Merge branch 'mlx5-rd-sgl' into rdma.git for-next

From Yamin Friedman:

====================
This series from Yamin implements long standing "TODO" existed in rw.c. It
allows the driver to specify a cut-over point where it is faster to build
a lkey MR rather than do a large SGL for RDMA READ operations.

mlx5 HW gets a notable performane boost by switching to MRs.
====================

Based on the mlx5-next branch from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux for
dependencies

* branch 'mlx5-rd-sgl': (3 commits)
  RDMA/mlx5: Add capability for max sge to get optimized performance
  RDMA/rw: Support threshold for registration vs scattering to local pages
  net/mlx5: Expose optimal performance scatter entries capability

4 files changed, 57 insertions, 3 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index c99b4f2482c6..4fe35d600ab8 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -1003,6 +1003,8 @@ struct drm_amdgpu_info_device {
 	__u64 high_va_max;
 	/* gfx10 pa_sc_tile_steering_override */
 	__u32 pa_sc_tile_steering_override;
+	/* disabled TCCs */
+	__u64 tcc_disabled_mask;
 };
 
 struct drm_amdgpu_info_hw_ip {
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 1c215ea1798e..e168dc59e9a0 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
 	__u32	result;
 };
 
+struct nvme_passthru_cmd64 {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u64	result;
+};
+
 #define nvme_admin_cmd nvme_passthru_cmd
 
 #define NVME_IOCTL_ID		_IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
 #define NVME_IOCTL_RESET	_IO('N', 0x44)
 #define NVME_IOCTL_SUBSYS_RESET	_IO('N', 0x45)
 #define NVME_IOCTL_RESCAN	_IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD	_IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
 
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */
diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h
index 364c350e85cd..62b6f69bd9fb 100644
--- a/include/uapi/linux/pg.h
+++ b/include/uapi/linux/pg.h
@@ -35,6 +35,9 @@
 
 */
 
+#ifndef _UAPI_LINUX_PG_H
+#define _UAPI_LINUX_PG_H
+
 #define PG_MAGIC	'P'
 #define PG_RESET	'Z'
 #define PG_COMMAND	'C'
@@ -61,4 +64,4 @@ struct pg_read_hdr {
 
 };
 
-/* end of pg.h */
+#endif /* _UAPI_LINUX_PG_H */
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index b3105ac1381a..99335e1f4a27 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -33,8 +33,31 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
-/*
- * Arguments for the clone3 syscall
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags:       Flags for the new process as listed above.
+ *               All flags are valid except for CSIGNAL and
+ *               CLONE_DETACHED.
+ * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
+ *               returned in this argument.
+ * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
+ *               child process will be returned in the child's
+ *               memory.
+ * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
+ *               the child process will be returned in the
+ *               parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ *               sent when the child exits.
+ * @stack:       Specify the location of the stack for the
+ *               child process.
+ * @stack_size:  The size of the stack for the child process.
+ * @tls:         If CLONE_SETTLS is set, the tls descriptor
+ *               is set to tls.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
  */
 struct clone_args {
 	__aligned_u64 flags;
@@ -46,6 +69,9 @@ struct clone_args {
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
 };
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 
 /*
  * Scheduling policies