Introduce Microsoft Azure Network Adapter (MANA) RDMA driver
Subsystems (5)
v6 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: Add functions for allocating doorbell page from GDMA
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 RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
MAINTAINERS | 4 +
drivers/infiniband/Kconfig | 1 +
drivers/infiniband/hw/Makefile | 1 +
drivers/infiniband/hw/mana/Kconfig | 7 +
drivers/infiniband/hw/mana/Makefile | 4 +
drivers/infiniband/hw/mana/cq.c | 80 +++
drivers/infiniband/hw/mana/device.c | 129 ++++
drivers/infiniband/hw/mana/main.c | 555 ++++++++++++++++++
drivers/infiniband/hw/mana/mana_ib.h | 165 ++++++
drivers/infiniband/hw/mana/mr.c | 133 +++++
drivers/infiniband/hw/mana/qp.c | 501 ++++++++++++++++
drivers/infiniband/hw/mana/wq.c | 114 ++++
drivers/net/ethernet/microsoft/Kconfig | 1 +
.../net/ethernet/microsoft/mana/gdma_main.c | 96 ++-
.../net/ethernet/microsoft/mana/hw_channel.c | 6 +-
.../net/ethernet/microsoft/mana/mana_bpf.c | 2 +-
drivers/net/ethernet/microsoft/mana/mana_en.c | 176 +++++-
.../ethernet/microsoft/mana/mana_ethtool.c | 2 +-
.../net/ethernet/microsoft/mana/shm_channel.c | 2 +-
.../microsoft => include/net}/mana/gdma.h | 162 ++++-
.../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, 2196 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 v6 1/12 net: mana: Add support for auxiliary device
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
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 | 84 ++++++++++++++++++- 4 files changed, 96 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 +83 -1
114 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v6 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 v6 3/12 net: mana: Handle vport sharing between devices
In reply to [email protected]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 v6 4/12 net: mana: Add functions 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. Implement those functions and expose them for use by the RDMA driver.
---
Change log:
v4: use EXPORT_SYMBOL_NS
drivers/net/ethernet/microsoft/mana/gdma.h | 29 ++++++++++ .../net/ethernet/microsoft/mana/gdma_main.c | 56 +++++++++++++++++++ 2 files changed, 85 insertions(+)
drivers/net/ethernet/microsoft/mana/gdma.h +29 -0
@@ -22,11 +22,15 @@ 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,
@@ -578,6 +582,26 @@ 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;
@@ -686,4 +710,9 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi);int mana_gd_send_request (struct gdma_context *gc,u32 req_len,const void *req,u32 resp_len,void *resp); + +int mana_gd_allocate_doorbell_page (struct gdma_context *gc,int *doorbell_page); + +int mana_gd_destroy_doorbell_page (struct gdma_context *gc,int doorbell_page); +#endif /* _GDMA_H */
drivers/net/ethernet/microsoft/mana/gdma_main.c +56 -0
62 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v6 5/12 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
@@ -1419,6 +1419,12 @@ 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 v6 6/12 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
PATCH v6 7/12 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 v6 8/12 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 v6 9/12 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
@@ -431,6 +431,13 @@ 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 v6 10/12 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 v6 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 | 120 +++++++++++++++++- 3 files changed, 142 insertions(+), 23 deletions(-)
drivers/net/ethernet/microsoft/mana/gdma_main.c +17 -10
@@ -254,7 +254,7 @@ 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;
@@ -268,7 +268,7 @@ 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 ; }
@@ -722,24 +722,30 @@ 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)
@@ -784,14 +790,15 @@ 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;
@@ -914,7 +921,7 @@ 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 +115 -5
174 lines not on this page · raw message
Signature · 1 line
2.17.1
PATCH v6 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()
MAINTAINERS | 3 + drivers/infiniband/Kconfig | 1 + drivers/infiniband/hw/Makefile | 1 + drivers/infiniband/hw/mana/Kconfig | 7 + drivers/infiniband/hw/mana/Makefile | 4 + drivers/infiniband/hw/mana/cq.c | 80 ++++ drivers/infiniband/hw/mana/device.c | 129 ++++++ drivers/infiniband/hw/mana/main.c | 555 ++++++++++++++++++++++++ drivers/infiniband/hw/mana/mana_ib.h | 165 +++++++ drivers/infiniband/hw/mana/mr.c | 133 ++++++ drivers/infiniband/hw/mana/qp.c | 501 +++++++++++++++++++++ drivers/infiniband/hw/mana/wq.c | 114 +++++ 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, 1763 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 +3 -0
@@ -9426,6 +9426,7 @@ M: Haiyang Zhang <[email protected]> M: Stephen Hemminger <[email protected]> M: Wei Liu <[email protected]> M: Dexuan Cui <[email protected]> +M: Long Li <[email protected]> L: [email protected] S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
@@ -9444,6 +9445,7 @@ F: arch/x86/kernel/cpu/mshyperv.c F: drivers/clocksource/hyperv_timer.c F: drivers/hid/hid-hyperv.c F: drivers/hv/ +F: drivers/infiniband/hw/mana/ F: drivers/input/serio/hyperv-keyboard.c F: drivers/iommu/hyperv-iommu.c F: drivers/net/ethernet/microsoft/
@@ -9459,6 +9461,7 @@ F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h F: include/net/mana F: include/uapi/linux/hyperv.h +F: include/uapi/rdma/mana-abi.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/
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 +1,7 @@ +# 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).
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 +80 -0
80 lines not on this page · raw message
drivers/infiniband/hw/mana/device.c new file +129 -0
129 lines not on this page · raw message
drivers/infiniband/hw/mana/main.c new file +555 -0
555 lines not on this page · raw message
drivers/infiniband/hw/mana/mana_ib.h new file +165 -0
165 lines not on this page · raw message
drivers/infiniband/hw/mana/mr.c new file +133 -0
133 lines not on this page · raw message
drivers/infiniband/hw/mana/qp.c new file +501 -0
501 lines not on this page · raw message
drivers/infiniband/hw/mana/wq.c new file +114 -0
114 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
Re: [Patch v6 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 21 lines · On Tue, Sep 20, 2022 at 06:22:32PM -0700, [email protected] wrote:
MAINTAINERS +2
-0@@ -9426,6 +9426,7 @@ M: Haiyang Zhang <[email protected]> M: Stephen Hemminger <[email protected]> M: Wei Liu <[email protected]> M: Dexuan Cui <[email protected]> +M: Long Li <[email protected]> L: [email protected] S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git@@ -9444,6 +9445,7 @@ F: arch/x86/kernel/cpu/mshyperv.c F: drivers/clocksource/hyperv_timer.c F: drivers/hid/hid-hyperv.c F: drivers/hv/ +F: drivers/infiniband/hw/mana/ F: drivers/input/serio/hyperv-keyboard.c F: drivers/iommu/hyperv-iommu.c F: drivers/net/ethernet/microsoft/
MAINTAINERS F: include/clocksource/hyperv_timer.h · line 9466
Quoted 6 lines
MAINTAINERS +1
-0@@ -9459,6 +9461,7 @@ F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h F: include/net/mana F: include/uapi/linux/hyperv.h +F: include/uapi/rdma/mana-abi.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/
This is not the proper way to write a maintainers entry, a driver should be stand-alone and have L: entries for the subsystem mailing list, not be bundled like this. If you do this patches will not go to the correct lists and will not be applied.
Follow the example of every other rdma driver please.
Jason
RE: [Patch v6 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 37 lines
Subject: Re: [Patch v6 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 21 lines · On Tue, Sep 20, 2022 at 06:22:32PM -0700, [email protected] wrote:
MAINTAINERS index renamed from MAINTAINERS +0
-0
8b9a50756c7e..7bcc19e27f97100644MAINTAINERS +2
-0@@ -9426,6 +9426,7 @@ M: Haiyang Zhang <[email protected]> M: Stephen Hemminger <[email protected]> M: Wei Liu <[email protected]> M: Dexuan Cui <[email protected]> +M: Long Li <[email protected]> L: [email protected] S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git@@ -9444,6 +9445,7 @@ F: arch/x86/kernel/cpu/mshyperv.c F: drivers/clocksource/hyperv_timer.c F: drivers/hid/hid-hyperv.c F: drivers/hv/ +F: drivers/infiniband/hw/mana/ F: drivers/input/serio/hyperv-keyboard.c F: drivers/iommu/hyperv-iommu.c F: drivers/net/ethernet/microsoft/MAINTAINERS F: include/clocksource/hyperv_timer.h · line 9466
Quoted 6 lines
MAINTAINERS +1
-0@@ -9459,6 +9461,7 @@ F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h F: include/net/mana F: include/uapi/linux/hyperv.h +F: include/uapi/rdma/mana-abi.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/This is not the proper way to write a maintainers entry, a driver should be stand-alone and have L: entries for the subsystem mailing list, not be bundled like this. If you do this patches will not go to the correct lists and will not be applied.
Quoted 3 lines
Follow the example of every other rdma driver please.
Jason
Will fix this.
Thanks,
Long
Re: [Patch v6 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
In reply to [email protected]drivers/infiniband/hw/mana/cq.c line 17
Quoted 10 lines · On Tue, Sep 20, 2022 at 06:22:32PM -0700, [email protected] wrote:
drivers/infiniband/hw/mana/cq.c new file +10
-0+int mana_ib_create_cq (struct ib_cq *ibcq,const struct ib_cq_init_attr *attr, +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);
Stylistically these container_of's are usually in the definitions section, at least pick a form and stick to it consistently.
Quoted 22 lines
drivers/infiniband/hw/mana/cq.c new file +21
-0+if (udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + err =ib_copy_from_udata (&ucmd, udata,min (sizeof (ucmd), udata->inlen)); +if (err) { +ibdev_dbg (ibdev, +"Failed to copy from udata for create cq, %d\n" , err); +return -EFAULT ; + } + +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 , +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",
drivers/infiniband/hw/mana/cq.c line 49
Quoted 10 lines
drivers/infiniband/hw/mana/cq.c new file +10
-0+ err); +return err; + } + + err =mana_ib_gd_create_dma_region (mdev, cq->umem, &cq->gdma_region, +PAGE_SIZE ); +if (err) { +ibdev_err (ibdev, +"Failed to create dma region for create cq, %d\n" , + err);
Prints on userspace paths are not allowed, this should be dbg. There are many other cases like this, please fix them all. This driver may have too many dbg prints too, not every failure if should have a print :(
drivers/infiniband/hw/mana/cq.c line 59
Quoted 7 lines
drivers/infiniband/hw/mana/cq.c new file +7
-0+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_qp +*/
Wrong comment style, rdma uses the leading empty blank line for some reason
/*
* The CQ ID is not known at this time. The ID is generated at create_qp. */
Quoted 26 lines
drivers/infiniband/hw/mana/device.c new file +26
-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, +}; + +static int __init mana_ib_init (void ) +{
drivers/infiniband/hw/mana/device.c line 127
Quoted 10 lines
drivers/infiniband/hw/mana/device.c new file +10
-0+auxiliary_driver_register (&mana_driver); + +return 0 ; +} + +static void __exit mana_ib_cleanup(void) +{ +auxiliary_driver_unregister (&mana_driver); +} +
All this is just module_auxiliary_driver()
drivers/infiniband/hw/mana/main.c line 50
Quoted 7 lines
drivers/infiniband/hw/mana/main.c new file +7
-0+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);
This leaves vport_use_count elevated.
drivers/infiniband/hw/mana/main.c line 105
Quoted 9 lines
drivers/infiniband/hw/mana/main.c new file +9
-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 mana_ib_dev *dev; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); +return mana_ib_gd_destroy_pd (dev, pd->pd_handle);
This is the only place that calls mana_ib_gd_destroy_pd(), don't have a spaghetti of functions calling single other functions like this, just inline it.
Also it shouldn't have been non-static, please check everything that everything non-static actually has an out-of-file user.
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-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;
drivers/infiniband/hw/mana/main.c line 152
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+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_err (ibdev,"Failed to destroy doorbell page %d\n" , ret);
This already printing on error
And again, why is this driver split up so strangely? mana_gd_destroy_doorbell_page() is an RDMA function, it is only called by the RDMA code, why is it located under drivers/net/ethernet?
I do not want an RDMA driver in drivers/net/ethernet.
Quoted 22 lines
drivers/infiniband/hw/mana/main.c new file +22
-0+} + +int mana_ib_gd_create_dma_region (struct mana_ib_dev *dev,struct ib_umem *umem, +mana_handle_t *gdma_region,u64 page_sz) +{ +size_t num_pages_total =ib_umem_num_dma_blocks (umem, page_sz); +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; +struct gdma_dev *mdev; +unsigned int i; +int err; + + mdev = dev->gdma_dev; + gc = mdev->gdma_context; + hwc = gc->hwc.driver_data;
drivers/infiniband/hw/mana/main.c line 184
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ 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); + + create_req =kzalloc (create_req_msg_size,GFP_KERNEL ); +if (!create_req)
Is this a multi-order allocation, I can't tell how big max_req_msg_size is?
This design seems to repeat the mistakes we made in mlx5, the low levels of the driver already has memory allocated - why not get a pointer to that memory here and directly fill the message buffer instead of all this allocation and memory copying?
Quoted 11 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ibdev_dbg (&dev->ib_dev, +"size_dma_region %lu num_pages_total %lu, " +"page_sz 0x%llx offset_in_page %u\n" , + umem->length, num_pages_total, 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);
drivers/infiniband/hw/mana/main.c line 216
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+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; + +ibdev_dbg (&dev->ib_dev,"page num %u cur_addr 0x%llx\n" , i, + cur_addr);
Please get rid of the worthless debugging code, actually test your driver with EBUG enabled and ensure it is usuable. Printing thousands of lines of garbage is not OK. Especially when what should have been a 1 line loop body is expended into a big block just to have a worthless debug statement.
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+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);
drivers/infiniband/hw/mana/main.c line 253
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ + 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 =kmalloc (add_req_msg_size,GFP_KERNEL );
And allocating every loop iteration seems like overkill, why not just reuse the large buffer that create_req allocated?
Usually the way these loops are structured is to fill the array and then check for fullness, trigger an action to drain the array, and reset the indexes back to the start.
Quoted 13 lines
drivers/infiniband/hw/mana/main.c new file +13
-0+int mana_ib_gd_create_pd (struct mana_ib_dev *dev,u64 *pd_handle,u32 *pd_id, +enum gdma_pd_flags flags) +{ +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_create_pd_resp resp = {}; +struct gdma_create_pd_req req = {}; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context; + +mana_gd_init_req_hdr (&req.hdr,GDMA_CREATE_PD ,sizeof (req), +sizeof (resp));
drivers/infiniband/hw/mana/main.c line 354
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ + req.flags = flags; + err =mana_gd_send_request (gc,sizeof (req), &req,sizeof (resp), &resp); + +if (err || resp.hdr.status) { +ibdev_err (&dev->ib_dev, +"Failed to get pd_id err %d status %u\n" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ;
This pattern is repeated everywhere, you should fix mana_gd_send_request() to return EPROTO.
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+return err; + } + + *pd_handle = resp.pd_handle; + *pd_id = resp.pd_id; +ibdev_dbg (&dev->ib_dev,"pd_handle 0x%llx pd_id %d\n" , *pd_handle, + *pd_id); + +return 0 ; +}
drivers/infiniband/hw/mana/main.c line 375
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ +int mana_ib_gd_destroy_pd (struct mana_ib_dev *dev,u64 pd_handle) +{ +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_destory_pd_resp resp = {}; +struct gdma_destroy_pd_req req = {}; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context;
Why the local for a variable that is used once?
Quoted 7 lines
drivers/infiniband/hw/mana/main.c new file +7
-0+int mana_ib_mmap (struct ib_ucontext *ibcontext,struct vm_area_struct *vma) +{ +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;
drivers/infiniband/hw/mana/main.c line 488
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+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_err (ibdev,"Unexpected vm_pgoff %lu\n" , vma->vm_pgoff); +return -EINVAL ;
More user triggerable printing
drivers/infiniband/hw/mana/mr.c line 125
Quoted 12 lines
drivers/infiniband/hw/mana/mr.c new file +12
-0+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;
mana_ib_gd_destroy_mr() is only ever called here, why is it in main.c?
Quoted 62 lines
drivers/infiniband/hw/mana/qp.c new file +62
-0+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; +struct ib_cq *ibcq; +struct ib_wq *ibwq; +int i =0 , ret; +u32 port; + + mc = gd->driver_data; + +if (udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + ret =ib_copy_from_udata (&ucmd, udata,min (sizeof (ucmd), udata->inlen)); +if (ret) { +ibdev_dbg (&mdev->ib_dev, +"Failed copy from udata for create rss-qp, err %d\n" , + ret); +return -EFAULT ; + } + +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 ; + } + +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 ;
drivers/infiniband/hw/mana/qp.c line 162
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ } + 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 =kzalloc (sizeof (mana_handle_t) * + (1 << ind_tbl->log_ind_tbl_size), +GFP_KERNEL );
Should be careful about maths overflow on this calculation.
Quoted 7 lines
drivers/infiniband/hw/mana/qp.c new file +7
-0+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);
drivers/infiniband/hw/mana/qp.c line 328
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+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,PAGE_SIZE ); +if (err) {
All these cases that process a page list have to call ib_umem_find_best_XXX()!
It does important validation against hostile user input, including checking the critical iova.
You have missed that the user can request that an unaligned umem be created and this creates a starting offset from the first page that must be honored in HW, or there will be weird memory corruption. Since it looks like this HW doesn't support a starting page offset this should call ib_umem_find_best_pgsz() with a SZ_4K and a 0 iova. Also never use PAGE_SIZE to describe a HW limitation.
There is alot of repeated code here, it would do well to have a wrapper function consolidating this pattern.
Jason
RE: [Patch v6 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 6 lines
Subject: Re: [Patch v6 12/12] RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Quoted 1 line · On Tue, Sep 20, 2022 at 06:22:32PM -0700, [email protected] wrote:
+int mana_ib_create_cq(struct
ib_cq*ibcq, const structib_cq_init_attr*attr,
Quoted 12 lines
drivers/infiniband/hw/mana/cq.c line 17
Quoted 9 lines
drivers/infiniband/hw/mana/cq.c new file +9
-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);Stylistically these container_of's are usually in the definitions section, at least pick a form and stick to it consistently.
I will review all the other occurrences for consistency. I'm trying to use the "reverse Christmas tree" for definitions, so putting "mdev =" in a separate line.
Quoted 26 lines
Quoted 10 lines
drivers/infiniband/hw/mana/cq.c new file +4
-0+if (udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-inlen));
drivers/infiniband/hw/mana/cq.c new file +3
-0+if (err) { +ibdev_dbg (ibdev, +"Failed to copy from udata for create cq, %d\n" , err);drivers/infiniband/hw/mana/cq.c
Quoted 10 lines
drivers/infiniband/hw/mana/cq.c new file +10
-0+return -EFAULT ; + } + +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 15 lines
drivers/infiniband/hw/mana/cq.c line 49
Quoted 11 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 new file +5
-0+ PAGE_SIZE); +if (err) { +ibdev_err (ibdev, +"Failed to create dma region for create cq, %d\n" , + err);Prints on userspace paths are not allowed, this should be dbg. There are many other cases like this, please fix them all. This driver may have too many dbg prints too, not every failure if should have a print :(
Will fix those.
Quoted 13 lines
Review
Quoted 3 lines
(quoted diff) +2
-0+ ibdev_dbg(ibdev, + "mana_ib_gd_create_dma_region ret %d gdma_region0x%llx\n",
drivers/infiniband/hw/mana/cq.c line 59
Quoted 5 lines
drivers/infiniband/hw/mana/cq.c new file +5
-0+ err, cq->gdma_region); + +/* The CQ ID is not known at this time +* The ID is generated at create_qp +*/ Wrong comment style, rdma uses the leading empty blank line for some reason
Quoted 3 lines
/*
* The CQ ID is not known at this time. The ID is generated atcreate_qp. */
Will fix all the comments.
Quoted 29 lines
Quoted 29 lines
drivers/infiniband/hw/mana/device.c new file +28
-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, +}; + +static int __init mana_ib_init (void ) +{ +auxiliary_driver_register (&mana_driver); + +return 0 ;
Quoted 8 lines
drivers/infiniband/hw/mana/device.c line 127
Quoted 6 lines
drivers/infiniband/hw/mana/device.c new file +6
-0+} + +static void __exit mana_ib_cleanup(void) { +auxiliary_driver_unregister (&mana_driver); +} +All this is just
module_auxiliary_driver()
Will fix this.
Quoted 10 lines
drivers/infiniband/hw/mana/main.c line 50
Quoted 8 lines
drivers/infiniband/hw/mana/main.c new file +7
-0+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);This leaves
vport_use_countelevated.
This is intentional. The code will call mana_ib_uncfg_vport() (which decreases vport_use_count ) when destroying the QP.
Quoted 14 lines
Review
Quoted 4 lines
(quoted diff) +3
-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);
drivers/infiniband/hw/mana/main.c line 105
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+struct ib_device *ibdev = ibpd->device; +struct mana_ib_dev *dev; + + dev = container_of(ibdev, struct mana_ib_dev, ib_dev); +return mana_ib_gd_destroy_pd (dev, pd->pd_handle);This is the only place that calls
mana_ib_gd_destroy_pd(), don't have a spaghetti of functions calling single other functions like this, just inline it.
Quoted 2 lines
Also it shouldn't have been non-static, please check everything that everything non-static actually has an out-of-file user.
Will fix those.
Quoted 20 lines
Review
Quoted 4 lines
(quoted diff) +3
-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 line 152
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_err (ibdev,"Failed to destroy doorbell page %d\n" , ret);This already printing on error
Quoted 5 lines
And again, why is this driver split up so strangely?
mana_gd_destroy_doorbell_page()is an RDMA function, it is only called by the RDMA code, why is it located underdrivers/net/ethernet?I do not want an RDMA driver in
drivers/net/ethernet.
Will move this function (and mana_gd_allocate_doorbell_page) to the RDMA driver.
Quoted 41 lines
drivers/infiniband/hw/mana/cq.c
Quoted 5 lines
drivers/infiniband/hw/mana/cq.c new file +3
-0+} + +int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct
ib_umem*umem,drivers/infiniband/hw/mana/main.c line 156
Quoted 1 line
drivers/infiniband/hw/mana/main.c new file +1
-0+ mana_handle_t *gdma_region, u64 page_sz){
Review
Quoted 1 line
(quoted diff) +1
-0+ size_t num_pages_total = ib_umem_num_dma_blocks(umem,
page_sz);Quoted 8 lines
drivers/infiniband/hw/mana/main.c new file +8
-0+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;drivers/infiniband/hw/mana/main.c
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+struct gdma_context *gc; +struct gdma_dev *mdev; +unsigned int i; +int err; + + mdev = dev->gdma_dev; + gc = mdev->gdma_context; + hwc = gc->hwc.driver_data; + max_pgs_create_cmd = + (hwc->max_req_msg_size - sizeof(*create_req)) /sizeof(u64);
drivers/infiniband/hw/mana/main.c
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-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 line 184
Quoted 3 lines
drivers/infiniband/hw/mana/main.c new file +3
-0+ + create_req =kzalloc (create_req_msg_size,GFP_KERNEL ); +if (!create_req)Is this a multi-order allocation, I can't tell how big
max_req_msg_sizeis?
Quoted 4 lines
This design seems to repeat the mistakes we made in mlx5, the low levels of the driver already has memory allocated - why not get a pointer to that memory here and directly fill the message buffer instead of all this allocation and memory copying?
max_req_msg_size is 4k bytes (one page). I think this allocation is still necessary as we don't have a buffer for this request. But we should be able to reuse this buffer for subsequent commands (details below).
Quoted 22 lines
drivers/infiniband/hw/mana/main.c
Quoted 7 lines
drivers/infiniband/hw/mana/main.c new file +7
-0+ibdev_dbg (&dev->ib_dev, +"size_dma_region %lu num_pages_total %lu, " +"page_sz 0x%llx offset_in_page %u\n" , + umem->length, num_pages_total, page_sz, + create_req->offset_in_page); + + ibdev_dbg(&dev->ib_dev, "num_pages_to_handle %lu,
gdma_page_type%u",drivers/infiniband/hw/mana/main.c
Quoted 13 lines
drivers/infiniband/hw/mana/main.c new file +12
-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; + + ibdev_dbg(&dev->ib_dev, "page num %u cur_addr 0x%llx\n",i,
Quoted 7 lines
drivers/infiniband/hw/mana/main.c line 216
Quoted 1 line
drivers/infiniband/hw/mana/main.c new file +1
-0+ cur_addr);Please get rid of the worthless debugging code, actually test your driver with EBUG enabled and ensure it is usuable. Printing thousands of lines of garbage is not OK. Especially when what should have been a
1 line loop body is expended into a big block just to have a worthless debug statement.
Will remove those debugging code.
Quoted 21 lines
Quoted 7 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+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);drivers/infiniband/hw/mana/main.c line 253
Quoted 10 lines
drivers/infiniband/hw/mana/main.c new file +10
-0+ + 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 =kmalloc (add_req_msg_size,GFP_KERNEL );And allocating every loop iteration seems like overkill, why not just reuse the large buffer that
create_reqallocated?
Quoted 3 lines
Usually the way these loops are structured is to fill the array and then check for fullness, trigger an action to drain the array, and reset the indexes back to the start.
I will reuse the command buffer allocated earlier as you suggested.
Quoted 21 lines
Quoted 2 lines
+int mana_ib_gd_create_pd(struct
mana_ib_dev*dev, u64*pd_handle,u32
*pd_id,Quoted 18 lines
drivers/infiniband/hw/mana/main.c new file +18
-0+ enum gdma_pd_flags flags) +{ +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_create_pd_resp resp = {}; +struct gdma_create_pd_req req = {}; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context; + +mana_gd_init_req_hdr (&req.hdr,GDMA_CREATE_PD ,sizeof (req), +sizeof (resp)); + + req.flags = flags; + err =mana_gd_send_request (gc,sizeof (req), &req,sizeof (resp), +&resp); + +if (err || resp.hdr.status) {
Quoted 8 lines
drivers/infiniband/hw/mana/main.c line 354
Quoted 5 lines
drivers/infiniband/hw/mana/main.c new file +5
-0+ibdev_err (&dev->ib_dev, +"Failed to get pd_id err %d status %u\n" , err, + resp.hdr.status); +if (!err) + err = -EPROTO ;This pattern is repeated everywhere, you should fix
mana_gd_send_request()to return EPROTO.
This pattern is also used all over in the ethernet driver. Since this patch series is for the RDMA driver, can we make a separate patch to refactor the code in mana_gd_send_request()? This can minimize the code changes to the ethernet driver in this patch series.
Quoted 8 lines
drivers/infiniband/hw/mana/main.c
Quoted 7 lines
drivers/infiniband/hw/mana/main.c new file +6
-0+return err; + } + + *pd_handle = resp.pd_handle; + *pd_id = resp.pd_id; + ibdev_dbg(&dev->ib_dev, "pd_handle 0x%llx pd_id %d\n",
*pd_handle,
Quoted 15 lines
drivers/infiniband/hw/mana/main.c line 375
Quoted 13 lines
drivers/infiniband/hw/mana/main.c new file +13
-0+ *pd_id); + +return 0 ; +} + +int mana_ib_gd_destroy_pd (struct mana_ib_dev *dev,u64 pd_handle) { +struct gdma_dev *mdev = dev->gdma_dev; +struct gdma_destory_pd_resp resp = {}; +struct gdma_destroy_pd_req req = {}; +struct gdma_context *gc; +int err; + + gc = mdev->gdma_context;Why the local for a variable that is used once?
Will refactoring the code.
Quoted 26 lines
Review
Quoted 5 lines
(quoted diff) +4
-0+int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct +*vma) { + 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_err(ibdev, "Unexpected vm_pgoff %lu\n", vma-
vm_pgoff);Review
Quoted 1 line
(quoted diff) +1
-0+ return -EINVAL;More user triggerable printing
Review
Quoted 2 lines
(quoted diff) +2
-0+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 11 lines
drivers/infiniband/hw/mana/mr.c line 125
Quoted 9 lines
drivers/infiniband/hw/mana/mr.c new file +9
-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;
mana_ib_gd_destroy_mr()is only ever called here, why is it inmain.c?
Will move it and mana_ib_gd_create_mr to mr.c
Quoted 65 lines
drivers/infiniband/hw/mana/qp.c
Quoted 6 lines
drivers/infiniband/hw/mana/qp.c new file +5
-0+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 36 lines
drivers/infiniband/hw/mana/qp.c new file +23
-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; +struct ib_cq *ibcq; +struct ib_wq *ibwq; +int i =0 , ret; +u32 port; + + mc = gd->driver_data; + +if (udata->inlen <sizeof (ucmd)) +return -EINVAL ; + + ret = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata-inlen));
drivers/infiniband/hw/mana/qp.c new file +12
-0+if (ret) { +ibdev_dbg (&mdev->ib_dev, +"Failed copy from udata for create rss-qp, err %d\n" , + ret); +return -EFAULT ; + } + +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 ;drivers/infiniband/hw/mana/qp.c
Quoted 10 lines
drivers/infiniband/hw/mana/qp.c new file +10
-0+ } + +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 ; + } + +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 14 lines
drivers/infiniband/hw/mana/qp.c line 162
Quoted 12 lines
drivers/infiniband/hw/mana/qp.c new file +12
-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 =kzalloc (sizeof (mana_handle_t) * + (1 << ind_tbl->log_ind_tbl_size), +GFP_KERNEL );Should be careful about maths overflow on this calculation.
Will add a check.
Quoted 26 lines
drivers/infiniband/hw/mana/qp.c
Quoted 5 lines
drivers/infiniband/hw/mana/qp.c new file +4
-0+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,
drivers/infiniband/hw/mana/qp.c line 328
Quoted 13 lines
drivers/infiniband/hw/mana/qp.c new file +13
-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" , + err); + goto err_free_vport; + } + qp->sq_umem = umem; + + err =mana_ib_gd_create_dma_region (mdev, qp->sq_umem, + &qp->sq_gdma_region,PAGE_SIZE ); +if (err) {All these cases that process a page list have to call
ib_umem_find_best_XXX()!It does important validation against hostile user input, including checking the critical iova.
Quoted 6 lines
You have missed that the user can request that an unaligned umem be created and this creates a starting offset from the first page that must be honored in HW, or there will be weird memory corruption. Since it looks like this HW doesn't support a starting page offset this should call
ib_umem_find_best_pgsz()with aSZ_4Kand a 0 iova. Also never usePAGE_SIZEto describe a HW limitation.
Thank you, will fix this.
Quoted 3 lines
There is alot of repeated code here, it would do well to have a wrapper function consolidating this pattern.
Will factor the code.
Thanks,
Long
Quoted 20 lines · On Tue, Sep 20, 2022 at 06:22:20PM -0700, [email protected] wrote:
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/1177Ajay 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
Quoted 10 lines
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: Add functions for allocating doorbell page from GDMA
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 RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter
Still some basic checkpatchy stuff:
/tmp/tmpm2fsg47h/0012-RDMA-mana_ib-Add-a-driver-for-Microsoft-Azure-Network-Adapter.patch:412: WARNING: quoted string split across lines #412: FILE: drivers/infiniband/hw/mana/main.c:70:
+ "vport handle %llx pdid %x doorbell_id %x "
+ "tx_shortform_allowed %d tx_vp_offset %u\n",
/tmp/tmpm2fsg47h/0012-RDMA-mana_ib-Add-a-driver-for-Microsoft-Azure-Network-Adapter.patch:540: WARNING: quoted string split across lines #540: FILE: drivers/infiniband/hw/mana/main.c:198:
+ "size_dma_region %lu num_pages_total %lu, "
+ "page_sz 0x%llx offset_in_page %u\n",
And it thinks you should write more for the kconfig symbol, eg why would someone want to turn it on (hint, to use dpkd on some Azure instances)
/tmp/tmpm2fsg47h/0012-RDMA-mana_ib-Add-a-driver-for-Microsoft-Azure-Network-Adapter.patch:100: WARNING: please write a help paragraph that fully describes the config symbol #100: FILE: drivers/infiniband/hw/mana/Kconfig:2:
+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).
I'll put it in linux-next and you can fix the rest of the stuff bots will usually find.
Jason
Quoted 68 lines
Subject: Re: [Patch v6 00/12] Introduce Microsoft Azure Network Adapter (MANA) RDMA driver
Quoted 7 lines · On Tue, Sep 20, 2022 at 06:22:20PM -0700, [email protected] wrote:
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.
Quoted 4 lines
The last patch implementes the RDMA driver.
The user-mode of the driver is being reviewed at:
https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgith
Quoted 1 line
ub.com%2Flinux-rdma%2Frdma-
core%2Fpull%2F1177&data=05%7C01%7Clongl
Quoted 1 line
i%40microsoft.com%7C1d30ce9d49bc411b0fb808da9bede4bd%7C72f988bf86 f141a
Quoted 1 line
f91ab2d7cd011db47%7C1%7C0%7C637993743320198387%7CUnknown%7CT WFpbGZsb3d
Quoted 1 line
8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% 3D%7C
Quoted 1 line
3000%7C%7C%7C&sdata=4cT9PFnKqb2yHRLkKNrbVVMAGwO6Ig91eoQ zomlm6lY%3D
Quoted 10 lines
&reserved=0
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
registrationQuoted 10 lines
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: Add functions for allocating doorbell page from GDMA
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 RDMA/mana_ib: Add a driver for Microsoft Azure Network AdapterStill some basic checkpatchy stuff:
/tmp/tmpm2fsg47h/0012-RDMA-mana_ib-Add-a-driver-for-Microsoft-Azure-Network-Adapter.patch:412: WARNING: quoted string split across lines
#412: FILE:drivers/infiniband/hw/mana/main.c:70:(quoted diff) +2
-0+ "vport handle %llx pdid %x doorbell_id %x " + "tx_shortform_allowed %d tx_vp_offset %u\n",
/tmp/tmpm2fsg47h/0012-RDMA-mana_ib-Add-a-driver-for-Microsoft-Azure-Network-Adapter.patch:540: WARNING: quoted string split across lines
#540: FILE:drivers/infiniband/hw/mana/main.c:198:(quoted diff) +2
-0+ "size_dma_region %lu num_pages_total %lu, " + "page_sz 0x%llx offset_in_page %u\n",
Quoted 3 lines
And it thinks you should write more for the kconfig symbol, eg why would someone want to turn it on (hint, to use dpkd on some Azure instances)
Will fix those.
Quoted 13 lines
/tmp/tmpm2fsg47h/0012-RDMA-mana_ib-Add-a-driver-for-Microsoft-Azure-Network-Adapter.patch:100: WARNING: please write a help paragraph that fully describes the config symbol #100: FILE:drivers/infiniband/hw/mana/Kconfig:2:(quoted diff) +3
-0+config MANA_INFINIBAND + tristate "Microsoft Azure Network Adapter support" + depends on NETDEVICES && ETHERNET && PCI &&
MICROSOFT_MANA(quoted diff) +3
-0+ help + This driver provides low-level RDMA support for + Microsoft Azure Network Adapter (MANA).