Skip to contentSkip to conversation

RDMA/rxe: Implement memory windows

PATCH Applied Bob Pearson 2 participants 13 messages Jun 8, 2021 – Jun 18, 2021

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

v9 cover RDMA/rxe: Implement memory windows

This series of patches implement memory windows for the rdma_rxe driver. This is a shorter reimplementation of an earlier patch set. They apply to and depend on the current for-next linux rdma tree.

---
v9:
Fixed error return from bind MW local operation.
v8:
Dropped wr.mw.flags in the rxe_send_wr struct in rdma_user_rxe.h.
v7:
Fixed a duplicate INIT_RDMA_OBJ_SIZE(ib_mw, ...) in rxe_verbs.c.
v6:
Added rxe_ prefix to subroutine names in lines that changed from Zhu's review of v5.
v5:
Fixed a typo in 10th patch.
v4:
Added a 10th patch to check when MRs have bound MWs and disallow dereg and invalidate operations.
v3:
cleaned up void return and lower case enums from
Zhu's review.
v2:
cleaned up an issue in rdma_user_rxe.h
cleaned up a collision in rxe_resp.c

Bob Pearson (10):
RDMA/rxe: Add bind MW fields to rxe_send_wr RDMA/rxe: Return errors for add index and key RDMA/rxe: Enable MW object pool
RDMA/rxe: Add ib_alloc_mw and ib_dealloc_mw verbs RDMA/rxe: Replace WR_REG_MASK by WR_LOCAL_OP_MASK RDMA/rxe: Move local ops to subroutine RDMA/rxe: Add support for bind MW work requests RDMA/rxe: Implement invalidate MW operations RDMA/rxe: Implement memory access through MWs RDMA/rxe: Disallow MR dereg and invalidate when bound

 drivers/infiniband/sw/rxe/Makefile     |   1 +
 drivers/infiniband/sw/rxe/rxe.c        |   1 +
 drivers/infiniband/sw/rxe/rxe_comp.c   |   5 +-
 drivers/infiniband/sw/rxe/rxe_loc.h    |  36 +--
 drivers/infiniband/sw/rxe/rxe_mr.c     | 126 ++++++---
 drivers/infiniband/sw/rxe/rxe_mw.c     | 343 +++++++++++++++++++++++++
 drivers/infiniband/sw/rxe/rxe_opcode.c |  11 +-
 drivers/infiniband/sw/rxe/rxe_opcode.h |   3 +-
 drivers/infiniband/sw/rxe/rxe_param.h  |  19 +-
 drivers/infiniband/sw/rxe/rxe_pool.c   |  45 ++--
 drivers/infiniband/sw/rxe/rxe_pool.h   |   8 +-
 drivers/infiniband/sw/rxe/rxe_req.c    | 104 +++++---
 drivers/infiniband/sw/rxe/rxe_resp.c   | 111 +++++---
 drivers/infiniband/sw/rxe/rxe_verbs.c  |  15 +-
 drivers/infiniband/sw/rxe/rxe_verbs.h  |  48 +++-
 include/uapi/rdma/rdma_user_rxe.h      |  10 +
 16 files changed, 702 insertions(+), 184 deletions(-)
 create mode 100644 drivers/infiniband/sw/rxe/rxe_mw.c
Signature · 1 line
2.27.0
#1 lore raw

PATCH v9 2/10 RDMA/rxe: Return errors for add index and key

Modify rxe_add_index() and rxe_add_key() to return an error if the index or key is aleady present in the pool. Currently they print a warning and silently fail with bad consequences to the caller.

---
 drivers/infiniband/sw/rxe/rxe_pool.c | 44 ++++++++++++++++++----------
 drivers/infiniband/sw/rxe/rxe_pool.h |  8 ++---
 2 files changed, 32 insertions(+), 20 deletions(-)
drivers/infiniband/sw/rxe/rxe_pool.c +28 -16
index d24901f2af3f..df0bec719341 100644
@@ -183,7 +183,7 @@ static u32 alloc_index(struct rxe_pool *pool)
 	return index + pool->index.min_index;
 }
 
-static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
+static int rxe_insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
 {
 	struct rb_node **link = &pool->index.tree.rb_node;
 	struct rb_node *parent = NULL;
@@ -195,7 +195,7 @@ static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
 
 		if (elem->index == new->index) {
 			pr_warn("element already exists!\n");
-			goto out;
+			return -EINVAL;
 		}
 
 		if (elem->index > new->index)
@@ -206,11 +206,11 @@ static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
 
 	rb_link_node(&new->index_node, parent, link);
 	rb_insert_color(&new->index_node, &pool->index.tree);
-out:
-	return;
+
+	return 0;
 }
 
-static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
+static int rxe_insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
 {
 	struct rb_node **link = &pool->key.tree.rb_node;
 	struct rb_node *parent = NULL;
@@ -226,7 +226,7 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
 
 		if (cmp == 0) {
 			pr_warn("key already exists!\n");
-			goto out;
+			return -EINVAL;
 		}
 
 		if (cmp > 0)
@@ -237,26 +237,32 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
 
 	rb_link_node(&new->key_node, parent, link);
 	rb_insert_color(&new->key_node, &pool->key.tree);
-out:
-	return;
+
+	return 0;
 }
 
-void __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key)
+int __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key)
 {
 	struct rxe_pool *pool = elem->pool;
+	int err;
 
 	memcpy((u8 *)elem + pool->key.key_offset, key, pool->key.key_size);
-	insert_key(pool, elem);
+	err = rxe_insert_key(pool, elem);
+
+	return err;
 }
 
-void __rxe_add_key(struct rxe_pool_entry *elem, void *key)
+int __rxe_add_key(struct rxe_pool_entry *elem, void *key)
 {
 	struct rxe_pool *pool = elem->pool;
 	unsigned long flags;
+	int err;
 
 	write_lock_irqsave(&pool->pool_lock, flags);
-	__rxe_add_key_locked(elem, key);
+	err = __rxe_add_key_locked(elem, key);
 	write_unlock_irqrestore(&pool->pool_lock, flags);
+
+	return err;
 }
 
 void __rxe_drop_key_locked(struct rxe_pool_entry *elem)
@@ -276,22 +282,28 @@ void __rxe_drop_key(struct rxe_pool_entry *elem)
 	write_unlock_irqrestore(&pool->pool_lock, flags);
 }
 
-void __rxe_add_index_locked(struct rxe_pool_entry *elem)
+int __rxe_add_index_locked(struct rxe_pool_entry *elem)
 {
 	struct rxe_pool *pool = elem->pool;
+	int err;
 
 	elem->index = alloc_index(pool);
-	insert_index(pool, elem);
+	err = rxe_insert_index(pool, elem);
+
+	return err;
 }
 
-void __rxe_add_index(struct rxe_pool_entry *elem)
+int __rxe_add_index(struct rxe_pool_entry *elem)
 {
 	struct rxe_pool *pool = elem->pool;
 	unsigned long flags;
+	int err;
 
 	write_lock_irqsave(&pool->pool_lock, flags);
-	__rxe_add_index_locked(elem);
+	err = __rxe_add_index_locked(elem);
 	write_unlock_irqrestore(&pool->pool_lock, flags);
+
+	return err;
 }
 
 void __rxe_drop_index_locked(struct rxe_pool_entry *elem)
drivers/infiniband/sw/rxe/rxe_pool.h +4 -4
index 61210b300a78..1feca1bffced 100644
@@ -111,11 +111,11 @@ int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem);
 /* assign an index to an indexed object and insert object into
  *  pool's rb tree holding and not holding the pool_lock
  */
-void __rxe_add_index_locked(struct rxe_pool_entry *elem);
+int __rxe_add_index_locked(struct rxe_pool_entry *elem);
 
 #define rxe_add_index_locked(obj) __rxe_add_index_locked(&(obj)->pelem)
 
-void __rxe_add_index(struct rxe_pool_entry *elem);
+int __rxe_add_index(struct rxe_pool_entry *elem);
 
 #define rxe_add_index(obj) __rxe_add_index(&(obj)->pelem)
 
@@ -133,11 +133,11 @@ void __rxe_drop_index(struct rxe_pool_entry *elem);
 /* assign a key to a keyed object and insert object into
  * pool's rb tree holding and not holding pool_lock
  */
-void __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key);
+int __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key);
 
 #define rxe_add_key_locked(obj, key) __rxe_add_key_locked(&(obj)->pelem, key)
 
-void __rxe_add_key(struct rxe_pool_entry *elem, void *key);
+int __rxe_add_key(struct rxe_pool_entry *elem, void *key);
 
 #define rxe_add_key(obj, key) __rxe_add_key(&(obj)->pelem, key)
 
Signature · 1 line
2.30.2
#2 lore raw

PATCH v9 1/9 RDMA/rxe: Add bind MW fields to rxe_send_wr

In reply to Bob Pearson

Add fields to struct rxe_send_wr in rdma_user_rxe.h to support bind MW work requests

---
v8:
Dropped the flags field in wr.mw which was no longer needed. The size of the mw struct broke binary compatibility because it extended the size of the wr union beyond 40 bytes.

---
 include/uapi/rdma/rdma_user_rxe.h | 10 ++++++++++
 1 file changed, 10 insertions(+)
include/uapi/rdma/rdma_user_rxe.h +10 -0
index 068433e2229d..e283c2220aba 100644
@@ -99,7 +99,16 @@ struct rxe_send_wr {
 			__u32	remote_qkey;
 			__u16	pkey_index;
 		} ud;
+		struct {
+			__aligned_u64	addr;
+			__aligned_u64	length;
+			__u32		mr_lkey;
+			__u32		mw_rkey;
+			__u32		rkey;
+			__u32		access;
+		} mw;
 		/* reg is only used by the kernel and is not part of the uapi */
+#ifdef __KERNEL__
 		struct {
 			union {
 				struct ib_mr *mr;
@@ -108,6 +117,7 @@ struct rxe_send_wr {
 			__u32	     key;
 			__u32	     access;
 		} reg;
+#endif
 	} wr;
 };
 
Signature · 1 line
2.30.2
#3 lore raw

PATCH v9 3/10 RDMA/rxe: Enable MW object pool

In reply to Bob Pearson

Currently the rxe driver has a rxe_mw struct object but nothing about memory windows is enabled. This patch turns on memory windows and some minor cleanup.

Set device attribute in rxe.c so max_mw = MAX_MW. Change parameters in rxe_param.h so that MAX_MW is the same as MAX_MR. Reduce the number of MRs and MWs to 4K from 256K. Add device capability bits for 2a and 2b memory windows. Removed RXE_MR_TYPE_MW from the rxe_mr_type enum.

---
 drivers/infiniband/sw/rxe/rxe.c       |  1 +
 drivers/infiniband/sw/rxe/rxe_param.h | 19 ++++++++++++-------
 drivers/infiniband/sw/rxe/rxe_verbs.h |  1 -
 3 files changed, 13 insertions(+), 8 deletions(-)
drivers/infiniband/sw/rxe/rxe.c +1 -0
index 95f0de0c8b49..8e0f9c489cab 100644
@@ -54,6 +54,7 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
 	rxe->attr.max_cq			= RXE_MAX_CQ;
 	rxe->attr.max_cqe			= (1 << RXE_MAX_LOG_CQE) - 1;
 	rxe->attr.max_mr			= RXE_MAX_MR;
+	rxe->attr.max_mw			= RXE_MAX_MW;
 	rxe->attr.max_pd			= RXE_MAX_PD;
 	rxe->attr.max_qp_rd_atom		= RXE_MAX_QP_RD_ATOM;
 	rxe->attr.max_res_rd_atom		= RXE_MAX_RES_RD_ATOM;
drivers/infiniband/sw/rxe/rxe_param.h +12 -7
index 25ab50d9b7c2..742e6ec93686 100644
@@ -37,7 +37,6 @@ static inline enum ib_mtu eth_mtu_int_to_enum(int mtu)
 enum rxe_device_param {
 	RXE_MAX_MR_SIZE			= -1ull,
 	RXE_PAGE_SIZE_CAP		= 0xfffff000,
-	RXE_MAX_QP			= 0x10000,
 	RXE_MAX_QP_WR			= 0x4000,
 	RXE_DEVICE_CAP_FLAGS		= IB_DEVICE_BAD_PKEY_CNTR
 					| IB_DEVICE_BAD_QKEY_CNTR
@@ -49,7 +48,10 @@ enum rxe_device_param {
 					| IB_DEVICE_RC_RNR_NAK_GEN
 					| IB_DEVICE_SRQ_RESIZE
 					| IB_DEVICE_MEM_MGT_EXTENSIONS
-					| IB_DEVICE_ALLOW_USER_UNREG,
+					| IB_DEVICE_ALLOW_USER_UNREG
+					| IB_DEVICE_MEM_WINDOW
+					| IB_DEVICE_MEM_WINDOW_TYPE_2A
+					| IB_DEVICE_MEM_WINDOW_TYPE_2B,
 	RXE_MAX_SGE			= 32,
 	RXE_MAX_WQE_SIZE		= sizeof(struct rxe_send_wqe) +
 					  sizeof(struct ib_sge) * RXE_MAX_SGE,
@@ -58,7 +60,6 @@ enum rxe_device_param {
 	RXE_MAX_SGE_RD			= 32,
 	RXE_MAX_CQ			= 16384,
 	RXE_MAX_LOG_CQE			= 15,
-	RXE_MAX_MR			= 256 * 1024,
 	RXE_MAX_PD			= 0x7ffc,
 	RXE_MAX_QP_RD_ATOM		= 128,
 	RXE_MAX_RES_RD_ATOM		= 0x3f000,
@@ -67,7 +68,6 @@ enum rxe_device_param {
 	RXE_MAX_MCAST_QP_ATTACH		= 56,
 	RXE_MAX_TOT_MCAST_QP_ATTACH	= 0x70000,
 	RXE_MAX_AH			= 100,
-	RXE_MAX_SRQ			= 960,
 	RXE_MAX_SRQ_WR			= 0x4000,
 	RXE_MIN_SRQ_WR			= 1,
 	RXE_MAX_SRQ_SGE			= 27,
@@ -80,16 +80,21 @@ enum rxe_device_param {
 
 	RXE_NUM_PORT			= 1,
 
+	RXE_MAX_QP			= 0x10000,
 	RXE_MIN_QP_INDEX		= 16,
 	RXE_MAX_QP_INDEX		= 0x00020000,
 
+	RXE_MAX_SRQ			= 0x00001000,
 	RXE_MIN_SRQ_INDEX		= 0x00020001,
 	RXE_MAX_SRQ_INDEX		= 0x00040000,
 
+	RXE_MAX_MR			= 0x00001000,
+	RXE_MAX_MW			= 0x00001000,
 	RXE_MIN_MR_INDEX		= 0x00000001,
-	RXE_MAX_MR_INDEX		= 0x00040000,
-	RXE_MIN_MW_INDEX		= 0x00040001,
-	RXE_MAX_MW_INDEX		= 0x00060000,
+	RXE_MAX_MR_INDEX		= 0x00010000,
+	RXE_MIN_MW_INDEX		= 0x00010001,
+	RXE_MAX_MW_INDEX		= 0x00020000,
+
 	RXE_MAX_PKT_PER_ACK		= 64,
 
 	RXE_MAX_UNACKED_PSNS		= 128,
drivers/infiniband/sw/rxe/rxe_verbs.h +0 -1
index 11eba7a3ba8f..8d32e3f50813 100644
@@ -273,7 +273,6 @@ enum rxe_mr_type {
 	RXE_MR_TYPE_NONE,
 	RXE_MR_TYPE_DMA,
 	RXE_MR_TYPE_MR,
-	RXE_MR_TYPE_MW,
 };
 
 #define RXE_BUF_PER_MAP		(PAGE_SIZE / sizeof(struct rxe_phys_buf))
Signature · 1 line
2.30.2
#4 lore raw

PATCH v9 4/10 RDMA/rxe: Add ib_alloc_mw and ib_dealloc_mw verbs

In reply to Bob Pearson

Add ib_alloc_mw and ib_dealloc_mw verbs APIs.

Added new file rxe_mw.c focused on MWs. Changed the 8 bit random key generator. Added a cleanup routine for MWs. Added verbs routines to ib_device_ops.

---
v7:
Removed duplicate INIT_RDMA_OBJ_SIZE(ib_mw, ...) in rxe_verbs.c. This was already added in patch 03/10.

---
 drivers/infiniband/sw/rxe/Makefile    |  1 +
 drivers/infiniband/sw/rxe/rxe_loc.h   |  6 +++
 drivers/infiniband/sw/rxe/rxe_mr.c    | 20 +++++-----
 drivers/infiniband/sw/rxe/rxe_mw.c    | 53 +++++++++++++++++++++++++++
 drivers/infiniband/sw/rxe/rxe_pool.c  |  1 +
 drivers/infiniband/sw/rxe/rxe_verbs.c |  2 +
 drivers/infiniband/sw/rxe/rxe_verbs.h |  2 +
 7 files changed, 74 insertions(+), 11 deletions(-)
 create mode 100644 drivers/infiniband/sw/rxe/rxe_mw.c
drivers/infiniband/sw/rxe/Makefile +1 -0
index 66af72dca759..1e24673e9318 100644
@@ -15,6 +15,7 @@ rdma_rxe-y := \
 	rxe_qp.o \
 	rxe_cq.o \
 	rxe_mr.o \
+	rxe_mw.o \
 	rxe_opcode.o \
 	rxe_mmap.o \
 	rxe_icrc.o \
drivers/infiniband/sw/rxe/rxe_loc.h +6 -0
index b21038cb370f..422b9481d5f6 100644
@@ -76,6 +76,7 @@ enum copy_direction {
 	from_mr_obj,
 };
 
+u8 rxe_get_next_key(u32 last_key);
 void rxe_mr_init_dma(struct rxe_pd *pd, int access, struct rxe_mr *mr);
 
 int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
@@ -106,6 +107,11 @@ void rxe_mr_cleanup(struct rxe_pool_entry *arg);
 
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
 
+/* rxe_mw.c */
+int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata);
+int rxe_dealloc_mw(struct ib_mw *ibmw);
+void rxe_mw_cleanup(struct rxe_pool_entry *arg);
+
 /* rxe_net.c */
 void rxe_loopback(struct sk_buff *skb);
 int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb);
drivers/infiniband/sw/rxe/rxe_mr.c +9 -11
index 373b46aab043..cfd35a442c10 100644
@@ -7,19 +7,17 @@
 #include "rxe.h"
 #include "rxe_loc.h"
 
-/*
- * lfsr (linear feedback shift register) with period 255
+/* Return a random 8 bit key value that is
+ * different than the last_key. Set last_key to -1
+ * if this is the first key for an MR or MW
  */
-static u8 rxe_get_key(void)
+u8 rxe_get_next_key(u32 last_key)
 {
-	static u32 key = 1;
-
-	key = key << 1;
-
-	key |= (0 != (key & 0x100)) ^ (0 != (key & 0x10))
-		^ (0 != (key & 0x80)) ^ (0 != (key & 0x40));
+	u8 key;
 
-	key &= 0xff;
+	do {
+		get_random_bytes(&key, 1);
+	} while (key == last_key);
 
 	return key;
 }
@@ -47,7 +45,7 @@ int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
 
 static void rxe_mr_init(int access, struct rxe_mr *mr)
 {
-	u32 lkey = mr->pelem.index << 8 | rxe_get_key();
+	u32 lkey = mr->pelem.index << 8 | rxe_get_next_key(-1);
 	u32 rkey = (access & IB_ACCESS_REMOTE) ? lkey : 0;
 
 	mr->ibmr.lkey = lkey;
drivers/infiniband/sw/rxe/rxe_mw.c new file +53 -0

53 lines not on this page · raw message

drivers/infiniband/sw/rxe/rxe_pool.c +1 -0
index df0bec719341..0b8e7c6255a2 100644
@@ -65,6 +65,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
 		.name		= "rxe-mw",
 		.size		= sizeof(struct rxe_mw),
 		.elem_offset	= offsetof(struct rxe_mw, pelem),
+		.cleanup	= rxe_mw_cleanup,
 		.flags		= RXE_POOL_INDEX | RXE_POOL_NO_ALLOC,
 		.max_index	= RXE_MAX_MW_INDEX,
 		.min_index	= RXE_MIN_MW_INDEX,
drivers/infiniband/sw/rxe/rxe_verbs.c +2 -0
index 86a0965a88f6..552a1ea9c8b7 100644
@@ -1060,6 +1060,7 @@ static const struct ib_device_ops rxe_dev_ops = {
 
 	.alloc_hw_stats = rxe_ib_alloc_hw_stats,
 	.alloc_mr = rxe_alloc_mr,
+	.alloc_mw = rxe_alloc_mw,
 	.alloc_pd = rxe_alloc_pd,
 	.alloc_ucontext = rxe_alloc_ucontext,
 	.attach_mcast = rxe_attach_mcast,
@@ -1069,6 +1070,7 @@ static const struct ib_device_ops rxe_dev_ops = {
 	.create_srq = rxe_create_srq,
 	.create_user_ah = rxe_create_ah,
 	.dealloc_driver = rxe_dealloc,
+	.dealloc_mw = rxe_dealloc_mw,
 	.dealloc_pd = rxe_dealloc_pd,
 	.dealloc_ucontext = rxe_dealloc_ucontext,
 	.dereg_mr = rxe_dereg_mr,
drivers/infiniband/sw/rxe/rxe_verbs.h +2 -0
index 8d32e3f50813..c8597ae8c833 100644
@@ -323,6 +323,8 @@ enum rxe_mw_state {
 struct rxe_mw {
 	struct ib_mw ibmw;
 	struct rxe_pool_entry pelem;
+	spinlock_t lock;
+	enum rxe_mw_state state;
 };
 
 struct rxe_mc_grp {
Signature · 1 line
2.30.2
#5 lore raw

PATCH v9 5/10 RDMA/rxe: Replace WR_REG_MASK by WR_LOCAL_OP_MASK

In reply to Bob Pearson

Rxe has two mask bits WR_LOCAL_MASK and WR_REG_MASK with WR_REG_MASK used to indicate any local operation and WR_LOCAL_MASK unused. This patch replaces both of these with one mask bit WR_LOCAL_OP_MASK which is clearer.

---
 drivers/infiniband/sw/rxe/rxe_opcode.c | 4 ++--
 drivers/infiniband/sw/rxe/rxe_opcode.h | 3 +--
 drivers/infiniband/sw/rxe/rxe_req.c    | 2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c  | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)
drivers/infiniband/sw/rxe/rxe_opcode.c +2 -2
index 0cb4b01fd910..1e4b67b048f3 100644
@@ -87,13 +87,13 @@ struct rxe_wr_opcode_info rxe_wr_opcode_info[] = {
 	[IB_WR_LOCAL_INV]				= {
 		.name	= "IB_WR_LOCAL_INV",
 		.mask	= {
-			[IB_QPT_RC]	= WR_REG_MASK,
+			[IB_QPT_RC]	= WR_LOCAL_OP_MASK,
 		},
 	},
 	[IB_WR_REG_MR]					= {
 		.name	= "IB_WR_REG_MR",
 		.mask	= {
-			[IB_QPT_RC]	= WR_REG_MASK,
+			[IB_QPT_RC]	= WR_LOCAL_OP_MASK,
 		},
 	},
 };
drivers/infiniband/sw/rxe/rxe_opcode.h +1 -2
index 1041ac9a9233..e02f039b8c44 100644
@@ -19,8 +19,7 @@ enum rxe_wr_mask {
 	WR_SEND_MASK			= BIT(2),
 	WR_READ_MASK			= BIT(3),
 	WR_WRITE_MASK			= BIT(4),
-	WR_LOCAL_MASK			= BIT(5),
-	WR_REG_MASK			= BIT(6),
+	WR_LOCAL_OP_MASK		= BIT(5),
 
 	WR_READ_OR_WRITE_MASK		= WR_READ_MASK | WR_WRITE_MASK,
 	WR_READ_WRITE_OR_SEND_MASK	= WR_READ_OR_WRITE_MASK | WR_SEND_MASK,
drivers/infiniband/sw/rxe/rxe_req.c +1 -1
index 3664cdae7e1f..0d4dcd514c55 100644
@@ -593,7 +593,7 @@ int rxe_requester(void *arg)
 	if (unlikely(!wqe))
 		goto exit;
 
-	if (wqe->mask & WR_REG_MASK) {
+	if (wqe->mask & WR_LOCAL_OP_MASK) {
 		if (wqe->wr.opcode == IB_WR_LOCAL_INV) {
 			struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
 			struct rxe_mr *rmr;
drivers/infiniband/sw/rxe/rxe_verbs.c +1 -1
index 552a1ea9c8b7..4860e8ab378e 100644
@@ -577,7 +577,7 @@ static void init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr,
 	init_send_wr(qp, &wqe->wr, ibwr);
 
 	/* local operation */
-	if (unlikely(mask & WR_REG_MASK)) {
+	if (unlikely(mask & WR_LOCAL_OP_MASK)) {
 		wqe->mask = mask;
 		wqe->state = wqe_state_posted;
 		return;
Signature · 1 line
2.30.2
#6 lore raw

PATCH v9 6/10 RDMA/rxe: Move local ops to subroutine

In reply to Bob Pearson

Simplify rxe_requester() by moving the local operations to a subroutine. Add an error return for illegal send WR opcode. Moved next_index ahead of rxe_run_task which fixed a small bug where work completions were delayed until after the next wqe which was not the intended behavior. Let errors return their own WC status. Previously all errors were reported as protection errors which was incorrect. Changed the return of errors from rxe_do_local_ops() to err: which causes an immediate completion. Without this an error on a last WR may get lost. Changed fill_packet() to finish_packet() which is more accurate.

Fixes 8700e2e7c485 ("The software RoCE driver")

---
v9:
Fixed long standing incorrect WC status values and error returns.

---
 drivers/infiniband/sw/rxe/rxe_req.c | 103 +++++++++++++++++-----------
 1 file changed, 63 insertions(+), 40 deletions(-)
drivers/infiniband/sw/rxe/rxe_req.c +63 -40
index 889c7fea6f18..80872ec54219 100644
@@ -462,7 +462,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
 	return skb;
 }
 
-static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
+static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 		       struct rxe_pkt_info *pkt, struct sk_buff *skb,
 		       int paylen)
 {
@@ -578,6 +578,54 @@ static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 			  jiffies + qp->qp_timeout_jiffies);
 }
 
+static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
+{
+	u8 opcode = wqe->wr.opcode;
+	struct rxe_dev *rxe;
+	struct rxe_mr *mr;
+	u32 rkey;
+
+	switch (opcode) {
+	case IB_WR_LOCAL_INV:
+		rxe = to_rdev(qp->ibqp.device);
+		rkey = wqe->wr.ex.invalidate_rkey;
+		mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8);
+		if (!mr) {
+			pr_err("No MR for rkey %#x\n", rkey);
+			wqe->status = IB_WC_LOC_QP_OP_ERR;
+			return -EINVAL;
+		}
+		mr->state = RXE_MR_STATE_FREE;
+		rxe_drop_ref(mr);
+		break;
+	case IB_WR_REG_MR:
+		mr = to_rmr(wqe->wr.wr.reg.mr);
+
+		rxe_add_ref(mr);
+		mr->state = RXE_MR_STATE_VALID;
+		mr->access = wqe->wr.wr.reg.access;
+		mr->ibmr.lkey = wqe->wr.wr.reg.key;
+		mr->ibmr.rkey = wqe->wr.wr.reg.key;
+		mr->iova = wqe->wr.wr.reg.mr->iova;
+		rxe_drop_ref(mr);
+		break;
+	default:
+		pr_err("Unexpected send wqe opcode %d\n", opcode);
+		wqe->status = IB_WC_LOC_QP_OP_ERR;
+		return -EINVAL;
+	}
+
+	wqe->state = wqe_state_done;
+	wqe->status = IB_WC_SUCCESS;
+	qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index);
+
+	if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
+	    qp->sq_sig_type == IB_SIGNAL_ALL_WR)
+		rxe_run_task(&qp->comp.task, 1);
+
+	return 0;
+}
+
 int rxe_requester(void *arg)
 {
 	struct rxe_qp *qp = (struct rxe_qp *)arg;
@@ -618,42 +666,11 @@ int rxe_requester(void *arg)
 		goto exit;
 
 	if (wqe->mask & WR_LOCAL_OP_MASK) {
-		if (wqe->wr.opcode == IB_WR_LOCAL_INV) {
-			struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
-			struct rxe_mr *rmr;
-
-			rmr = rxe_pool_get_index(&rxe->mr_pool,
-						 wqe->wr.ex.invalidate_rkey >> 8);
-			if (!rmr) {
-				pr_err("No mr for key %#x\n",
-				       wqe->wr.ex.invalidate_rkey);
-				wqe->state = wqe_state_error;
-				wqe->status = IB_WC_MW_BIND_ERR;
-				goto exit;
-			}
-			rmr->state = RXE_MR_STATE_FREE;
-			rxe_drop_ref(rmr);
-			wqe->state = wqe_state_done;
-			wqe->status = IB_WC_SUCCESS;
-		} else if (wqe->wr.opcode == IB_WR_REG_MR) {
-			struct rxe_mr *rmr = to_rmr(wqe->wr.wr.reg.mr);
-
-			rmr->state = RXE_MR_STATE_VALID;
-			rmr->access = wqe->wr.wr.reg.access;
-			rmr->ibmr.lkey = wqe->wr.wr.reg.key;
-			rmr->ibmr.rkey = wqe->wr.wr.reg.key;
-			rmr->iova = wqe->wr.wr.reg.mr->iova;
-			wqe->state = wqe_state_done;
-			wqe->status = IB_WC_SUCCESS;
-		} else {
-			goto exit;
-		}
-		if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
-		    qp->sq_sig_type == IB_SIGNAL_ALL_WR)
-			rxe_run_task(&qp->comp.task, 1);
-		qp->req.wqe_index = next_index(qp->sq.queue,
-						qp->req.wqe_index);
-		goto next_wqe;
+		ret = rxe_do_local_ops(qp, wqe);
+		if (unlikely(ret))
+			goto err;
+		else
+			goto next_wqe;
 	}
 
 	if (unlikely(qp_type(qp) == IB_QPT_RC &&
@@ -711,11 +728,17 @@ int rxe_requester(void *arg)
 	skb = init_req_packet(qp, wqe, opcode, payload, &pkt);
 	if (unlikely(!skb)) {
 		pr_err("qp#%d Failed allocating skb\n", qp_num(qp));
+		wqe->status = IB_WC_LOC_QP_OP_ERR;
 		goto err;
 	}
 
-	if (fill_packet(qp, wqe, &pkt, skb, payload)) {
-		pr_debug("qp#%d Error during fill packet\n", qp_num(qp));
+	ret = finish_packet(qp, wqe, &pkt, skb, payload);
+	if (unlikely(ret)) {
+		pr_debug("qp#%d Error during finish packet\n", qp_num(qp));
+		if (ret == -EFAULT)
+			wqe->status = IB_WC_LOC_PROT_ERR;
+		else
+			wqe->status = IB_WC_LOC_QP_OP_ERR;
 		kfree_skb(skb);
 		goto err;
 	}
@@ -740,6 +763,7 @@ int rxe_requester(void *arg)
 			goto exit;
 		}
 
+		wqe->status = IB_WC_LOC_QP_OP_ERR;
 		goto err;
 	}
 
@@ -748,7 +772,6 @@ int rxe_requester(void *arg)
 	goto next_wqe;
 
 err:
-	wqe->status = IB_WC_LOC_PROT_ERR;
 	wqe->state = wqe_state_error;
 	__rxe_do_task(&qp->comp.task);
 
Signature · 1 line
2.30.2
#7 lore raw

PATCH v9 7/10 RDMA/rxe: Add support for bind MW work requests

In reply to Bob Pearson

Add support for bind MW work requests from user space. Since rdma/core does not support bind mw in ib_send_wr there is no way to support bind mw in kernel space.

Added bind_mw local operation in rxe_req.c. Added bind_mw WR operation in rxe_opcode.c. Added bind_mw WC in rxe_comp.c. Added additional fields to rxe_mw in rxe_verbs.h. Added rxe_do_dealloc_mw() subroutine to cleanup an mw when rxe_dealloc_mw is called. Added code to implement bind_mw operation in rxe_mw.c

---
 drivers/infiniband/sw/rxe/rxe_comp.c   |   1 +
 drivers/infiniband/sw/rxe/rxe_loc.h    |   1 +
 drivers/infiniband/sw/rxe/rxe_mw.c     | 202 ++++++++++++++++++++++++-
 drivers/infiniband/sw/rxe/rxe_opcode.c |   7 +
 drivers/infiniband/sw/rxe/rxe_req.c    |   8 +
 drivers/infiniband/sw/rxe/rxe_verbs.h  |  15 +-
 6 files changed, 229 insertions(+), 5 deletions(-)
drivers/infiniband/sw/rxe/rxe_comp.c +1 -0
index 32e587c47637..02bc93e186cc 100644
@@ -103,6 +103,7 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode)
 	case IB_WR_RDMA_READ_WITH_INV:		return IB_WC_RDMA_READ;
 	case IB_WR_LOCAL_INV:			return IB_WC_LOCAL_INV;
 	case IB_WR_REG_MR:			return IB_WC_REG_MR;
+	case IB_WR_BIND_MW:			return IB_WC_BIND_MW;
 
 	default:
 		return 0xff;
drivers/infiniband/sw/rxe/rxe_loc.h +1 -0
index 422b9481d5f6..e97048e77451 100644
@@ -110,6 +110,7 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
 /* rxe_mw.c */
 int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata);
 int rxe_dealloc_mw(struct ib_mw *ibmw);
+int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
 void rxe_mw_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_net.c */
drivers/infiniband/sw/rxe/rxe_mw.c +201 -1

220 lines not on this page · raw message

drivers/infiniband/sw/rxe/rxe_opcode.c +7 -0
index 1e4b67b048f3..3ef5a10a6efd 100644
@@ -96,6 +96,13 @@ struct rxe_wr_opcode_info rxe_wr_opcode_info[] = {
 			[IB_QPT_RC]	= WR_LOCAL_OP_MASK,
 		},
 	},
+	[IB_WR_BIND_MW]					= {
+		.name	= "IB_WR_BIND_MW",
+		.mask	= {
+			[IB_QPT_RC]	= WR_LOCAL_OP_MASK,
+			[IB_QPT_UC]	= WR_LOCAL_OP_MASK,
+		},
+	},
 };
 
 struct rxe_opcode_info rxe_opcode[RXE_NUM_OPCODE] = {
drivers/infiniband/sw/rxe/rxe_req.c +8 -0
index 80872ec54219..6583f8ca95dc 100644
@@ -584,6 +584,7 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	struct rxe_dev *rxe;
 	struct rxe_mr *mr;
 	u32 rkey;
+	int ret;
 
 	switch (opcode) {
 	case IB_WR_LOCAL_INV:
@@ -609,6 +610,13 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 		mr->iova = wqe->wr.wr.reg.mr->iova;
 		rxe_drop_ref(mr);
 		break;
+	case IB_WR_BIND_MW:
+		ret = rxe_bind_mw(qp, wqe);
+		if (unlikely(ret)) {
+			wqe->status = IB_WC_MW_BIND_ERR;
+			return ret;
+		}
+		break;
 	default:
 		pr_err("Unexpected send wqe opcode %d\n", opcode);
 		wqe->status = IB_WC_LOC_QP_OP_ERR;
drivers/infiniband/sw/rxe/rxe_verbs.h +11 -4
index 5effb12d22cc..3d0ab8b7804f 100644
@@ -315,6 +315,8 @@ struct rxe_mr {
 	u32			num_map;
 
 	struct rxe_map		**map;
+
+	atomic_t		num_mw;
 };
 
 enum rxe_mw_state {
@@ -324,10 +326,15 @@ enum rxe_mw_state {
 };
 
 struct rxe_mw {
-	struct ib_mw ibmw;
-	struct rxe_pool_entry pelem;
-	spinlock_t lock;
-	enum rxe_mw_state state;
+	struct			ib_mw ibmw;
+	struct			rxe_pool_entry pelem;
+	spinlock_t		lock;
+	enum rxe_mw_state	state;
+	struct rxe_qp		*qp;	/* Type 2 only */
+	struct rxe_mr		*mr;
+	int			access;
+	u64			addr;
+	u64			length;
 };
 
 struct rxe_mc_grp {
Signature · 1 line
2.30.2
#8 lore raw

PATCH v9 8/10 RDMA/rxe: Implement invalidate MW operations

In reply to Bob Pearson

Implement invalidate MW and cleaned up invalidate MR operations.

Added code to perform remote invalidate for send with invalidate. Added code to perform local invalidation. Deleted some blank lines in rxe_loc.h.

---
v6:
Added rxe_ to subroutine names in lines that changed.
v3:
Replaced enums in lower case with upper case and moved to rxe_verbs.h which is where enums live.

---
 drivers/infiniband/sw/rxe/rxe_comp.c  |  4 +-
 drivers/infiniband/sw/rxe/rxe_loc.h   | 29 ++--------
 drivers/infiniband/sw/rxe/rxe_mr.c    | 81 ++++++++++++++++++---------
 drivers/infiniband/sw/rxe/rxe_mw.c    | 67 ++++++++++++++++++++++
 drivers/infiniband/sw/rxe/rxe_req.c   | 18 +++---
 drivers/infiniband/sw/rxe/rxe_resp.c  | 60 ++++++++++++--------
 drivers/infiniband/sw/rxe/rxe_verbs.h | 33 ++++++++---
 7 files changed, 199 insertions(+), 93 deletions(-)
drivers/infiniband/sw/rxe/rxe_comp.c +2 -2
index 02bc93e186cc..d4ceb81a96df 100644
@@ -349,7 +349,7 @@ static inline enum comp_state do_read(struct rxe_qp *qp,
 
 	ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE,
 			&wqe->dma, payload_addr(pkt),
-			payload_size(pkt), to_mr_obj, NULL);
+			payload_size(pkt), RXE_TO_MR_OBJ, NULL);
 	if (ret)
 		return COMPST_ERROR;
 
@@ -369,7 +369,7 @@ static inline enum comp_state do_atomic(struct rxe_qp *qp,
 
 	ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE,
 			&wqe->dma, &atomic_orig,
-			sizeof(u64), to_mr_obj, NULL);
+			sizeof(u64), RXE_TO_MR_OBJ, NULL);
 	if (ret)
 		return COMPST_ERROR;
 	else
drivers/infiniband/sw/rxe/rxe_loc.h +6 -23
index e97048e77451..8a4633aeb2a8 100644
@@ -71,46 +71,29 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *dev, u32 size,
 int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
 
 /* rxe_mr.c */
-enum copy_direction {
-	to_mr_obj,
-	from_mr_obj,
-};
-
 u8 rxe_get_next_key(u32 last_key);
 void rxe_mr_init_dma(struct rxe_pd *pd, int access, struct rxe_mr *mr);
-
 int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
 		     int access, struct rxe_mr *mr);
-
 int rxe_mr_init_fast(struct rxe_pd *pd, int max_pages, struct rxe_mr *mr);
-
 int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
-		enum copy_direction dir, u32 *crcp);
-
+		enum rxe_mr_copy_dir dir, u32 *crcp);
 int copy_data(struct rxe_pd *pd, int access,
 	      struct rxe_dma_info *dma, void *addr, int length,
-	      enum copy_direction dir, u32 *crcp);
-
+	      enum rxe_mr_copy_dir dir, u32 *crcp);
 void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length);
-
-enum lookup_type {
-	lookup_local,
-	lookup_remote,
-};
-
 struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
-			 enum lookup_type type);
-
+			 enum rxe_mr_lookup_type type);
 int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
-
-void rxe_mr_cleanup(struct rxe_pool_entry *arg);
-
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
+int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey);
+void rxe_mr_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_mw.c */
 int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata);
 int rxe_dealloc_mw(struct ib_mw *ibmw);
 int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
+int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey);
 void rxe_mw_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_net.c */
drivers/infiniband/sw/rxe/rxe_mr.c +55 -26

139 lines not on this page · raw message

drivers/infiniband/sw/rxe/rxe_mw.c +67 -0

73 lines not on this page · raw message

drivers/infiniband/sw/rxe/rxe_req.c +8 -10
index 6583f8ca95dc..c57699cc6578 100644
@@ -487,7 +487,7 @@ static int finish_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 		} else {
 			err = copy_data(qp->pd, 0, &wqe->dma,
 					payload_addr(pkt), paylen,
-					from_mr_obj,
+					RXE_FROM_MR_OBJ,
 					&crc);
 			if (err)
 				return err;
@@ -581,27 +581,25 @@ static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
 static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 {
 	u8 opcode = wqe->wr.opcode;
-	struct rxe_dev *rxe;
 	struct rxe_mr *mr;
 	u32 rkey;
 	int ret;
 
 	switch (opcode) {
 	case IB_WR_LOCAL_INV:
-		rxe = to_rdev(qp->ibqp.device);
 		rkey = wqe->wr.ex.invalidate_rkey;
-		mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8);
-		if (!mr) {
-			pr_err("No MR for rkey %#x\n", rkey);
+		if (rkey_is_mw(rkey))
+			ret = rxe_invalidate_mw(qp, rkey);
+		else
+			ret = rxe_invalidate_mr(qp, rkey);
+
+		if (unlikely(ret)) {
 			wqe->status = IB_WC_LOC_QP_OP_ERR;
-			return -EINVAL;
+			return ret;
 		}
-		mr->state = RXE_MR_STATE_FREE;
-		rxe_drop_ref(mr);
 		break;
 	case IB_WR_REG_MR:
 		mr = to_rmr(wqe->wr.wr.reg.mr);
-
 		rxe_add_ref(mr);
 		mr->state = RXE_MR_STATE_VALID;
 		mr->access = wqe->wr.wr.reg.access;
drivers/infiniband/sw/rxe/rxe_resp.c +36 -24

134 lines not on this page · raw message

drivers/infiniband/sw/rxe/rxe_verbs.h +25 -8
index 3d0ab8b7804f..47399bf7517e 100644
@@ -278,6 +278,16 @@ enum rxe_mr_type {
 	RXE_MR_TYPE_MR,
 };
 
+enum rxe_mr_copy_dir {
+	RXE_TO_MR_OBJ,
+	RXE_FROM_MR_OBJ,
+};
+
+enum rxe_mr_lookup_type {
+	RXE_LOOKUP_LOCAL,
+	RXE_LOOKUP_REMOTE,
+};
+
 #define RXE_BUF_PER_MAP		(PAGE_SIZE / sizeof(struct rxe_phys_buf))
 
 struct rxe_phys_buf {
@@ -289,6 +299,13 @@ struct rxe_map {
 	struct rxe_phys_buf	buf[RXE_BUF_PER_MAP];
 };
 
+static inline int rkey_is_mw(u32 rkey)
+{
+	u32 index = rkey >> 8;
+
+	return (index >= RXE_MIN_MW_INDEX) && (index <= RXE_MAX_MW_INDEX);
+}
+
 struct rxe_mr {
 	struct rxe_pool_entry	pelem;
 	struct ib_mr		ibmr;
@@ -314,23 +331,23 @@ struct rxe_mr {
 	u32			max_buf;
 	u32			num_map;
 
-	struct rxe_map		**map;
-
 	atomic_t		num_mw;
+
+	struct rxe_map		**map;
 };
 
 enum rxe_mw_state {
-	RXE_MW_STATE_INVALID = RXE_MR_STATE_INVALID,
-	RXE_MW_STATE_FREE = RXE_MR_STATE_FREE,
-	RXE_MW_STATE_VALID = RXE_MR_STATE_VALID,
+	RXE_MW_STATE_INVALID	= RXE_MR_STATE_INVALID,
+	RXE_MW_STATE_FREE	= RXE_MR_STATE_FREE,
+	RXE_MW_STATE_VALID	= RXE_MR_STATE_VALID,
 };
 
 struct rxe_mw {
-	struct			ib_mw ibmw;
-	struct			rxe_pool_entry pelem;
+	struct ib_mw		ibmw;
+	struct rxe_pool_entry	pelem;
 	spinlock_t		lock;
 	enum rxe_mw_state	state;
-	struct rxe_qp		*qp;	/* Type 2 only */
+	struct rxe_qp		*qp; /* Type 2 only */
 	struct rxe_mr		*mr;
 	int			access;
 	u64			addr;
Signature · 1 line
2.30.2
#9 lore raw

PATCH v9 9/10 RDMA/rxe: Implement memory access through MWs

In reply to Bob Pearson

Add code to implement memory access through memory windows.

---
 drivers/infiniband/sw/rxe/rxe_loc.h   |  1 +
 drivers/infiniband/sw/rxe/rxe_mw.c    | 23 +++++++++++
 drivers/infiniband/sw/rxe/rxe_resp.c  | 55 +++++++++++++++++++--------
 drivers/infiniband/sw/rxe/rxe_verbs.h | 11 ++++++
 4 files changed, 75 insertions(+), 15 deletions(-)
drivers/infiniband/sw/rxe/rxe_loc.h +1 -0
index 8a4633aeb2a8..6e4b5e22541e 100644
@@ -94,6 +94,7 @@ int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata);
 int rxe_dealloc_mw(struct ib_mw *ibmw);
 int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
 int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey);
+struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey);
 void rxe_mw_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_net.c */
drivers/infiniband/sw/rxe/rxe_mw.c +23 -0
index 594f8cef0a08..5ba77df7598e 100644
@@ -312,6 +312,29 @@ int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey)
 	return ret;
 }
 
+struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey)
+{
+	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+	struct rxe_pd *pd = to_rpd(qp->ibqp.pd);
+	struct rxe_mw *mw;
+	int index = rkey >> 8;
+
+	mw = rxe_pool_get_index(&rxe->mw_pool, index);
+	if (!mw)
+		return NULL;
+
+	if (unlikely((rxe_mw_rkey(mw) != rkey) || rxe_mw_pd(mw) != pd ||
+		     (mw->ibmw.type == IB_MW_TYPE_2 && mw->qp != qp) ||
+		     (mw->length == 0) ||
+		     (access && !(access & mw->access)) ||
+		     mw->state != RXE_MW_STATE_VALID)) {
+		rxe_drop_ref(mw);
+		return NULL;
+	}
+
+	return mw;
+}
+
 void rxe_mw_cleanup(struct rxe_pool_entry *elem)
 {
 	struct rxe_mw *mw = container_of(elem, typeof(*mw), pelem);
drivers/infiniband/sw/rxe/rxe_resp.c +40 -15

112 lines not on this page · raw message

drivers/infiniband/sw/rxe/rxe_verbs.h +11 -0
index 74fcd871757d..cf8cae64f7df 100644
@@ -183,6 +183,7 @@ struct rxe_resp_info {
 
 	/* RDMA read / atomic only */
 	u64			va;
+	u64			offset;
 	struct rxe_mr		*mr;
 	u32			resid;
 	u32			rkey;
@@ -480,6 +481,16 @@ static inline u32 mr_rkey(struct rxe_mr *mr)
 	return mr->ibmr.rkey;
 }
 
+static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw)
+{
+	return to_rpd(mw->ibmw.pd);
+}
+
+static inline u32 rxe_mw_rkey(struct rxe_mw *mw)
+{
+	return mw->ibmw.rkey;
+}
+
 int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
 
 void rxe_mc_cleanup(struct rxe_pool_entry *arg);
Signature · 1 line
2.30.2
#10 lore raw

PATCH v9 10/10 RDMA/rxe: Disallow MR dereg and invalidate when bound

In reply to Bob Pearson

Check that an MR has no bound MWs before allowing a dereg or invalidate operation.

---
 drivers/infiniband/sw/rxe/rxe_loc.h   |  1 +
 drivers/infiniband/sw/rxe/rxe_mr.c    | 25 +++++++++++++++++++++++++
 drivers/infiniband/sw/rxe/rxe_verbs.c | 11 -----------
 3 files changed, 26 insertions(+), 11 deletions(-)
drivers/infiniband/sw/rxe/rxe_loc.h +1 -0
index 6e4b5e22541e..1ddb20855dee 100644
@@ -87,6 +87,7 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
 int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
 int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey);
+int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
 void rxe_mr_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_mw.c */
drivers/infiniband/sw/rxe/rxe_mr.c +25 -0
index 3fb58d2c7814..7f169329a8bf 100644
@@ -546,6 +546,13 @@ int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey)
 		goto err_drop_ref;
 	}
 
+	if (atomic_read(&mr->num_mw) > 0) {
+		pr_warn("%s: Attempt to invalidate an MR while bound to MWs\n",
+			__func__);
+		ret = -EINVAL;
+		goto err_drop_ref;
+	}
+
 	mr->state = RXE_MR_STATE_FREE;
 	ret = 0;
 
@@ -555,6 +562,24 @@ int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey)
 	return ret;
 }
 
+int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
+{
+	struct rxe_mr *mr = to_rmr(ibmr);
+
+	if (atomic_read(&mr->num_mw) > 0) {
+		pr_warn("%s: Attempt to deregister an MR while bound to MWs\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	mr->state = RXE_MR_STATE_ZOMBIE;
+	rxe_drop_ref(mr_pd(mr));
+	rxe_drop_index(mr);
+	rxe_drop_ref(mr);
+
+	return 0;
+}
+
 void rxe_mr_cleanup(struct rxe_pool_entry *arg)
 {
 	struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem);
drivers/infiniband/sw/rxe/rxe_verbs.c +0 -11
index 4860e8ab378e..3e0bab4994d1 100644
@@ -913,17 +913,6 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
 	return ERR_PTR(err);
 }
 
-static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
-{
-	struct rxe_mr *mr = to_rmr(ibmr);
-
-	mr->state = RXE_MR_STATE_ZOMBIE;
-	rxe_drop_ref(mr_pd(mr));
-	rxe_drop_index(mr);
-	rxe_drop_ref(mr);
-	return 0;
-}
-
 static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
 				  u32 max_num_sg)
 {
Signature · 1 line
2.30.2
maintainer Applied
#11 lore raw
In reply to Bob Pearson
Quoted 4 lines · Bob Pearson

This series of patches implement memory windows for the rdma_rxe driver. This is a shorter reimplementation of an earlier patch set. They apply to and depend on the current for-next linux rdma tree.

Quoted 11 lines

Bob Pearson (10):
RDMA/rxe: Add bind MW fields to rxe_send_wr RDMA/rxe: Return errors for add index and key RDMA/rxe: Enable MW object pool
RDMA/rxe: Add ib_alloc_mw and ib_dealloc_mw verbs RDMA/rxe: Replace WR_REG_MASK by WR_LOCAL_OP_MASK RDMA/rxe: Move local ops to subroutine RDMA/rxe: Add support for bind MW work requests RDMA/rxe: Implement invalidate MW operations RDMA/rxe: Implement memory access through MWs RDMA/rxe: Disallow MR dereg and invalidate when bound

Applied to for-next, thanks

Jason

#12 lore raw
Quoted 17 lines · Jason Gunthorpe
Quoted 4 lines · Bob Pearson

This series of patches implement memory windows for the rdma_rxe driver. This is a shorter reimplementation of an earlier patch set. They apply to and depend on the current for-next linux rdma tree.

Quoted 11 lines

Bob Pearson (10):
RDMA/rxe: Add bind MW fields to rxe_send_wr RDMA/rxe: Return errors for add index and key RDMA/rxe: Enable MW object pool
RDMA/rxe: Add ib_alloc_mw and ib_dealloc_mw verbs RDMA/rxe: Replace WR_REG_MASK by WR_LOCAL_OP_MASK RDMA/rxe: Move local ops to subroutine RDMA/rxe: Add support for bind MW work requests RDMA/rxe: Implement invalidate MW operations RDMA/rxe: Implement memory access through MWs RDMA/rxe: Disallow MR dereg and invalidate when bound

Quoted 4 lines

Applied to for-next, thanks

Jason

Thanks. I updated the provider in roce-core by applying clang-format-diff. I am not really sure it any better but I am convinced it is logically the same. Looks like the earlier commit already got accepted. So you can take this one or throw it away if you wish. I don't care one way or the other.

Bob