aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/mlx5
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-07 12:05:29 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-07 12:05:29 -0700
commite08466a7c00733a501d3c5328d29ec974478d717 (patch)
treed2fef4e7065aaaa1e1945ae92c06e318a2a04243 /drivers/infiniband/hw/mlx5
parentMerge tag 'mtd/for-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux (diff)
parentMerge tag 'v6.0' into rdma.git for-next (diff)
downloadlinux-dev-e08466a7c00733a501d3c5328d29ec974478d717.tar.xz
linux-dev-e08466a7c00733a501d3c5328d29ec974478d717.zip
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma updates from Jason Gunthorpe: "Not a big list of changes this cycle, mostly small things. The new MANA rdma driver should come next cycle along with a bunch of work on rxe. Summary: - Small bug fixes in mlx5, efa, rxe, hns, irdma, erdma, siw - rts tracing improvements - Code improvements: strlscpy conversion, unused parameter, spelling mistakes, unused variables, flex arrays - restrack device details report for hns - Simplify struct device initialization in SRP - Eliminate the never-used service_mask support in IB CM - Make rxe not print to the console for some kinds of network packets - Asymetric paths and router support in the CM through netlink messages - DMABUF importer support for mlx5devx umem's" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (84 commits) RDMA/rxe: Remove error/warning messages from packet receiver path RDMA/usnic: fix set-but-not-unused variable 'flags' warning IB/hfi1: Use skb_put_data() instead of skb_put/memcpy pair RDMA/hns: Unified Log Printing Style RDMA/hns: Replacing magic number with macros in apply_func_caps() RDMA/hns: Repacing 'dseg_len' by macros in fill_ext_sge_inl_data() RDMA/hns: Remove redundant 'max_srq_desc_sz' in caps RDMA/hns: Remove redundant 'num_mtt_segs' and 'max_extend_sg' RDMA/hns: Remove redundant 'phy_addr' in hns_roce_hem_list_find_mtt() RDMA/hns: Remove redundant 'use_lowmem' argument from hns_roce_init_hem_table() RDMA/hns: Remove redundant 'bt_level' for hem_list_alloc_item() RDMA/hns: Remove redundant 'attr_mask' in modify_qp_init_to_init() RDMA/hns: Remove unnecessary brackets when getting point RDMA/hns: Remove unnecessary braces for single statement blocks RDMA/hns: Cleanup for a spelling error of Asynchronous IB/rdmavt: Add __init/__exit annotations to module init/exit funcs RDMA/rxe: Remove redundant num_sge fields RDMA/mlx5: Enable ATS support for MRs and umems RDMA/mlx5: Add support for dmabuf to devx umem RDMA/core: Add UVERBS_ATTR_RAW_FD ...
Diffstat (limited to 'drivers/infiniband/hw/mlx5')
-rw-r--r--drivers/infiniband/hw/mlx5/devx.c57
-rw-r--r--drivers/infiniband/hw/mlx5/main.c6
-rw-r--r--drivers/infiniband/hw/mlx5/mem.c2
-rw-r--r--drivers/infiniband/hw/mlx5/mlx5_ib.h36
-rw-r--r--drivers/infiniband/hw/mlx5/mr.c8
-rw-r--r--drivers/infiniband/hw/mlx5/odp.c4
6 files changed, 88 insertions, 25 deletions
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 2a2a9e9afc9d..2211a0be16f3 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -907,6 +907,7 @@ static bool devx_is_whitelist_cmd(void *in)
case MLX5_CMD_OP_QUERY_HCA_CAP:
case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT:
case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT:
+ case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
return true;
default:
return false;
@@ -962,6 +963,7 @@ static bool devx_is_general_cmd(void *in, struct mlx5_ib_dev *dev)
case MLX5_CMD_OP_QUERY_CONG_PARAMS:
case MLX5_CMD_OP_QUERY_CONG_STATISTICS:
case MLX5_CMD_OP_QUERY_LAG:
+ case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
return true;
default:
return false;
@@ -2158,32 +2160,39 @@ err:
static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext,
struct uverbs_attr_bundle *attrs,
- struct devx_umem *obj)
+ struct devx_umem *obj, u32 access_flags)
{
u64 addr;
size_t size;
- u32 access;
int err;
if (uverbs_copy_from(&addr, attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_ADDR) ||
uverbs_copy_from(&size, attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_LEN))
return -EFAULT;
- err = uverbs_get_flags32(&access, attrs,
- MLX5_IB_ATTR_DEVX_UMEM_REG_ACCESS,
- IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE |
- IB_ACCESS_REMOTE_READ);
+ err = ib_check_mr_access(&dev->ib_dev, access_flags);
if (err)
return err;
- err = ib_check_mr_access(&dev->ib_dev, access);
- if (err)
- return err;
+ if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_DMABUF_FD)) {
+ struct ib_umem_dmabuf *umem_dmabuf;
+ int dmabuf_fd;
+
+ err = uverbs_get_raw_fd(&dmabuf_fd, attrs,
+ MLX5_IB_ATTR_DEVX_UMEM_REG_DMABUF_FD);
+ if (err)
+ return -EFAULT;
- obj->umem = ib_umem_get(&dev->ib_dev, addr, size, access);
- if (IS_ERR(obj->umem))
- return PTR_ERR(obj->umem);
+ umem_dmabuf = ib_umem_dmabuf_get_pinned(
+ &dev->ib_dev, addr, size, dmabuf_fd, access_flags);
+ if (IS_ERR(umem_dmabuf))
+ return PTR_ERR(umem_dmabuf);
+ obj->umem = &umem_dmabuf->umem;
+ } else {
+ obj->umem = ib_umem_get(&dev->ib_dev, addr, size, access_flags);
+ if (IS_ERR(obj->umem))
+ return PTR_ERR(obj->umem);
+ }
return 0;
}
@@ -2222,7 +2231,8 @@ static unsigned int devx_umem_find_best_pgsize(struct ib_umem *umem,
static int devx_umem_reg_cmd_alloc(struct mlx5_ib_dev *dev,
struct uverbs_attr_bundle *attrs,
struct devx_umem *obj,
- struct devx_umem_reg_cmd *cmd)
+ struct devx_umem_reg_cmd *cmd,
+ int access)
{
unsigned long pgsz_bitmap;
unsigned int page_size;
@@ -2271,6 +2281,9 @@ static int devx_umem_reg_cmd_alloc(struct mlx5_ib_dev *dev,
MLX5_SET(umem, umem, page_offset,
ib_umem_dma_offset(obj->umem, page_size));
+ if (mlx5_umem_needs_ats(dev, obj->umem, access))
+ MLX5_SET(umem, umem, ats, 1);
+
mlx5_ib_populate_pas(obj->umem, page_size, mtt,
(obj->umem->writable ? MLX5_IB_MTT_WRITE : 0) |
MLX5_IB_MTT_READ);
@@ -2288,20 +2301,30 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_UMEM_REG)(
struct mlx5_ib_ucontext *c = rdma_udata_to_drv_context(
&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
struct mlx5_ib_dev *dev = to_mdev(c->ibucontext.device);
+ int access_flags;
int err;
if (!c->devx_uid)
return -EINVAL;
+ err = uverbs_get_flags32(&access_flags, attrs,
+ MLX5_IB_ATTR_DEVX_UMEM_REG_ACCESS,
+ IB_ACCESS_LOCAL_WRITE |
+ IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_REMOTE_READ |
+ IB_ACCESS_RELAXED_ORDERING);
+ if (err)
+ return err;
+
obj = kzalloc(sizeof(struct devx_umem), GFP_KERNEL);
if (!obj)
return -ENOMEM;
- err = devx_umem_get(dev, &c->ibucontext, attrs, obj);
+ err = devx_umem_get(dev, &c->ibucontext, attrs, obj, access_flags);
if (err)
goto err_obj_free;
- err = devx_umem_reg_cmd_alloc(dev, attrs, obj, &cmd);
+ err = devx_umem_reg_cmd_alloc(dev, attrs, obj, &cmd, access_flags);
if (err)
goto err_umem_release;
@@ -2833,6 +2856,8 @@ DECLARE_UVERBS_NAMED_METHOD(
UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_DEVX_UMEM_REG_LEN,
UVERBS_ATTR_TYPE(u64),
UA_MANDATORY),
+ UVERBS_ATTR_RAW_FD(MLX5_IB_ATTR_DEVX_UMEM_REG_DMABUF_FD,
+ UA_OPTIONAL),
UVERBS_ATTR_FLAGS_IN(MLX5_IB_ATTR_DEVX_UMEM_REG_ACCESS,
enum ib_access_flags),
UVERBS_ATTR_CONST_IN(MLX5_IB_ATTR_DEVX_UMEM_REG_PGSZ_BITMAP,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 883d7c60143e..c669ef6e47e7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -26,7 +26,7 @@
#include <linux/mlx5/eswitch.h>
#include <linux/list.h>
#include <rdma/ib_smi.h>
-#include <rdma/ib_umem.h>
+#include <rdma/ib_umem_odp.h>
#include <rdma/lag.h>
#include <linux/in.h>
#include <linux/etherdevice.h>
@@ -46,7 +46,6 @@
#include <rdma/uverbs_ioctl.h>
#include <rdma/mlx5_user_ioctl_verbs.h>
#include <rdma/mlx5_user_ioctl_cmds.h>
-#include <rdma/ib_umem_odp.h>
#define UVERBS_MODULE_NAME mlx5_ib
#include <rdma/uverbs_named_ioctl.h>
@@ -1826,6 +1825,9 @@ static int set_ucontext_resp(struct ib_ucontext *uctx,
if (MLX5_CAP_GEN(dev->mdev, drain_sigerr))
resp->comp_mask |= MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_SQD2RTS;
+ resp->comp_mask |=
+ MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_MKEY_UPDATE_TAG;
+
return 0;
}
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 6191aa833ac2..96ffbbaf0a73 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -30,7 +30,6 @@
* SOFTWARE.
*/
-#include <rdma/ib_umem.h>
#include <rdma/ib_umem_odp.h>
#include "mlx5_ib.h"
#include <linux/jiffies.h>
@@ -152,6 +151,7 @@ static int post_send_nop(struct mlx5_ib_dev *dev, struct ib_qp *ibqp, u64 wr_id,
for (i = 0; i < 8; i++)
mlx5_write64(&mmio_wqe[i * 2],
bf->bfreg->map + bf->offset + i * 8);
+ io_stop_wc();
bf->offset ^= bf->buf_size;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 62338f44a30e..4a7f7064bd0e 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1563,4 +1563,40 @@ static inline bool rt_supported(int ts_cap)
return ts_cap == MLX5_TIMESTAMP_FORMAT_CAP_REAL_TIME ||
ts_cap == MLX5_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME;
}
+
+/*
+ * PCI Peer to Peer is a trainwreck. If no switch is present then things
+ * sometimes work, depending on the pci_distance_p2p logic for excluding broken
+ * root complexes. However if a switch is present in the path, then things get
+ * really ugly depending on how the switch is setup. This table assumes that the
+ * root complex is strict and is validating that all req/reps are matches
+ * perfectly - so any scenario where it sees only half the transaction is a
+ * failure.
+ *
+ * CR/RR/DT ATS RO P2P
+ * 00X X X OK
+ * 010 X X fails (request is routed to root but root never sees comp)
+ * 011 0 X fails (request is routed to root but root never sees comp)
+ * 011 1 X OK
+ * 10X X 1 OK
+ * 101 X 0 fails (completion is routed to root but root didn't see req)
+ * 110 X 0 SLOW
+ * 111 0 0 SLOW
+ * 111 1 0 fails (completion is routed to root but root didn't see req)
+ * 111 1 1 OK
+ *
+ * Unfortunately we cannot reliably know if a switch is present or what the
+ * CR/RR/DT ACS settings are, as in a VM that is all hidden. Assume that
+ * CR/RR/DT is 111 if the ATS cap is enabled and follow the last three rows.
+ *
+ * For now assume if the umem is a dma_buf then it is P2P.
+ */
+static inline bool mlx5_umem_needs_ats(struct mlx5_ib_dev *dev,
+ struct ib_umem *umem, int access_flags)
+{
+ if (!MLX5_CAP_GEN(dev->mdev, ats) || !umem->is_dmabuf)
+ return false;
+ return access_flags & IB_ACCESS_RELAXED_ORDERING;
+}
+
#endif /* MLX5_IB_H */
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 129d531bd01b..410cc5fd2523 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -39,9 +39,7 @@
#include <linux/delay.h>
#include <linux/dma-buf.h>
#include <linux/dma-resv.h>
-#include <rdma/ib_umem.h>
#include <rdma/ib_umem_odp.h>
-#include <rdma/ib_verbs.h>
#include "dm.h"
#include "mlx5_ib.h"
#include "umr.h"
@@ -937,7 +935,8 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
* cache then synchronously create an uncached one.
*/
if (!ent || ent->limit == 0 ||
- !mlx5r_umr_can_reconfig(dev, 0, access_flags)) {
+ !mlx5r_umr_can_reconfig(dev, 0, access_flags) ||
+ mlx5_umem_needs_ats(dev, umem, access_flags)) {
mutex_lock(&dev->slow_path_mutex);
mr = reg_create(pd, umem, iova, access_flags, page_size, false);
mutex_unlock(&dev->slow_path_mutex);
@@ -1018,6 +1017,8 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
MLX5_SET(mkc, mkc, translations_octword_size,
get_octo_len(iova, umem->length, mr->page_shift));
MLX5_SET(mkc, mkc, log_page_size, mr->page_shift);
+ if (mlx5_umem_needs_ats(dev, umem, access_flags))
+ MLX5_SET(mkc, mkc, ma_translation_mode, 1);
if (populate) {
MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
get_octo_len(iova, umem->length, mr->page_shift));
@@ -1402,7 +1403,6 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd,
upd_flags |= MLX5_IB_UPD_XLT_ACCESS;
}
- mr->ibmr.length = new_umem->length;
mr->ibmr.iova = iova;
mr->ibmr.length = new_umem->length;
mr->page_shift = order_base_2(page_size);
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index e305bf1dc6c2..bc97958818bb 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -30,7 +30,6 @@
* SOFTWARE.
*/
-#include <rdma/ib_umem.h>
#include <rdma/ib_umem_odp.h>
#include <linux/kernel.h>
#include <linux/dma-buf.h>
@@ -795,7 +794,8 @@ static bool mkey_is_eq(struct mlx5_ib_mkey *mmkey, u32 key)
{
if (!mmkey)
return false;
- if (mmkey->type == MLX5_MKEY_MW)
+ if (mmkey->type == MLX5_MKEY_MW ||
+ mmkey->type == MLX5_MKEY_INDIRECT_DEVX)
return mlx5_base_mkey(mmkey->key) == mlx5_base_mkey(key);
return mmkey->key == key;
}