- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] drm/xe: Check return value of GGTT workqueue allocation" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x ce29214ada6d08dbde1eeb5a69c3b09ddf3da146 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102655-unsettled-dingy-acaf@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ce29214ada6d08dbde1eeb5a69c3b09ddf3da146 Mon Sep 17 00:00:00 2001 From: Matthew Brost <matthew.brost(a)intel.com> Date: Tue, 21 Oct 2025 17:55:36 -0700 Subject: [PATCH] drm/xe: Check return value of GGTT workqueue allocation Workqueue allocation can fail, so check the return value of the GGTT workqueue allocation and fail driver initialization if the allocation fails. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: stable(a)vger.kernel.org Signed-off-by: Matthew Brost <matthew.brost(a)intel.com> Reviewed-by: Matthew Auld <matthew.auld(a)intel.com> Link: https://lore.kernel.org/r/20251022005538.828980-2-matthew.brost@intel.com (cherry picked from commit 1f1314e8e71385bae319e43082b798c11f6648bc) Signed-off-by: Lucas De Marchi <lucas.demarchi(a)intel.com> diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 7fdd0a97a628..5edc0cad47e2 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -292,6 +292,9 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt) ggtt->pt_ops = &xelp_pt_ops; ggtt->wq = alloc_workqueue("xe-ggtt-wq", 0, WQ_MEM_RECLAIM); + if (!ggtt->wq) + return -ENOMEM; + __xe_ggtt_init_early(ggtt, xe_wopcm_size(xe)); err = drmm_add_action_or_reset(&xe->drm, ggtt_fini_early, ggtt);

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] io_uring/sqpoll: switch away from getrusage() for CPU" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x 8ac9b0d33e5c0a995338ee5f25fe1b6ff7d97f65 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102606-showplace-direness-c7b3@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8ac9b0d33e5c0a995338ee5f25fe1b6ff7d97f65 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe(a)kernel.dk> Date: Tue, 21 Oct 2025 07:16:08 -0600 Subject: [PATCH] io_uring/sqpoll: switch away from getrusage() for CPU accounting getrusage() does a lot more than what the SQPOLL accounting needs, the latter only cares about (and uses) the stime. Rather than do a full RUSAGE_SELF summation, just query the used stime instead. Cc: stable(a)vger.kernel.org Fixes: 3fcb9d17206e ("io_uring/sqpoll: statistics of the true utilization of sq threads") Reviewed-by: Gabriel Krisman Bertazi <krisman(a)suse.de> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index ff3364531c77..294c75a8a3bd 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -59,7 +59,6 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { struct io_overflow_cqe *ocqe; struct io_rings *r = ctx->rings; - struct rusage sq_usage; unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; unsigned int sq_head = READ_ONCE(r->sq.head); unsigned int sq_tail = READ_ONCE(r->sq.tail); @@ -152,14 +151,15 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) * thread termination. */ if (tsk) { + u64 usec; + get_task_struct(tsk); rcu_read_unlock(); - getrusage(tsk, RUSAGE_SELF, &sq_usage); + usec = io_sq_cpu_usec(tsk); put_task_struct(tsk); sq_pid = sq->task_pid; sq_cpu = sq->sq_cpu; - sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000 - + sq_usage.ru_stime.tv_usec); + sq_total_time = usec; sq_work_time = sq->work_time; } else { rcu_read_unlock(); diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index a3f11349ce06..2b816fdb9866 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -11,6 +11,7 @@ #include <linux/audit.h> #include <linux/security.h> #include <linux/cpuset.h> +#include <linux/sched/cputime.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> @@ -169,6 +170,20 @@ static inline bool io_sqd_events_pending(struct io_sq_data *sqd) return READ_ONCE(sqd->state); } +u64 io_sq_cpu_usec(struct task_struct *tsk) +{ + u64 utime, stime; + + task_cputime_adjusted(tsk, &utime, &stime); + do_div(stime, 1000); + return stime; +} + +static void io_sq_update_worktime(struct io_sq_data *sqd, u64 usec) +{ + sqd->work_time += io_sq_cpu_usec(current) - usec; +} + static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) { unsigned int to_submit; @@ -255,26 +270,15 @@ static bool io_sq_tw_pending(struct llist_node *retry_list) return retry_list || !llist_empty(&tctx->task_list); } -static void io_sq_update_worktime(struct io_sq_data *sqd, struct rusage *start) -{ - struct rusage end; - - getrusage(current, RUSAGE_SELF, &end); - end.ru_stime.tv_sec -= start->ru_stime.tv_sec; - end.ru_stime.tv_usec -= start->ru_stime.tv_usec; - - sqd->work_time += end.ru_stime.tv_usec + end.ru_stime.tv_sec * 1000000; -} - static int io_sq_thread(void *data) { struct llist_node *retry_list = NULL; struct io_sq_data *sqd = data; struct io_ring_ctx *ctx; - struct rusage start; unsigned long timeout = 0; char buf[TASK_COMM_LEN] = {}; DEFINE_WAIT(wait); + u64 start; /* offload context creation failed, just exit */ if (!current->io_uring) { @@ -317,7 +321,7 @@ static int io_sq_thread(void *data) } cap_entries = !list_is_singular(&sqd->ctx_list); - getrusage(current, RUSAGE_SELF, &start); + start = io_sq_cpu_usec(current); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { int ret = __io_sq_thread(ctx, cap_entries); @@ -333,7 +337,7 @@ static int io_sq_thread(void *data) if (sqt_spin || !time_after(jiffies, timeout)) { if (sqt_spin) { - io_sq_update_worktime(sqd, &start); + io_sq_update_worktime(sqd, start); timeout = jiffies + sqd->sq_thread_idle; } if (unlikely(need_resched())) { diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h index b83dcdec9765..fd2f6f29b516 100644 --- a/io_uring/sqpoll.h +++ b/io_uring/sqpoll.h @@ -29,6 +29,7 @@ void io_sq_thread_unpark(struct io_sq_data *sqd); void io_put_sq_data(struct io_sq_data *sqd); void io_sqpoll_wait_sq(struct io_ring_ctx *ctx); int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask); +u64 io_sq_cpu_usec(struct task_struct *tsk); static inline struct task_struct *sqpoll_task_locked(struct io_sq_data *sqd) {

1 month, 3 weeks

2
1
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102615-unsoiled-renovator-7821@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102614-knickers-other-9f02@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102614-trustful-rancidity-1b04@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102614-goatskin-stopped-5434@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102613-disgrace-junkman-a4f1@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102613-alarm-decipher-135c@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] smb: client: allocate enough space for MR WRs and" failed to apply to 6.17-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.17-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.17.y git checkout FETCH_HEAD git cherry-pick -x e607ef686ab95fbcb0dfd16f49aea7918be626e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025102613-galvanize-commerce-52df@gregkh' --subject-prefix 'PATCH 6.17.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e607ef686ab95fbcb0dfd16f49aea7918be626e1 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher <metze(a)samba.org> Date: Thu, 16 Oct 2025 12:54:21 +0200 Subject: [PATCH] smb: client: allocate enough space for MR WRs and ib_drain_qp() The IB_WR_REG_MR and IB_WR_LOCAL_INV operations for smbdirect_mr_io structures should never fail because the submission or completion queues are too small. So we allocate more send_wr depending on the (local) max number of MRs. While there also add additional space for ib_drain_qp(). This should make sure ib_post_send() will never fail because the submission queue is full. Fixes: f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection") Fixes: cc55f65dd352 ("smb: client: make use of common smbdirect_socket_parameters") Cc: stable(a)vger.kernel.org Cc: Steve French <smfrench(a)gmail.com> Cc: Tom Talpey <tom(a)talpey.com> Cc: Long Li <longli(a)microsoft.com> Cc: Namjae Jeon <linkinjeon(a)kernel.org> Cc: linux-cifs(a)vger.kernel.org Cc: samba-technical(a)lists.samba.org Signed-off-by: Stefan Metzmacher <metze(a)samba.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..b1218ea4aa8b 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1767,6 +1767,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1839,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1868,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1876,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1899,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources;

1 month, 3 weeks

1
0
0 0

🕘 Mark Your Calendar: DUOONE OLED SPAN/FOLD Launches on Kickstarter on Nov 15!

by InnLead Innovative

🕘 Mark Your Calendar: DUOONE OLED SPAN/FOLD Launches on Kickstarter on Nov 15! Multiplayer Gaming, Dual Fun & Work | Duel, Tabletop & Video Games | 1ms Respones Time | Vivid Lifelike OLED ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ Hello, Hope you’ve been doing great! I just wanted to share something I’m really excited about — we’ve been working on a game-changing OLED dual-monitor called DUOONE OLED SPAN/FOLD, and it’s finally launching on Kickstarter ( http://tracking.nextech.shop/tracking/click?d=4AivePE4XMH7w6uFxD5qcyyWtLdIu… )at: 🕘 9:00 AM, Saturday, November 15 (New York time) Time zones: * America/New York: 9:00 AM (EST) * Europe/London: 2:00 PM (GMT) * Europe/Rome: 3:00 PM (CET) * Asia/Singapore: 10:00 PM (SGT) * Asia/Tokyo: 11:00 PM (JST) What makes it special? It’s super light, compact, and offers ultimate flexibility with vivid OLED colors, deep contrast, and plug-and-play compatibility for everything — gaming, work, and creative projects. 🎲 Board & Tabletop Games 🎮 Mobile & Console Gaming 🤝 Multiplayer & Party Games 📚 Book Mode & Work Modes 🆚 Head-to-Head & Versus Games If you’re curious, here’s the prelaunch page (no pressure at all — just wanted you to take a look): 👉Notify Me: Get Mine on Kickstarter ( http://tracking.nextech.shop/tracking/click?d=4AivePE4XMH7w6uFxD5qcyyWtLdIu… ) Those who follow early will get Free Shipping and $405 off.. ( http://tracking.nextech.shop/tracking/click?d=4AivePE4XMH7w6uFxD5qcyyWtLdIu… ) ( http://tracking.nextech.shop/tracking/click?d=4AivePE4XMH7w6uFxD5qcyyWtLdIu… ) Don't miss out and reserve yours now. ( http://tracking.nextech.shop/tracking/click?d=4AivePE4XMH7w6uFxD5qcyyWtLdIu… ) Can’t wait to see you on Kickstarter — your support means everything! Best, DUOONE Team

1 month, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror