgs_create_cmd = + (hwc->max_req_msg_size -sizeof (*create_req)) /sizeof (u64); + num_pages_to_handle = +min_t (size_t, num_pages_total, max_pgs_create_cmd); + create_req_msg_size = +struct_size (create_req, page_addr_list, num_pages_to_handle); + + request_buf =kzalloc (hwc->max_req_msg_size,GFP_KERNEL ); +if (!request_buf) +return -ENOMEM ; + + create_req = request_buf; +mana_gd_init_req_hdr (&create_req->hdr,GDMA_CREATE_DMA_REGION , + create_req_msg_size,sizeof (create_resp)); + + create_req->length = umem->length; + create_req->offset_in_page = umem->address & (page_sz -1 ); + create_req->gdma_page_type =order_base_2 (page_sz) -PAGE_SHIFT ; + create_req->page_count = num_pages_total; + create_req->page_addr_list_len = num_pages_to_handle; + +ibdev_dbg (&dev->ib_dev,"size_dma_region %lu num_pages_total %lu\n" , + umem->length, num_pages_total); + +ibdev_dbg (&dev->ib_dev,"page_sz %lu offset_in_page %u\n" , + page_sz, create_req->offset_in_page); + +ibdev_dbg (&dev->ib_dev,"num_pages_to_handle %lu, gdma_page_type %u" , + num_pages_to_handle, create_req->gdma_page_type); + +__rdma_umem_block_iter_start (&biter, umem, page_sz); + +for (i =0 ; i < num_pages_to_handle; ++i) { +dma_addr_t cur_addr; + +__rdma_block_iter_next (&biter); + cur_addr =rdma_block_iter_dma_address (&biter); + + create_req->page_addr_list[i] = cur_addr; + } + + err =mana_gd_send_request (gc, create_req_msg_size, create_req, +sizeof (create_resp), &create_resp); +if (err || create_resp.hdr.status) { +ibdev_dbg (&dev->ib_dev, +"Failed to create DMA region: %d, 0x%x\n" , err, + create_resp.hdr.status); +if (!err) + err = -EPROTO ; + + goto out; + } + + *gdma_region = create_resp.dma_region_handle; +ibdev_dbg (&dev->ib_dev,"Created DMA region with handle 0x%llx\n" , + *gdma_region); + + num_pages_cur = num_pages_to_handle; + +if (num_pages_cur < num_pages_total) { +unsigned int add_req_msg_size; +size_t max_pgs_add_cmd = + (hwc->max_req_msg_size -sizeof (*add_req)) / +sizeof (u64); + + num_pages_to_handle = +min_t (size_t, num_pages_total - num_pages_cur, + max_pgs_add_cmd); + +/* Calculate the max num of pages that will be handled */ + add_req_msg_size =struct_size (add_req, page_addr_list, + num_pages_to_handle); + add_req = request_buf; + +while (num_pages_cur < num_pages_total) { +struct gdma_general_resp add_resp = {}; +u32 expected_status =0 ; + +if (num_pages_cur + num_pages_to_handle < + num_pages_total) { +/* Status indicating more pages are needed */ + expected_status =GDMA_STATUS_MORE_ENTRIES ; + } + +memset (add_req,0 , add_req_msg_size); + +mana_gd_init_req_hdr (&add_req->hdr, +GDMA_DMA_REGION_ADD_PAGES , + add_req_msg_size, +sizeof (add_resp)); + add_req->dma_region_handle = *gdma_region; + add_req->page_addr_list_len = num_pages_to_handle; + +for (i =0 ; i < num_pages_to_handle; ++i) { +dma_addr_t cur_addr = +rdma_block_iter_dma_address (&biter); + add_req->page_addr_list[i] = cur_addr; +__rdma_block_iter_next (&biter); + +ibdev_dbg (&dev->ib_dev, +"page_addr_list %lu addr 0x%llx\n" , + num_pages_cur + i, cur_addr); + } + + err =mana_gd_send_request (gc, add_req_msg_size, + add_req,sizeof (add_resp), + &add_resp); +if (err || add_resp.hdr.status != expected_status) { +ibdev_dbg (&dev->ib_dev, +"Failed put DMA pages %u: %d,0x%x\n" , + i, err, add_resp.hdr.status); + err = -EPROTO ; +break ; + } + + num_pages_cur += num_pages_to_handle; + num_pages_to_handle = +min_t (size_t, num_pages_total - num_pages_cur, + max_pgs_add_cmd); + add_req_msg_size =sizeof (*add_req) + + num_pages_to_handle *sizeof (u64); + } + } + +if (err) + mana_ib_gd_destroy_dma_region(dev,create_resp.dma_region_handle);
drivers/infiniband/hw/mana/main.c new file +7
-0+ +out: +kfree (request_buf); +return err; +} + +int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev, u64
gdma_region)drivers/infiniband/hw/mana/main.c new file +11
-0+{ +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_context *gc; + + gc = mdev->gdma_context; +ibdev_dbg (&dev->ib_dev,"destroy dma region 0x%llx\n" , gdma_region); + +return mana_gd_destroy_dma_region (gc, gdma_region); +} + +int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct*vma)
drivers/infiniband/hw/mana/main.c new file +48
-0+{ +struct mana_ib_ucontext *mana_ucontext = + container_of(ibcontext, struct mana_ib_ucontext, ibucontext); +struct ib_device *ibdev = ibcontext->device; +struct mana_ib_dev *mdev; +struct gdma_context *gc; +phys_addr_t pfn; +pgprot_t prot; +int ret; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + gc = mdev->gdma_dev->gdma_context; + +if (vma->vm_pgoff !=0 ) { +ibdev_dbg (ibdev,"Unexpected vm_pgoff %lu\n" , vma->vm_pgoff); +return -EINVAL ; + } + +/* Map to the page indexed by ucontext->doorbell */ + pfn = (gc->phys_db_page_base + + gc->db_page_size * mana_ucontext->doorbell) >> +PAGE_SHIFT ; + prot =pgprot_writecombine (vma->vm_page_prot); + + ret =rdma_user_mmap_io (ibcontext, vma, pfn, gc->db_page_size, prot, +NULL ); +if (ret) +ibdev_dbg (ibdev,"can't rdma_user_mmap_io ret %d\n" , ret); +else +ibdev_dbg (ibdev,"mapped I/O pfn 0x%llx page_size %u, ret %d\n" , + pfn, gc->db_page_size, ret); + +return ret; +} + +int mana_ib_get_port_immutable (struct ib_device *ibdev,u32 port_num, +struct ib_port_immutable *immutable) +{ +/* +* This version only support RAW_PACKET +* other values need to be filled for other types +*/ + immutable->core_cap_flags =RDMA_CORE_PORT_RAW_PACKET ; + +return 0 ; +} + +int mana_ib_query_device(struct ib_device *ibdev, struct ib_device_attr*props,
drivers/infiniband/hw/mana/main.c line 473
Quoted 3 lines
drivers/infiniband/hw/mana/main.c new file +3
-0+ struct ib_udata *uhw) +{ + props->max_qp =MANA_MAX_NUM_QUEUES ;
This resource limit is defined, but not enforced during QP creation, so there is no limit on number of QPs?
In general, the driver seem to be rather lazy regarding device resource limits reporting. Only a very limited number of ib_device_attr gets set. I'd expect to see all other values to be zeroed out.
drivers/infiniband/hw/mana/main.c line 484
Quoted 11 lines
drivers/infiniband/hw/mana/main.c new file +11
-0+ props->max_qp_wr =MAX_SEND_BUFFERS_PER_QUEUE ; + +/* +* max_cqe could be potentially much bigger. +* As this version of driver only support RAW QP, set it to the same +* value as max_qp_wr +*/ + props->max_cqe =MAX_SEND_BUFFERS_PER_QUEUE ; + + props->max_mr_size =MANA_IB_MAX_MR_SIZE ; + props->max_mr =INT_MAX ;
How the 24 bit wide MR keys can handle INT_MAX unique MR's?
drivers/infiniband/hw/mana/main.c line 495
Quoted 11 lines
drivers/infiniband/hw/mana/main.c new file +11
-0+ props->max_send_sge =MAX_TX_WQE_SGL_ENTRIES ; + props->max_recv_sge =MAX_RX_WQE_SGL_ENTRIES ; + +return 0 ; +} + +int mana_ib_query_port (struct ib_device *ibdev,u32 port, +struct ib_port_attr *props) +{ +/* This version doesn't return port properties */ +return 0 ;
While I understand the driver is currently used in a proprietary environment only, where even the port state seem not to matter, I am not sure this looks good. Shouldn't the driver better adhere to basic assumptions of its RDMA core environment?
Thanks,
Bernard.
Quoted 1,143 lines
drivers/infiniband/hw/mana/main.c new file +12
-0+} + +int mana_ib_query_gid (struct ib_device *ibdev,u32 port,int index, +union ib_gid *gid) +{ +/* This version doesn't return GID properties */ +return 0 ; +} + +void mana_ib_disassociate_ucontext (struct ib_ucontext *ibcontext) +{ +}drivers/infiniband/hw/mana/mana_ib.h new file +17
-0@@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* +* Copyright (c) 2022 Microsoft Corporation. All rights reserved. +*/ + +#ifndef _MANA_IB_H_ +#define _MANA_IB_H_ + +#include <rdma/ib_verbs.h> +#include <rdma/ib_mad.h> +#include <rdma/ib_umem.h> +#include <rdma/mana-abi.h> +#include <rdma/uverbs_ioctl.h> + +#include <net/mana/mana.h> + +#define PAGE_SZ_BM \
drivers/infiniband/hw/mana/mana_ib.h new file +1
-0+ (SZ_4K | SZ_8K | SZ_16K | SZ_32K | SZ_64K | SZ_128K | SZ_256K |\
drivers/infiniband/hw/mana/mana_ib.h new file +71
-0+ SZ_512K | SZ_1M | SZ_2M) + +/* MANA doesn't have any limit for MR size */ +#define MANA_IB_MAX_MR_SIZE U64_MAX + +struct mana_ib_dev { +struct ib_device ib_dev; +struct gdma_dev *gdma_dev; +}; + +struct mana_ib_wq { +struct ib_wq ibwq; +struct ib_umem *umem; +int wqe; +u32 wq_buf_size; +u64 gdma_region; +u64 id; +mana_handle_t rx_object; +}; + +struct mana_ib_pd { +struct ib_pd ibpd; +u32 pdn; +mana_handle_t pd_handle; + +/* Mutex for sharing access to vport_use_count */ +struct mutex vport_mutex; +int vport_use_count; + +bool tx_shortform_allowed; +u32 tx_vp_offset; +}; + +struct mana_ib_mr { +struct ib_mr ibmr; +struct ib_umem *umem; +mana_handle_t mr_handle; +}; + +struct mana_ib_cq { +struct ib_cq ibcq; +struct ib_umem *umem; +int cqe; +u64 gdma_region; +u64 id; +}; + +struct mana_ib_qp { +struct ib_qp ibqp; + +/* Work queue info */ +struct ib_umem *sq_umem; +int sqe; +u64 sq_gdma_region; +u64 sq_id; +mana_handle_t tx_object; + +/* The port on the IB device, starting with 1 */ +u32 port; +}; + +struct mana_ib_ucontext { +struct ib_ucontext ibucontext; +u32 doorbell; +}; + +struct mana_ib_rwq_ind_table { +struct ib_rwq_ind_table ib_ind_table; +}; + +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem*umem,
drivers/infiniband/hw/mana/mana_ib.h new file +15
-0+ mana_handle_t *gdma_region); + +int mana_ib_gd_destroy_dma_region (struct mana_ib_dev *dev, +mana_handle_t gdma_region); + +struct ib_wq *mana_ib_create_wq (struct ib_pd *pd, +struct ib_wq_init_attr *init_attr, +struct ib_udata *udata); + +int mana_ib_modify_wq (struct ib_wq *wq,struct ib_wq_attr *wq_attr, +u32 wq_attr_mask,struct ib_udata *udata); + +int mana_ib_destroy_wq (struct ib_wq *ibwq,struct ib_udata *udata); + +int mana_ib_create_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_table,drivers/infiniband/hw/mana/mana_ib.h new file +4
-0+struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); + +int mana_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_tbl);drivers/infiniband/hw/mana/mana_ib.h new file +10
-0+ +struct ib_mr *mana_ib_get_dma_mr (struct ib_pd *ibpd,int access_flags); + +struct ib_mr *mana_ib_reg_user_mr (struct ib_pd *pd,u64 start,u64 length, +u64 iova,int access_flags, +struct ib_udata *udata); + +int mana_ib_dereg_mr (struct ib_mr *ibmr,struct ib_udata *udata); + +int mana_ib_create_qp(struct ib_qp *qp, struct ib_qp_init_attr
*qp_init_attr,drivers/infiniband/hw/mana/mana_ib.h new file +13
-0+ struct ib_udata *udata); + +int mana_ib_modify_qp (struct ib_qp *ibqp,struct ib_qp_attr *attr, +int attr_mask,struct ib_udata *udata); + +int mana_ib_destroy_qp (struct ib_qp *ibqp,struct ib_udata *udata); + +int mana_ib_cfg_vport (struct mana_ib_dev *dev,u32 port_id, +struct mana_ib_pd *pd,u32 doorbell_id); +void mana_ib_uncfg_vport (struct mana_ib_dev *dev,struct mana_ib_pd *pd, +u32 port); + +int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr*attr,
drivers/infiniband/hw/mana/mana_ib.h new file +12
-0+ struct ib_udata *udata); + +int mana_ib_destroy_cq (struct ib_cq *ibcq,struct ib_udata *udata); + +int mana_ib_alloc_pd (struct ib_pd *ibpd,struct ib_udata *udata); +int mana_ib_dealloc_pd (struct ib_pd *ibpd,struct ib_udata *udata); + +int mana_ib_alloc_ucontext (struct ib_ucontext *ibcontext, +struct ib_udata *udata); +void mana_ib_dealloc_ucontext (struct ib_ucontext *ibcontext); + +int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct*vma);
drivers/infiniband/hw/mana/mana_ib.h new file +4
-0+ +int mana_ib_get_port_immutable (struct ib_device *ibdev,u32 port_num, +struct ib_port_immutable *immutable); +int mana_ib_query_device(struct ib_device *ibdev, struct ib_device_attr*props,
drivers/infiniband/hw/mana/mana_ib.h new file +9
-0+ struct ib_udata *uhw); +int mana_ib_query_port (struct ib_device *ibdev,u32 port, +struct ib_port_attr *props); +int mana_ib_query_gid (struct ib_device *ibdev,u32 port,int index, +union ib_gid *gid); + +void mana_ib_disassociate_ucontext (struct ib_ucontext *ibcontext); + +#endif drivers/infiniband/hw/mana/mr.c new file +8
-0@@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +#define VALID_MR_FLAGS \
drivers/infiniband/hw/mana/mr.c new file +1
-0+ (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
IB_ACCESS_REMOTE_READ)drivers/infiniband/hw/mana/mr.c new file +19
-0+ +static enum gdma_mr_access_flags +mana_ib_verbs_to_gdma_access_flags (int access_flags) +{ +enum gdma_mr_access_flags flags =GDMA_ACCESS_FLAG_LOCAL_READ ; + +if (access_flags &IB_ACCESS_LOCAL_WRITE ) + flags |=GDMA_ACCESS_FLAG_LOCAL_WRITE ; + +if (access_flags &IB_ACCESS_REMOTE_WRITE ) + flags |=GDMA_ACCESS_FLAG_REMOTE_WRITE ; + +if (access_flags &IB_ACCESS_REMOTE_READ ) + flags |=GDMA_ACCESS_FLAG_REMOTE_READ ; + +return flags; +} + +static int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct mana_ib_mr*mr,
drivers/infiniband/hw/mana/mr.c new file +30
-0+ struct gdma_create_mr_params *mr_params) +{ +struct gdma_create_mr_response resp = {}; +struct gdma_create_mr_request req = {}; +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context; + +mana_gd_init_req_hdr (&req.hdr,GDMA_CREATE_MR ,sizeof (req), +sizeof (resp)); + req.pd_handle = mr_params->pd_handle; + req.mr_type = mr_params->mr_type; + +switch (mr_params->mr_type) { +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; + req.gva.access_flags = mr_params->gva.access_flags; +break ; + +default : +ibdev_dbg (&dev->ib_dev, +"invalid param (GDMA_MR_TYPE) passed, type %d\n" , + req.mr_type); +return -EINVAL ; + } + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/mr.c new file +18
-0+ +if (err || resp.hdr.status) { +ibdev_dbg (&dev->ib_dev,"Failed to create mr %d, %u" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ; + +return err; + } + + mr->ibmr.lkey = resp.lkey; + mr->ibmr.rkey = resp.rkey; + mr->mr_handle = resp.mr_handle; + +return 0 ; +} + +static int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev,
gdma_obj_handle_tmr_handle)drivers/infiniband/hw/mana/mr.c new file +15
-0+{ +struct gdma_destroy_mr_response resp = {}; +struct gdma_destroy_mr_request req = {}; +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context; + +mana_gd_init_req_hdr (&req.hdr,GDMA_DESTROY_MR ,sizeof (req), +sizeof (resp)); + + req.mr_handle = mr_handle; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/mr.c new file +12
-0+if (err || resp.hdr.status) { +dev_err (gc->dev,"Failed to destroy MR: %d, 0x%x\n" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ; +return err; + } + +return 0 ; +} + +struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64length,
drivers/infiniband/hw/mana/mr.c new file +33
-0+ u64 iova, int access_flags, + struct ib_udata *udata) +{ + 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; +gdma_obj_handle_t dma_region_handle; +struct mana_ib_dev *dev; +struct mana_ib_mr *mr; +int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + +ibdev_dbg (ibdev, +"start 0x%llx, iova 0x%llx length 0x%llx access_flags 0x%x" , + start, iova, length, access_flags); + +if (access_flags & ~VALID_MR_FLAGS ) +return ERR_PTR (-EINVAL ); + + mr =kzalloc (sizeof (*mr),GFP_KERNEL ); +if (!mr) +return ERR_PTR (-ENOMEM ); + + mr->umem =ib_umem_get (ibdev, start, length, access_flags); +if (IS_ERR (mr->umem)) { + err =PTR_ERR (mr->umem); +ibdev_dbg (ibdev, +"Failed to get umem for register user-mr, %d\n" , err); + goto err_free; + } + + err = mana_ib_gd_create_dma_region(dev, mr->umem,
&dma_region_handle);drivers/infiniband/hw/mana/mr.c new file +61
-0+if (err) { +ibdev_dbg (ibdev,"Failed create dma region for user-mr, %d\n" , + err); + goto err_umem; + } + +ibdev_dbg (ibdev, +"mana_ib_gd_create_dma_region ret %d gdma_region %llx\n" , err, + dma_region_handle); + + mr_params.pd_handle = pd->pd_handle; + mr_params.mr_type =GDMA_MR_TYPE_GVA ; + mr_params.gva.dma_region_handle = dma_region_handle; + mr_params.gva.virtual_address = iova; + mr_params.gva.access_flags = +mana_ib_verbs_to_gdma_access_flags (access_flags); + + err =mana_ib_gd_create_mr (dev, mr, &mr_params); +if (err) + goto err_dma_region; + +/* +* There is no need to keep track of dma_region_handle after MR is +* successfully created. The dma_region_handle is tracked in the PF +* as part of the lifecycle of this MR. +*/ + +return &mr->ibmr; + +err_dma_region: +mana_gd_destroy_dma_region (dev->gdma_dev->gdma_context, + dma_region_handle); + +err_umem: +ib_umem_release (mr->umem); + +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); +struct ib_device *ibdev = ibmr->device; +struct mana_ib_dev *dev; +int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + + err =mana_ib_gd_destroy_mr (dev, mr->mr_handle); +if (err) +return err; + +if (mr->umem) +ib_umem_release (mr->umem); + +kfree (mr); + +return 0 ; +}drivers/infiniband/hw/mana/qp.c new file +42
-0@@ -0,0 +1,506 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +static int mana_ib_cfg_vport_steering (struct mana_ib_dev *dev, +struct net_device *ndev, +mana_handle_t default_rxobj, +mana_handle_t ind_table[], +u32 log_ind_tbl_size,u32 rx_hash_key_len, +u8 *rx_hash_key) +{ +struct mana_port_context *mpc =netdev_priv (ndev); +struct mana_cfg_rx_steer_req *req =NULL ; +struct mana_cfg_rx_steer_resp resp = {}; +mana_handle_t *req_indir_tab; +struct gdma_context *gc; +struct gdma_dev *mdev; +u32 req_buf_size; +int i, err; + + mdev = dev->gdma_dev; + gc = mdev->gdma_context; + + req_buf_size = +sizeof (*req) +sizeof (mana_handle_t) *MANA_INDIRECT_TABLE_SIZE ; + req =kzalloc (req_buf_size,GFP_KERNEL ); +if (!req) +return -ENOMEM ; + +mana_gd_init_req_hdr (&req->hdr,MANA_CONFIG_VPORT_RX , req_buf_size, +sizeof (resp)); + + req->vport = mpc->port_handle; + req->rx_enable =1 ; + req->update_default_rxobj =1 ; + req->default_rxobj = default_rxobj; + req->hdr.dev_id = mdev->dev_id; + +/* If there are more than 1 entries in indirection table, enable RSS */
drivers/infiniband/hw/mana/qp.c new file +13
-0+if (log_ind_tbl_size) + req->rss_enable = true; + + req->num_indir_entries =MANA_INDIRECT_TABLE_SIZE ; + req->indir_tab_offset =sizeof (*req); + req->update_indir_tab = true; + + req_indir_tab = (mana_handle_t *)(req +1 ); +/* The ind table passed to the hardware must have +* MANA_INDIRECT_TABLE_SIZE entries. Adjust the verb +* ind_table to MANA_INDIRECT_TABLE_SIZE if required +*/ + ibdev_dbg(&dev->ib_dev, "ind table size %u\n", 1 <<
log_ind_tbl_size);drivers/infiniband/hw/mana/qp.c new file +16
-0+for (i =0 ; i <MANA_INDIRECT_TABLE_SIZE ; i++) { + req_indir_tab[i] = ind_table[i % (1 << log_ind_tbl_size)]; +ibdev_dbg (&dev->ib_dev,"index %u handle 0x%llx\n" , i, + req_indir_tab[i]); + } + + req->update_hashkey = true; +if (rx_hash_key_len) +memcpy (req->hashkey, rx_hash_key, rx_hash_key_len); +else +netdev_rss_key_fill (req->hashkey,MANA_HASH_KEY_SIZE ); + +ibdev_dbg (&dev->ib_dev,"vport handle %llu default_rxobj 0x%llx\n" , + req->vport, default_rxobj); + + err = mana_gd_send_request(gc, req_buf_size, req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/qp.c new file +50
-0+if (err) { +netdev_err (ndev,"Failed to configure vPort RX: %d\n" , err); + goto out; + } + +if (resp.hdr.status) { +netdev_err (ndev,"vPort RX configuration failed: 0x%x\n" , + resp.hdr.status); + err = -EPROTO ; + goto out; + } + +netdev_info (ndev,"Configured steering vPort %llu log_entries %u\n" , + mpc->port_handle, log_ind_tbl_size); + +out: +kfree (req); +return err; +} + +static int mana_ib_create_qp_rss (struct ib_qp *ibqp,struct ib_pd *pd, +struct ib_qp_init_attr *attr, +struct ib_udata *udata) +{ + struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); +struct mana_ib_dev *mdev = + container_of(pd->device, struct mana_ib_dev, ib_dev); +struct ib_rwq_ind_table *ind_tbl = attr->rwq_ind_tbl; +struct mana_ib_create_qp_rss_resp resp = {}; +struct mana_ib_create_qp_rss ucmd = {}; +struct gdma_dev *gd = mdev->gdma_dev; +mana_handle_t *mana_ind_table; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct mana_ib_cq *cq; +struct mana_ib_wq *wq; +unsigned int ind_tbl_size; +struct ib_cq *ibcq; +struct ib_wq *ibwq; +int i =0 ; +u32 port; +int ret; + + mc = gd->driver_data; + +if (!udata || udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + ret = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/qp.c new file +162
-0+if (ret) { +ibdev_dbg (&mdev->ib_dev, +"Failed copy from udata for create rss-qp, err %d\n" , + ret); +return ret; + } + +if (attr->cap.max_recv_wr >MAX_SEND_BUFFERS_PER_QUEUE ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_recv_wr %d exceeding limit\n" , + attr->cap.max_recv_wr); +return -EINVAL ; + } + +if (attr->cap.max_recv_sge >MAX_RX_WQE_SGL_ENTRIES ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_recv_sge %d exceeding limit\n" , + attr->cap.max_recv_sge); +return -EINVAL ; + } + + ind_tbl_size =1 << ind_tbl->log_ind_tbl_size; +if (ind_tbl_size >MANA_INDIRECT_TABLE_SIZE ) { +ibdev_dbg (&mdev->ib_dev, +"Indirect table size %d exceeding limit\n" , + ind_tbl_size); +return -EINVAL ; + } + +if (ucmd.rx_hash_function !=MANA_IB_RX_HASH_FUNC_TOEPLITZ ) { +ibdev_dbg (&mdev->ib_dev, +"RX Hash function is not supported, %d\n" , + ucmd.rx_hash_function); +return -EINVAL ; + } + +/* IB ports start with 1, MANA start with 0 */ + port = ucmd.port; +if (port <1 || port > mc->num_ports) { +ibdev_dbg (&mdev->ib_dev,"Invalid port %u in creating qp\n" , + port); +return -EINVAL ; + } + ndev = mc->ports[port -1 ]; + mpc =netdev_priv (ndev); + +ibdev_dbg (&mdev->ib_dev,"rx_hash_function %d port %d\n" , + ucmd.rx_hash_function, port); + + mana_ind_table =kcalloc (ind_tbl_size,sizeof (mana_handle_t), +GFP_KERNEL ); +if (!mana_ind_table) { + ret = -ENOMEM ; + goto fail; + } + + qp->port = port; + +for (i =0 ; i < ind_tbl_size; i++) { +struct mana_obj_spec wq_spec = {}; +struct mana_obj_spec cq_spec = {}; + + ibwq = ind_tbl->ind_tbl[i]; + wq = container_of(ibwq, struct mana_ib_wq, ibwq); + + ibcq = ibwq->cq; + cq = container_of(ibcq, struct mana_ib_cq, ibcq); + + wq_spec.gdma_region = wq->gdma_region; + wq_spec.queue_size = wq->wq_buf_size; + + cq_spec.gdma_region = cq->gdma_region; + cq_spec.queue_size = cq->cqe *COMP_ENTRY_SIZE ; + cq_spec.modr_ctx_id =0 ; + cq_spec.attached_eq =GDMA_CQ_NO_EQ ; + + ret =mana_create_wq_obj (mpc, mpc->port_handle,GDMA_RQ , + &wq_spec, &cq_spec, &wq->rx_object); +if (ret) + goto fail; + +/* The GDMA regions are now owned by the WQ object */ + wq->gdma_region =GDMA_INVALID_DMA_REGION ; + cq->gdma_region =GDMA_INVALID_DMA_REGION ; + + wq->id = wq_spec.queue_index; + cq->id = cq_spec.queue_index; + +ibdev_dbg (&mdev->ib_dev, +"ret %d rx_object 0x%llx wq id %llu cq id %llu\n" , + ret, wq->rx_object, wq->id, cq->id); + + resp.entries[i].cqid = cq->id; + resp.entries[i].wqid = wq->id; + + mana_ind_table[i] = wq->rx_object; + } + resp.num_entries = i; + + ret =mana_ib_cfg_vport_steering (mdev, ndev, wq->rx_object, + mana_ind_table, + ind_tbl->log_ind_tbl_size, + ucmd.rx_hash_key_len, + ucmd.rx_hash_key); +if (ret) + goto fail; + + ret =ib_copy_to_udata (udata, &resp,sizeof (resp)); +if (ret) { +ibdev_dbg (&mdev->ib_dev, +"Failed to copy to udata create rss-qp, %d\n" , + ret); + goto fail; + } + +kfree (mana_ind_table); + +return 0 ; + +fail: +while (i-- >0 ) { + ibwq = ind_tbl->ind_tbl[i]; + wq = container_of(ibwq, struct mana_ib_wq, ibwq); +mana_destroy_wq_obj (mpc,GDMA_RQ , wq->rx_object); + } + +kfree (mana_ind_table); + +return ret; +} + +static int mana_ib_create_qp_raw (struct ib_qp *ibqp,struct ib_pd *ibpd, +struct ib_qp_init_attr *attr, +struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd); + struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); +struct mana_ib_dev *mdev = + container_of(ibpd->device, struct mana_ib_dev, ib_dev); +struct mana_ib_cq *send_cq = + container_of(attr->send_cq, struct mana_ib_cq, ibcq); +struct mana_ib_ucontext *mana_ucontext = + rdma_udata_to_drv_context(udata, struct mana_ib_ucontext, + ibucontext); +struct mana_ib_create_qp_resp resp = {}; +struct gdma_dev *gd = mdev->gdma_dev; +struct mana_ib_create_qp ucmd = {}; +struct mana_obj_spec wq_spec = {}; +struct mana_obj_spec cq_spec = {}; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct ib_umem *umem; +int err; +u32 port; + + mc = gd->driver_data; + +if (!mana_ucontext || udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/qp.c new file +28
-0+if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to copy from udata create qp-raw, %d\n" , err); +return err; + } + +/* IB ports start with 1, MANA Ethernet ports start with 0 */ + port = ucmd.port; +if (ucmd.port > mc->num_ports) +return -EINVAL ; + +if (attr->cap.max_send_wr >MAX_SEND_BUFFERS_PER_QUEUE ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_send_wr %d exceeding limit\n" , + attr->cap.max_send_wr); +return -EINVAL ; + } + +if (attr->cap.max_send_sge >MAX_TX_WQE_SGL_ENTRIES ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_send_sge %d exceeding limit\n" , + attr->cap.max_send_sge); +return -EINVAL ; + } + + ndev = mc->ports[port -1 ]; + mpc =netdev_priv (ndev); + ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port, ndev,mpc);
drivers/infiniband/hw/mana/qp.c new file +149
-0+ + err =mana_ib_cfg_vport (mdev, port -1 , pd, mana_ucontext->doorbell); +if (err) +return -ENODEV ; + + qp->port = port; + +ibdev_dbg (&mdev->ib_dev,"ucmd sq_buf_addr 0x%llx port %u\n" , + ucmd.sq_buf_addr, ucmd.port); + + umem =ib_umem_get (ibpd->device, ucmd.sq_buf_addr, ucmd.sq_buf_size, +IB_ACCESS_LOCAL_WRITE ); +if (IS_ERR (umem)) { + err =PTR_ERR (umem); +ibdev_dbg (&mdev->ib_dev, +"Failed to get umem for create qp-raw, err %d\n" , + err); + goto err_free_vport; + } + qp->sq_umem = umem; + + err =mana_ib_gd_create_dma_region (mdev, qp->sq_umem, + &qp->sq_gdma_region); +if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to create dma region for create qp-raw, %d\n" , + err); + goto err_release_umem; + } + +ibdev_dbg (&mdev->ib_dev, +"mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n" , + err, qp->sq_gdma_region); + +/* Create a WQ on the same port handle used by the Ethernet */ + wq_spec.gdma_region = qp->sq_gdma_region; + wq_spec.queue_size = ucmd.sq_buf_size; + + cq_spec.gdma_region = send_cq->gdma_region; + cq_spec.queue_size = send_cq->cqe *COMP_ENTRY_SIZE ; + cq_spec.modr_ctx_id =0 ; + cq_spec.attached_eq =GDMA_CQ_NO_EQ ; + + err =mana_create_wq_obj (mpc, mpc->port_handle,GDMA_SQ , &wq_spec, + &cq_spec, &qp->tx_object); +if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to create wq for create raw-qp, err %d\n" , + err); + goto err_destroy_dma_region; + } + +/* The GDMA regions are now owned by the WQ object */ + qp->sq_gdma_region =GDMA_INVALID_DMA_REGION ; + send_cq->gdma_region =GDMA_INVALID_DMA_REGION ; + + qp->sq_id = wq_spec.queue_index; + send_cq->id = cq_spec.queue_index; + +ibdev_dbg (&mdev->ib_dev, +"ret %d qp->tx_object 0x%llx sq id %llu cq id %llu\n" , err, + qp->tx_object, qp->sq_id, send_cq->id); + + resp.sqid = qp->sq_id; + resp.cqid = send_cq->id; + resp.tx_vp_offset = pd->tx_vp_offset; + + err =ib_copy_to_udata (udata, &resp,sizeof (resp)); +if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed copy udata for create qp-raw, %d\n" , + err); + goto err_destroy_wq_obj; + } + +return 0 ; + +err_destroy_wq_obj: +mana_destroy_wq_obj (mpc,GDMA_SQ , qp->tx_object); + +err_destroy_dma_region: +mana_ib_gd_destroy_dma_region (mdev, qp->sq_gdma_region); + +err_release_umem: +ib_umem_release (umem); + +err_free_vport: +mana_ib_uncfg_vport (mdev, pd, port -1 ); + +return err; +} + +int mana_ib_create_qp (struct ib_qp *ibqp,struct ib_qp_init_attr *attr, +struct ib_udata *udata) +{ +switch (attr->qp_type) { +case IB_QPT_RAW_PACKET : +/* When rwq_ind_tbl is used, it's for creating WQs for RSS */ +if (attr->rwq_ind_tbl) +return mana_ib_create_qp_rss (ibqp, ibqp->pd, attr, + udata); + +return mana_ib_create_qp_raw (ibqp, ibqp->pd, attr, udata); +default : +/* Creating QP other than IB_QPT_RAW_PACKET is not supported */ +ibdev_dbg (ibqp->device,"Creating QP type %u not supported\n" , + attr->qp_type); + } + +return -EINVAL ; +} + +int mana_ib_modify_qp (struct ib_qp *ibqp,struct ib_qp_attr *attr, +int attr_mask,struct ib_udata *udata) +{ +/* modify_qp is not supported by this version of the driver */ +return -EOPNOTSUPP ; +} + +static int mana_ib_destroy_qp_rss (struct mana_ib_qp *qp, +struct ib_rwq_ind_table *ind_tbl, +struct ib_udata *udata) +{ +struct mana_ib_dev *mdev = + container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev); +struct gdma_dev *gd = mdev->gdma_dev; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct mana_ib_wq *wq; +struct ib_wq *ibwq; +int i; + + mc = gd->driver_data; + ndev = mc->ports[qp->port -1 ]; + mpc =netdev_priv (ndev); + +for (i =0 ; i < (1 << ind_tbl->log_ind_tbl_size); i++) { + ibwq = ind_tbl->ind_tbl[i]; + wq = container_of(ibwq, struct mana_ib_wq, ibwq); +ibdev_dbg (&mdev->ib_dev,"destroying wq->rx_object %llu\n" , + wq->rx_object); +mana_destroy_wq_obj (mpc,GDMA_RQ , wq->rx_object); + } + +return 0 ; +} + +static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata*udata)
drivers/infiniband/hw/mana/qp.c new file +46
-0+{ +struct mana_ib_dev *mdev = + container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev); +struct gdma_dev *gd = mdev->gdma_dev; +struct ib_pd *ibpd = qp->ibqp.pd; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct mana_ib_pd *pd; + + mc = gd->driver_data; + ndev = mc->ports[qp->port -1 ]; + mpc =netdev_priv (ndev); + pd = container_of(ibpd, struct mana_ib_pd, ibpd); + +mana_destroy_wq_obj (mpc,GDMA_SQ , qp->tx_object); + +if (qp->sq_umem) { +mana_ib_gd_destroy_dma_region (mdev, qp->sq_gdma_region); +ib_umem_release (qp->sq_umem); + } + +mana_ib_uncfg_vport (mdev, pd, qp->port -1 ); + +return 0 ; +} + +int mana_ib_destroy_qp (struct ib_qp *ibqp,struct ib_udata *udata) +{ + struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); + +switch (ibqp->qp_type) { +case IB_QPT_RAW_PACKET : +if (ibqp->rwq_ind_tbl) +return mana_ib_destroy_qp_rss (qp, ibqp->rwq_ind_tbl, + udata); + +return mana_ib_destroy_qp_raw (qp, udata); + +default : +ibdev_dbg (ibqp->device,"Unexpected QP type %u\n" , + ibqp->qp_type); + } + +return -ENOENT ; +}drivers/infiniband/hw/mana/wq.c new file +22
-0@@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +struct ib_wq *mana_ib_create_wq (struct ib_pd *pd, +struct ib_wq_init_attr *init_attr, +struct ib_udata *udata) +{ +struct mana_ib_dev *mdev = + container_of(pd->device, struct mana_ib_dev, ib_dev); +struct mana_ib_create_wq ucmd = {}; +struct mana_ib_wq *wq; +struct ib_umem *umem; +int err; + +if (udata->inlen <sizeof (ucmd)) +return ERR_PTR (-EINVAL ); + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/wq.c new file +11
-0+if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to copy from udata for create wq, %d\n" , err); +return ERR_PTR (err); + } + + wq =kzalloc (sizeof (*wq),GFP_KERNEL ); +if (!wq) +return ERR_PTR (-ENOMEM ); + + ibdev_dbg(&mdev->ib_dev, "ucmd wq_buf_addr 0x%llx\n",ucmd.wq_buf_addr);
drivers/infiniband/hw/mana/wq.c new file +64
-0+ + umem =ib_umem_get (pd->device, ucmd.wq_buf_addr, ucmd.wq_buf_size, +IB_ACCESS_LOCAL_WRITE ); +if (IS_ERR (umem)) { + err =PTR_ERR (umem); +ibdev_dbg (&mdev->ib_dev, +"Failed to get umem for create wq, err %d\n" , err); + goto err_free_wq; + } + + wq->umem = umem; + wq->wqe = init_attr->max_wr; + wq->wq_buf_size = ucmd.wq_buf_size; + wq->rx_object =INVALID_MANA_HANDLE ; + + err =mana_ib_gd_create_dma_region (mdev, wq->umem, &wq->gdma_region); +if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to create dma region for create wq, %d\n" , + err); + goto err_release_umem; + } + +ibdev_dbg (&mdev->ib_dev, +"mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n" , + err, wq->gdma_region); + +/* WQ ID is returned at wq_create time, doesn't know the value yet */ + +return &wq->ibwq; + +err_release_umem: +ib_umem_release (umem); + +err_free_wq: +kfree (wq); + +return ERR_PTR (err); +} + +int mana_ib_modify_wq (struct ib_wq *wq,struct ib_wq_attr *wq_attr, +u32 wq_attr_mask,struct ib_udata *udata) +{ +/* modify_wq is not supported by this version of the driver */ +return -EOPNOTSUPP ; +} + +int mana_ib_destroy_wq (struct ib_wq *ibwq,struct ib_udata *udata) +{ + struct mana_ib_wq *wq = container_of(ibwq, struct mana_ib_wq, ibwq); +struct ib_device *ib_dev = ibwq->device; +struct mana_ib_dev *mdev; + + mdev = container_of(ib_dev, struct mana_ib_dev, ib_dev); + +mana_ib_gd_destroy_dma_region (mdev, wq->gdma_region); +ib_umem_release (wq->umem); + +kfree (wq); + +return 0 ; +} + +int mana_ib_create_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_table,drivers/infiniband/hw/mana/wq.c new file +18
-0+ struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata) +{ +/* +* There is no additional data in ind_table to be maintained by this +* driver, do nothing +*/ +return 0 ; +} + +int mana_ib_destroy_rwq_ind_table (struct ib_rwq_ind_table *ib_rwq_ind_tbl) +{ +/* +* There is no additional data in ind_table to be maintained by this +* driver, do nothing +*/ +return 0 ; +}include/net/mana/mana.h +3
-0@@ -412,6 +412,9 @@ int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);extern const struct ethtool_ops mana_ethtool_ops; +/* A CQ can be created not associated with any EQ */ +#define GDMA_CQ_NO_EQ 0xffff +struct mana_obj_spec {u32 queue_index;include/net/mana/mana.h +0
-0u64 gdma_region;include/uapi/rdma/ib_user_ioctl_verbs.h +1
-0@@ -251,6 +251,7 @@ enum rdma_driver_id {RDMA_DRIVER_EFA ,RDMA_DRIVER_SIW ,RDMA_DRIVER_ERDMA , + RDMA_DRIVER_MANA, }; enum ib_uverbs_gid_type {include/uapi/rdma/mana-abi.h new file +66
-1@@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#ifndef MANA_ABI_USER_H +#define MANA_ABI_USER_H + +#include <linux/types.h> +#include <rdma/ib_user_ioctl_verbs.h> + +/* +* Increment this value if any changes that break userspace ABI +* compatibility are made. +*/ + +#define MANA_IB_UVERBS_ABI_VERSION 1 + +struct mana_ib_create_cq { +__aligned_u64 buf_addr; +}; + +struct mana_ib_create_qp { +__aligned_u64 sq_buf_addr; +__u32 sq_buf_size; +__u32 port; +}; + +struct mana_ib_create_qp_resp { +__u32 sqid; +__u32 cqid; +__u32 tx_vp_offset; +__u32 reserved; +}; + +struct mana_ib_create_wq { +__aligned_u64 wq_buf_addr; +__u32 wq_buf_size; +__u32 reserved; +}; + +/* RX Hash function flags */ +enum mana_ib_rx_hash_function_flags { +MANA_IB_RX_HASH_FUNC_TOEPLITZ =1 <<0 , +}; + +struct mana_ib_create_qp_rss { +__aligned_u64 rx_hash_fields_mask; +__u8 rx_hash_function; +__u8 reserved[7 ]; +__u32 rx_hash_key_len; +__u8 rx_hash_key[40 ]; +__u32 port; +}; + +struct rss_resp_entry { +__u32 cqid; +__u32 wqid; +}; + +struct mana_ib_create_qp_rss_resp { +__aligned_u64 num_entries; +struct rss_resp_entry entries[64 ]; +}; + +#endif --2.17.1
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 927 lines
Subject: RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 5 lines
-----Original Message-----
From: [email protected] <[email protected]>
Sent: Thursday, 20 October 2022 00:24
To: K. Y. Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Stephen Hemminger<[email protected]>; Wei
Quoted 1 line
Liu <[email protected]>; Dexuan Cui <[email protected]>; David S.
Miller
Quoted 2 lines
<[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jason Gunthorpe <[email protected]>; Leon
Romanovsky
Quoted 1 line
Ajay
Quoted 35 lines
Sharma <[email protected]>
Cc: [email protected]; [email protected]; linux- [email protected]; [email protected]; Long Li <[email protected]>
Subject: [EXTERNAL] [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network AdapterFrom: Long Li <[email protected]>
Add a RDMA VF driver for Microsoft Azure Network Adapter (MANA).
Co-developed-by Ajay Sharma <[email protected]>Signed-off-by Ajay Sharma <[email protected]>Reviewed-by Dexuan Cui <[email protected]>Signed-off-by Long Li <[email protected]>---
Change log:
v2:
Changed coding sytles/formats
Checked undersize for udata length
Changed all logging to useibdev_xxx()
Avoided page array copy when doing MR
Sorted driver ops
Fixed warnings reported by kernel test robot <[email protected]>v3:
More coding sytle/format changesv4:
Process error on hardware vport configurationv5:
Change licenses to GPL-2.0-only
Fix error handling inmana_ib_gd_create_dma_region()Quoted 7 lines
v6:
rebased to rdma-next
removed redundant initialization to return value inmana_ib_probe()added missing tabs at the end ofmana_ib_gd_create_dma_region()v7:
movemana_gd_destroy_doorbell_page()and
mana_gd_allocate_doorbell_page()Quoted 21 lines
from GDMA to this driver
useib_umem_find_best_pgsz()for finding page size for registering dma regions with hardware
fix a bug that may double freemana_ind_tableinmana_ib_create_qp_rss()add Ajay Sharma <[email protected]> to maintainer list add details to description indrivers/infiniband/hw/mana/Kconfigchange multiple lines comments to use RDMA style from NETDEV style changemana_ib_dev_opsto static
usemodule_auxiliary_driver()in place ofmodule_initandmodule_exitmove all user-triggerable error messages to debug messages check forind_tbl_sizeoverflow inmana_ib_create_qp_rss()v8:
instead of EFAULT, use return code fromib_copy_from_udata()fix the race condition onmana_cfg_vport()
use return code frommana_gd_allocate_doorbell_page()simplify error handling code inmana_ib_gd_create_dma_region()useU64_MAXin place of ((u64)(~(0ULL)))
remove confusing debug output on vport steering failure fix uninitialized cleanup index i inmana_ib_create_qp_rss()Quoted 8 lines
MAINTAINERS | 9 + drivers/infiniband/Kconfig | 1 + drivers/infiniband/hw/Makefile | 1 + drivers/infiniband/hw/mana/Kconfig | 10 + drivers/infiniband/hw/mana/Makefile | 4 + drivers/infiniband/hw/mana/cq.c | 79 ++++ drivers/infiniband/hw/mana/device.c | 117 ++++++ drivers/infiniband/hw/mana/main.c | 507++++++++++++++++++++++++
Quoted 71 lines
drivers/infiniband/hw/mana/mana_ib.h | 156 ++++++++ drivers/infiniband/hw/mana/mr.c | 197 +++++++++ drivers/infiniband/hw/mana/qp.c | 506 +++++++++++++++++++++++ drivers/infiniband/hw/mana/wq.c | 115 ++++++ include/net/mana/mana.h | 3 + include/uapi/rdma/ib_user_ioctl_verbs.h | 1 + include/uapi/rdma/mana-abi.h | 66 +++ 15 files changed, 1772 insertions(+) create mode 100644 drivers/infiniband/hw/mana/Kconfig create mode 100644 drivers/infiniband/hw/mana/Makefile create mode 100644 drivers/infiniband/hw/mana/cq.c create mode 100644 drivers/infiniband/hw/mana/device.c create mode 100644 drivers/infiniband/hw/mana/main.c create mode 100644 drivers/infiniband/hw/mana/mana_ib.h create mode 100644 drivers/infiniband/hw/mana/mr.c create mode 100644 drivers/infiniband/hw/mana/qp.c create mode 100644 drivers/infiniband/hw/mana/wq.c create mode 100644 include/uapi/rdma/mana-abi.hMAINTAINERS +9
-0@@ -13506,6 +13506,15 @@ F: drivers/scsi/smartpqi/smartpqi*.[ch] F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h +MICROSOFT MANA RDMA DRIVER +M: Long Li <[email protected]> +M: Ajay Sharma <[email protected]> +L: [email protected] +S: Supported +F: drivers/infiniband/hw/mana/ +F: include/net/mana +F: include/uapi/rdma/mana-abi.h + MICROSOFT SURFACE AGGREGATOR TABLET-MODE SWITCH M: Maximilian Luz <[email protected]> L: [email protected]drivers/infiniband/Kconfig +1
-0@@ -85,6 +85,7 @@ source "drivers/infiniband/hw/erdma/Kconfig" source "drivers/infiniband/hw/hfi1/Kconfig" source "drivers/infiniband/hw/hns/Kconfig" source "drivers/infiniband/hw/irdma/Kconfig" +source "drivers/infiniband/hw/mana/Kconfig" source "drivers/infiniband/hw/mlx4/Kconfig" source "drivers/infiniband/hw/mlx5/Kconfig" source "drivers/infiniband/hw/mthca/Kconfig"drivers/infiniband/hw/Makefile +1
-0@@ -4,6 +4,7 @@ obj-$(CONFIG_INFINIBAND_QIB) += qib/ obj-$(CONFIG_INFINIBAND_CXGB4) += cxgb4/ obj-$(CONFIG_INFINIBAND_EFA) += efa/ obj-$(CONFIG_INFINIBAND_IRDMA) += irdma/ +obj-$(CONFIG_MANA_INFINIBAND) += mana/ obj-$(CONFIG_MLX4_INFINIBAND) += mlx4/ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5/ obj-$(CONFIG_INFINIBAND_OCRDMA) += ocrdma/drivers/infiniband/hw/mana/Kconfig new file +0
-0drivers/infiniband/hw/mana/Kconfig line 4
Quoted 4 lines
drivers/infiniband/hw/mana/Kconfig new file +4
-0@@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +config MANA_INFINIBAND + tristate "Microsoft Azure Network Adapter support" + depends on NETDEVICES && ETHERNET && PCI &&
MICROSOFT_MANAdrivers/infiniband/hw/mana/Kconfig
Quoted 3 lines
drivers/infiniband/hw/mana/Kconfig new file +3
-0+ help + This driver provides low-level RDMA support for Microsoft Azure + Network Adapter (MANA). MANA supports RDMA features that canbe
drivers/infiniband/hw/mana/Kconfig
Quoted 3 lines
used
drivers/infiniband/hw/mana/Kconfig new file +2
-0+ for workloads (e.g. DPDK, MPI etc) that uses RDMA verbs to directly + access hardware from user-mode processes in Microsoft Azurecloud
Quoted 57 lines
drivers/infiniband/hw/mana/Kconfig new file +1
-0+ environment.drivers/infiniband/hw/mana/Makefile new file +4
-0@@ -0,0 +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.odrivers/infiniband/hw/mana/cq.c new file +8
-0@@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr*attr,
drivers/infiniband/hw/mana/cq.c new file +14
-0+ struct ib_udata *udata) +{ + struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq); +struct ib_device *ibdev = ibcq->device; +struct mana_ib_create_cq ucmd = {}; +struct mana_ib_dev *mdev; +int err; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + +if (udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/cq.c new file +13
-0+if (err) { +ibdev_dbg (ibdev, +"Failed to copy from udata for create cq, %d\n" , err); +return err; + } + +if (attr->cqe >MAX_SEND_BUFFERS_PER_QUEUE ) { +ibdev_dbg (ibdev,"CQE %d exceeding limit\n" , attr->cqe); +return -EINVAL ; + } + + cq->cqe = attr->cqe; + cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, cq->cqe *
COMP_ENTRY_SIZE,drivers/infiniband/hw/mana/cq.c
Quoted 4 lines
drivers/infiniband/hw/mana/cq.c new file +4
-0+ IB_ACCESS_LOCAL_WRITE); +if (IS_ERR (cq->umem)) { + err =PTR_ERR (cq->umem); + ibdev_dbg(ibdev, "Failed to get umem for create cq,err %d\n",
Quoted 6 lines
drivers/infiniband/hw/mana/cq.c new file +5
-0+ err); +return err; + } + + err = mana_ib_gd_create_dma_region(mdev, cq->umem, &cq-
gdma_region);drivers/infiniband/hw/mana/cq.c
Quoted 9 lines
drivers/infiniband/hw/mana/cq.c new file +9
-0+if (err) { +ibdev_dbg (ibdev, +"Failed to create dma region for create cq, %d\n" , + err); + goto err_release_umem; + } + + ibdev_dbg(ibdev, + "mana_ib_gd_create_dma_region ret %d gdma_region0x%llx\n",
Quoted 76 lines
drivers/infiniband/hw/mana/cq.c new file +4
-0+ err, cq->gdma_region); + +/* +* The CQ ID is not known at this time. The ID is generated at
create_qpdrivers/infiniband/hw/mana/cq.c new file +22
-0+*/ + +return 0 ; + +err_release_umem: +ib_umem_release (cq->umem); +return err; +} + +int mana_ib_destroy_cq (struct ib_cq *ibcq,struct ib_udata *udata) +{ + struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq); +struct ib_device *ibdev = ibcq->device; +struct mana_ib_dev *mdev; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + +mana_ib_gd_destroy_dma_region (mdev, cq->gdma_region); +ib_umem_release (cq->umem); + +return 0 ; +}drivers/infiniband/hw/mana/device.c new file +42
-0@@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" +#include <net/mana/mana_auxiliary.h> + +MODULE_DESCRIPTION ("Microsoft Azure Network Adapter IB driver" ); +MODULE_LICENSE ("GPL" ); +MODULE_IMPORT_NS (NET_MANA ); + +static const struct ib_device_ops mana_ib_dev_ops = { + .owner =THIS_MODULE , + .driver_id =RDMA_DRIVER_MANA , + .uverbs_abi_ver =MANA_IB_UVERBS_ABI_VERSION , + + .alloc_pd = mana_ib_alloc_pd, + .alloc_ucontext = mana_ib_alloc_ucontext, + .create_cq = mana_ib_create_cq, + .create_qp = mana_ib_create_qp, + .create_rwq_ind_table = mana_ib_create_rwq_ind_table, + .create_wq = mana_ib_create_wq, + .dealloc_pd = mana_ib_dealloc_pd, + .dealloc_ucontext = mana_ib_dealloc_ucontext, + .dereg_mr = mana_ib_dereg_mr, + .destroy_cq = mana_ib_destroy_cq, + .destroy_qp = mana_ib_destroy_qp, + .destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table, + .destroy_wq = mana_ib_destroy_wq, + .disassociate_ucontext = mana_ib_disassociate_ucontext, + .get_port_immutable = mana_ib_get_port_immutable, + .mmap = mana_ib_mmap, + .modify_qp = mana_ib_modify_qp, + .modify_wq = mana_ib_modify_wq, + .query_device = mana_ib_query_device, + .query_gid = mana_ib_query_gid, + .query_port = mana_ib_query_port, + .reg_user_mr = mana_ib_reg_user_mr, + +INIT_RDMA_OBJ_SIZE (ib_cq, mana_ib_cq, ibcq), +INIT_RDMA_OBJ_SIZE (ib_pd, mana_ib_pd, ibpd),drivers/infiniband/hw/mana/device.c line 52
Quoted 10 lines
drivers/infiniband/hw/mana/device.c new file +10
-0+INIT_RDMA_OBJ_SIZE (ib_qp, mana_ib_qp, ibqp), +INIT_RDMA_OBJ_SIZE (ib_ucontext, mana_ib_ucontext, ibucontext), +INIT_RDMA_OBJ_SIZE (ib_rwq_ind_table, mana_ib_rwq_ind_table, + ib_ind_table), +}; + +static int mana_ib_probe (struct auxiliary_device *adev, +const struct auxiliary_device_id *id) +{ + struct mana_adev *madev = container_of(adev, struct mana_adev,adev);
Quoted 6 lines
drivers/infiniband/hw/mana/device.c new file +6
-0+struct gdma_dev *mdev = madev->mdev; +struct mana_context *mc; +struct mana_ib_dev *dev; +int ret; + + mc = mdev->driver_data;drivers/infiniband/hw/mana/device.c
Quoted 10 lines
drivers/infiniband/hw/mana/device.c new file +10
-0+ + dev =ib_alloc_device (mana_ib_dev, ib_dev); +if (!dev) +return -ENOMEM ; + +ib_set_device_ops (&dev->ib_dev, &mana_ib_dev_ops); + + dev->ib_dev.phys_port_cnt = mc->num_ports; + + ibdev_dbg(&dev->ib_dev, "mdev=%p id=%d num_ports=%d\n",mdev,
Quoted 56 lines
drivers/infiniband/hw/mana/device.c new file +49
-0+ mdev->dev_id.as_uint32, dev->ib_dev.phys_port_cnt); + + dev->gdma_dev = mdev; + dev->ib_dev.node_type =RDMA_NODE_IB_CA ; + +/* +* num_comp_vectors needs to set to the max MSIX index +* when interrupts and event queues are implemented +*/ + dev->ib_dev.num_comp_vectors =1 ; + dev->ib_dev.dev.parent = mdev->gdma_context->dev; + + ret =ib_register_device (&dev->ib_dev,"mana_%d" , + mdev->gdma_context->dev); +if (ret) { +ib_dealloc_device (&dev->ib_dev); +return ret; + } + +dev_set_drvdata (&adev->dev, dev); + +return 0 ; +} + +static void mana_ib_remove (struct auxiliary_device *adev) +{ +struct mana_ib_dev *dev =dev_get_drvdata (&adev->dev); + +ib_unregister_device (&dev->ib_dev); +ib_dealloc_device (&dev->ib_dev); +} + +static const struct auxiliary_device_id mana_id_table[] = { + { + .name ="mana.rdma" , + }, + {}, +}; + +MODULE_DEVICE_TABLE (auxiliary, mana_id_table); + +static struct auxiliary_driver mana_driver = { + .name ="rdma" , + .probe = mana_ib_probe, + .remove = mana_ib_remove, + .id_table = mana_id_table, +}; + +module_auxiliary_driver (mana_driver);drivers/infiniband/hw/mana/main.c new file +0
-0drivers/infiniband/hw/mana/main.c line 8
Quoted 8 lines
drivers/infiniband/hw/mana/main.c new file +8
-0@@ -0,0 +1,507 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd*pd,
Quoted 13 lines
drivers/infiniband/hw/mana/main.c new file +13
-0+ u32 port) +{ +struct gdma_dev *gd = dev->gdma_dev; +struct mana_port_context *mpc; +struct net_device *ndev; +struct mana_context *mc; + + mc = gd->driver_data; + ndev = mc->ports[port]; + mpc =netdev_priv (ndev); + +mutex_lock (&pd->vport_mutex); +drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ pd->vport_use_count--; +WARN_ON (pd->vport_use_count <0 ); + +if (!pd->vport_use_count) +mana_uncfg_vport (mpc); + +mutex_unlock (&pd->vport_mutex); +} + +int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct
mana_ib_pdQuoted 19 lines
*pd,
drivers/infiniband/hw/mana/main.c new file +18
-0+ u32 doorbell_id) +{ +struct gdma_dev *mdev = dev->gdma_dev; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +int err; + + mc = mdev->driver_data; + ndev = mc->ports[port]; + mpc =netdev_priv (ndev); + +mutex_lock (&pd->vport_mutex); + + pd->vport_use_count++; +if (pd->vport_use_count >1 ) { +ibdev_dbg (&dev->ib_dev, +"Skip as this PD is already configured vport\n" );drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+mutex_unlock (&pd->vport_mutex); +return 0 ; + } + + err =mana_cfg_vport (mpc, pd->pdn, doorbell_id); +if (err) { + pd->vport_use_count--; +mutex_unlock (&pd->vport_mutex); + + ibdev_dbg(&dev->ib_dev, "Failed to configure vPort %d\n",err);
drivers/infiniband/hw/mana/main.c
Quoted 9 lines
drivers/infiniband/hw/mana/main.c new file +9
-0+return err; + } + +mutex_unlock (&pd->vport_mutex); + + pd->tx_shortform_allowed = mpc->tx_shortform_allowed; + pd->tx_vp_offset = mpc->tx_vp_offset; + + ibdev_dbg(&dev->ib_dev, "vport handle %llx pdid %x
doorbell_id%x\n",drivers/infiniband/hw/mana/main.c
Quoted 8 lines
drivers/infiniband/hw/mana/main.c new file +8
-0+ mpc->port_handle, pd->pdn, doorbell_id); + +return 0 ; +} + +int mana_ib_alloc_pd (struct ib_pd *ibpd,struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd,ibpd);
Quoted 6 lines
drivers/infiniband/hw/mana/main.c new file +6
-0+struct ib_device *ibdev = ibpd->device; +struct gdma_create_pd_resp resp = {}; +struct gdma_create_pd_req req = {}; +enum gdma_pd_flags flags =0 ; +struct mana_ib_dev *dev; +struct gdma_dev *mdev;drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + mdev = dev->gdma_dev; + +mana_gd_init_req_hdr (&req.hdr,GDMA_CREATE_PD ,sizeof (req), +sizeof (resp)); + + req.flags = flags; + err = mana_gd_send_request(mdev->gdma_context, sizeof(req),&req,
Quoted 15 lines
drivers/infiniband/hw/mana/main.c new file +15
-0+ sizeof(resp), &resp); + +if (err || resp.hdr.status) { +ibdev_dbg (&dev->ib_dev, +"Failed to get pd_id err %d status %u\n" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ; + +return err; + } + + pd->pd_handle = resp.pd_handle; + pd->pdn = resp.pd_id; + ibdev_dbg(&dev->ib_dev, "pd_handle 0x%llx pd_id %d\n",drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ pd->pd_handle, pd->pdn); + +mutex_init (&pd->vport_mutex); + pd->vport_use_count =0 ; +return 0 ; +} + +int mana_ib_dealloc_pd (struct ib_pd *ibpd,struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd,ibpd);
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+struct ib_device *ibdev = ibpd->device; +struct gdma_destory_pd_resp resp = {}; +struct gdma_destroy_pd_req req = {}; +struct mana_ib_dev *dev; +struct gdma_dev *mdev;drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + mdev = dev->gdma_dev; + +mana_gd_init_req_hdr (&req.hdr,GDMA_DESTROY_PD ,sizeof (req), +sizeof (resp)); + + req.pd_handle = pd->pd_handle; + err = mana_gd_send_request(mdev->gdma_context, sizeof(req),&req,
drivers/infiniband/hw/mana/main.c
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+ sizeof(resp), &resp); + +if (err || resp.hdr.status) { + ibdev_dbg(&dev->ib_dev, + "Failed to destroy pd_handle 0x%llx err %dstatus %u",
Quoted 6 lines
drivers/infiniband/hw/mana/main.c new file +6
-0+ pd->pd_handle, err, resp.hdr.status); +if (!err) + err = -EPROTO ; + } + +return err;drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+} + +static int mana_gd_destroy_doorbell_page (struct gdma_context *gc, +int doorbell_page) +{ +struct gdma_destroy_resource_range_req req = {}; +struct gdma_resp_hdr resp = {}; +int err; + + mana_gd_init_req_hdr(&req.hdr,
GDMA_DESTROY_RESOURCE_RANGE,Quoted 16 lines
drivers/infiniband/hw/mana/main.c new file +7
-0+ sizeof(req), sizeof(resp)); + + req.resource_type =GDMA_RESOURCE_DOORBELL_PAGE ; + req.num_resources =1 ; + req.allocated_resources = doorbell_page; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/main.c new file +8
-0+if (err || resp.status) { +dev_err (gc->dev, +"Failed to destroy doorbell page: ret %d, 0x%x\n" , + err, resp.status); +return err ?: -EPROTO ; + } + +return 0 ;drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+} + +static int mana_gd_allocate_doorbell_page (struct gdma_context *gc, +int *doorbell_page) +{ +struct gdma_allocate_resource_range_req req = {}; +struct gdma_allocate_resource_range_resp resp = {}; +int err; + + mana_gd_init_req_hdr(&req.hdr,
GDMA_ALLOCATE_RESOURCE_RANGE,Quoted 18 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ sizeof(req), sizeof(resp)); + + req.resource_type =GDMA_RESOURCE_DOORBELL_PAGE ; + req.num_resources =1 ; + req.alignment =1 ; + +/* Have GDMA start searching from 0 */ + req.allocated_resources =0 ; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/main.c new file +7
-0+if (err || resp.hdr.status) { +dev_err (gc->dev, +"Failed to allocate doorbell page: ret %d, 0x%x\n" , + err, resp.hdr.status); +return err ?: -EPROTO ; + } +drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ *doorbell_page = resp.allocated_resources; + +return 0 ; +} + +int mana_ib_alloc_ucontext (struct ib_ucontext *ibcontext, +struct ib_udata *udata) +{ +struct mana_ib_ucontext *ucontext = + container_of(ibcontext, struct mana_ib_ucontext,ibucontext);
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+struct ib_device *ibdev = ibcontext->device; +struct mana_ib_dev *mdev; +struct gdma_context *gc; +struct gdma_dev *dev; +int doorbell_page;drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+int ret; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + dev = mdev->gdma_dev; + gc = dev->gdma_context; + +/* Allocate a doorbell page index */ + ret =mana_gd_allocate_doorbell_page (gc, &doorbell_page); +if (ret) { + ibdev_dbg(ibdev, "Failed to allocate doorbell page %d\n",ret);
Quoted 4 lines
drivers/infiniband/hw/mana/main.c new file +4
-0+return ret; + } + +ibdev_dbg (ibdev,"Doorbell page allocated %d\n" , doorbell_page);drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ + ucontext->doorbell = doorbell_page; + +return 0 ; +} + +void mana_ib_dealloc_ucontext (struct ib_ucontext *ibcontext) +{ +struct mana_ib_ucontext *mana_ucontext = + container_of(ibcontext, struct mana_ib_ucontext,ibucontext);
drivers/infiniband/hw/mana/main.c
Quoted 12 lines
drivers/infiniband/hw/mana/main.c new file +9
-0+struct ib_device *ibdev = ibcontext->device; +struct mana_ib_dev *mdev; +struct gdma_context *gc; +int ret; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + gc = mdev->gdma_dev->gdma_context; + + ret = mana_gd_destroy_doorbell_page(gc, mana_ucontext-doorbell);
drivers/infiniband/hw/mana/main.c new file +2
-0+if (ret) + ibdev_dbg(ibdev, "Failed to destroy doorbell page %d\n",ret);
drivers/infiniband/hw/mana/main.c
Quoted 3 lines
drivers/infiniband/hw/mana/main.c new file +3
-0+} + +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct
ib_umemQuoted 23 lines
*umem,
drivers/infiniband/hw/mana/main.c new file +22
-0+ mana_handle_t *gdma_region) +{ +struct gdma_dma_region_add_pages_req *add_req =NULL ; +struct gdma_create_dma_region_resp create_resp = {}; +struct gdma_create_dma_region_req *create_req; +size_t num_pages_cur, num_pages_to_handle; +unsigned int create_req_msg_size; +struct hw_channel_context *hwc; +struct ib_block_iter biter; +size_t max_pgs_create_cmd; +struct gdma_context *gc; +size_t num_pages_total; +struct gdma_dev *mdev; +unsigned long page_sz; +void *request_buf; +unsigned int i; +int err; + + mdev = dev->gdma_dev; + gc = mdev->gdma_context; + hwc = gc->hwc.driver_data; +drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+/* Hardware requires dma region to align to chosen page size */ + page_sz =ib_umem_find_best_pgsz (umem,PAGE_SZ_BM ,0 ); +if (!page_sz) { +ibdev_dbg (&dev->ib_dev,"failed to find page size.\n" ); +return -ENOMEM ; + } + num_pages_total =ib_umem_num_dma_blocks (umem, page_sz); + + max_pgs_create_cmd = + (hwc->max_req_msg_size - sizeof(*create_req)) /sizeof(u64);
drivers/infiniband/hw/mana/main.c
Quoted 4 lines
drivers/infiniband/hw/mana/main.c new file +4
-0+ num_pages_to_handle = +min_t (size_t, num_pages_total, max_pgs_create_cmd); + create_req_msg_size = + struct_size(create_req, page_addr_list,
num_pages_to_handle);drivers/infiniband/hw/mana/main.c
Quoted 7 lines
drivers/infiniband/hw/mana/main.c new file +7
-0+ + request_buf =kzalloc (hwc->max_req_msg_size,GFP_KERNEL ); +if (!request_buf) +return -ENOMEM ; + + create_req = request_buf; + mana_gd_init_req_hdr(&create_req->hdr,
GDMA_CREATE_DMA_REGION,drivers/infiniband/hw/mana/main.c
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+ create_req_msg_size, sizeof(create_resp)); + + create_req->length = umem->length; + create_req->offset_in_page = umem->address & (page_sz -1 ); + create_req->gdma_page_type = order_base_2(page_sz) -
PAGE_SHIFT;drivers/infiniband/hw/mana/main.c
Quoted 4 lines
drivers/infiniband/hw/mana/main.c new file +4
-0+ create_req->page_count = num_pages_total; + create_req->page_addr_list_len = num_pages_to_handle; + + ibdev_dbg(&dev->ib_dev, "size_dma_region %lu
num_pages_total%lu\n",drivers/infiniband/hw/mana/main.c
Quoted 6 lines
drivers/infiniband/hw/mana/main.c new file +6
-0+ umem->length, num_pages_total); + +ibdev_dbg (&dev->ib_dev,"page_sz %lu offset_in_page %u\n" , + page_sz, create_req->offset_in_page); + + ibdev_dbg(&dev->ib_dev, "num_pages_to_handle %lu,
gdma_page_type%u",Quoted 17 lines
drivers/infiniband/hw/mana/main.c new file +17
-0+ num_pages_to_handle, create_req->gdma_page_type); + +__rdma_umem_block_iter_start (&biter, umem, page_sz); + +for (i =0 ; i < num_pages_to_handle; ++i) { +dma_addr_t cur_addr; + +__rdma_block_iter_next (&biter); + cur_addr =rdma_block_iter_dma_address (&biter); + + create_req->page_addr_list[i] = cur_addr; + } + + err =mana_gd_send_request (gc, create_req_msg_size, create_req, +sizeof (create_resp), &create_resp); +if (err || create_resp.hdr.status) { + ibdev_dbg(&dev->ib_dev,drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+"Failed to create DMA region: %d, 0x%x\n" , err, + create_resp.hdr.status); +if (!err) + err = -EPROTO ; + + goto out; + } + + *gdma_region = create_resp.dma_region_handle; + ibdev_dbg(&dev->ib_dev, "Created DMA region with handle0x%llx\n",
Quoted 16 lines
drivers/infiniband/hw/mana/main.c new file +16
-0+ *gdma_region); + + num_pages_cur = num_pages_to_handle; + +if (num_pages_cur < num_pages_total) { +unsigned int add_req_msg_size; +size_t max_pgs_add_cmd = + (hwc->max_req_msg_size -sizeof (*add_req)) / +sizeof (u64); + + num_pages_to_handle = +min_t (size_t, num_pages_total - num_pages_cur, + max_pgs_add_cmd); + +/* Calculate the max num of pages that will be handled */ + add_req_msg_size = struct_size(add_req, page_addr_list,drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ num_pages_to_handle); + add_req = request_buf; + +while (num_pages_cur < num_pages_total) { +struct gdma_general_resp add_resp = {}; +u32 expected_status =0 ; + +if (num_pages_cur + num_pages_to_handle < + num_pages_total) { +/* Status indicating more pages are needed */
drivers/infiniband/hw/mana/main.c
Quoted 1 line
drivers/infiniband/hw/mana/main.c new file +1
-0+ expected_status =
GDMA_STATUS_MORE_ENTRIES;drivers/infiniband/hw/mana/main.c line 371
Quoted 6 lines
drivers/infiniband/hw/mana/main.c new file +6
-0+ } + +memset (add_req,0 , add_req_msg_size); + + mana_gd_init_req_hdr(&add_req->hdr, +
GDMA_DMA_REGION_ADD_PAGES,drivers/infiniband/hw/mana/main.c
Quoted 4 lines
drivers/infiniband/hw/mana/main.c new file +4
-0+ add_req_msg_size, + sizeof(add_resp)); + add_req->dma_region_handle = *gdma_region; + add_req->page_addr_list_len =
num_pages_to_handle;drivers/infiniband/hw/mana/main.c line 377
Quoted 4 lines
drivers/infiniband/hw/mana/main.c new file +4
-0+ +for (i =0 ; i < num_pages_to_handle; ++i) { + dma_addr_t cur_addr = +rdma_block_iter_dma_address(&biter);Quoted 4 lines
drivers/infiniband/hw/mana/main.c new file +4
-0+ add_req->page_addr_list[i] = cur_addr; +__rdma_block_iter_next (&biter); + + ibdev_dbg(&dev->ib_dev,drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+"page_addr_list %lu addr 0x%llx\n" , + num_pages_cur + i, cur_addr); + } + + err =mana_gd_send_request (gc, add_req_msg_size, + add_req,sizeof (add_resp), + &add_resp); +if (err || add_resp.hdr.status != expected_status) { + ibdev_dbg(&dev->ib_dev, + "Failed put DMApages %u: %d,0x%x\n",
drivers/infiniband/hw/mana/main.c
Quoted 8 lines
drivers/infiniband/hw/mana/main.c new file +8
-0+ i, err, add_resp.hdr.status); + err = -EPROTO ; +break ; + } + + num_pages_cur += num_pages_to_handle; + num_pages_to_handle = + min_t(size_t, num_pages_total -
num_pages_cur,drivers/infiniband/hw/mana/main.c
Quoted 3 lines
drivers/infiniband/hw/mana/main.c new file +3
-0+ max_pgs_add_cmd); + add_req_msg_size =sizeof (*add_req) + + num_pages_to_handle *sizeof(u64);
Quoted 14 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+ } + } + +if (err) + mana_ib_gd_destroy_dma_region(dev,create_resp.dma_region_handle);
drivers/infiniband/hw/mana/main.c new file +7
-0+ +out: +kfree (request_buf); +return err; +} + +int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev, u64
gdma_region)drivers/infiniband/hw/mana/main.c
Quoted 6 lines
drivers/infiniband/hw/mana/main.c new file +6
-0+{ +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_context *gc; + + gc = mdev->gdma_context; + ibdev_dbg(&dev->ib_dev, "destroy dma region 0x%llx\n",
gdma_region);drivers/infiniband/hw/mana/main.c
Quoted 9 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+ +return mana_gd_destroy_dma_region (gc, gdma_region); +} + +int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct*vma)
drivers/infiniband/hw/mana/main.c new file +3
-0+{ +struct mana_ib_ucontext *mana_ucontext = + container_of(ibcontext, struct mana_ib_ucontext,ibucontext);
Quoted 13 lines
drivers/infiniband/hw/mana/main.c new file +12
-0+struct ib_device *ibdev = ibcontext->device; +struct mana_ib_dev *mdev; +struct gdma_context *gc; +phys_addr_t pfn; +pgprot_t prot; +int ret; + + mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + gc = mdev->gdma_dev->gdma_context; + +if (vma->vm_pgoff !=0 ) { + ibdev_dbg(ibdev, "Unexpected vm_pgoff %lu\n", vma-
vm_pgoff);drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+return -EINVAL ; + } + +/* Map to the page indexed by ucontext->doorbell */ + pfn = (gc->phys_db_page_base + + gc->db_page_size * mana_ucontext->doorbell) >> +PAGE_SHIFT ; + prot =pgprot_writecombine (vma->vm_page_prot); + + ret = rdma_user_mmap_io(ibcontext, vma, pfn, gc->db_page_size,prot,
drivers/infiniband/hw/mana/main.c
Quoted 3 lines
drivers/infiniband/hw/mana/main.c new file +3
-0+ NULL); +if (ret) + ibdev_dbg(ibdev, "can't rdma_user_mmap_io ret %d\n",ret);
drivers/infiniband/hw/mana/main.c
Quoted 2 lines
drivers/infiniband/hw/mana/main.c new file +2
-0+else + ibdev_dbg(ibdev, "mapped I/O pfn 0x%llx page_size %u,ret %d\n",
Quoted 17 lines
drivers/infiniband/hw/mana/main.c new file +17
-0+ pfn, gc->db_page_size, ret); + +return ret; +} + +int mana_ib_get_port_immutable (struct ib_device *ibdev,u32 port_num, +struct ib_port_immutable *immutable) +{ +/* +* This version only support RAW_PACKET +* other values need to be filled for other types +*/ + immutable->core_cap_flags =RDMA_CORE_PORT_RAW_PACKET ; + +return 0 ; +} +
Quoted 8 lines
drivers/infiniband/hw/mana/main.c line 473
Quoted 5 lines
+int mana_ib_query_device(struct
ib_device*ibdev, structib_device_attr*props,drivers/infiniband/hw/mana/main.c new file +3
-0+ struct ib_udata *uhw) +{ + props->max_qp =MANA_MAX_NUM_QUEUES ;This resource limit is defined, but not enforced during QP creation, so there is no limit on number of QPs?
The limit is enforced by the PF when calling mana_create_wq_obj().
Quoted 5 lines
In general, the driver seem to be rather lazy regarding device resource limits reporting. Only a very limited number of
ib_device_attrgets set. I'd expect to see all other values to be zeroed out.
This version of the driver supports RAW_QP. All the necessary resource limits are exposed for the user-mode to create this QP type. As we are adding RC_QP support, other required resource limits will be reported.
Quoted 16 lines
drivers/infiniband/hw/mana/main.c line 484
Quoted 13 lines
drivers/infiniband/hw/mana/main.c new file +11
-0+ props->max_qp_wr =MAX_SEND_BUFFERS_PER_QUEUE ; + +/* +* max_cqe could be potentially much bigger. +* As this version of driver only support RAW QP, set it to the same +* value as max_qp_wr +*/ + props->max_cqe =MAX_SEND_BUFFERS_PER_QUEUE ; + + props->max_mr_size =MANA_IB_MAX_MR_SIZE ; + props->max_mr =INT_MAX ;How the 24 bit wide MR keys can handle
INT_MAXunique MR's?
Not sure if I understand this correctly, lkey and rkey are u32 in ib_mr.
Quoted 18 lines
drivers/infiniband/hw/mana/main.c line 495
Quoted 12 lines
drivers/infiniband/hw/mana/main.c new file +11
-0+ props->max_send_sge =MAX_TX_WQE_SGL_ENTRIES ; + props->max_recv_sge =MAX_RX_WQE_SGL_ENTRIES ; + +return 0 ; +} + +int mana_ib_query_port (struct ib_device *ibdev,u32 port, +struct ib_port_attr *props) +{ +/* This version doesn't return port properties */ +return 0 ;While I understand the driver is currently used in a proprietary environment only, where even the port state seem not to matter, I am not sure this looks good. Shouldn't the driver better adhere to basic assumptions of its RDMA core environment?
The user space code is for DPDK. They are at:
https://github.com/DPDK/dpdk/tree/main/drivers/net/mana
The RAW_QP implementation provides all necessary values for its targeted usage. I'm not aware of mandatory values that should be reported according to RDMA verbs interface spec. If there are mandatory required values, please point me to the spec, I will add those to the driver.
Thanks,
Long
Quoted 1,194 lines
Thanks,
Bernard.Quoted 100 lines
drivers/infiniband/hw/mana/main.c new file +12
-0+} + +int mana_ib_query_gid (struct ib_device *ibdev,u32 port,int index, +union ib_gid *gid) +{ +/* This version doesn't return GID properties */ +return 0 ; +} + +void mana_ib_disassociate_ucontext (struct ib_ucontext *ibcontext) +{ +}drivers/infiniband/hw/mana/mana_ib.h new file +17
-0@@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* +* Copyright (c) 2022 Microsoft Corporation. All rights reserved. +*/ + +#ifndef _MANA_IB_H_ +#define _MANA_IB_H_ + +#include <rdma/ib_verbs.h> +#include <rdma/ib_mad.h> +#include <rdma/ib_umem.h> +#include <rdma/mana-abi.h> +#include <rdma/uverbs_ioctl.h> + +#include <net/mana/mana.h> + +#define PAGE_SZ_BM \
drivers/infiniband/hw/mana/mana_ib.h new file +1
-0+ (SZ_4K | SZ_8K | SZ_16K | SZ_32K | SZ_64K | SZ_128K | SZ_256K |\
drivers/infiniband/hw/mana/mana_ib.h new file +61
-0+ SZ_512K | SZ_1M | SZ_2M) + +/* MANA doesn't have any limit for MR size */ +#define MANA_IB_MAX_MR_SIZE U64_MAX + +struct mana_ib_dev { +struct ib_device ib_dev; +struct gdma_dev *gdma_dev; +}; + +struct mana_ib_wq { +struct ib_wq ibwq; +struct ib_umem *umem; +int wqe; +u32 wq_buf_size; +u64 gdma_region; +u64 id; +mana_handle_t rx_object; +}; + +struct mana_ib_pd { +struct ib_pd ibpd; +u32 pdn; +mana_handle_t pd_handle; + +/* Mutex for sharing access to vport_use_count */ +struct mutex vport_mutex; +int vport_use_count; + +bool tx_shortform_allowed; +u32 tx_vp_offset; +}; + +struct mana_ib_mr { +struct ib_mr ibmr; +struct ib_umem *umem; +mana_handle_t mr_handle; +}; + +struct mana_ib_cq { +struct ib_cq ibcq; +struct ib_umem *umem; +int cqe; +u64 gdma_region; +u64 id; +}; + +struct mana_ib_qp { +struct ib_qp ibqp; + +/* Work queue info */ +struct ib_umem *sq_umem; +int sqe; +u64 sq_gdma_region; +u64 sq_id; +mana_handle_t tx_object; + +/* The port on the IB device, starting with 1 */ +u32 port; +}; +drivers/infiniband/hw/mana/mana_ib.h
Quoted 10 lines
drivers/infiniband/hw/mana/mana_ib.h new file +10
-0+struct mana_ib_ucontext { +struct ib_ucontext ibucontext; +u32 doorbell; +}; + +struct mana_ib_rwq_ind_table { +struct ib_rwq_ind_table ib_ind_table; +}; + +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct
ib_umemQuoted 22 lines
*umem,
drivers/infiniband/hw/mana/mana_ib.h new file +15
-0+ mana_handle_t *gdma_region); + +int mana_ib_gd_destroy_dma_region (struct mana_ib_dev *dev, +mana_handle_t gdma_region); + +struct ib_wq *mana_ib_create_wq (struct ib_pd *pd, +struct ib_wq_init_attr *init_attr, +struct ib_udata *udata); + +int mana_ib_modify_wq (struct ib_wq *wq,struct ib_wq_attr *wq_attr, +u32 wq_attr_mask,struct ib_udata *udata); + +int mana_ib_destroy_wq (struct ib_wq *ibwq,struct ib_udata *udata); + +int mana_ib_create_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_table,drivers/infiniband/hw/mana/mana_ib.h new file +4
-0+struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); + +int mana_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_tbl);drivers/infiniband/hw/mana/mana_ib.h
Quoted 4 lines
drivers/infiniband/hw/mana/mana_ib.h new file +4
-0+ +struct ib_mr *mana_ib_get_dma_mr (struct ib_pd *ibpd,int access_flags); + +struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64length,
Quoted 7 lines
drivers/infiniband/hw/mana/mana_ib.h new file +6
-0+ u64 iova, int access_flags, + struct ib_udata *udata); + +int mana_ib_dereg_mr (struct ib_mr *ibmr,struct ib_udata *udata); + +int mana_ib_create_qp(struct ib_qp *qp, struct ib_qp_init_attr
*qp_init_attr,drivers/infiniband/hw/mana/mana_ib.h
Quoted 10 lines
drivers/infiniband/hw/mana/mana_ib.h new file +10
-0+ struct ib_udata *udata); + +int mana_ib_modify_qp (struct ib_qp *ibqp,struct ib_qp_attr *attr, +int attr_mask,struct ib_udata *udata); + +int mana_ib_destroy_qp (struct ib_qp *ibqp,struct ib_udata *udata); + +int mana_ib_cfg_vport (struct mana_ib_dev *dev,u32 port_id, +struct mana_ib_pd *pd,u32 doorbell_id); +void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd*pd,
Quoted 49 lines
drivers/infiniband/hw/mana/mana_ib.h new file +3
-0+ u32 port); + +int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr*attr,
drivers/infiniband/hw/mana/mana_ib.h new file +12
-0+ struct ib_udata *udata); + +int mana_ib_destroy_cq (struct ib_cq *ibcq,struct ib_udata *udata); + +int mana_ib_alloc_pd (struct ib_pd *ibpd,struct ib_udata *udata); +int mana_ib_dealloc_pd (struct ib_pd *ibpd,struct ib_udata *udata); + +int mana_ib_alloc_ucontext (struct ib_ucontext *ibcontext, +struct ib_udata *udata); +void mana_ib_dealloc_ucontext (struct ib_ucontext *ibcontext); + +int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct*vma);
drivers/infiniband/hw/mana/mana_ib.h new file +4
-0+ +int mana_ib_get_port_immutable (struct ib_device *ibdev,u32 port_num, +struct ib_port_immutable *immutable); +int mana_ib_query_device(struct ib_device *ibdev, struct ib_device_attr*props,
drivers/infiniband/hw/mana/mana_ib.h new file +9
-0+ struct ib_udata *uhw); +int mana_ib_query_port (struct ib_device *ibdev,u32 port, +struct ib_port_attr *props); +int mana_ib_query_gid (struct ib_device *ibdev,u32 port,int index, +union ib_gid *gid); + +void mana_ib_disassociate_ucontext (struct ib_ucontext *ibcontext); + +#endif drivers/infiniband/hw/mana/mr.c new file +8
-0@@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +#define VALID_MR_FLAGS \
drivers/infiniband/hw/mana/mr.c new file +1
-0+ (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
IB_ACCESS_REMOTE_READ)drivers/infiniband/hw/mana/mr.c
Quoted 5 lines
drivers/infiniband/hw/mana/mr.c new file +5
-0+ +static enum gdma_mr_access_flags +mana_ib_verbs_to_gdma_access_flags (int access_flags) +{ + enum gdma_mr_access_flags flags =
GDMA_ACCESS_FLAG_LOCAL_READ;Quoted 4 lines
drivers/infiniband/hw/mana/mr.c new file +4
-0+ +if (access_flags &IB_ACCESS_LOCAL_WRITE ) + flags |=GDMA_ACCESS_FLAG_LOCAL_WRITE ; +drivers/infiniband/hw/mana/mr.c
Quoted 10 lines
drivers/infiniband/hw/mana/mr.c new file +10
-0+if (access_flags &IB_ACCESS_REMOTE_WRITE ) + flags |=GDMA_ACCESS_FLAG_REMOTE_WRITE ; + +if (access_flags &IB_ACCESS_REMOTE_READ ) + flags |=GDMA_ACCESS_FLAG_REMOTE_READ ; + +return flags; +} + +static int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct
mana_ib_mrQuoted 20 lines
*mr,
drivers/infiniband/hw/mana/mr.c new file +18
-0+ struct gdma_create_mr_params *mr_params) +{ +struct gdma_create_mr_response resp = {}; +struct gdma_create_mr_request req = {}; +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context; + +mana_gd_init_req_hdr (&req.hdr,GDMA_CREATE_MR ,sizeof (req), +sizeof (resp)); + req.pd_handle = mr_params->pd_handle; + req.mr_type = mr_params->mr_type; + +switch (mr_params->mr_type) { +case GDMA_MR_TYPE_GVA : + req.gva.dma_region_handle = mr_params-gva.dma_region_handle;
drivers/infiniband/hw/mana/mr.c
Quoted 7 lines
drivers/infiniband/hw/mana/mr.c new file +7
-0+ req.gva.virtual_address = mr_params->gva.virtual_address; + req.gva.access_flags = mr_params->gva.access_flags; +break ; + +default : + ibdev_dbg(&dev->ib_dev, + "invalid param (GDMA_MR_TYPE) passed,type %d\n",
Quoted 54 lines
drivers/infiniband/hw/mana/mr.c new file +5
-0+ req.mr_type); +return -EINVAL ; + } + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/mr.c new file +18
-0+ +if (err || resp.hdr.status) { +ibdev_dbg (&dev->ib_dev,"Failed to create mr %d, %u" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ; + +return err; + } + + mr->ibmr.lkey = resp.lkey; + mr->ibmr.rkey = resp.rkey; + mr->mr_handle = resp.mr_handle; + +return 0 ; +} + +static int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev,
gdma_obj_handle_tmr_handle)drivers/infiniband/hw/mana/mr.c new file +15
-0+{ +struct gdma_destroy_mr_response resp = {}; +struct gdma_destroy_mr_request req = {}; +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context; + +mana_gd_init_req_hdr (&req.hdr,GDMA_DESTROY_MR ,sizeof (req), +sizeof (resp)); + + req.mr_handle = mr_handle; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/mr.c new file +12
-0+if (err || resp.hdr.status) { +dev_err (gc->dev,"Failed to destroy MR: %d, 0x%x\n" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ; +return err; + } + +return 0 ; +} + +struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64length,
drivers/infiniband/hw/mana/mr.c
Quoted 4 lines
drivers/infiniband/hw/mana/mr.c new file +4
-0+ u64 iova, int access_flags, + struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd,ibpd);
Quoted 15 lines
drivers/infiniband/hw/mana/mr.c new file +15
-0+struct gdma_create_mr_params mr_params = {}; +struct ib_device *ibdev = ibpd->device; +gdma_obj_handle_t dma_region_handle; +struct mana_ib_dev *dev; +struct mana_ib_mr *mr; +int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + +ibdev_dbg (ibdev, +"start 0x%llx, iova 0x%llx length 0x%llx access_flags 0x%x" , + start, iova, length, access_flags); + +if (access_flags & ~VALID_MR_FLAGS ) +return ERR_PTR (-EINVAL );drivers/infiniband/hw/mana/mr.c
Quoted 10 lines
drivers/infiniband/hw/mana/mr.c new file +10
-0+ + mr =kzalloc (sizeof (*mr),GFP_KERNEL ); +if (!mr) +return ERR_PTR (-ENOMEM ); + + mr->umem =ib_umem_get (ibdev, start, length, access_flags); +if (IS_ERR (mr->umem)) { + err =PTR_ERR (mr->umem); + ibdev_dbg(ibdev, + "Failed to get umem for register user-mr, %d\n",err);
drivers/infiniband/hw/mana/mr.c
Quoted 7 lines
drivers/infiniband/hw/mana/mr.c new file +4
-0+ goto err_free; + } + + err = mana_ib_gd_create_dma_region(dev, mr->umem,
&dma_region_handle);drivers/infiniband/hw/mana/mr.c new file +2
-0+if (err) { + ibdev_dbg(ibdev, "Failed create dma region for user-mr, %d\n",
drivers/infiniband/hw/mana/mr.c
Quoted 6 lines
drivers/infiniband/hw/mana/mr.c new file +6
-0+ err); + goto err_umem; + } + + ibdev_dbg(ibdev, + "mana_ib_gd_create_dma_region ret %d
gdma_region%llx\n", err,Quoted 26 lines
drivers/infiniband/hw/mana/mr.c new file +26
-0+ dma_region_handle); + + mr_params.pd_handle = pd->pd_handle; + mr_params.mr_type =GDMA_MR_TYPE_GVA ; + mr_params.gva.dma_region_handle = dma_region_handle; + mr_params.gva.virtual_address = iova; + mr_params.gva.access_flags = +mana_ib_verbs_to_gdma_access_flags (access_flags); + + err =mana_ib_gd_create_mr (dev, mr, &mr_params); +if (err) + goto err_dma_region; + +/* +* There is no need to keep track of dma_region_handle after MR is +* successfully created. The dma_region_handle is tracked in the PF +* as part of the lifecycle of this MR. +*/ + +return &mr->ibmr; + +err_dma_region: +mana_gd_destroy_dma_region (dev->gdma_dev->gdma_context, + dma_region_handle); + +err_umem:drivers/infiniband/hw/mana/mr.c
Quoted 10 lines
drivers/infiniband/hw/mana/mr.c new file +10
-0+ib_umem_release (mr->umem); + +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);
Quoted 26 lines
drivers/infiniband/hw/mana/mr.c new file +17
-0+struct ib_device *ibdev = ibmr->device; +struct mana_ib_dev *dev; +int err; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); + + err =mana_ib_gd_destroy_mr (dev, mr->mr_handle); +if (err) +return err; + +if (mr->umem) +ib_umem_release (mr->umem); + +kfree (mr); + +return 0 ; +}drivers/infiniband/hw/mana/qp.c new file +2
-0@@ -0,0 +1,506 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* drivers/infiniband/hw/mana/qp.c line 12
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +static int mana_ib_cfg_vport_steering (struct mana_ib_dev *dev, +struct net_device *ndev, +mana_handle_t default_rxobj, +mana_handle_t ind_table[], + u32 log_ind_tbl_size, u32
rx_hash_key_len,Quoted 6 lines
drivers/infiniband/hw/mana/qp.c new file +6
-0+ u8 *rx_hash_key) +{ +struct mana_port_context *mpc =netdev_priv (ndev); +struct mana_cfg_rx_steer_req *req =NULL ; +struct mana_cfg_rx_steer_resp resp = {}; +mana_handle_t *req_indir_tab;drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+struct gdma_context *gc; +struct gdma_dev *mdev; +u32 req_buf_size; +int i, err; + + mdev = dev->gdma_dev; + gc = mdev->gdma_context; + + req_buf_size = + sizeof(*req) + sizeof(mana_handle_t) *
MANA_INDIRECT_TABLE_SIZE;drivers/infiniband/hw/mana/qp.c
Quoted 5 lines
drivers/infiniband/hw/mana/qp.c new file +5
-0+ req =kzalloc (req_buf_size,GFP_KERNEL ); +if (!req) +return -ENOMEM ; + + mana_gd_init_req_hdr(&req->hdr, MANA_CONFIG_VPORT_RX,
req_buf_size,Quoted 27 lines
drivers/infiniband/hw/mana/qp.c new file +9
-0+ sizeof(resp)); + + req->vport = mpc->port_handle; + req->rx_enable =1 ; + req->update_default_rxobj =1 ; + req->default_rxobj = default_rxobj; + req->hdr.dev_id = mdev->dev_id; + +/* If there are more than 1 entries in indirection table, enable RSS */
drivers/infiniband/hw/mana/qp.c new file +13
-0+if (log_ind_tbl_size) + req->rss_enable = true; + + req->num_indir_entries =MANA_INDIRECT_TABLE_SIZE ; + req->indir_tab_offset =sizeof (*req); + req->update_indir_tab = true; + + req_indir_tab = (mana_handle_t *)(req +1 ); +/* The ind table passed to the hardware must have +* MANA_INDIRECT_TABLE_SIZE entries. Adjust the verb +* ind_table to MANA_INDIRECT_TABLE_SIZE if required +*/ + ibdev_dbg(&dev->ib_dev, "ind table size %u\n", 1 <<
log_ind_tbl_size);drivers/infiniband/hw/mana/qp.c new file +3
-0+for (i =0 ; i <MANA_INDIRECT_TABLE_SIZE ; i++) { + req_indir_tab[i] = ind_table[i % (1 << log_ind_tbl_size)]; + ibdev_dbg(&dev->ib_dev, "index %u handle 0x%llx\n", i,drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ req_indir_tab[i]); + } + + req->update_hashkey = true; +if (rx_hash_key_len) +memcpy (req->hashkey, rx_hash_key, rx_hash_key_len); +else +netdev_rss_key_fill (req->hashkey,MANA_HASH_KEY_SIZE ); + + ibdev_dbg(&dev->ib_dev, "vport handle %llu default_rxobj0x%llx\n",
Quoted 7 lines
drivers/infiniband/hw/mana/qp.c new file +3
-0+ req->vport, default_rxobj); + + err = mana_gd_send_request(gc, req_buf_size, req, sizeof(resp),&resp);
drivers/infiniband/hw/mana/qp.c new file +3
-0+if (err) { +netdev_err (ndev,"Failed to configure vPort RX: %d\n" , err); + goto out;drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ } + +if (resp.hdr.status) { +netdev_err (ndev,"vPort RX configuration failed: 0x%x\n" , + resp.hdr.status); + err = -EPROTO ; + goto out; + } + + netdev_info(ndev, "Configured steering vPort %llu
log_entries%u\n",drivers/infiniband/hw/mana/qp.c
Quoted 12 lines
drivers/infiniband/hw/mana/qp.c new file +12
-0+ mpc->port_handle, log_ind_tbl_size); + +out: +kfree (req); +return err; +} + +static int mana_ib_create_qp_rss (struct ib_qp *ibqp,struct ib_pd *pd, +struct ib_qp_init_attr *attr, +struct ib_udata *udata) +{ + struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp,ibqp);
Quoted 46 lines
drivers/infiniband/hw/mana/qp.c new file +25
-0+struct mana_ib_dev *mdev = + container_of(pd->device, struct mana_ib_dev, ib_dev); +struct ib_rwq_ind_table *ind_tbl = attr->rwq_ind_tbl; +struct mana_ib_create_qp_rss_resp resp = {}; +struct mana_ib_create_qp_rss ucmd = {}; +struct gdma_dev *gd = mdev->gdma_dev; +mana_handle_t *mana_ind_table; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct mana_ib_cq *cq; +struct mana_ib_wq *wq; +unsigned int ind_tbl_size; +struct ib_cq *ibcq; +struct ib_wq *ibwq; +int i =0 ; +u32 port; +int ret; + + mc = gd->driver_data; + +if (!udata || udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + ret = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/qp.c new file +20
-0+if (ret) { +ibdev_dbg (&mdev->ib_dev, +"Failed copy from udata for create rss-qp, err %d\n" , + ret); +return ret; + } + +if (attr->cap.max_recv_wr >MAX_SEND_BUFFERS_PER_QUEUE ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_recv_wr %d exceeding limit\n" , + attr->cap.max_recv_wr); +return -EINVAL ; + } + +if (attr->cap.max_recv_sge >MAX_RX_WQE_SGL_ENTRIES ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_recv_sge %d exceeding limit\n" , + attr->cap.max_recv_sge); +return -EINVAL ; + }drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ + ind_tbl_size =1 << ind_tbl->log_ind_tbl_size; +if (ind_tbl_size >MANA_INDIRECT_TABLE_SIZE ) { +ibdev_dbg (&mdev->ib_dev, +"Indirect table size %d exceeding limit\n" , + ind_tbl_size); +return -EINVAL ; + } + +if (ucmd.rx_hash_function !=MANA_IB_RX_HASH_FUNC_TOEPLITZ ){
drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ibdev_dbg (&mdev->ib_dev, +"RX Hash function is not supported, %d\n" , + ucmd.rx_hash_function); +return -EINVAL ; + } + +/* IB ports start with 1, MANA start with 0 */ + port = ucmd.port; +if (port <1 || port > mc->num_ports) { + ibdev_dbg(&mdev->ib_dev, "Invalid port %u in creatingqp\n",
Quoted 27 lines
drivers/infiniband/hw/mana/qp.c new file +27
-0+ port); +return -EINVAL ; + } + ndev = mc->ports[port -1 ]; + mpc =netdev_priv (ndev); + +ibdev_dbg (&mdev->ib_dev,"rx_hash_function %d port %d\n" , + ucmd.rx_hash_function, port); + + mana_ind_table =kcalloc (ind_tbl_size,sizeof (mana_handle_t), +GFP_KERNEL ); +if (!mana_ind_table) { + ret = -ENOMEM ; + goto fail; + } + + qp->port = port; + +for (i =0 ; i < ind_tbl_size; i++) { +struct mana_obj_spec wq_spec = {}; +struct mana_obj_spec cq_spec = {}; + + ibwq = ind_tbl->ind_tbl[i]; + wq = container_of(ibwq, struct mana_ib_wq, ibwq); + + ibcq = ibwq->cq; + cq = container_of(ibcq, struct mana_ib_cq, ibcq);drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ + wq_spec.gdma_region = wq->gdma_region; + wq_spec.queue_size = wq->wq_buf_size; + + cq_spec.gdma_region = cq->gdma_region; + cq_spec.queue_size = cq->cqe *COMP_ENTRY_SIZE ; + cq_spec.modr_ctx_id =0 ; + cq_spec.attached_eq =GDMA_CQ_NO_EQ ; + + ret = mana_create_wq_obj(mpc, mpc->port_handle,
GDMA_RQ,Quoted 50 lines
drivers/infiniband/hw/mana/qp.c new file +1
-0+ &wq_spec, &cq_spec, &wq-
rx_object);drivers/infiniband/hw/mana/qp.c new file +48
-0+if (ret) + goto fail; + +/* The GDMA regions are now owned by the WQ object */ + wq->gdma_region =GDMA_INVALID_DMA_REGION ; + cq->gdma_region =GDMA_INVALID_DMA_REGION ; + + wq->id = wq_spec.queue_index; + cq->id = cq_spec.queue_index; + +ibdev_dbg (&mdev->ib_dev, +"ret %d rx_object 0x%llx wq id %llu cq id %llu\n" , + ret, wq->rx_object, wq->id, cq->id); + + resp.entries[i].cqid = cq->id; + resp.entries[i].wqid = wq->id; + + mana_ind_table[i] = wq->rx_object; + } + resp.num_entries = i; + + ret =mana_ib_cfg_vport_steering (mdev, ndev, wq->rx_object, + mana_ind_table, + ind_tbl->log_ind_tbl_size, + ucmd.rx_hash_key_len, + ucmd.rx_hash_key); +if (ret) + goto fail; + + ret =ib_copy_to_udata (udata, &resp,sizeof (resp)); +if (ret) { +ibdev_dbg (&mdev->ib_dev, +"Failed to copy to udata create rss-qp, %d\n" , + ret); + goto fail; + } + +kfree (mana_ind_table); + +return 0 ; + +fail: +while (i-- >0 ) { + ibwq = ind_tbl->ind_tbl[i]; + wq = container_of(ibwq, struct mana_ib_wq, ibwq); +mana_destroy_wq_obj (mpc,GDMA_RQ , wq->rx_object); + } +drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+kfree (mana_ind_table); + +return ret; +} + +static int mana_ib_create_qp_raw (struct ib_qp *ibqp,struct ib_pd *ibpd, +struct ib_qp_init_attr *attr, +struct ib_udata *udata) +{ + struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd,ibpd);
drivers/infiniband/hw/mana/qp.c
Quoted 1 line
drivers/infiniband/hw/mana/qp.c new file +1
-0+ struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp,ibqp);
drivers/infiniband/hw/mana/qp.c
Quoted 6 lines
drivers/infiniband/hw/mana/qp.c new file +6
-0+struct mana_ib_dev *mdev = + container_of(ibpd->device, struct mana_ib_dev, ib_dev); +struct mana_ib_cq *send_cq = + container_of(attr->send_cq, struct mana_ib_cq, ibcq); +struct mana_ib_ucontext *mana_ucontext = + rdma_udata_to_drv_context(udata, struct
mana_ib_ucontext,Quoted 20 lines
drivers/infiniband/hw/mana/qp.c new file +19
-0+ ibucontext); +struct mana_ib_create_qp_resp resp = {}; +struct gdma_dev *gd = mdev->gdma_dev; +struct mana_ib_create_qp ucmd = {}; +struct mana_obj_spec wq_spec = {}; +struct mana_obj_spec cq_spec = {}; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct ib_umem *umem; +int err; +u32 port; + + mc = gd->driver_data; + +if (!mana_ucontext || udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/qp.c
Quoted 3 lines
drivers/infiniband/hw/mana/qp.c new file +3
-0+if (err) { + ibdev_dbg(&mdev->ib_dev, + "Failed to copy from udata create qp-raw, %d\n",err);
Quoted 15 lines
drivers/infiniband/hw/mana/qp.c new file +15
-0+return err; + } + +/* IB ports start with 1, MANA Ethernet ports start with 0 */ + port = ucmd.port; +if (ucmd.port > mc->num_ports) +return -EINVAL ; + +if (attr->cap.max_send_wr >MAX_SEND_BUFFERS_PER_QUEUE ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_send_wr %d exceeding limit\n" , + attr->cap.max_send_wr); +return -EINVAL ; + } +drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+if (attr->cap.max_send_sge >MAX_TX_WQE_SGL_ENTRIES ) { +ibdev_dbg (&mdev->ib_dev, +"Requested max_send_sge %d exceeding limit\n" , + attr->cap.max_send_sge); +return -EINVAL ; + } + + ndev = mc->ports[port -1 ]; + mpc =netdev_priv (ndev); + ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port,ndev,
drivers/infiniband/hw/mana/qp.c
Quoted 13 lines
mpc);
drivers/infiniband/hw/mana/qp.c new file +2
-0+ + err = mana_ib_cfg_vport(mdev, port - 1, pd, mana_ucontext-doorbell);
drivers/infiniband/hw/mana/qp.c new file +9
-0+if (err) +return -ENODEV ; + + qp->port = port; + +ibdev_dbg (&mdev->ib_dev,"ucmd sq_buf_addr 0x%llx port %u\n" , + ucmd.sq_buf_addr, ucmd.port); + + umem = ib_umem_get(ibpd->device, ucmd.sq_buf_addr,ucmd.sq_buf_size,
Quoted 5 lines
drivers/infiniband/hw/mana/qp.c new file +5
-0+ IB_ACCESS_LOCAL_WRITE); +if (IS_ERR (umem)) { + err =PTR_ERR (umem); + ibdev_dbg(&mdev->ib_dev, + "Failed to get umem for create qp-raw, err %d\n",drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ err); + goto err_free_vport; + } + qp->sq_umem = umem; + + err =mana_ib_gd_create_dma_region (mdev, qp->sq_umem, + &qp->sq_gdma_region); +if (err) { + ibdev_dbg(&mdev->ib_dev, + "Failed to create dma region for create qp-raw, %d\n",
drivers/infiniband/hw/mana/qp.c
Quoted 6 lines
drivers/infiniband/hw/mana/qp.c new file +6
-0+ err); + goto err_release_umem; + } + + ibdev_dbg(&mdev->ib_dev, + "mana_ib_gd_create_dma_region ret %d gdma_region0x%llx\n",
drivers/infiniband/hw/mana/qp.c
Quoted 12 lines
drivers/infiniband/hw/mana/qp.c new file +12
-0+ err, qp->sq_gdma_region); + +/* Create a WQ on the same port handle used by the Ethernet */ + wq_spec.gdma_region = qp->sq_gdma_region; + wq_spec.queue_size = ucmd.sq_buf_size; + + cq_spec.gdma_region = send_cq->gdma_region; + cq_spec.queue_size = send_cq->cqe *COMP_ENTRY_SIZE ; + cq_spec.modr_ctx_id =0 ; + cq_spec.attached_eq =GDMA_CQ_NO_EQ ; + + err = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_SQ,
&wq_spec,Quoted 51 lines
drivers/infiniband/hw/mana/qp.c new file +51
-0+ &cq_spec, &qp->tx_object); +if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to create wq for create raw-qp, err %d\n" , + err); + goto err_destroy_dma_region; + } + +/* The GDMA regions are now owned by the WQ object */ + qp->sq_gdma_region =GDMA_INVALID_DMA_REGION ; + send_cq->gdma_region =GDMA_INVALID_DMA_REGION ; + + qp->sq_id = wq_spec.queue_index; + send_cq->id = cq_spec.queue_index; + +ibdev_dbg (&mdev->ib_dev, +"ret %d qp->tx_object 0x%llx sq id %llu cq id %llu\n" , err, + qp->tx_object, qp->sq_id, send_cq->id); + + resp.sqid = qp->sq_id; + resp.cqid = send_cq->id; + resp.tx_vp_offset = pd->tx_vp_offset; + + err =ib_copy_to_udata (udata, &resp,sizeof (resp)); +if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed copy udata for create qp-raw, %d\n" , + err); + goto err_destroy_wq_obj; + } + +return 0 ; + +err_destroy_wq_obj: +mana_destroy_wq_obj (mpc,GDMA_SQ , qp->tx_object); + +err_destroy_dma_region: +mana_ib_gd_destroy_dma_region (mdev, qp->sq_gdma_region); + +err_release_umem: +ib_umem_release (umem); + +err_free_vport: +mana_ib_uncfg_vport (mdev, pd, port -1 ); + +return err; +} + +int mana_ib_create_qp (struct ib_qp *ibqp,struct ib_qp_init_attr *attr, +struct ib_udata *udata) +{drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+switch (attr->qp_type) { +case IB_QPT_RAW_PACKET : +/* When rwq_ind_tbl is used, it's for creating WQs for RSS */ +if (attr->rwq_ind_tbl) +return mana_ib_create_qp_rss (ibqp, ibqp->pd, attr, + udata); + +return mana_ib_create_qp_raw (ibqp, ibqp->pd, attr, udata); +default : +/* Creating QP other than IB_QPT_RAW_PACKET is not supported */
drivers/infiniband/hw/mana/qp.c
Quoted 1 line
drivers/infiniband/hw/mana/qp.c new file +1
-0+ ibdev_dbg(ibqp->device, "Creating QP type %u notsupported\n",
Quoted 36 lines
drivers/infiniband/hw/mana/qp.c new file +35
-0+ attr->qp_type); + } + +return -EINVAL ; +} + +int mana_ib_modify_qp (struct ib_qp *ibqp,struct ib_qp_attr *attr, +int attr_mask,struct ib_udata *udata) +{ +/* modify_qp is not supported by this version of the driver */ +return -EOPNOTSUPP ; +} + +static int mana_ib_destroy_qp_rss (struct mana_ib_qp *qp, +struct ib_rwq_ind_table *ind_tbl, +struct ib_udata *udata) +{ +struct mana_ib_dev *mdev = + container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev); +struct gdma_dev *gd = mdev->gdma_dev; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct mana_ib_wq *wq; +struct ib_wq *ibwq; +int i; + + mc = gd->driver_data; + ndev = mc->ports[qp->port -1 ]; + mpc =netdev_priv (ndev); + +for (i =0 ; i < (1 << ind_tbl->log_ind_tbl_size); i++) { + ibwq = ind_tbl->ind_tbl[i]; + wq = container_of(ibwq, struct mana_ib_wq, ibwq); + ibdev_dbg(&mdev->ib_dev, "destroying wq-
rx_object%llu\n",drivers/infiniband/hw/mana/qp.c
Quoted 8 lines
drivers/infiniband/hw/mana/qp.c new file +8
-0+ wq->rx_object); +mana_destroy_wq_obj (mpc,GDMA_RQ , wq->rx_object); + } + +return 0 ; +} + +static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct
ib_udataQuoted 22 lines
*udata)
drivers/infiniband/hw/mana/qp.c new file +19
-0+{ +struct mana_ib_dev *mdev = + container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev); +struct gdma_dev *gd = mdev->gdma_dev; +struct ib_pd *ibpd = qp->ibqp.pd; +struct mana_port_context *mpc; +struct mana_context *mc; +struct net_device *ndev; +struct mana_ib_pd *pd; + + mc = gd->driver_data; + ndev = mc->ports[qp->port -1 ]; + mpc =netdev_priv (ndev); + pd = container_of(ibpd, struct mana_ib_pd, ibpd); + +mana_destroy_wq_obj (mpc,GDMA_SQ , qp->tx_object); + +if (qp->sq_umem) { + mana_ib_gd_destroy_dma_region(mdev, qp-
sq_gdma_region);drivers/infiniband/hw/mana/qp.c new file +1
-0+ib_umem_release (qp->sq_umem);drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ } + +mana_ib_uncfg_vport (mdev, pd, qp->port -1 ); + +return 0 ; +} + +int mana_ib_destroy_qp (struct ib_qp *ibqp,struct ib_udata *udata) +{ + struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp,ibqp);
Quoted 47 lines
drivers/infiniband/hw/mana/qp.c new file +5
-0+ +switch (ibqp->qp_type) { +case IB_QPT_RAW_PACKET : +if (ibqp->rwq_ind_tbl) + return mana_ib_destroy_qp_rss(qp, ibqp-
rwq_ind_tbl,drivers/infiniband/hw/mana/qp.c new file +11
-0+ udata); + +return mana_ib_destroy_qp_raw (qp, udata); + +default : +ibdev_dbg (ibqp->device,"Unexpected QP type %u\n" , + ibqp->qp_type); + } + +return -ENOENT ; +}drivers/infiniband/hw/mana/wq.c new file +22
-0@@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#include "mana_ib.h" + +struct ib_wq *mana_ib_create_wq (struct ib_pd *pd, +struct ib_wq_init_attr *init_attr, +struct ib_udata *udata) +{ +struct mana_ib_dev *mdev = + container_of(pd->device, struct mana_ib_dev, ib_dev); +struct mana_ib_create_wq ucmd = {}; +struct mana_ib_wq *wq; +struct ib_umem *umem; +int err; + +if (udata->inlen <sizeof (ucmd)) +return ERR_PTR (-EINVAL ); + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-Quoted 1 line
inlen));
drivers/infiniband/hw/mana/wq.c
Quoted 3 lines
drivers/infiniband/hw/mana/wq.c new file +3
-0+if (err) { + ibdev_dbg(&mdev->ib_dev, + "Failed to copy from udata for create wq, %d\n",err);
drivers/infiniband/hw/mana/wq.c
Quoted 11 lines
drivers/infiniband/hw/mana/wq.c new file +8
-0+return ERR_PTR (err); + } + + wq =kzalloc (sizeof (*wq),GFP_KERNEL ); +if (!wq) +return ERR_PTR (-ENOMEM ); + + ibdev_dbg(&mdev->ib_dev, "ucmd wq_buf_addr 0x%llx\n",ucmd.wq_buf_addr);
drivers/infiniband/hw/mana/wq.c new file +2
-0+ + umem = ib_umem_get(pd->device, ucmd.wq_buf_addr,ucmd.wq_buf_size,
Quoted 15 lines
drivers/infiniband/hw/mana/wq.c new file +14
-0+ IB_ACCESS_LOCAL_WRITE); +if (IS_ERR (umem)) { + err =PTR_ERR (umem); +ibdev_dbg (&mdev->ib_dev, +"Failed to get umem for create wq, err %d\n" , err); + goto err_free_wq; + } + + wq->umem = umem; + wq->wqe = init_attr->max_wr; + wq->wq_buf_size = ucmd.wq_buf_size; + wq->rx_object =INVALID_MANA_HANDLE ; + + err = mana_ib_gd_create_dma_region(mdev, wq->umem, &wq-
gdma_region);drivers/infiniband/hw/mana/wq.c
Quoted 9 lines
drivers/infiniband/hw/mana/wq.c new file +9
-0+if (err) { +ibdev_dbg (&mdev->ib_dev, +"Failed to create dma region for create wq, %d\n" , + err); + goto err_release_umem; + } + + ibdev_dbg(&mdev->ib_dev, + "mana_ib_gd_create_dma_region ret %d gdma_region0x%llx\n",
drivers/infiniband/hw/mana/wq.c
Quoted 3 lines
drivers/infiniband/hw/mana/wq.c new file +3
-0+ err, wq->gdma_region); + +/* WQ ID is returned at wq_create time, doesn't know the value yet */
Quoted 12 lines
drivers/infiniband/hw/mana/wq.c new file +12
-0+ +return &wq->ibwq; + +err_release_umem: +ib_umem_release (umem); + +err_free_wq: +kfree (wq); + +return ERR_PTR (err); +} +drivers/infiniband/hw/mana/wq.c
Quoted 10 lines
drivers/infiniband/hw/mana/wq.c new file +10
-0+int mana_ib_modify_wq (struct ib_wq *wq,struct ib_wq_attr *wq_attr, +u32 wq_attr_mask,struct ib_udata *udata) +{ +/* modify_wq is not supported by this version of the driver */ +return -EOPNOTSUPP ; +} + +int mana_ib_destroy_wq (struct ib_wq *ibwq,struct ib_udata *udata) +{ + struct mana_ib_wq *wq = container_of(ibwq, struct mana_ib_wq,ibwq);
Quoted 16 lines
drivers/infiniband/hw/mana/wq.c new file +14
-0+struct ib_device *ib_dev = ibwq->device; +struct mana_ib_dev *mdev; + + mdev = container_of(ib_dev, struct mana_ib_dev, ib_dev); + +mana_ib_gd_destroy_dma_region (mdev, wq->gdma_region); +ib_umem_release (wq->umem); + +kfree (wq); + +return 0 ; +} + +int mana_ib_create_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_table,drivers/infiniband/hw/mana/wq.c new file +1
-0+ struct ib_rwq_ind_table_init_attr *init_attr,drivers/infiniband/hw/mana/wq.c
Quoted 10 lines
drivers/infiniband/hw/mana/wq.c new file +10
-0+ struct ib_udata *udata) +{ +/* +* There is no additional data in ind_table to be maintained by this +* driver, do nothing +*/ +return 0 ; +} + +int mana_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table
*ib_rwq_ind_tbl)include/net/mana/mana.h int mana_bpf(struct net_device *ndev, struct
Quoted 12 lines
drivers/infiniband/hw/mana/wq.c new file +7
-0+{ +/* +* There is no additional data in ind_table to be maintained by this +* driver, do nothing +*/ +return 0 ; +}include/net/mana/mana.h +0
-0@@ -412,6 +412,9 @@ int mana_bpf(struct net_device *ndev, struct
netdev_bpfinclude/uapi/rdma/mana-
Quoted 24 lines
include/net/mana/mana.h +3
-0*bpf);extern const struct ethtool_ops mana_ethtool_ops; +/* A CQ can be created not associated with any EQ */ +#define GDMA_CQ_NO_EQ 0xffff +struct mana_obj_spec {u32 queue_index;include/net/mana/mana.h +0
-0u64 gdma_region;include/uapi/rdma/ib_user_ioctl_verbs.h +1
-0@@ -251,6 +251,7 @@ enum rdma_driver_id {RDMA_DRIVER_EFA ,RDMA_DRIVER_SIW ,RDMA_DRIVER_ERDMA , + RDMA_DRIVER_MANA, }; enum ib_uverbs_gid_type {include/uapi/rdma/mana- renamed from include/uapi/rdma/mana-abi.h +0
-0
abi.hQuoted 73 lines
new file mode 100644
index 000000000000..5fcb31b37fb9include/uapi/rdma/mana-abi.h new file +66
-1@@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ +/* +* Copyright (c) 2022, Microsoft Corporation. All rights reserved. +*/ + +#ifndef MANA_ABI_USER_H +#define MANA_ABI_USER_H + +#include <linux/types.h> +#include <rdma/ib_user_ioctl_verbs.h> + +/* +* Increment this value if any changes that break userspace ABI +* compatibility are made. +*/ + +#define MANA_IB_UVERBS_ABI_VERSION 1 + +struct mana_ib_create_cq { +__aligned_u64 buf_addr; +}; + +struct mana_ib_create_qp { +__aligned_u64 sq_buf_addr; +__u32 sq_buf_size; +__u32 port; +}; + +struct mana_ib_create_qp_resp { +__u32 sqid; +__u32 cqid; +__u32 tx_vp_offset; +__u32 reserved; +}; + +struct mana_ib_create_wq { +__aligned_u64 wq_buf_addr; +__u32 wq_buf_size; +__u32 reserved; +}; + +/* RX Hash function flags */ +enum mana_ib_rx_hash_function_flags { +MANA_IB_RX_HASH_FUNC_TOEPLITZ =1 <<0 , +}; + +struct mana_ib_create_qp_rss { +__aligned_u64 rx_hash_fields_mask; +__u8 rx_hash_function; +__u8 reserved[7 ]; +__u32 rx_hash_key_len; +__u8 rx_hash_key[40 ]; +__u32 port; +}; + +struct rss_resp_entry { +__u32 cqid; +__u32 wqid; +}; + +struct mana_ib_create_qp_rss_resp { +__aligned_u64 num_entries; +struct rss_resp_entry entries[64 ]; +}; + +#endif --2.17.1
Re: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 17 lines · Long Li
Quoted 16 lines
[Bernard wrote...]
drivers/infiniband/hw/mana/main.c line 484
Quoted 11 lines
drivers/infiniband/hw/mana/main.c new file +11
-0+ props->max_qp_wr =MAX_SEND_BUFFERS_PER_QUEUE ; + +/* +* max_cqe could be potentially much bigger. +* As this version of driver only support RAW QP, set it to the same +* value as max_qp_wr +*/ + props->max_cqe =MAX_SEND_BUFFERS_PER_QUEUE ; + + props->max_mr_size =MANA_IB_MAX_MR_SIZE ; + props->max_mr =INT_MAX ;How the 24 bit wide MR keys can handle
INT_MAXunique MR's?
Quoted 1 line
Not sure if I understand this correctly, lkey and rkey are u32 in
ib_mr.
The upper 8 bits of an ib_mr remote token are reserved for use as a rotating key, this allows a consumer to more safely reuse an ib_mr without having to overallocate large region pools.
Tom.
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 36 lines
-----Original Message-----
From: Tom Talpey <[email protected]>
Sent: Friday, 21 October 2022 16:34
To: Long Li <[email protected]>; Bernard Metzler <[email protected]>; KY Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Stephen Hemminger <[email protected]>; Wei Liu <[email protected]>; Dexuan Cui <[email protected]>; David S. Miller <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jason Gunthorpe <[email protected]>; Leon Romanovsky <[email protected]>; [email protected]; [email protected]; Ajay Sharma <[email protected]>
Cc: [email protected]; [email protected]; linux- [email protected]; [email protected]
Subject: [EXTERNAL] Re: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network AdapterQuoted 17 lines · Long Li
Quoted 16 lines
[Bernard wrote...]
drivers/infiniband/hw/mana/main.c line 484
Quoted 11 lines
drivers/infiniband/hw/mana/main.c new file +11
-0+ props->max_qp_wr =MAX_SEND_BUFFERS_PER_QUEUE ; + +/* +* max_cqe could be potentially much bigger. +* As this version of driver only support RAW QP, set it to the same +* value as max_qp_wr +*/ + props->max_cqe =MAX_SEND_BUFFERS_PER_QUEUE ; + + props->max_mr_size =MANA_IB_MAX_MR_SIZE ; + props->max_mr =INT_MAX ;How the 24 bit wide MR keys can handle
INT_MAXunique MR's?
Quoted 7 lines
Quoted 1 line
Not sure if I understand this correctly, lkey and rkey are u32 in
ib_mr.The upper 8 bits of an
ib_mrremote token are reserved for use as a rotating key, this allows a consumer to more safely reuse anib_mrwithout having to overallocate large region pools.Tom.
Right, my point was that one cannot encode INT_MAX different MR identifiers into 32 - 8 = 24 bits.
Best,
Bernard.
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to Long LiQuoted 21 lines
-----Original Message-----
From: Long Li <[email protected]>
Sent: Thursday, 20 October 2022 22:42
To: Bernard Metzler <[email protected]>; KY Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Stephen Hemminger <[email protected]>; Wei Liu <[email protected]>; Dexuan Cui <[email protected]>; David S. Miller <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jason Gunthorpe <[email protected]>; Leon Romanovsky <[email protected]>; [email protected]; [email protected]; Ajay Sharma <[email protected]>
Cc: [email protected]; [email protected]; linux- [email protected]; [email protected]
Subject: [EXTERNAL] RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network AdapterQuoted 3 lines
Subject: RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
<snip>
Quoted 14 lines
Quoted 6 lines
While I understand the driver is currently used in a proprietary environment only, where even the port state seem not to matter, I am not sure this looks good. Shouldn't the driver better adhere to basic assumptions of its RDMA core environment?
The user space code is for DPDK. They are at:
INVALID URI REMOVED 3A__github.com_DPDK_dpdk_tree_main_drivers_net_mana&d=DwIGaQ&c=jf_iaSHvJObT bx-siA1ZOg&r=2TaYXQ0T- r8ZO1PP1alNwU_QJcRRLfmYTAgd3QCvqSc&m=Wwob5ZbYrjAfZhKpS3eLoAVYnqDfpHBNoIoW88 iq3fhkBx0yeS2BtrlXpYu3FsIr&s=kBEadEfaoNf85WNoAYWaviwBQnUyNbP4fq2aK4HnS5I&e=
Quoted 6 lines
The
RAW_QPimplementation provides all necessary values for its targeted usage. I'm not aware of mandatory values that should be reported according to RDMA verbs interface spec. If there are mandatory required values, please point me to the spec, I will add those to the driver.
I am not sure if we shall discuss specifications here. It might hurt badly, see for example that well aged verbs specification:
http://www.rdmaconsortium.org/home/draft-hilland-iwarp-verbs-v1.0-RDMAC.pdf
section '9.2.1.2 Query RNIC'. So many attributes to report ;) (and most of those are reflected in ib_qp_attr)
For good reasons there are no abstract interface specifications in Linux kernel. I was just wondering if it is good to leave concrete attributes which are not (yet?) reported at random. It is obviously working okay today for your environment. But memset zero everything you don't care about today might be just safe to detect an unexpected interpretation of those fields in the future?
Thanks,
Bernard.
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to Bernard MetzlerQuoted 11 lines
Quoted 5 lines
The upper 8 bits of an
ib_mrremote token are reserved for use as a rotating key, this allows a consumer to more safely reuse anib_mrwithout having to overallocate large region pools.Tom.
Right, my point was that one cannot encode
INT_MAXdifferent MR identifiers into 32 - 8 = 24 bits.Best,
Bernard.
The hardware exposes the number of MRs that exceeds UINT32_MAX. There is no software stack limit from hardware perspective.
In this case, maybe it's a good idea to set it to 0xFFFFFF. I'm making the change.
Thanks,
Long
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to Bernard MetzlerQuoted 11 lines
For good reasons there are no abstract interface specifications in Linux kernel. I was just wondering if it is good to leave concrete attributes which are not (yet?) reported at random. It is obviously working okay today for your environment.
But memset zero everything you don't care about today might be just safe to detect an unexpected interpretation of those fields in the future?Thanks,
Bernard.
Thank you for the pointer.
I'm making the changes as you suggested.
Long
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 10 lines
Quoted 1 line
For good reasons there are no abstract interface specifications in Linux
kernel.
Quoted 8 lines
I was just wondering if it is good to leave concrete attributes which are not
(yet?) reported at random. It is obviously working okay today for your environment.
But memset zero everything you don't care about today might be just safe to detect an unexpected interpretation of those fields in the future?
Quoted 8 lines
Quoted 2 lines
Thanks,
Bernard.Thank you for the pointer.
I'm making the changes as you suggested.
Long
Went through the code that IB upper layer calls query_xxx into lower driver. It seems the upper layer always zero out the values (or set them) before calling.
I think we should be safe for the code as is.
Re: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to Long LiQuoted 9 lines · Long Li
Quoted 9 lines
Quoted 5 lines
The upper 8 bits of an
ib_mrremote token are reserved for use as a rotating key, this allows a consumer to more safely reuse anib_mrwithout having to overallocate large region pools.Tom.
Right, my point was that one cannot encode
INT_MAXdifferent MR identifiers into 32 - 8 = 24 bits.
Quoted 7 lines
Quoted 2 lines
Best,
Bernard.The hardware exposes the number of MRs that exceeds
UINT32_MAX. There is no software stack limit from hardware perspective.In this case, maybe it's a good idea to set it to
0xFFFFFF. I'm making the change.
Actually, 2^24 MRs is enormous in itself. Does this driver actually support that many? Without falling over?
Tom.
RE: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 19 lines
Subject: Re: [Patch v8 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 15 lines · Long Li
Quoted 11 lines
Quoted 5 lines
The upper 8 bits of an
ib_mrremote token are reserved for use as a rotating key, this allows a consumer to more safely reuse anib_mrwithout having to overallocate large region pools.Tom.
Right, my point was that one cannot encode
INT_MAXdifferent MR identifiers into 32 - 8 = 24 bits.Best,
Bernard.The hardware exposes the number of MRs that exceeds
UINT32_MAX. There is no software stack limit from hardware perspective.
Quoted 7 lines
Quoted 1 line
In this case, maybe it's a good idea to set it to
0xFFFFFF. I'm making thechange.
Actually, 2^24 MRs is enormous in itself. Does this driver actually support that many? Without falling over?
Tom.
The hardware can support that much. I don't see this driver will enforce other limitation on that.