From 78683c25c80e54bf3e8015fdfb8cba2fcd03daa5 Mon Sep 17 00:00:00 2001 From: Konstantin Taranov Date: Mon, 20 Jan 2025 09:27:07 -0800 Subject: RDMA/mana_ib: Allow registration of DMA-mapped memory in PDs Allow the HW to register DMA-mapped memory for kernel-level PDs. Signed-off-by: Konstantin Taranov Link: https://patch.msgid.link/1737394039-28772-2-git-send-email-kotaranov@linux.microsoft.com Reviewed-by: Shiraz Saleem Reviewed-by: Long Li Signed-off-by: Leon Romanovsky --- include/net/mana/gdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 90f56656b572..03e1b257953e 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -775,6 +775,7 @@ struct gdma_destroy_dma_region_req { enum gdma_pd_flags { GDMA_PD_FLAG_INVALID = 0, + GDMA_PD_FLAG_ALLOW_GPA_MR = 1, }; struct gdma_create_pd_req { -- cgit v1.2.3 From 6e1b8bdcd04f4e84c924489e2f837cf620002b69 Mon Sep 17 00:00:00 2001 From: Konstantin Taranov Date: Mon, 20 Jan 2025 09:27:08 -0800 Subject: RDMA/mana_ib: implement get_dma_mr Implement allocation of DMA-mapped memory regions. Signed-off-by: Konstantin Taranov Link: https://patch.msgid.link/1737394039-28772-3-git-send-email-kotaranov@linux.microsoft.com Reviewed-by: Shiraz Saleem Reviewed-by: Long Li Signed-off-by: Leon Romanovsky --- include/net/mana/gdma.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 03e1b257953e..a94b04ea926f 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -801,6 +801,11 @@ struct gdma_destory_pd_resp { };/* HW DATA */ enum gdma_mr_type { + /* + * Guest Physical Address - MRs of this type allow access + * to any DMA-mapped memory using bus-logical address + */ + GDMA_MR_TYPE_GPA = 1, /* Guest Virtual Address - MRs of this type allow access * to memory mapped by PTEs associated with this MR using a virtual * address that is set up in the MST -- cgit v1.2.3 From 5459f6523c1f1a053cdc6411a810061ee717219c Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Mon, 3 Feb 2025 14:48:04 +0200 Subject: IB/cache: Add log messages for IB device state changes Enhance visibility into IB device state transitions by adding log messages to the kernel log (dmesg). Whenever an IB device changes state, a relevant print will be printed, such as: "mlx5_core 0000:08:00.0 mlx5_0: Port: 1 Link DOWN" "mlx5_core 0000:08:00.0 rdmap8s0f0: Port: 2 Link ACTIVE" Signed-off-by: Maher Sanalla Link: https://patch.msgid.link/2d26ccbd669bad99089fa2aebb5cba4014fc4999.1738586601.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 0ad104dae253..b59bf30de430 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -519,6 +519,23 @@ enum ib_port_state { IB_PORT_ACTIVE_DEFER = 5 }; +static inline const char *__attribute_const__ +ib_port_state_to_str(enum ib_port_state state) +{ + const char * const states[] = { + [IB_PORT_NOP] = "NOP", + [IB_PORT_DOWN] = "DOWN", + [IB_PORT_INIT] = "INIT", + [IB_PORT_ARMED] = "ARMED", + [IB_PORT_ACTIVE] = "ACTIVE", + [IB_PORT_ACTIVE_DEFER] = "ACTIVE_DEFER", + }; + + if (state < ARRAY_SIZE(states)) + return states[state]; + return "UNKNOWN"; +} + enum ib_port_phys_state { IB_PORT_PHYS_STATE_SLEEP = 1, IB_PORT_PHYS_STATE_POLLING = 2, -- cgit v1.2.3 From bad4480934c8227d8a03b6b76e276349506b2bfe Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Wed, 5 Feb 2025 02:35:12 -0800 Subject: RDMA/mana_ib: Query feature_flags bitmask from FW Extend the mana_ib_gd_query_adapter_caps function to retrieve and store the feature_flags from the firmware response. Signed-off-by: Shiraz Saleem Signed-off-by: Konstantin Taranov Link: https://patch.msgid.link/1738751713-16169-2-git-send-email-kotaranov@linux.microsoft.com Signed-off-by: Leon Romanovsky --- include/net/mana/gdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index a94b04ea926f..50ffbc408346 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -152,6 +152,7 @@ struct gdma_general_req { #define GDMA_MESSAGE_V1 1 #define GDMA_MESSAGE_V2 2 #define GDMA_MESSAGE_V3 3 +#define GDMA_MESSAGE_V4 4 struct gdma_general_resp { struct gdma_resp_hdr hdr; -- cgit v1.2.3 From a1ecb30f90856b0be4168ad51b8875148e285c1f Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Thu, 27 Feb 2025 16:54:20 +0000 Subject: RDMA/core: Don't expose hw_counters outside of init net namespace Commit 467f432a521a ("RDMA/core: Split port and device counter sysfs attributes") accidentally almost exposed hw counters to non-init net namespaces. It didn't expose them fully, as an attempt to read any of those counters leads to a crash like this one: [42021.807566] BUG: kernel NULL pointer dereference, address: 0000000000000028 [42021.814463] #PF: supervisor read access in kernel mode [42021.819549] #PF: error_code(0x0000) - not-present page [42021.824636] PGD 0 P4D 0 [42021.827145] Oops: 0000 [#1] SMP PTI [42021.830598] CPU: 82 PID: 2843922 Comm: switchto-defaul Kdump: loaded Tainted: G S W I XXX [42021.841697] Hardware name: XXX [42021.849619] RIP: 0010:hw_stat_device_show+0x1e/0x40 [ib_core] [42021.855362] Code: 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 49 89 d0 4c 8b 5e 20 48 8b 8f b8 04 00 00 48 81 c7 f0 fa ff ff <48> 8b 41 28 48 29 ce 48 83 c6 d0 48 c1 ee 04 69 d6 ab aa aa aa 48 [42021.873931] RSP: 0018:ffff97fe90f03da0 EFLAGS: 00010287 [42021.879108] RAX: ffff9406988a8c60 RBX: ffff940e1072d438 RCX: 0000000000000000 [42021.886169] RDX: ffff94085f1aa000 RSI: ffff93c6cbbdbcb0 RDI: ffff940c7517aef0 [42021.893230] RBP: ffff97fe90f03e70 R08: ffff94085f1aa000 R09: 0000000000000000 [42021.900294] R10: ffff94085f1aa000 R11: ffffffffc0775680 R12: ffffffff87ca2530 [42021.907355] R13: ffff940651602840 R14: ffff93c6cbbdbcb0 R15: ffff94085f1aa000 [42021.914418] FS: 00007fda1a3b9700(0000) GS:ffff94453fb80000(0000) knlGS:0000000000000000 [42021.922423] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [42021.928130] CR2: 0000000000000028 CR3: 00000042dcfb8003 CR4: 00000000003726f0 [42021.935194] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [42021.942257] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [42021.949324] Call Trace: [42021.951756] [42021.953842] [] ? show_regs+0x64/0x70 [42021.959030] [] ? __die+0x78/0xc0 [42021.963874] [] ? page_fault_oops+0x2b5/0x3b0 [42021.969749] [] ? exc_page_fault+0x1a2/0x3c0 [42021.975549] [] ? asm_exc_page_fault+0x26/0x30 [42021.981517] [] ? __pfx_show_hw_stats+0x10/0x10 [ib_core] [42021.988482] [] ? hw_stat_device_show+0x1e/0x40 [ib_core] [42021.995438] [] dev_attr_show+0x1e/0x50 [42022.000803] [] sysfs_kf_seq_show+0x81/0xe0 [42022.006508] [] seq_read_iter+0xf4/0x410 [42022.011954] [] vfs_read+0x16e/0x2f0 [42022.017058] [] ksys_read+0x6e/0xe0 [42022.022073] [] do_syscall_64+0x6a/0xa0 [42022.027441] [] entry_SYSCALL_64_after_hwframe+0x78/0xe2 The problem can be reproduced using the following steps: ip netns add foo ip netns exec foo bash cat /sys/class/infiniband/mlx4_0/hw_counters/* The panic occurs because of casting the device pointer into an ib_device pointer using container_of() in hw_stat_device_show() is wrong and leads to a memory corruption. However the real problem is that hw counters should never been exposed outside of the non-init net namespace. Fix this by saving the index of the corresponding attribute group (it might be 1 or 2 depending on the presence of driver-specific attributes) and zeroing the pointer to hw_counters group for compat devices during the initialization. With this fix applied hw_counters are not available in a non-init net namespace: find /sys/class/infiniband/mlx4_0/ -name hw_counters /sys/class/infiniband/mlx4_0/ports/1/hw_counters /sys/class/infiniband/mlx4_0/ports/2/hw_counters /sys/class/infiniband/mlx4_0/hw_counters ip netns add foo ip netns exec foo bash find /sys/class/infiniband/mlx4_0/ -name hw_counters Fixes: 467f432a521a ("RDMA/core: Split port and device counter sysfs attributes") Signed-off-by: Roman Gushchin Cc: Jason Gunthorpe Cc: Leon Romanovsky Cc: Maher Sanalla Cc: linux-rdma@vger.kernel.org Cc: linux-kernel@vger.kernel.org Link: https://patch.msgid.link/20250227165420.3430301-1-roman.gushchin@linux.dev Reviewed-by: Parav Pandit Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index b59bf30de430..a5761038935d 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2767,6 +2767,7 @@ struct ib_device { * It is a NULL terminated array. */ const struct attribute_group *groups[4]; + u8 hw_stats_attr_index; u64 uverbs_cmd_mask; -- cgit v1.2.3 From 61e51682816d395307f78ae06d640089054c28ab Mon Sep 17 00:00:00 2001 From: Chiara Meiohas Date: Thu, 6 Mar 2025 13:51:26 +0200 Subject: RDMA/uverbs: Introduce UCAP (User CAPabilities) API Implement a new User CAPabilities (UCAP) API to provide fine-grained control over specific firmware features. This approach offers more granular capabilities than the existing Linux capabilities, which may be too generic for certain FW features. This mechanism represents each capability as a character device with root read-write access. Root processes can grant users special privileges by allowing access to these character devices (e.g., using chown). UCAP character devices are located in /dev/infiniband and the class path is /sys/class/infiniband_ucaps. Signed-off-by: Chiara Meiohas Link: https://patch.msgid.link/5a1379187cd21178e8554afc81a3c941f21af22f.1741261611.git.leon@kernel.org Reviewed-by: Yishai Hadas Reviewed-by: Zhu Yanjun Signed-off-by: Leon Romanovsky --- include/rdma/ib_ucaps.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 include/rdma/ib_ucaps.h (limited to 'include') diff --git a/include/rdma/ib_ucaps.h b/include/rdma/ib_ucaps.h new file mode 100644 index 000000000000..d9f96be3a553 --- /dev/null +++ b/include/rdma/ib_ucaps.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* + * Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ + +#ifndef _IB_UCAPS_H_ +#define _IB_UCAPS_H_ + +#define UCAP_ENABLED(ucaps, type) (!!((ucaps) & (1U << (type)))) + +enum rdma_user_cap { + RDMA_UCAP_MLX5_CTRL_LOCAL, + RDMA_UCAP_MLX5_CTRL_OTHER_VHCA, + RDMA_UCAP_MAX +}; + +void ib_cleanup_ucaps(void); +int ib_get_ucaps(int *fds, int fd_count, uint64_t *idx_mask); +#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) +int ib_create_ucap(enum rdma_user_cap type); +void ib_remove_ucap(enum rdma_user_cap type); +#else +static inline int ib_create_ucap(enum rdma_user_cap type) +{ + return -EOPNOTSUPP; +} +static inline void ib_remove_ucap(enum rdma_user_cap type) {} +#endif /* CONFIG_INFINIBAND_USER_ACCESS */ + +#endif /* _IB_UCAPS_H_ */ -- cgit v1.2.3 From fe9d7822baee65d8e77542391799b2777f5216f5 Mon Sep 17 00:00:00 2001 From: Chiara Meiohas Date: Thu, 6 Mar 2025 13:51:28 +0200 Subject: RDMA/uverbs: Add support for UCAPs in context creation Add support for file descriptor array attribute for GET_CONTEXT commands. Check that the file descriptor (fd) array represents fds for valid UCAPs. Store the enabled UCAPs from the fd array as a bitmask in ib_ucontext. Signed-off-by: Chiara Meiohas Link: https://patch.msgid.link/ebfb30bc947e2259b193c96a319c80e82599045b.1741261611.git.leon@kernel.org Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 1 + include/uapi/rdma/ib_user_ioctl_cmds.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a5761038935d..9941f4185c79 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1530,6 +1530,7 @@ struct ib_ucontext { struct ib_uverbs_file *ufile; struct ib_rdmacg_object cg_obj; + u64 enabled_caps; /* * Implementation details of the RDMA core, don't use in drivers: */ diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h index ec719053aab9..ac7b162611ed 100644 --- a/include/uapi/rdma/ib_user_ioctl_cmds.h +++ b/include/uapi/rdma/ib_user_ioctl_cmds.h @@ -88,6 +88,7 @@ enum uverbs_attrs_query_port_cmd_attr_ids { enum uverbs_attrs_get_context_attr_ids { UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS, UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT, + UVERBS_ATTR_GET_CONTEXT_FD_ARR, }; enum uverbs_attrs_query_context_attr_ids { -- cgit v1.2.3 From 74934ddf124a6f6e438b570ab5fb70ef83626707 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 6 Mar 2025 13:51:30 +0200 Subject: RDMA/mlx5: Expose RDMA TRANSPORT flow table types to userspace This patch adds RDMA_TRANSPORT_RX and RDMA_TRANSPORT_TX as a new flow table type for matcher creation. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky Link: https://patch.msgid.link/2287d8c50483e880450c7e8e08d9de34cdec1b14.1741261611.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 1 + include/uapi/rdma/mlx5_user_ioctl_verbs.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index fd2e4a3a56b3..18f9fe070213 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -239,6 +239,7 @@ enum mlx5_ib_flow_matcher_create_attrs { MLX5_IB_ATTR_FLOW_MATCHER_MATCH_CRITERIA, MLX5_IB_ATTR_FLOW_MATCHER_FLOW_FLAGS, MLX5_IB_ATTR_FLOW_MATCHER_FT_TYPE, + MLX5_IB_ATTR_FLOW_MATCHER_IB_PORT, }; enum mlx5_ib_flow_matcher_destroy_attrs { diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h index 7c233df475e7..8f86e79d78a5 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h +++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h @@ -45,6 +45,8 @@ enum mlx5_ib_uapi_flow_table_type { MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB = 0x2, MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX = 0x3, MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TX = 0x4, + MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_RX = 0x5, + MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_TRANSPORT_TX = 0x6, }; enum mlx5_ib_uapi_flow_action_packet_reformat_type { -- cgit v1.2.3 From a8445cfec101c42e9d64cdb2dac13973b22c205c Mon Sep 17 00:00:00 2001 From: Long Li Date: Wed, 12 Mar 2025 16:15:31 -0700 Subject: net: mana: Change the function signature of mana_get_primary_netdev_rcu Change mana_get_primary_netdev_rcu() to mana_get_primary_netdev(), and return the ndev with refcount held. The caller is responsible for dropping the refcount. Also drop the check for IFF_SLAVE as it is not necessary if the upper device is present. Signed-off-by: Long Li Link: https://patch.msgid.link/1741821332-9392-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Leon Romanovsky --- include/net/mana/mana.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 0d00b24eacaf..0f78065de8fe 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -827,5 +827,7 @@ 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); -struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index); +struct net_device *mana_get_primary_netdev(struct mana_context *ac, + u32 port_index, + netdevice_tracker *tracker); #endif /* _MANA_H */ -- cgit v1.2.3 From 81f8f7454ad9e0bf95efdec6542afdc9a6ab1e24 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Wed, 26 Feb 2025 15:54:13 +0200 Subject: RDMA/uverbs: Propagate errors from rdma_lookup_get_uobject() Currently, the IB uverbs API calls uobj_get_uobj_read(), which in turn uses the rdma_lookup_get_uobject() helper to retrieve user objects. In case of failure, uobj_get_uobj_read() returns NULL, overriding the error code from rdma_lookup_get_uobject(). The IB uverbs API then translates this NULL to -EINVAL, masking the actual error and complicating debugging. For example, applications calling ibv_modify_qp that fails with EBUSY when retrieving the QP uobject will see the overridden error code EINVAL instead, masking the actual error. Furthermore, based on rdma-core commit: "2a22f1ced5f3 ("Merge pull request #1568 from jakemoroni/master")" Kernel's IB uverbs return values are either ignored and passed on as is to application or overridden with other errnos in a few cases. Thus, to improve error reporting and debuggability, propagate the original error from rdma_lookup_get_uobject() instead of replacing it with EINVAL. Signed-off-by: Maher Sanalla Link: https://patch.msgid.link/64f9d3711b183984e939962c2f83383904f97dfb.1740577869.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/rdma/uverbs_std_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h index fe0512116958..555ea3d142a4 100644 --- a/include/rdma/uverbs_std_types.h +++ b/include/rdma/uverbs_std_types.h @@ -34,7 +34,7 @@ static inline void *_uobj_get_obj_read(struct ib_uobject *uobj) { if (IS_ERR(uobj)) - return NULL; + return ERR_CAST(uobj); return uobj->object; } #define uobj_get_obj_read(_object, _type, _id, _attrs) \ -- cgit v1.2.3 From d375db42a8effdfeb7973d4f1b0b5985e066fd28 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Mar 2025 16:18:41 +0200 Subject: RDMA/mlx5: Add optional counters for RDMA_TX/RX_packets/bytes Add the following optional counters: rdma_tx_packets,rdma_rx_bytes,rdma_rx_packets,rdma_tx_bytes. Which counts all RDMA packets/bytes sent and received per link. Note that since each direction packet and byte counter are shared, the counter is only reset when both counters of that direction are removed. But from user-perspective each can be enabled/disabled separately. The counters can be enabled using: sudo rdma stat set link rocep8s0f0/1 optional-counters rdma_tx_packets And can be seen using: rdma stat -j show link rocep8s0f0/1 Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://patch.msgid.link/9f2753ad636f21704416df64b47395c8991d1123.1741875070.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8fe56d0362c6..63f0d9fb94b4 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1532,8 +1532,8 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } -#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 2 -#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 1 +#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 3 +#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 2 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1 -- cgit v1.2.3 From 7e53b31acc7f976d01a0718724a4c36f1fddf739 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Mar 2025 16:18:42 +0200 Subject: RDMA/core: Create and destroy rdma_counter using rdma_zalloc_drv_obj() Change rdma_counter allocation to use rdma_zalloc_drv_obj() instead of, explicitly allocating at core, in order to be contained inside driver specific structures. Adjust all drivers that use it to have their containing structure, and add driver specific initialization operation. This change is needed to allow upcoming patches to implement optional-counters binding whereas inside each driver specific counter struct his bound optional-counters will be maintained. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://patch.msgid.link/a5a484f421fc2e5595158e61a354fba43272b02d.1741875070.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9941f4185c79..90e93297d59e 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2665,6 +2665,11 @@ struct ib_device_ops { */ int (*counter_update_stats)(struct rdma_counter *counter); + /** + * counter_init - Initialize the driver specific rdma counter struct. + */ + void (*counter_init)(struct rdma_counter *counter); + /** * Allows rdma drivers to add their own restrack attributes * dumped via 'rdma stat' iproute2 command. @@ -2716,6 +2721,7 @@ struct ib_device_ops { DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); + DECLARE_RDMA_OBJ_SIZE(rdma_counter); }; struct ib_core_device { -- cgit v1.2.3 From da3711074f5252ee35d6348ca286351013f1d7fe Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Mar 2025 16:18:43 +0200 Subject: RDMA/core: Add support to optional-counters binding configuration Whenever a new counter is created, save inside it the user requested configuration for optional-counters binding, for manual configuration it is requested directly by the user and for the automatic configuration it depends on if the automatic binding was enabled with or without optional-counters binding. This argument will later be used by the driver to determine if to bind the optional-counters as well or not when trying to bind this counter to a QP. It indicates that when binding counters to a QP we also want the currently enabled link optional-counters to be bound as well. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://patch.msgid.link/82f1c357606a16932979ef9a5910122675c74a3a.1741875070.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/rdma/rdma_counter.h | 5 ++++- include/uapi/rdma/rdma_netlink.h | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/rdma_counter.h b/include/rdma/rdma_counter.h index 45d5481a7846..74e635409ff7 100644 --- a/include/rdma/rdma_counter.h +++ b/include/rdma/rdma_counter.h @@ -23,6 +23,7 @@ struct rdma_counter_mode { enum rdma_nl_counter_mode mode; enum rdma_nl_counter_mask mask; struct auto_mode_param param; + bool bind_opcnt; }; struct rdma_port_counter { @@ -47,6 +48,7 @@ void rdma_counter_init(struct ib_device *dev); void rdma_counter_release(struct ib_device *dev); int rdma_counter_set_auto_mode(struct ib_device *dev, u32 port, enum rdma_nl_counter_mask mask, + bool bind_opcnt, struct netlink_ext_ack *extack); int rdma_counter_bind_qp_auto(struct ib_qp *qp, u32 port); int rdma_counter_unbind_qp(struct ib_qp *qp, bool force); @@ -61,7 +63,8 @@ int rdma_counter_unbind_qpn(struct ib_device *dev, u32 port, u32 qp_num, u32 counter_id); int rdma_counter_get_mode(struct ib_device *dev, u32 port, enum rdma_nl_counter_mode *mode, - enum rdma_nl_counter_mask *mask); + enum rdma_nl_counter_mask *mask, + bool *opcnt); int rdma_counter_modify(struct ib_device *dev, u32 port, unsigned int index, bool enable); diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 9f9cf20c1cd8..f41f0228fcd0 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -580,6 +580,8 @@ enum rdma_nldev_attr { RDMA_NLDEV_ATTR_EVENT_TYPE, /* u8 */ RDMA_NLDEV_SYS_ATTR_MONITOR_MODE, /* u8 */ + + RDMA_NLDEV_ATTR_STAT_OPCOUNTER_ENABLED, /* u8 */ /* * Always the end */ -- cgit v1.2.3 From 88ae02feda84f0f78ff7243ef437e79624fdcd80 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Mar 2025 16:18:44 +0200 Subject: RDMA/core: Pass port to counter bind/unbind operations This will be useful for the next patches in the series since port number is needed for optional counters binding and unbinding. Note that this change is needed since when the operation is done qp->port isn't necessarily initialized yet and can't be used. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://patch.msgid.link/b6f6797844acbd517358e8d2a270ea9b3e6ecba1.1741875070.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 5 +++-- include/rdma/rdma_counter.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 90e93297d59e..d42eae69d9a8 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2644,12 +2644,13 @@ struct ib_device_ops { * @counter - The counter to be bound. If counter->id is zero then * the driver needs to allocate a new counter and set counter->id */ - int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp); + int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp, + u32 port); /** * counter_unbind_qp - Unbind the qp from the dynamically-allocated * counter and bind it onto the default one */ - int (*counter_unbind_qp)(struct ib_qp *qp); + int (*counter_unbind_qp)(struct ib_qp *qp, u32 port); /** * counter_dealloc -De-allocate the hw counter */ diff --git a/include/rdma/rdma_counter.h b/include/rdma/rdma_counter.h index 74e635409ff7..4204d08a010a 100644 --- a/include/rdma/rdma_counter.h +++ b/include/rdma/rdma_counter.h @@ -51,7 +51,7 @@ int rdma_counter_set_auto_mode(struct ib_device *dev, u32 port, bool bind_opcnt, struct netlink_ext_ack *extack); int rdma_counter_bind_qp_auto(struct ib_qp *qp, u32 port); -int rdma_counter_unbind_qp(struct ib_qp *qp, bool force); +int rdma_counter_unbind_qp(struct ib_qp *qp, u32 port, bool force); int rdma_counter_query_stats(struct rdma_counter *counter); u64 rdma_counter_get_hwstat_value(struct ib_device *dev, u32 port, u32 index); -- cgit v1.2.3 From fd24c9ef6c8f12fd045524c7cae1992f7967e94b Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 13 Mar 2025 16:18:46 +0200 Subject: RDMA/mlx5: Support optional-counters binding for QPs Add support to allow optional-counters binding to a QP, whereas when a bind operation is requested depending on the counter optional-counter binding state the driver will determine if to also add optional-counters to this QP binding. The optional-counter binding is done by simply adding a steering rule for the specific optional-counter condition with the additional match over that QP number. Note that optional-counters per QP rules are handled on an earlier prio than per device counters, and per device counter correctness is maintained by core whereas it is responsible to sum active counters when checking device counter and to add them to history count when they are deallocated. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://patch.msgid.link/2cad1b891a6641ae61fe8d92f867e1059121813a.1741875070.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 63f0d9fb94b4..344124644697 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1532,8 +1532,8 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } -#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 3 -#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 2 +#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 6 +#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 4 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1 -- cgit v1.2.3