diff mbox series

[for-next,v6,02/10] RDMA: Extend RDMA kernel verbs ABI to support flush

Message ID 20221116081951.32750-3-lizhijian@fujitsu.com (mailing list archive)
State Superseded
Headers show
Series RDMA/rxe: Add RDMA FLUSH operation | expand

Commit Message

Zhijian Li (Fujitsu) Nov. 16, 2022, 8:19 a.m. UTC 
This commit extends the RDMA kernel verbs ABI to support the flush
operation defined in IBA A19.4.1. These changes are
backwards compatible with the existing RDMA kernel verbs ABI.

It makes device/HCA support new FLUSH attributes/capabilities, and it
also makes memory region support new FLUSH access flags.

Users can use ibv_reg_mr(3) to register flush access flags. Only the
access flags also supported by device's capabilities can be registered
successfully.

Once registered successfully, it means the MR is flushable. Similarly,
A flushable MR should also have one or both of GLOBAL_VISIBILITY and
PERSISTENT attributes/capabilities like device/HCA.

Reviewed-by: Zhu Yanjun <zyjzyj2000@gmail.com>
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
V5: new names and new patch split scheme, suggested by Bob
---
 include/rdma/ib_pack.h  |  3 +++
 include/rdma/ib_verbs.h | 20 +++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index a9162f25beaf..56211d1cc9f9 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -84,6 +84,7 @@  enum {
 	/* opcode 0x15 is reserved */
 	IB_OPCODE_SEND_LAST_WITH_INVALIDATE         = 0x16,
 	IB_OPCODE_SEND_ONLY_WITH_INVALIDATE         = 0x17,
+	IB_OPCODE_FLUSH                             = 0x1C,
 
 	/* real constants follow -- see comment about above IB_OPCODE()
 	   macro for more details */
@@ -112,6 +113,7 @@  enum {
 	IB_OPCODE(RC, FETCH_ADD),
 	IB_OPCODE(RC, SEND_LAST_WITH_INVALIDATE),
 	IB_OPCODE(RC, SEND_ONLY_WITH_INVALIDATE),
+	IB_OPCODE(RC, FLUSH),
 
 	/* UC */
 	IB_OPCODE(UC, SEND_FIRST),
@@ -149,6 +151,7 @@  enum {
 	IB_OPCODE(RD, ATOMIC_ACKNOWLEDGE),
 	IB_OPCODE(RD, COMPARE_SWAP),
 	IB_OPCODE(RD, FETCH_ADD),
+	IB_OPCODE(RD, FLUSH),
 
 	/* UD */
 	IB_OPCODE(UD, SEND_ONLY),
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index a1f4d53a4bb6..bd436e0135ba 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -270,6 +270,9 @@  enum ib_device_cap_flags {
 	/* The device supports padding incoming writes to cacheline. */
 	IB_DEVICE_PCI_WRITE_END_PADDING =
 		IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING,
+	/* Placement type attributes */
+	IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL,
+	IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT,
 };
 
 enum ib_kernel_cap_flags {
@@ -985,6 +988,7 @@  enum ib_wc_opcode {
 	IB_WC_REG_MR,
 	IB_WC_MASKED_COMP_SWAP,
 	IB_WC_MASKED_FETCH_ADD,
+	IB_WC_FLUSH = IB_UVERBS_WC_FLUSH,
 /*
  * Set value of IB_WC_RECV so consumers can test if a completion is a
  * receive by testing (opcode & IB_WC_RECV).
@@ -1325,6 +1329,7 @@  enum ib_wr_opcode {
 		IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP,
 	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD =
 		IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD,
+	IB_WR_FLUSH = IB_UVERBS_WR_FLUSH,
 
 	/* These are kernel only and can not be issued by userspace */
 	IB_WR_REG_MR = 0x20,
@@ -1458,10 +1463,14 @@  enum ib_access_flags {
 	IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND,
 	IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB,
 	IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING,
+	IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL,
+	IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT,
+	IB_ACCESS_FLUSHABLE = IB_ACCESS_FLUSH_GLOBAL |
+			      IB_ACCESS_FLUSH_PERSISTENT,
 
 	IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE,
 	IB_ACCESS_SUPPORTED =
-		((IB_ACCESS_HUGETLB << 1) - 1) | IB_ACCESS_OPTIONAL,
+		((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL,
 };
 
 /*
@@ -4321,6 +4330,8 @@  int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata);
 static inline int ib_check_mr_access(struct ib_device *ib_dev,
 				     unsigned int flags)
 {
+	u64 device_cap = ib_dev->attrs.device_cap_flags;
+
 	/*
 	 * Local write permission is required if remote write or
 	 * remote atomic permission is also requested.
@@ -4335,6 +4346,13 @@  static inline int ib_check_mr_access(struct ib_device *ib_dev,
 	if (flags & IB_ACCESS_ON_DEMAND &&
 	    !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING))
 		return -EOPNOTSUPP;
+
+	if ((flags & IB_ACCESS_FLUSH_GLOBAL &&
+	    !(device_cap & IB_DEVICE_FLUSH_GLOBAL)) ||
+	    (flags & IB_ACCESS_FLUSH_PERSISTENT &&
+	    !(device_cap & IB_DEVICE_FLUSH_PERSISTENT)))
+		return -EOPNOTSUPP;
+
 	return 0;
 }