* [PATCH v5 for-next 1/7] RDMA/bnxt_re: Use the common mmap helper functions
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
@ 2023-06-12 9:48 ` Selvin Xavier
2023-06-12 18:07 ` Jason Gunthorpe
2023-06-12 9:48 ` [PATCH v5 for-next 2/7] RDMA/bnxt_re: Add disassociate ucontext support Selvin Xavier
` (5 subsequent siblings)
6 siblings, 1 reply; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:48 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 8663 bytes --]
Replace the mmap handling function with common code in
IB core. Create rdma_user_mmap_entry for each mmap
resource and add to the ib_core mmap list. Add mmap_free
verb support. Also, use rdma_user_mmap_io while mapping
Doorbell pages.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/ib_verbs.c | 113 ++++++++++++++++++++++++------
drivers/infiniband/hw/bnxt_re/ib_verbs.h | 15 ++++
drivers/infiniband/hw/bnxt_re/main.c | 1 +
drivers/infiniband/hw/bnxt_re/qplib_res.c | 2 +-
4 files changed, 107 insertions(+), 24 deletions(-)
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 053afc9..2c08fa8 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -533,12 +533,43 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd)
return rc;
}
+static struct bnxt_re_user_mmap_entry*
+bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset,
+ enum bnxt_re_mmap_flag mmap_flag, u64 *offset)
+{
+ struct bnxt_re_user_mmap_entry *entry;
+ int ret;
+
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return NULL;
+
+ entry->mem_offset = mem_offset;
+ entry->mmap_flag = mmap_flag;
+
+ ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx,
+ &entry->rdma_entry, PAGE_SIZE);
+ if (ret) {
+ kfree(entry);
+ return NULL;
+ }
+ if (offset)
+ *offset = rdma_user_mmap_get_offset(&entry->rdma_entry);
+
+ return entry;
+}
+
/* Protection Domains */
int bnxt_re_dealloc_pd(struct ib_pd *ib_pd, struct ib_udata *udata)
{
struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
struct bnxt_re_dev *rdev = pd->rdev;
+ if (udata) {
+ rdma_user_mmap_entry_remove(pd->pd_db_mmap);
+ pd->pd_db_mmap = NULL;
+ }
+
bnxt_re_destroy_fence_mr(pd);
if (pd->qplib_pd.id) {
@@ -557,7 +588,8 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
struct bnxt_re_ucontext *ucntx = rdma_udata_to_drv_context(
udata, struct bnxt_re_ucontext, ib_uctx);
struct bnxt_re_pd *pd = container_of(ibpd, struct bnxt_re_pd, ib_pd);
- int rc;
+ struct bnxt_re_user_mmap_entry *entry = NULL;
+ int rc = 0;
pd->rdev = rdev;
if (bnxt_qplib_alloc_pd(&rdev->qplib_res.pd_tbl, &pd->qplib_pd)) {
@@ -567,7 +599,7 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
}
if (udata) {
- struct bnxt_re_pd_resp resp;
+ struct bnxt_re_pd_resp resp = {};
if (!ucntx->dpi.dbr) {
/* Allocate DPI in alloc_pd to avoid failing of
@@ -584,12 +616,21 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
resp.pdid = pd->qplib_pd.id;
/* Still allow mapping this DBR to the new user PD. */
resp.dpi = ucntx->dpi.dpi;
- resp.dbr = (u64)ucntx->dpi.umdbr;
- rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+ entry = bnxt_re_mmap_entry_insert(ucntx, (u64)ucntx->dpi.umdbr,
+ BNXT_RE_MMAP_UC_DB, &resp.dbr);
+
+ if (!entry) {
+ rc = -ENOMEM;
+ goto dbfail;
+ }
+
+ pd->pd_db_mmap = &entry->rdma_entry;
+
+ rc = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen));
if (rc) {
- ibdev_err(&rdev->ibdev,
- "Failed to copy user response\n");
+ rdma_user_mmap_entry_remove(pd->pd_db_mmap);
+ rc = -EFAULT;
goto dbfail;
}
}
@@ -3964,6 +4005,7 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
container_of(ctx, struct bnxt_re_ucontext, ib_uctx);
struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+ struct bnxt_re_user_mmap_entry *entry;
struct bnxt_re_uctx_resp resp = {};
u32 chip_met_rev_num = 0;
int rc;
@@ -4002,6 +4044,13 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
resp.mode = rdev->chip_ctx->modes.wqe_mode;
+ entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL);
+ if (!entry) {
+ rc = -ENOMEM;
+ goto cfail;
+ }
+ uctx->shpage_mmap = &entry->rdma_entry;
+
rc = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
if (rc) {
ibdev_err(ibdev, "Failed to copy user context");
@@ -4025,6 +4074,8 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
struct bnxt_re_dev *rdev = uctx->rdev;
+ rdma_user_mmap_entry_remove(uctx->shpage_mmap);
+ uctx->shpage_mmap = NULL;
if (uctx->shpg)
free_page((unsigned long)uctx->shpg);
@@ -4044,27 +4095,43 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
struct bnxt_re_ucontext *uctx = container_of(ib_uctx,
struct bnxt_re_ucontext,
ib_uctx);
- struct bnxt_re_dev *rdev = uctx->rdev;
+ struct bnxt_re_user_mmap_entry *bnxt_entry;
+ struct rdma_user_mmap_entry *rdma_entry;
+ int ret = 0;
u64 pfn;
- if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+ rdma_entry = rdma_user_mmap_entry_get(&uctx->ib_uctx, vma);
+ if (!rdma_entry)
return -EINVAL;
- if (vma->vm_pgoff) {
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
- PAGE_SIZE, vma->vm_page_prot)) {
- ibdev_err(&rdev->ibdev, "Failed to map DPI");
- return -EAGAIN;
- }
- } else {
- pfn = virt_to_phys(uctx->shpg) >> PAGE_SHIFT;
- if (remap_pfn_range(vma, vma->vm_start,
- pfn, PAGE_SIZE, vma->vm_page_prot)) {
- ibdev_err(&rdev->ibdev, "Failed to map shared page");
- return -EAGAIN;
- }
+ bnxt_entry = container_of(rdma_entry, struct bnxt_re_user_mmap_entry,
+ rdma_entry);
+
+ switch (bnxt_entry->mmap_flag) {
+ case BNXT_RE_MMAP_UC_DB:
+ pfn = bnxt_entry->mem_offset >> PAGE_SHIFT;
+ ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE,
+ pgprot_noncached(vma->vm_page_prot),
+ rdma_entry);
+ break;
+ case BNXT_RE_MMAP_SH_PAGE:
+ ret = vm_insert_page(vma, vma->vm_start, virt_to_page(uctx->shpg));
+ break;
+ default:
+ ret = -EINVAL;
+ break;
}
- return 0;
+ rdma_user_mmap_entry_put(rdma_entry);
+ return ret;
+}
+
+void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry)
+{
+ struct bnxt_re_user_mmap_entry *bnxt_entry;
+
+ bnxt_entry = container_of(rdma_entry, struct bnxt_re_user_mmap_entry,
+ rdma_entry);
+
+ kfree(bnxt_entry);
}
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index 31f7e34..dcd31ae 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -60,6 +60,7 @@ struct bnxt_re_pd {
struct bnxt_re_dev *rdev;
struct bnxt_qplib_pd qplib_pd;
struct bnxt_re_fence_data fence;
+ struct rdma_user_mmap_entry *pd_db_mmap;
};
struct bnxt_re_ah {
@@ -136,6 +137,18 @@ struct bnxt_re_ucontext {
struct bnxt_qplib_dpi dpi;
void *shpg;
spinlock_t sh_lock; /* protect shpg */
+ struct rdma_user_mmap_entry *shpage_mmap;
+};
+
+enum bnxt_re_mmap_flag {
+ BNXT_RE_MMAP_SH_PAGE,
+ BNXT_RE_MMAP_UC_DB,
+};
+
+struct bnxt_re_user_mmap_entry {
+ struct rdma_user_mmap_entry rdma_entry;
+ u64 mem_offset;
+ u8 mmap_flag;
};
static inline u16 bnxt_re_get_swqe_size(int nsge)
@@ -213,6 +226,8 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata);
void bnxt_re_dealloc_ucontext(struct ib_ucontext *context);
int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
+void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry);
+
unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp);
void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags);
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index a2c7d3f..acef429 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -545,6 +545,7 @@ static const struct ib_device_ops bnxt_re_dev_ops = {
.get_port_immutable = bnxt_re_get_port_immutable,
.map_mr_sg = bnxt_re_map_mr_sg,
.mmap = bnxt_re_mmap,
+ .mmap_free = bnxt_re_mmap_free,
.modify_qp = bnxt_re_modify_qp,
.modify_srq = bnxt_re_modify_srq,
.poll_cq = bnxt_re_poll_cq,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 126d4f2..920ab87 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -813,7 +813,7 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res,
return 0;
unmap_io:
- pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+ iounmap(dpit->dbr_bar_reg_iomem);
dpit->dbr_bar_reg_iomem = NULL;
return -ENOMEM;
}
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [PATCH v5 for-next 1/7] RDMA/bnxt_re: Use the common mmap helper functions
2023-06-12 9:48 ` [PATCH v5 for-next 1/7] RDMA/bnxt_re: Use the common mmap helper functions Selvin Xavier
@ 2023-06-12 18:07 ` Jason Gunthorpe
2023-06-13 4:48 ` Selvin Xavier
0 siblings, 1 reply; 15+ messages in thread
From: Jason Gunthorpe @ 2023-06-12 18:07 UTC (permalink / raw)
To: Selvin Xavier; +Cc: leon, linux-rdma, andrew.gospodarek
On Mon, Jun 12, 2023 at 02:48:56AM -0700, Selvin Xavier wrote:
> @@ -4002,6 +4044,13 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
> resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
> resp.mode = rdev->chip_ctx->modes.wqe_mode;
>
> + entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL);
> + if (!entry) {
> + rc = -ENOMEM;
> + goto cfail;
> + }
> + uctx->shpage_mmap = &entry->rdma_entry;
How can this be called with a NULL offset return?
It seems like the offset is hardwired by userspace?
If so it should use of the insert exact offset APIs
Jason
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH v5 for-next 1/7] RDMA/bnxt_re: Use the common mmap helper functions
2023-06-12 18:07 ` Jason Gunthorpe
@ 2023-06-13 4:48 ` Selvin Xavier
0 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-13 4:48 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: leon, linux-rdma, andrew.gospodarek
[-- Attachment #1: Type: text/plain, Size: 957 bytes --]
On Mon, Jun 12, 2023 at 11:37 PM Jason Gunthorpe <jgg@nvidia.com> wrote:
>
> On Mon, Jun 12, 2023 at 02:48:56AM -0700, Selvin Xavier wrote:
>
> > @@ -4002,6 +4044,13 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
> > resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
> > resp.mode = rdev->chip_ctx->modes.wqe_mode;
> >
> > + entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL);
> > + if (!entry) {
> > + rc = -ENOMEM;
> > + goto cfail;
> > + }
> > + uctx->shpage_mmap = &entry->rdma_entry;
>
> How can this be called with a NULL offset return?
>
> It seems like the offset is hardwired by userspace?
>
Yes. It is hardwired to maintain backward compatibility with
libbnxt_re from older rdma-core.
> If so it should use of the insert exact offset APIs
Will use rdma_user_mmap_entry_insert_exact and repost the series.
>
> Jason
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH v5 for-next 2/7] RDMA/bnxt_re: Add disassociate ucontext support
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
2023-06-12 9:48 ` [PATCH v5 for-next 1/7] RDMA/bnxt_re: Use the common mmap helper functions Selvin Xavier
@ 2023-06-12 9:48 ` Selvin Xavier
2023-06-12 9:48 ` [PATCH v5 for-next 3/7] RDMA/bnxt_re: Optimize the bnxt_re_init_hwrm_hdr usage Selvin Xavier
` (4 subsequent siblings)
6 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:48 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 1170 bytes --]
Add driver disassociation support. Driver uses the APIs
rdma_user_mmap_io api while mapping the IO pages to user space.
Add empty stub for disassociate ucontext.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/main.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index acef429..406b100 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -472,6 +472,10 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
return rc;
}
+static void bnxt_re_disassociate_ucontext(struct ib_ucontext *ibcontext)
+{
+}
+
/* Device */
static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev)
@@ -538,6 +542,7 @@ static const struct ib_device_ops bnxt_re_dev_ops = {
.destroy_qp = bnxt_re_destroy_qp,
.destroy_srq = bnxt_re_destroy_srq,
.device_group = &bnxt_re_dev_attr_group,
+ .disassociate_ucontext = bnxt_re_disassociate_ucontext,
.get_dev_fw_str = bnxt_re_query_fw_str,
.get_dma_mr = bnxt_re_get_dma_mr,
.get_hw_stats = bnxt_re_ib_get_hw_stats,
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH v5 for-next 3/7] RDMA/bnxt_re: Optimize the bnxt_re_init_hwrm_hdr usage
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
2023-06-12 9:48 ` [PATCH v5 for-next 1/7] RDMA/bnxt_re: Use the common mmap helper functions Selvin Xavier
2023-06-12 9:48 ` [PATCH v5 for-next 2/7] RDMA/bnxt_re: Add disassociate ucontext support Selvin Xavier
@ 2023-06-12 9:48 ` Selvin Xavier
2023-06-12 9:48 ` [PATCH v5 for-next 4/7] RDMA/bnxt_re: Query function capabilities from firmware Selvin Xavier
` (3 subsequent siblings)
6 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:48 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 5418 bytes --]
As of now bnxt_re_init_hwrm_hdr is taking only the opcode from
the caller. compl_ring and target_id field is always -1. These
fields might be changed when newer features are added. For now,
removing these parameters as they are hard coded. Also, remove
the rdev field which is not used.
Also, initialize the structure bnxt_fw_msg during declaration
itself.
Suggested-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/main.c | 48 ++++++++++++++----------------------
1 file changed, 19 insertions(+), 29 deletions(-)
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 406b100..1b16c42 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -321,12 +321,11 @@ static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev)
return rc;
}
-static void bnxt_re_init_hwrm_hdr(struct bnxt_re_dev *rdev, struct input *hdr,
- u16 opcd, u16 crid, u16 trid)
+static void bnxt_re_init_hwrm_hdr(struct input *hdr, u16 opcd)
{
hdr->req_type = cpu_to_le16(opcd);
- hdr->cmpl_ring = cpu_to_le16(crid);
- hdr->target_id = cpu_to_le16(trid);
+ hdr->cmpl_ring = cpu_to_le16(-1);
+ hdr->target_id = cpu_to_le16(-1);
}
static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
@@ -344,9 +343,9 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
u16 fw_ring_id, int type)
{
struct bnxt_en_dev *en_dev;
- struct hwrm_ring_free_input req = {0};
+ struct hwrm_ring_free_input req = {};
struct hwrm_ring_free_output resp;
- struct bnxt_fw_msg fw_msg;
+ struct bnxt_fw_msg fw_msg = {};
int rc = -EINVAL;
if (!rdev)
@@ -360,9 +359,7 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
return 0;
- memset(&fw_msg, 0, sizeof(fw_msg));
-
- bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1);
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_RING_FREE);
req.ring_type = type;
req.ring_id = cpu_to_le16(fw_ring_id);
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
@@ -379,16 +376,15 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev,
u16 *fw_ring_id)
{
struct bnxt_en_dev *en_dev = rdev->en_dev;
- struct hwrm_ring_alloc_input req = {0};
+ struct hwrm_ring_alloc_input req = {};
struct hwrm_ring_alloc_output resp;
- struct bnxt_fw_msg fw_msg;
+ struct bnxt_fw_msg fw_msg = {};
int rc = -EINVAL;
if (!en_dev)
return rc;
- memset(&fw_msg, 0, sizeof(fw_msg));
- bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_ALLOC, -1, -1);
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_RING_ALLOC);
req.enables = 0;
req.page_tbl_addr = cpu_to_le64(ring_attr->dma_arr[0]);
if (ring_attr->pages > 1) {
@@ -417,7 +413,7 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev,
struct bnxt_en_dev *en_dev = rdev->en_dev;
struct hwrm_stat_ctx_free_input req = {};
struct hwrm_stat_ctx_free_output resp = {};
- struct bnxt_fw_msg fw_msg;
+ struct bnxt_fw_msg fw_msg = {};
int rc = -EINVAL;
if (!en_dev)
@@ -426,9 +422,7 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev,
if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
return 0;
- memset(&fw_msg, 0, sizeof(fw_msg));
-
- bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_FREE, -1, -1);
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_FREE);
req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id);
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
@@ -445,10 +439,10 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
u32 *fw_stats_ctx_id)
{
struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx;
- struct hwrm_stat_ctx_alloc_output resp = {0};
- struct hwrm_stat_ctx_alloc_input req = {0};
+ struct hwrm_stat_ctx_alloc_output resp = {};
+ struct hwrm_stat_ctx_alloc_input req = {};
struct bnxt_en_dev *en_dev = rdev->en_dev;
- struct bnxt_fw_msg fw_msg;
+ struct bnxt_fw_msg fw_msg = {};
int rc = -EINVAL;
*fw_stats_ctx_id = INVALID_STATS_CTX_ID;
@@ -456,9 +450,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
if (!en_dev)
return rc;
- memset(&fw_msg, 0, sizeof(fw_msg));
-
- bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1);
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_ALLOC);
req.update_period_ms = cpu_to_le32(1000);
req.stats_dma_addr = cpu_to_le64(dma_map);
req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size);
@@ -1045,15 +1037,13 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev)
static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev)
{
struct bnxt_en_dev *en_dev = rdev->en_dev;
- struct hwrm_ver_get_output resp = {0};
- struct hwrm_ver_get_input req = {0};
+ struct hwrm_ver_get_output resp = {};
+ struct hwrm_ver_get_input req = {};
struct bnxt_qplib_chip_ctx *cctx;
- struct bnxt_fw_msg fw_msg;
+ struct bnxt_fw_msg fw_msg = {};
int rc = 0;
- memset(&fw_msg, 0, sizeof(fw_msg));
- bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
- HWRM_VER_GET, -1, -1);
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_VER_GET);
req.hwrm_intf_maj = HWRM_VERSION_MAJOR;
req.hwrm_intf_min = HWRM_VERSION_MINOR;
req.hwrm_intf_upd = HWRM_VERSION_UPDATE;
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH v5 for-next 4/7] RDMA/bnxt_re: Query function capabilities from firmware
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
` (2 preceding siblings ...)
2023-06-12 9:48 ` [PATCH v5 for-next 3/7] RDMA/bnxt_re: Optimize the bnxt_re_init_hwrm_hdr usage Selvin Xavier
@ 2023-06-12 9:48 ` Selvin Xavier
2023-06-12 9:49 ` [PATCH v5 for-next 5/7] RDMA/bnxt_re: Move the interface version to chip context structure Selvin Xavier
` (2 subsequent siblings)
6 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:48 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 2025 bytes --]
Query Function capabilities to enable advanced features.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/main.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 1b16c42..247f724 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -83,6 +83,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier,
unsigned long event, void *ptr);
static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev);
static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev);
+static int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev);
static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
{
@@ -91,6 +92,9 @@ static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
cctx = rdev->chip_ctx;
cctx->modes.wqe_mode = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
mode : BNXT_QPLIB_WQE_MODE_STATIC;
+ if (bnxt_re_hwrm_qcaps(rdev))
+ dev_err(rdev_to_dev(rdev),
+ "Failed to query hwrm qcaps\n");
}
static void bnxt_re_destroy_chip_ctx(struct bnxt_re_dev *rdev)
@@ -339,6 +343,23 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
fw_msg->timeout = timeout;
}
+/* Query function capabilities using common hwrm */
+int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
+{
+ struct bnxt_en_dev *en_dev = rdev->en_dev;
+ struct hwrm_func_qcaps_output resp = {};
+ struct hwrm_func_qcaps_input req = {};
+ struct bnxt_qplib_chip_ctx *cctx;
+ struct bnxt_fw_msg fw_msg = {};
+
+ cctx = rdev->chip_ctx;
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_FUNC_QCAPS);
+ req.fid = cpu_to_le16(0xffff);
+ bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+ sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+ return bnxt_send_msg(en_dev, &fw_msg);
+}
+
static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
u16 fw_ring_id, int type)
{
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH v5 for-next 5/7] RDMA/bnxt_re: Move the interface version to chip context structure
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
` (3 preceding siblings ...)
2023-06-12 9:48 ` [PATCH v5 for-next 4/7] RDMA/bnxt_re: Query function capabilities from firmware Selvin Xavier
@ 2023-06-12 9:49 ` Selvin Xavier
2023-06-12 9:49 ` [PATCH v5 for-next 6/7] RDMA/bnxt_re: Reorg the bar mapping Selvin Xavier
2023-06-12 9:49 ` [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push Selvin Xavier
6 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:49 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 1523 bytes --]
FW interface version check is required for multiple features. Moving
the interface version to chip context structure.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/main.c | 2 +-
drivers/infiniband/hw/bnxt_re/qplib_res.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 247f724..f8b4265 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1078,7 +1078,7 @@ static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev)
}
cctx = rdev->chip_ctx;
- rdev->qplib_ctx.hwrm_intf_ver =
+ cctx->hwrm_intf_ver =
(u64)le16_to_cpu(resp.hwrm_intf_major) << 48 |
(u64)le16_to_cpu(resp.hwrm_intf_minor) << 32 |
(u64)le16_to_cpu(resp.hwrm_intf_build) << 16 |
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 77f0b84..070451a 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -57,6 +57,7 @@ struct bnxt_qplib_chip_ctx {
u16 hw_stats_size;
u16 hwrm_cmd_max_timeout;
struct bnxt_qplib_drv_modes modes;
+ u64 hwrm_intf_ver;
};
#define PTR_CNT_PER_PG (PAGE_SIZE / sizeof(void *))
@@ -242,7 +243,6 @@ struct bnxt_qplib_ctx {
struct bnxt_qplib_tqm_ctx tqm_ctx;
struct bnxt_qplib_stats stats;
struct bnxt_qplib_vf_res vf_res;
- u64 hwrm_intf_ver;
};
struct bnxt_qplib_res {
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH v5 for-next 6/7] RDMA/bnxt_re: Reorg the bar mapping
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
` (4 preceding siblings ...)
2023-06-12 9:49 ` [PATCH v5 for-next 5/7] RDMA/bnxt_re: Move the interface version to chip context structure Selvin Xavier
@ 2023-06-12 9:49 ` Selvin Xavier
2023-06-12 9:49 ` [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push Selvin Xavier
6 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:49 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 18477 bytes --]
Reorganize the code for allocation and mapping of
Doorbell pages. Implements new HW command to get the BAR length
used by L2 driver. These changes are used by the future patch
which maps the WC Doorbell pages.
Also, introduced a new lock dpi_tbl_lock for synchronize the
DB page allocation from users.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/ib_verbs.c | 7 +-
drivers/infiniband/hw/bnxt_re/main.c | 71 +++++++++++-
drivers/infiniband/hw/bnxt_re/qplib_fp.c | 4 +-
drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 2 +
drivers/infiniband/hw/bnxt_re/qplib_res.c | 174 +++++++++++++++++++----------
drivers/infiniband/hw/bnxt_re/qplib_res.h | 28 ++++-
drivers/infiniband/hw/bnxt_re/qplib_sp.c | 3 +
drivers/infiniband/hw/bnxt_re/qplib_sp.h | 1 +
8 files changed, 213 insertions(+), 77 deletions(-)
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 2c08fa8..fa28419 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -606,8 +606,8 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
* ibv_devinfo and family of application when DPIs
* are depleted.
*/
- if (bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
- &ucntx->dpi, ucntx)) {
+ if (bnxt_qplib_alloc_dpi(&rdev->qplib_res,
+ &ucntx->dpi, ucntx, BNXT_QPLIB_DPI_TYPE_UC)) {
rc = -ENOMEM;
goto dbfail;
}
@@ -4083,8 +4083,7 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
/* Free DPI only if this is the first PD allocated by the
* application and mark the context dpi as NULL
*/
- bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
- &rdev->qplib_res.dpi_tbl, &uctx->dpi);
+ bnxt_qplib_dealloc_dpi(&rdev->qplib_res, &uctx->dpi);
uctx->dpi.dbr = NULL;
}
}
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f8b4265..0c68113 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -85,6 +85,40 @@ static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev);
static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev);
static int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev);
+static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len,
+ u32 *offset);
+static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev)
+{
+ struct bnxt_qplib_chip_ctx *cctx;
+ struct bnxt_en_dev *en_dev;
+ struct bnxt_qplib_res *res;
+ u32 l2db_len = 0;
+ u32 offset = 0;
+ u32 barlen;
+ int rc;
+
+ res = &rdev->qplib_res;
+ en_dev = rdev->en_dev;
+ cctx = rdev->chip_ctx;
+
+ /* Issue qcfg */
+ rc = bnxt_re_hwrm_qcfg(rdev, &l2db_len, &offset);
+ if (rc)
+ dev_info(rdev_to_dev(rdev),
+ "Couldn't get DB bar size, Low latency framework is disabled\n");
+ /* set register offsets for both UC and WC */
+ res->dpi_tbl.ucreg.offset = res->is_vf ? BNXT_QPLIB_DBR_VF_DB_OFFSET :
+ BNXT_QPLIB_DBR_PF_DB_OFFSET;
+ res->dpi_tbl.wcreg.offset = res->dpi_tbl.ucreg.offset;
+
+ /* If WC mapping is disabled by L2 driver then en_dev->l2_db_size
+ * is equal to the DB-Bar actual size. This indicates that L2
+ * is mapping entire bar as UC-. RoCE driver can't enable WC mapping
+ * in such cases and DB-push will be disabled.
+ */
+ barlen = pci_resource_len(res->pdev, RCFW_DBR_PCI_BAR_REGION);
+}
+
static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
{
struct bnxt_qplib_chip_ctx *cctx;
@@ -116,6 +150,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode)
{
struct bnxt_qplib_chip_ctx *chip_ctx;
struct bnxt_en_dev *en_dev;
+ int rc;
en_dev = rdev->en_dev;
@@ -134,6 +169,12 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode)
rdev->qplib_res.is_vf = BNXT_EN_VF(en_dev);
bnxt_re_set_drv_mode(rdev, wqe_mode);
+
+ bnxt_re_set_db_offset(rdev);
+ rc = bnxt_qplib_map_db_bar(&rdev->qplib_res);
+ if (rc)
+ return rc;
+
if (bnxt_qplib_determine_atomics(en_dev->pdev))
ibdev_info(&rdev->ibdev,
"platform doesn't support global atomics.");
@@ -343,6 +384,30 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
fw_msg->timeout = timeout;
}
+/* Query device config using common hwrm */
+static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len,
+ u32 *offset)
+{
+ struct bnxt_en_dev *en_dev = rdev->en_dev;
+ struct hwrm_func_qcfg_output resp = {0};
+ struct hwrm_func_qcfg_input req = {0};
+ struct bnxt_fw_msg fw_msg;
+ int rc;
+
+ memset(&fw_msg, 0, sizeof(fw_msg));
+ bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
+ HWRM_FUNC_QCFG, -1, -1);
+ req.fid = cpu_to_le16(0xffff);
+ bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+ sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+ rc = bnxt_send_msg(en_dev, &fw_msg);
+ if (!rc) {
+ *db_len = PAGE_ALIGN(le16_to_cpu(resp.l2_doorbell_bar_size_kb) * 1024);
+ *offset = PAGE_ALIGN(le16_to_cpu(resp.legacy_l2_db_size_kb) * 1024);
+ }
+ return rc;
+}
+
/* Query function capabilities using common hwrm */
int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
{
@@ -847,7 +912,6 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev)
if (rdev->qplib_res.dpi_tbl.max) {
bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
- &rdev->qplib_res.dpi_tbl,
&rdev->dpi_privileged);
}
if (rdev->qplib_res.rcfw) {
@@ -875,9 +939,9 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
if (rc)
goto fail;
- rc = bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
+ rc = bnxt_qplib_alloc_dpi(&rdev->qplib_res,
&rdev->dpi_privileged,
- rdev);
+ rdev, BNXT_QPLIB_DPI_TYPE_KERNEL);
if (rc)
goto dealloc_res;
@@ -917,7 +981,6 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
bnxt_qplib_free_nq(&rdev->nq[i]);
}
bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
- &rdev->qplib_res.dpi_tbl,
&rdev->dpi_privileged);
dealloc_res:
bnxt_qplib_free_res(&rdev->qplib_res);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index d48a26e..d5d418a 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -668,7 +668,7 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
srq->dbinfo.xid = srq->id;
srq->dbinfo.db = srq->dpi->dbr;
srq->dbinfo.max_slot = 1;
- srq->dbinfo.priv_db = res->dpi_tbl.dbr_bar_reg_iomem;
+ srq->dbinfo.priv_db = res->dpi_tbl.priv_db;
if (srq->threshold)
bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA);
srq->arm_req = false;
@@ -2104,7 +2104,7 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
cq->dbinfo.hwq = &cq->hwq;
cq->dbinfo.xid = cq->id;
cq->dbinfo.db = cq->dpi->dbr;
- cq->dbinfo.priv_db = res->dpi_tbl.dbr_bar_reg_iomem;
+ cq->dbinfo.priv_db = res->dpi_tbl.priv_db;
bnxt_qplib_armen_db(&cq->dbinfo, DBC_DBC_TYPE_CQ_ARMENA);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index f46de07..7b31bee 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -130,6 +130,8 @@ static inline u32 bnxt_qplib_set_cmd_slots(struct cmdq_base *req)
#define RCFW_MAX_COOKIE_VALUE (BNXT_QPLIB_CMDQE_MAX_CNT - 1)
#define RCFW_CMD_IS_BLOCKING 0x8000
+#define HWRM_VERSION_DEV_ATTR_MAX_DPI 0x1000A0000000DULL
+
/* Crsq buf is 1024-Byte */
struct bnxt_qplib_crsbe {
u8 data[1024];
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 920ab87..e1cbe59 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -704,44 +704,73 @@ static int bnxt_qplib_alloc_pd_tbl(struct bnxt_qplib_res *res,
}
/* DPIs */
-int bnxt_qplib_alloc_dpi(struct bnxt_qplib_dpi_tbl *dpit,
- struct bnxt_qplib_dpi *dpi,
- void *app)
+int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res,
+ struct bnxt_qplib_dpi *dpi,
+ void *app, u8 type)
{
+ struct bnxt_qplib_dpi_tbl *dpit = &res->dpi_tbl;
+ struct bnxt_qplib_reg_desc *reg;
u32 bit_num;
+ u64 umaddr;
+
+ reg = &dpit->wcreg;
+ mutex_lock(&res->dpi_tbl_lock);
bit_num = find_first_bit(dpit->tbl, dpit->max);
- if (bit_num == dpit->max)
+ if (bit_num == dpit->max) {
+ mutex_unlock(&res->dpi_tbl_lock);
return -ENOMEM;
+ }
/* Found unused DPI */
clear_bit(bit_num, dpit->tbl);
dpit->app_tbl[bit_num] = app;
- dpi->dpi = bit_num;
- dpi->dbr = dpit->dbr_bar_reg_iomem + (bit_num * PAGE_SIZE);
- dpi->umdbr = dpit->unmapped_dbr + (bit_num * PAGE_SIZE);
+ dpi->bit = bit_num;
+ dpi->dpi = bit_num + (reg->offset - dpit->ucreg.offset) / PAGE_SIZE;
+
+ umaddr = reg->bar_base + reg->offset + bit_num * PAGE_SIZE;
+ dpi->umdbr = umaddr;
+
+ switch (type) {
+ case BNXT_QPLIB_DPI_TYPE_KERNEL:
+ /* priviledged dbr was already mapped just initialize it. */
+ dpi->umdbr = dpit->ucreg.bar_base +
+ dpit->ucreg.offset + bit_num * PAGE_SIZE;
+ dpi->dbr = dpit->priv_db;
+ dpi->dpi = dpi->bit;
+ break;
+ default:
+ dpi->dbr = ioremap(umaddr, PAGE_SIZE);
+ break;
+ }
+ dpi->type = type;
+ mutex_unlock(&res->dpi_tbl_lock);
return 0;
+
}
int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
- struct bnxt_qplib_dpi_tbl *dpit,
- struct bnxt_qplib_dpi *dpi)
+ struct bnxt_qplib_dpi *dpi)
{
- if (dpi->dpi >= dpit->max) {
- dev_warn(&res->pdev->dev, "Invalid DPI? dpi = %d\n", dpi->dpi);
- return -EINVAL;
- }
- if (test_and_set_bit(dpi->dpi, dpit->tbl)) {
- dev_warn(&res->pdev->dev, "Freeing an unused DPI? dpi = %d\n",
- dpi->dpi);
+ struct bnxt_qplib_dpi_tbl *dpit = &res->dpi_tbl;
+
+ mutex_lock(&res->dpi_tbl_lock);
+ if (dpi->dpi && dpi->type != BNXT_QPLIB_DPI_TYPE_KERNEL)
+ pci_iounmap(res->pdev, dpi->dbr);
+
+ if (test_and_set_bit(dpi->bit, dpit->tbl)) {
+ dev_warn(&res->pdev->dev,
+ "Freeing an unused DPI? dpi = %d, bit = %d\n",
+ dpi->dpi, dpi->bit);
+ mutex_unlock(&res->dpi_tbl_lock);
return -EINVAL;
}
if (dpit->app_tbl)
- dpit->app_tbl[dpi->dpi] = NULL;
+ dpit->app_tbl[dpi->bit] = NULL;
memset(dpi, 0, sizeof(*dpi));
-
+ mutex_unlock(&res->dpi_tbl_lock);
return 0;
}
@@ -750,52 +779,38 @@ static void bnxt_qplib_free_dpi_tbl(struct bnxt_qplib_res *res,
{
kfree(dpit->tbl);
kfree(dpit->app_tbl);
- if (dpit->dbr_bar_reg_iomem)
- pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
- memset(dpit, 0, sizeof(*dpit));
+ dpit->tbl = NULL;
+ dpit->app_tbl = NULL;
+ dpit->max = 0;
}
-static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res,
- struct bnxt_qplib_dpi_tbl *dpit,
- u32 dbr_offset)
+static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res,
+ struct bnxt_qplib_dev_attr *dev_attr)
{
- u32 dbr_bar_reg = RCFW_DBR_PCI_BAR_REGION;
- resource_size_t bar_reg_base;
- u32 dbr_len, bytes;
-
- if (dpit->dbr_bar_reg_iomem) {
- dev_err(&res->pdev->dev, "DBR BAR region %d already mapped\n",
- dbr_bar_reg);
- return -EALREADY;
- }
-
- bar_reg_base = pci_resource_start(res->pdev, dbr_bar_reg);
- if (!bar_reg_base) {
- dev_err(&res->pdev->dev, "BAR region %d resc start failed\n",
- dbr_bar_reg);
- return -ENOMEM;
- }
+ struct bnxt_qplib_dpi_tbl *dpit;
+ struct bnxt_qplib_reg_desc *reg;
+ unsigned long bar_len;
+ u32 dbr_offset;
+ u32 bytes;
- dbr_len = pci_resource_len(res->pdev, dbr_bar_reg) - dbr_offset;
- if (!dbr_len || ((dbr_len & (PAGE_SIZE - 1)) != 0)) {
- dev_err(&res->pdev->dev, "Invalid DBR length %d\n", dbr_len);
- return -ENOMEM;
- }
+ dpit = &res->dpi_tbl;
+ reg = &dpit->wcreg;
- dpit->dbr_bar_reg_iomem = ioremap(bar_reg_base + dbr_offset,
- dbr_len);
- if (!dpit->dbr_bar_reg_iomem) {
- dev_err(&res->pdev->dev,
- "FP: DBR BAR region %d mapping failed\n", dbr_bar_reg);
- return -ENOMEM;
+ if (!bnxt_qplib_is_chip_gen_p5(res->cctx)) {
+ /* Offest should come from L2 driver */
+ dbr_offset = dev_attr->l2_db_size;
+ dpit->ucreg.offset = dbr_offset;
+ dpit->wcreg.offset = dbr_offset;
}
- dpit->unmapped_dbr = bar_reg_base + dbr_offset;
- dpit->max = dbr_len / PAGE_SIZE;
+ bar_len = pci_resource_len(res->pdev, reg->bar_id);
+ dpit->max = (bar_len - reg->offset) / PAGE_SIZE;
+ if (dev_attr->max_dpi)
+ dpit->max = min_t(u32, dpit->max, dev_attr->max_dpi);
- dpit->app_tbl = kcalloc(dpit->max, sizeof(void *), GFP_KERNEL);
+ dpit->app_tbl = kcalloc(dpit->max, sizeof(void *), GFP_KERNEL);
if (!dpit->app_tbl)
- goto unmap_io;
+ return -ENOMEM;
bytes = dpit->max >> 3;
if (!bytes)
@@ -805,17 +820,14 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res,
if (!dpit->tbl) {
kfree(dpit->app_tbl);
dpit->app_tbl = NULL;
- goto unmap_io;
+ return -ENOMEM;
}
memset((u8 *)dpit->tbl, 0xFF, bytes);
+ dpit->priv_db = dpit->ucreg.bar_reg + dpit->ucreg.offset;
return 0;
-unmap_io:
- iounmap(dpit->dbr_bar_reg_iomem);
- dpit->dbr_bar_reg_iomem = NULL;
- return -ENOMEM;
}
/* Stats */
@@ -882,7 +894,7 @@ int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
if (rc)
goto fail;
- rc = bnxt_qplib_alloc_dpi_tbl(res, &res->dpi_tbl, dev_attr->l2_db_size);
+ rc = bnxt_qplib_alloc_dpi_tbl(res, dev_attr);
if (rc)
goto fail;
@@ -892,6 +904,46 @@ int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
return rc;
}
+void bnxt_qplib_unmap_db_bar(struct bnxt_qplib_res *res)
+{
+ struct bnxt_qplib_reg_desc *reg;
+
+ reg = &res->dpi_tbl.ucreg;
+ if (reg->bar_reg)
+ pci_iounmap(res->pdev, reg->bar_reg);
+ reg->bar_reg = NULL;
+ reg->bar_base = 0;
+ reg->len = 0;
+ reg->bar_id = 0;
+}
+
+int bnxt_qplib_map_db_bar(struct bnxt_qplib_res *res)
+{
+ struct bnxt_qplib_reg_desc *ucreg;
+ struct bnxt_qplib_reg_desc *wcreg;
+
+ wcreg = &res->dpi_tbl.wcreg;
+ wcreg->bar_id = RCFW_DBR_PCI_BAR_REGION;
+ wcreg->bar_base = pci_resource_start(res->pdev, wcreg->bar_id);
+
+ ucreg = &res->dpi_tbl.ucreg;
+ ucreg->bar_id = RCFW_DBR_PCI_BAR_REGION;
+ ucreg->bar_base = pci_resource_start(res->pdev, ucreg->bar_id);
+ ucreg->len = ucreg->offset + PAGE_SIZE;
+ if (!ucreg->len || ((ucreg->len & (PAGE_SIZE - 1)) != 0)) {
+ dev_err(&res->pdev->dev, "QPLIB: invalid dbr length %d",
+ (int)ucreg->len);
+ return -EINVAL;
+ }
+ ucreg->bar_reg = ioremap(ucreg->bar_base, ucreg->len);
+ if (!ucreg->bar_reg) {
+ dev_err(&res->pdev->dev, "priviledged dpi map failed!");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
int bnxt_qplib_determine_atomics(struct pci_dev *dev)
{
int comp;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 070451a..398a469 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -60,6 +60,9 @@ struct bnxt_qplib_chip_ctx {
u64 hwrm_intf_ver;
};
+#define BNXT_QPLIB_DBR_PF_DB_OFFSET 0x10000
+#define BNXT_QPLIB_DBR_VF_DB_OFFSET 0x4000
+
#define PTR_CNT_PER_PG (PAGE_SIZE / sizeof(void *))
#define PTR_MAX_IDX_PER_PG (PTR_CNT_PER_PG - 1)
#define PTR_PG(x) (((x) & ~PTR_MAX_IDX_PER_PG) / PTR_CNT_PER_PG)
@@ -111,6 +114,7 @@ enum bnxt_qplib_hwrm_pg_size {
struct bnxt_qplib_reg_desc {
u8 bar_id;
resource_size_t bar_base;
+ unsigned long offset;
void __iomem *bar_reg;
size_t len;
};
@@ -187,18 +191,26 @@ struct bnxt_qplib_sgid_tbl {
u8 *vlan;
};
+enum {
+ BNXT_QPLIB_DPI_TYPE_KERNEL = 0,
+ BNXT_QPLIB_DPI_TYPE_UC = 1,
+};
+
struct bnxt_qplib_dpi {
u32 dpi;
+ u32 bit;
void __iomem *dbr;
u64 umdbr;
+ u8 type;
};
struct bnxt_qplib_dpi_tbl {
void **app_tbl;
unsigned long *tbl;
u16 max;
- void __iomem *dbr_bar_reg_iomem;
- u64 unmapped_dbr;
+ struct bnxt_qplib_reg_desc ucreg; /* Hold entire DB bar. */
+ struct bnxt_qplib_reg_desc wcreg;
+ void __iomem *priv_db;
};
struct bnxt_qplib_stats {
@@ -254,6 +266,8 @@ struct bnxt_qplib_res {
struct bnxt_qplib_pd_tbl pd_tbl;
struct bnxt_qplib_sgid_tbl sgid_tbl;
struct bnxt_qplib_dpi_tbl dpi_tbl;
+ /* To protect the dpi table bit map */
+ struct mutex dpi_tbl_lock;
bool prio;
bool is_vf;
};
@@ -345,11 +359,10 @@ int bnxt_qplib_alloc_pd(struct bnxt_qplib_pd_tbl *pd_tbl,
int bnxt_qplib_dealloc_pd(struct bnxt_qplib_res *res,
struct bnxt_qplib_pd_tbl *pd_tbl,
struct bnxt_qplib_pd *pd);
-int bnxt_qplib_alloc_dpi(struct bnxt_qplib_dpi_tbl *dpit,
- struct bnxt_qplib_dpi *dpi,
- void *app);
+int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res,
+ struct bnxt_qplib_dpi *dpi,
+ void *app, u8 type);
int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
- struct bnxt_qplib_dpi_tbl *dpi_tbl,
struct bnxt_qplib_dpi *dpi);
void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res);
int bnxt_qplib_init_res(struct bnxt_qplib_res *res);
@@ -362,6 +375,9 @@ void bnxt_qplib_free_ctx(struct bnxt_qplib_res *res,
int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res,
struct bnxt_qplib_ctx *ctx,
bool virt_fn, bool is_p5);
+int bnxt_qplib_map_db_bar(struct bnxt_qplib_res *res);
+void bnxt_qplib_unmap_db_bar(struct bnxt_qplib_res *res);
+
int bnxt_qplib_determine_atomics(struct pci_dev *dev);
static inline void bnxt_qplib_hwq_incr_prod(struct bnxt_qplib_hwq *hwq, u32 cnt)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 910d17d..d5ad086 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -170,6 +170,9 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
attr->tqm_alloc_reqs[i * 4 + 3] = *(++tqm_alloc);
}
+ if (rcfw->res->cctx->hwrm_intf_ver >= HWRM_VERSION_DEV_ATTR_MAX_DPI)
+ attr->max_dpi = le32_to_cpu(sb->max_dpi);
+
attr->is_atomic = bnxt_qplib_is_atomic_cap(rcfw);
bail:
bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 4061616..264ef3c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -72,6 +72,7 @@ struct bnxt_qplib_dev_attr {
u8 tqm_alloc_reqs[MAX_TQM_ALLOC_REQ];
bool is_atomic;
u16 dev_cap_flags;
+ u32 max_dpi;
};
struct bnxt_qplib_pd {
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push
2023-06-12 9:48 [PATCH v5 for-next 0/7] RDMA/bnxt_re: driver update for supporting low latency push Selvin Xavier
` (5 preceding siblings ...)
2023-06-12 9:49 ` [PATCH v5 for-next 6/7] RDMA/bnxt_re: Reorg the bar mapping Selvin Xavier
@ 2023-06-12 9:49 ` Selvin Xavier
2023-06-12 18:19 ` Jason Gunthorpe
2023-06-12 18:20 ` Jason Gunthorpe
6 siblings, 2 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-12 9:49 UTC (permalink / raw)
To: jgg, leon; +Cc: linux-rdma, andrew.gospodarek, Selvin Xavier
[-- Attachment #1: Type: text/plain, Size: 12925 bytes --]
Introduce driver specific uapi functionalites. Added
a alloc_page functionality for user library to allocate
specific pages. Currently added support for allocating
write combine pages for push functinality. This interface
shall be extended for other page allocations.
Allocate a WC page using the uapi hook for enabling the low latency
push in Gen P5 adapters for small packets. This is supported only
for the user space QPs.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
drivers/infiniband/hw/bnxt_re/bnxt_re.h | 3 +
drivers/infiniband/hw/bnxt_re/ib_verbs.c | 147 ++++++++++++++++++++++++++++++
drivers/infiniband/hw/bnxt_re/ib_verbs.h | 4 +
drivers/infiniband/hw/bnxt_re/main.c | 20 +++-
drivers/infiniband/hw/bnxt_re/qplib_res.c | 3 +
drivers/infiniband/hw/bnxt_re/qplib_res.h | 3 +-
include/uapi/rdma/bnxt_re-abi.h | 28 ++++++
7 files changed, 204 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index f34fb87..9e278d2 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -39,6 +39,7 @@
#ifndef __BNXT_RE_H__
#define __BNXT_RE_H__
+#include <rdma/uverbs_ioctl.h>
#include "hw_counters.h"
#define ROCE_DRV_MODULE_NAME "bnxt_re"
@@ -189,4 +190,6 @@ static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev)
return &rdev->ibdev.dev;
return NULL;
}
+
+extern const struct uapi_definition bnxt_re_uapi_defs[];
#endif
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index fa28419..b300b59 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -61,6 +61,15 @@
#include "bnxt_re.h"
#include "ib_verbs.h"
+
+#include <rdma/uverbs_types.h>
+#include <rdma/uverbs_std_types.h>
+
+#include <rdma/ib_user_ioctl_cmds.h>
+
+#define UVERBS_MODULE_NAME bnxt_re
+#include <rdma/uverbs_named_ioctl.h>
+
#include <rdma/bnxt_re-abi.h>
static int __from_ib_access_flags(int iflags)
@@ -546,6 +555,7 @@ bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset,
entry->mem_offset = mem_offset;
entry->mmap_flag = mmap_flag;
+ entry->uctx = uctx;
ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx,
&entry->rdma_entry, PAGE_SIZE);
@@ -4044,6 +4054,9 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
resp.mode = rdev->chip_ctx->modes.wqe_mode;
+ if (rdev->chip_ctx->modes.db_push)
+ resp.comp_mask |= BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED;
+
entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL);
if (!entry) {
rc = -ENOMEM;
@@ -4107,6 +4120,12 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
rdma_entry);
switch (bnxt_entry->mmap_flag) {
+ case BNXT_RE_MMAP_WC_DB:
+ pfn = bnxt_entry->mem_offset >> PAGE_SHIFT;
+ ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE,
+ pgprot_writecombine(vma->vm_page_prot),
+ rdma_entry);
+ break;
case BNXT_RE_MMAP_UC_DB:
pfn = bnxt_entry->mem_offset >> PAGE_SHIFT;
ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE,
@@ -4134,3 +4153,131 @@ void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry)
kfree(bnxt_entry);
}
+
+static int UVERBS_HANDLER(BNXT_RE_METHOD_ALLOC_PAGE)(struct uverbs_attr_bundle *attrs)
+{
+ struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
+ enum bnxt_re_alloc_page_type alloc_type;
+ struct bnxt_re_user_mmap_entry *entry;
+ enum bnxt_re_mmap_flag mmap_flag;
+ struct bnxt_qplib_chip_ctx *cctx;
+ struct bnxt_re_ucontext *uctx;
+ struct bnxt_re_dev *rdev;
+ u64 mmap_offset;
+ u32 length;
+ u32 dpi;
+ u64 dbr;
+ int err;
+
+ uctx = container_of(ib_uverbs_get_ucontext(attrs), struct bnxt_re_ucontext, ib_uctx);
+ if (IS_ERR(uctx))
+ return PTR_ERR(uctx);
+
+ err = uverbs_get_const(&alloc_type, attrs, BNXT_RE_ALLOC_PAGE_TYPE);
+ if (err)
+ return err;
+
+ rdev = uctx->rdev;
+ cctx = rdev->chip_ctx;
+
+ switch (alloc_type) {
+ case BNXT_RE_ALLOC_WC_PAGE:
+ if (cctx->modes.db_push) {
+ if (bnxt_qplib_alloc_dpi(&rdev->qplib_res, &uctx->wcdpi,
+ uctx, BNXT_QPLIB_DPI_TYPE_WC))
+ return -ENOMEM;
+ length = PAGE_SIZE;
+ dpi = uctx->wcdpi.dpi;
+ dbr = (u64)uctx->wcdpi.umdbr;
+ mmap_flag = BNXT_RE_MMAP_WC_DB;
+ } else {
+ return -EINVAL;
+ }
+
+ break;
+
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ entry = bnxt_re_mmap_entry_insert(uctx, dbr, mmap_flag, &mmap_offset);
+ if (IS_ERR(entry))
+ return PTR_ERR(entry);
+
+ uobj->object = entry;
+ uverbs_finalize_uobj_create(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
+ err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
+ &mmap_offset, sizeof(mmap_offset));
+ if (err)
+ return err;
+
+ err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_LENGTH,
+ &length, sizeof(length));
+ if (err)
+ return err;
+
+ err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_DPI,
+ &dpi, sizeof(length));
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int alloc_page_obj_cleanup(struct ib_uobject *uobject,
+ enum rdma_remove_reason why,
+ struct uverbs_attr_bundle *attrs)
+{
+ struct bnxt_re_user_mmap_entry *entry = uobject->object;
+ struct bnxt_re_ucontext *uctx = entry->uctx;
+
+ switch (entry->mmap_flag) {
+ case BNXT_RE_MMAP_WC_DB:
+ if (uctx && uctx->wcdpi.dbr) {
+ struct bnxt_re_dev *rdev = uctx->rdev;
+
+ bnxt_qplib_dealloc_dpi(&rdev->qplib_res, &uctx->wcdpi);
+ uctx->wcdpi.dbr = NULL;
+ }
+ break;
+ default:
+ goto exit;
+ }
+ rdma_user_mmap_entry_remove(&entry->rdma_entry);
+exit:
+ return 0;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(BNXT_RE_METHOD_ALLOC_PAGE,
+ UVERBS_ATTR_IDR(BNXT_RE_ALLOC_PAGE_HANDLE,
+ BNXT_RE_OBJECT_ALLOC_PAGE,
+ UVERBS_ACCESS_NEW,
+ UA_MANDATORY),
+ UVERBS_ATTR_CONST_IN(BNXT_RE_ALLOC_PAGE_TYPE,
+ enum bnxt_re_alloc_page_type,
+ UA_MANDATORY),
+ UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
+ UVERBS_ATTR_TYPE(u64),
+ UA_MANDATORY),
+ UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_MMAP_LENGTH,
+ UVERBS_ATTR_TYPE(u32),
+ UA_MANDATORY),
+ UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_DPI,
+ UVERBS_ATTR_TYPE(u32),
+ UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_METHOD_DESTROY(BNXT_RE_METHOD_DESTROY_PAGE,
+ UVERBS_ATTR_IDR(BNXT_RE_DESTROY_PAGE_HANDLE,
+ BNXT_RE_OBJECT_ALLOC_PAGE,
+ UVERBS_ACCESS_DESTROY,
+ UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_OBJECT(BNXT_RE_OBJECT_ALLOC_PAGE,
+ UVERBS_TYPE_ALLOC_IDR(alloc_page_obj_cleanup),
+ &UVERBS_METHOD(BNXT_RE_METHOD_ALLOC_PAGE),
+ &UVERBS_METHOD(BNXT_RE_METHOD_DESTROY_PAGE));
+
+const struct uapi_definition bnxt_re_uapi_defs[] = {
+ UAPI_DEF_CHAIN_OBJ_TREE_NAMED(BNXT_RE_OBJECT_ALLOC_PAGE),
+ {}
+};
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index dcd31ae..32d9e9d 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -61,6 +61,7 @@ struct bnxt_re_pd {
struct bnxt_qplib_pd qplib_pd;
struct bnxt_re_fence_data fence;
struct rdma_user_mmap_entry *pd_db_mmap;
+ struct rdma_user_mmap_entry *pd_wcdb_mmap;
};
struct bnxt_re_ah {
@@ -135,6 +136,7 @@ struct bnxt_re_ucontext {
struct ib_ucontext ib_uctx;
struct bnxt_re_dev *rdev;
struct bnxt_qplib_dpi dpi;
+ struct bnxt_qplib_dpi wcdpi;
void *shpg;
spinlock_t sh_lock; /* protect shpg */
struct rdma_user_mmap_entry *shpage_mmap;
@@ -143,10 +145,12 @@ struct bnxt_re_ucontext {
enum bnxt_re_mmap_flag {
BNXT_RE_MMAP_SH_PAGE,
BNXT_RE_MMAP_UC_DB,
+ BNXT_RE_MMAP_WC_DB,
};
struct bnxt_re_user_mmap_entry {
struct rdma_user_mmap_entry rdma_entry;
+ struct bnxt_re_ucontext *uctx;
u64 mem_offset;
u8 mmap_flag;
};
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 0c68113..0816cf2 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -66,6 +66,7 @@
#include <rdma/bnxt_re-abi.h>
#include "bnxt.h"
#include "hw_counters.h"
+#include "ib_verbs.h"
static char version[] =
BNXT_RE_DESC "\n";
@@ -117,6 +118,10 @@ static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev)
* in such cases and DB-push will be disabled.
*/
barlen = pci_resource_len(res->pdev, RCFW_DBR_PCI_BAR_REGION);
+ if (cctx->modes.db_push && l2db_len && en_dev->l2_db_size != barlen) {
+ res->dpi_tbl.wcreg.offset = en_dev->l2_db_size;
+ dev_info(rdev_to_dev(rdev), "Low latency framework is enabled\n");
+ }
}
static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
@@ -395,8 +400,7 @@ static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len,
int rc;
memset(&fw_msg, 0, sizeof(fw_msg));
- bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
- HWRM_FUNC_QCFG, -1, -1);
+ bnxt_re_init_hwrm_hdr((void *)&req, HWRM_FUNC_QCFG);
req.fid = cpu_to_le16(0xffff);
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
@@ -416,13 +420,20 @@ int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
struct hwrm_func_qcaps_input req = {};
struct bnxt_qplib_chip_ctx *cctx;
struct bnxt_fw_msg fw_msg = {};
+ int rc;
cctx = rdev->chip_ctx;
bnxt_re_init_hwrm_hdr((void *)&req, HWRM_FUNC_QCAPS);
req.fid = cpu_to_le16(0xffff);
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
- return bnxt_send_msg(en_dev, &fw_msg);
+
+ rc = bnxt_send_msg(en_dev, &fw_msg);
+ if (rc)
+ return rc;
+ cctx->modes.db_push = le32_to_cpu(resp.flags) & FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE;
+
+ return 0;
}
static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
@@ -669,6 +680,9 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
ibdev->dev.parent = &rdev->en_dev->pdev->dev;
ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
+ if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS))
+ ibdev->driver_def = bnxt_re_uapi_defs;
+
ib_set_device_ops(ibdev, &bnxt_re_dev_ops);
ret = ib_device_set_netdev(&rdev->ibdev, rdev->netdev, 1);
if (ret)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index e1cbe59..174db83 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -740,6 +740,9 @@ int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res,
dpi->dbr = dpit->priv_db;
dpi->dpi = dpi->bit;
break;
+ case BNXT_QPLIB_DPI_TYPE_WC:
+ dpi->dbr = ioremap_wc(umaddr, PAGE_SIZE);
+ break;
default:
dpi->dbr = ioremap(umaddr, PAGE_SIZE);
break;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 398a469..d850a55 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -47,7 +47,7 @@ extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero;
struct bnxt_qplib_drv_modes {
u8 wqe_mode;
- /* Other modes to follow here */
+ bool db_push;
};
struct bnxt_qplib_chip_ctx {
@@ -194,6 +194,7 @@ struct bnxt_qplib_sgid_tbl {
enum {
BNXT_QPLIB_DPI_TYPE_KERNEL = 0,
BNXT_QPLIB_DPI_TYPE_UC = 1,
+ BNXT_QPLIB_DPI_TYPE_WC = 2
};
struct bnxt_qplib_dpi {
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index c4e9077..f34e624 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -41,6 +41,7 @@
#define __BNXT_RE_UVERBS_ABI_H__
#include <linux/types.h>
+#include <rdma/ib_user_ioctl_cmds.h>
#define BNXT_RE_ABI_VERSION 1
@@ -51,6 +52,7 @@
enum {
BNXT_RE_UCNTX_CMASK_HAVE_CCTX = 0x1ULL,
BNXT_RE_UCNTX_CMASK_HAVE_MODE = 0x02ULL,
+ BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
};
enum bnxt_re_wqe_mode {
@@ -78,6 +80,7 @@ struct bnxt_re_uctx_resp {
* not 8 byted aligned. To avoid undesired padding in various cases we have to
* set this struct to packed.
*/
+
struct bnxt_re_pd_resp {
__u32 pdid;
__u32 dpi;
@@ -127,4 +130,29 @@ enum bnxt_re_shpg_offt {
BNXT_RE_END_RESV_OFFT = 0xFF0
};
+enum bnxt_re_objects {
+ BNXT_RE_OBJECT_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum bnxt_re_alloc_page_type {
+ BNXT_RE_ALLOC_WC_PAGE = 0,
+};
+
+enum bnxt_re_var_alloc_page_attrs {
+ BNXT_RE_ALLOC_PAGE_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+ BNXT_RE_ALLOC_PAGE_TYPE,
+ BNXT_RE_ALLOC_PAGE_DPI,
+ BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
+ BNXT_RE_ALLOC_PAGE_MMAP_LENGTH,
+};
+
+enum bnxt_re_alloc_page_attrs {
+ BNXT_RE_DESTROY_PAGE_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum bnxt_re_alloc_page_methods {
+ BNXT_RE_METHOD_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT),
+ BNXT_RE_METHOD_DESTROY_PAGE,
+};
+
#endif /* __BNXT_RE_UVERBS_ABI_H__*/
--
2.5.5
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push
2023-06-12 9:49 ` [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push Selvin Xavier
@ 2023-06-12 18:19 ` Jason Gunthorpe
2023-06-13 5:23 ` Selvin Xavier
2023-06-12 18:20 ` Jason Gunthorpe
1 sibling, 1 reply; 15+ messages in thread
From: Jason Gunthorpe @ 2023-06-12 18:19 UTC (permalink / raw)
To: Selvin Xavier; +Cc: leon, linux-rdma, andrew.gospodarek
On Mon, Jun 12, 2023 at 02:49:02AM -0700, Selvin Xavier wrote:
> +static int UVERBS_HANDLER(BNXT_RE_METHOD_ALLOC_PAGE)(struct uverbs_attr_bundle *attrs)
> +{
> + struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
> + enum bnxt_re_alloc_page_type alloc_type;
> + struct bnxt_re_user_mmap_entry *entry;
> + enum bnxt_re_mmap_flag mmap_flag;
> + struct bnxt_qplib_chip_ctx *cctx;
> + struct bnxt_re_ucontext *uctx;
> + struct bnxt_re_dev *rdev;
> + u64 mmap_offset;
> + u32 length;
> + u32 dpi;
> + u64 dbr;
> + int err;
> +
> + uctx = container_of(ib_uverbs_get_ucontext(attrs), struct bnxt_re_ucontext, ib_uctx);
> + if (IS_ERR(uctx))
> + return PTR_ERR(uctx);
> +
> + err = uverbs_get_const(&alloc_type, attrs, BNXT_RE_ALLOC_PAGE_TYPE);
> + if (err)
> + return err;
> +
> + rdev = uctx->rdev;
> + cctx = rdev->chip_ctx;
> +
> + switch (alloc_type) {
> + case BNXT_RE_ALLOC_WC_PAGE:
> + if (cctx->modes.db_push) {
> + if (bnxt_qplib_alloc_dpi(&rdev->qplib_res, &uctx->wcdpi,
> + uctx, BNXT_QPLIB_DPI_TYPE_WC))
> + return -ENOMEM;
> + length = PAGE_SIZE;
> + dpi = uctx->wcdpi.dpi;
> + dbr = (u64)uctx->wcdpi.umdbr;
> + mmap_flag = BNXT_RE_MMAP_WC_DB;
> + } else {
> + return -EINVAL;
> + }
> +
> + break;
> +
> + default:
> + return -EOPNOTSUPP;
> + }
> +
> + entry = bnxt_re_mmap_entry_insert(uctx, dbr, mmap_flag, &mmap_offset);
> + if (IS_ERR(entry))
> + return PTR_ERR(entry);
> +
> + uobj->object = entry;
> + uverbs_finalize_uobj_create(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
uverbs_finalize_uobj_create() is supposed to be called once the
function cannot fail anymore
> + err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
> + &mmap_offset, sizeof(mmap_offset));
> + if (err)
> + return err;
Because there is no way to undo it on error.
So the error handling here needs adjusting
Jason
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push
2023-06-12 18:19 ` Jason Gunthorpe
@ 2023-06-13 5:23 ` Selvin Xavier
2023-06-13 11:41 ` Jason Gunthorpe
0 siblings, 1 reply; 15+ messages in thread
From: Selvin Xavier @ 2023-06-13 5:23 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: leon, linux-rdma, andrew.gospodarek
[-- Attachment #1: Type: text/plain, Size: 2920 bytes --]
On Mon, Jun 12, 2023 at 11:49 PM Jason Gunthorpe <jgg@nvidia.com> wrote:
>
> On Mon, Jun 12, 2023 at 02:49:02AM -0700, Selvin Xavier wrote:
>
> > +static int UVERBS_HANDLER(BNXT_RE_METHOD_ALLOC_PAGE)(struct uverbs_attr_bundle *attrs)
> > +{
> > + struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
> > + enum bnxt_re_alloc_page_type alloc_type;
> > + struct bnxt_re_user_mmap_entry *entry;
> > + enum bnxt_re_mmap_flag mmap_flag;
> > + struct bnxt_qplib_chip_ctx *cctx;
> > + struct bnxt_re_ucontext *uctx;
> > + struct bnxt_re_dev *rdev;
> > + u64 mmap_offset;
> > + u32 length;
> > + u32 dpi;
> > + u64 dbr;
> > + int err;
> > +
> > + uctx = container_of(ib_uverbs_get_ucontext(attrs), struct bnxt_re_ucontext, ib_uctx);
> > + if (IS_ERR(uctx))
> > + return PTR_ERR(uctx);
> > +
> > + err = uverbs_get_const(&alloc_type, attrs, BNXT_RE_ALLOC_PAGE_TYPE);
> > + if (err)
> > + return err;
> > +
> > + rdev = uctx->rdev;
> > + cctx = rdev->chip_ctx;
> > +
> > + switch (alloc_type) {
> > + case BNXT_RE_ALLOC_WC_PAGE:
> > + if (cctx->modes.db_push) {
> > + if (bnxt_qplib_alloc_dpi(&rdev->qplib_res, &uctx->wcdpi,
> > + uctx, BNXT_QPLIB_DPI_TYPE_WC))
> > + return -ENOMEM;
> > + length = PAGE_SIZE;
> > + dpi = uctx->wcdpi.dpi;
> > + dbr = (u64)uctx->wcdpi.umdbr;
> > + mmap_flag = BNXT_RE_MMAP_WC_DB;
> > + } else {
> > + return -EINVAL;
> > + }
> > +
> > + break;
> > +
> > + default:
> > + return -EOPNOTSUPP;
> > + }
> > +
> > + entry = bnxt_re_mmap_entry_insert(uctx, dbr, mmap_flag, &mmap_offset);
> > + if (IS_ERR(entry))
> > + return PTR_ERR(entry);
> > +
> > + uobj->object = entry;
> > + uverbs_finalize_uobj_create(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
>
> uverbs_finalize_uobj_create() is supposed to be called once the
> function cannot fail anymore
>
> > + err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
> > + &mmap_offset, sizeof(mmap_offset));
> > + if (err)
> > + return err;
>
> Because there is no way to undo it on error.
>
> So the error handling here needs adjusting
Hi Jason,
uverbs_finalize_uobj_create is the last step before uverbs_copy_to.
All the error checking
after this is for uverbs_copy_to. Can you please clarify what needs
to be changed?
I took the reference of other modules that call
uverbs_finalize_uobj_create for this implementation
and was not able to find the issue you mentioned.
Thanks,
Selvin
>
> Jason
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push
2023-06-13 5:23 ` Selvin Xavier
@ 2023-06-13 11:41 ` Jason Gunthorpe
2023-06-13 11:51 ` Selvin Xavier
0 siblings, 1 reply; 15+ messages in thread
From: Jason Gunthorpe @ 2023-06-13 11:41 UTC (permalink / raw)
To: Selvin Xavier; +Cc: leon, linux-rdma, andrew.gospodarek
On Tue, Jun 13, 2023 at 10:53:11AM +0530, Selvin Xavier wrote:
> uverbs_finalize_uobj_create is the last step before uverbs_copy_to.
> All the error checking
Oh, you are right, I got this mixed up with a different subsystem
Jason
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push
2023-06-13 11:41 ` Jason Gunthorpe
@ 2023-06-13 11:51 ` Selvin Xavier
0 siblings, 0 replies; 15+ messages in thread
From: Selvin Xavier @ 2023-06-13 11:51 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: leon, linux-rdma, andrew.gospodarek
[-- Attachment #1: Type: text/plain, Size: 410 bytes --]
On Tue, Jun 13, 2023 at 5:12 PM Jason Gunthorpe <jgg@nvidia.com> wrote:
>
> On Tue, Jun 13, 2023 at 10:53:11AM +0530, Selvin Xavier wrote:
>
> > uverbs_finalize_uobj_create is the last step before uverbs_copy_to.
> > All the error checking
>
> Oh, you are right, I got this mixed up with a different subsystem
Thank you for the confirmation.will fix the other issues and post a v6 soon.
>
> Jason
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push
2023-06-12 9:49 ` [PATCH v5 for-next 7/7] RDMA/bnxt_re: Enable low latency push Selvin Xavier
2023-06-12 18:19 ` Jason Gunthorpe
@ 2023-06-12 18:20 ` Jason Gunthorpe
1 sibling, 0 replies; 15+ messages in thread
From: Jason Gunthorpe @ 2023-06-12 18:20 UTC (permalink / raw)
To: Selvin Xavier; +Cc: leon, linux-rdma, andrew.gospodarek
> diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
> index c4e9077..f34e624 100644
> --- a/include/uapi/rdma/bnxt_re-abi.h
> +++ b/include/uapi/rdma/bnxt_re-abi.h
> @@ -41,6 +41,7 @@
> #define __BNXT_RE_UVERBS_ABI_H__
>
> #include <linux/types.h>
> +#include <rdma/ib_user_ioctl_cmds.h>
>
> #define BNXT_RE_ABI_VERSION 1
>
> @@ -51,6 +52,7 @@
> enum {
> BNXT_RE_UCNTX_CMASK_HAVE_CCTX = 0x1ULL,
> BNXT_RE_UCNTX_CMASK_HAVE_MODE = 0x02ULL,
> + BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
> };
>
> enum bnxt_re_wqe_mode {
> @@ -78,6 +80,7 @@ struct bnxt_re_uctx_resp {
> * not 8 byted aligned. To avoid undesired padding in various cases we have to
> * set this struct to packed.
> */
> +
> struct bnxt_re_pd_resp {
> __u32 pdid;
> __u32 dpi;
Bogus space
Jason
^ permalink raw reply [flat|nested] 15+ messages in thread