Merge branch 'linus' into locking/core, to fix up conflicts

 Conflicts:
	mm/page_alloc.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 561 insertions, 84 deletions

diff --git a/include/uapi/drm/armada_drm.h b/include/uapi/drm/armada_drm.h
index 72e326f9c7de..0cb932416cfe 100644
--- a/include/uapi/drm/armada_drm.h
+++ b/include/uapi/drm/armada_drm.h
@@ -23,27 +23,27 @@ extern "C" {
 	DRM_##dir(DRM_COMMAND_BASE + DRM_ARMADA_##name, struct drm_armada_##str)
 
 struct drm_armada_gem_create {
-	uint32_t handle;
-	uint32_t size;
+	__u32 handle;
+	__u32 size;
 };
 #define DRM_IOCTL_ARMADA_GEM_CREATE \
 	ARMADA_IOCTL(IOWR, GEM_CREATE, gem_create)
 
 struct drm_armada_gem_mmap {
-	uint32_t handle;
-	uint32_t pad;
-	uint64_t offset;
-	uint64_t size;
-	uint64_t addr;
+	__u32 handle;
+	__u32 pad;
+	__u64 offset;
+	__u64 size;
+	__u64 addr;
 };
 #define DRM_IOCTL_ARMADA_GEM_MMAP \
 	ARMADA_IOCTL(IOWR, GEM_MMAP, gem_mmap)
 
 struct drm_armada_gem_pwrite {
-	uint64_t ptr;
-	uint32_t handle;
-	uint32_t offset;
-	uint32_t size;
+	__u64 ptr;
+	__u32 handle;
+	__u32 offset;
+	__u32 size;
 };
 #define DRM_IOCTL_ARMADA_GEM_PWRITE \
 	ARMADA_IOCTL(IOW, GEM_PWRITE, gem_pwrite)
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 101593ab10ac..97677cd6964d 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -700,6 +700,7 @@ struct drm_prime_handle {
 
 struct drm_syncobj_create {
 	__u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
 	__u32 flags;
 };
 
@@ -718,6 +719,24 @@ struct drm_syncobj_handle {
 	__u32 pad;
 };
 
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+struct drm_syncobj_wait {
+	__u64 handles;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+};
+
+struct drm_syncobj_array {
+	__u64 handles;
+	__u32 count_handles;
+	__u32 pad;
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -840,6 +859,9 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_DESTROY	DRM_IOWR(0xC0, struct drm_syncobj_destroy)
 #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD	DRM_IOWR(0xC1, struct drm_syncobj_handle)
 #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE	DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT		DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
 /**
  * Device specific ioctls should only be in their respective headers
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 7586c46f68bf..3ad838d3f93f 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -185,6 +185,8 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
 /* add more to the end as needed */
 
+#define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
+
 #define fourcc_mod_code(vendor, val) \
 	((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffULL))
 
@@ -197,6 +199,15 @@ extern "C" {
  */
 
 /*
+ * Invalid Modifier
+ *
+ * This modifier can be used as a sentinel to terminate the format modifiers
+ * list, or to initialize a variable with an invalid modifier. It might also be
+ * used to report an error back to userspace for certain APIs.
+ */
+#define DRM_FORMAT_MOD_INVALID	fourcc_mod_code(NONE, DRM_FORMAT_RESERVED)
+
+/*
  * Linear Layout
  *
  * Just plain linear layout. Note that this is different from no specifying any
@@ -253,6 +264,26 @@ extern "C" {
 #define I915_FORMAT_MOD_Yf_TILED fourcc_mod_code(INTEL, 3)
 
 /*
+ * Intel color control surface (CCS) for render compression
+ *
+ * The framebuffer format must be one of the 8:8:8:8 RGB formats.
+ * The main surface will be plane index 0 and must be Y/Yf-tiled,
+ * the CCS will be plane index 1.
+ *
+ * Each CCS tile matches a 1024x512 pixel area of the main surface.
+ * To match certain aspects of the 3D hardware the CCS is
+ * considered to be made up of normal 128Bx32 Y tiles, Thus
+ * the CCS pitch must be specified in multiples of 128 bytes.
+ *
+ * In reality the CCS tile appears to be a 64Bx64 Y tile, composed
+ * of QWORD (8 bytes) chunks instead of OWORD (16 bytes) chunks.
+ * But that fact is not relevant unless the memory is accessed
+ * directly.
+ */
+#define I915_FORMAT_MOD_Y_TILED_CCS	fourcc_mod_code(INTEL, 4)
+#define I915_FORMAT_MOD_Yf_TILED_CCS	fourcc_mod_code(INTEL, 5)
+
+/*
  * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
  *
  * Macroblocks are laid in a Z-shape, and each pixel data is following the
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 403339f98a92..54fc38c3c3f1 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -712,6 +712,56 @@ struct drm_mode_atomic {
 	__u64 user_data;
 };
 
+struct drm_format_modifier_blob {
+#define FORMAT_BLOB_CURRENT 1
+	/* Version of this blob format */
+	__u32 version;
+
+	/* Flags */
+	__u32 flags;
+
+	/* Number of fourcc formats supported */
+	__u32 count_formats;
+
+	/* Where in this blob the formats exist (in bytes) */
+	__u32 formats_offset;
+
+	/* Number of drm_format_modifiers */
+	__u32 count_modifiers;
+
+	/* Where in this blob the modifiers exist (in bytes) */
+	__u32 modifiers_offset;
+
+	/* __u32 formats[] */
+	/* struct drm_format_modifier modifiers[] */
+};
+
+struct drm_format_modifier {
+	/* Bitmask of formats in get_plane format list this info applies to. The
+	 * offset allows a sliding window of which 64 formats (bits).
+	 *
+	 * Some examples:
+	 * In today's world with < 65 formats, and formats 0, and 2 are
+	 * supported
+	 * 0x0000000000000005
+	 *		  ^-offset = 0, formats = 5
+	 *
+	 * If the number formats grew to 128, and formats 98-102 are
+	 * supported with the modifier:
+	 *
+	 * 0x0000003c00000000 0000000000000000
+	 *		  ^
+	 *		  |__offset = 64, formats = 0x3c00000000
+	 *
+	 */
+	__u64 formats;
+	__u32 offset;
+	__u32 pad;
+
+	/* The modifier that applies to the >get_plane format list bitmask. */
+	__u64 modifier;
+};
+
 /**
  * Create a new 'blob' data property, copying length bytes from data pointer,
  * and returning new blob ID.
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 7ccbd6a2bbe0..6598fb76d2c2 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
 #define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
 #define DRM_I915_PERF_OPEN		0x36
+#define DRM_I915_PERF_ADD_CONFIG	0x37
+#define DRM_I915_PERF_REMOVE_CONFIG	0x38
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
@@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 {
 	__u64 rsvd2;
 };
 
+struct drm_i915_gem_exec_fence {
+	/**
+	 * User's handle for a drm_syncobj to wait on or signal.
+	 */
+	__u32 handle;
+
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+	__u32 flags;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 DR1;
 	__u32 DR4;
 	__u32 num_cliprects;
-	/** This is a struct drm_clip_rect *cliprects */
+	/**
+	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+	 * struct drm_i915_gem_exec_fence *fences.
+	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (7<<0)
 #define I915_EXEC_DEFAULT                (0<<0)
@@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 {
  * element).
  */
 #define I915_EXEC_BATCH_FIRST		(1<<18)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1))
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type {
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+	/** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+	char uuid[36];
+
+	__u32 n_mux_regs;
+	__u32 n_boolean_regs;
+	__u32 n_flex_regs;
+
+	__u64 __user mux_regs_ptr;
+	__u64 __user boolean_regs_ptr;
+	__u64 __user flex_regs_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/qxl_drm.h b/include/uapi/drm/qxl_drm.h
index 7eef42213051..880999d2d863 100644
--- a/include/uapi/drm/qxl_drm.h
+++ b/include/uapi/drm/qxl_drm.h
@@ -80,8 +80,8 @@ struct drm_qxl_reloc {
 };
 
 struct drm_qxl_command {
-	__u64	 __user command; /* void* */
-	__u64	 __user relocs; /* struct drm_qxl_reloc* */
+	__u64		command; /* void* */
+	__u64		relocs; /* struct drm_qxl_reloc* */
 	__u32		type;
 	__u32		command_size;
 	__u32		relocs_num;
@@ -91,7 +91,7 @@ struct drm_qxl_command {
 struct drm_qxl_execbuffer {
 	__u32		flags;		/* for future use */
 	__u32		commands_num;
-	__u64	 __user commands;	/* struct drm_qxl_command* */
+	__u64		commands;	/* struct drm_qxl_command* */
 };
 
 struct drm_qxl_update_area {
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
index 6ac4c5c014cb..afae87004963 100644
--- a/include/uapi/drm/vc4_drm.h
+++ b/include/uapi/drm/vc4_drm.h
@@ -40,6 +40,7 @@ extern "C" {
 #define DRM_VC4_GET_PARAM                         0x07
 #define DRM_VC4_SET_TILING                        0x08
 #define DRM_VC4_GET_TILING                        0x09
+#define DRM_VC4_LABEL_BO                          0x0a
 
 #define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
 #define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
@@ -51,6 +52,7 @@ extern "C" {
 #define DRM_IOCTL_VC4_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_PARAM, struct drm_vc4_get_param)
 #define DRM_IOCTL_VC4_SET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SET_TILING, struct drm_vc4_set_tiling)
 #define DRM_IOCTL_VC4_GET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_TILING, struct drm_vc4_get_tiling)
+#define DRM_IOCTL_VC4_LABEL_BO            DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_LABEL_BO, struct drm_vc4_label_bo)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -153,6 +155,16 @@ struct drm_vc4_submit_cl {
 	__u32 pad:24;
 
 #define VC4_SUBMIT_CL_USE_CLEAR_COLOR			(1 << 0)
+/* By default, the kernel gets to choose the order that the tiles are
+ * rendered in.  If this is set, then the tiles will be rendered in a
+ * raster order, with the right-to-left vs left-to-right and
+ * top-to-bottom vs bottom-to-top dictated by
+ * VC4_SUBMIT_CL_RCL_ORDER_INCREASING_*.  This allows overlapping
+ * blits to be implemented using the 3D engine.
+ */
+#define VC4_SUBMIT_CL_FIXED_RCL_ORDER			(1 << 1)
+#define VC4_SUBMIT_CL_RCL_ORDER_INCREASING_X		(1 << 2)
+#define VC4_SUBMIT_CL_RCL_ORDER_INCREASING_Y		(1 << 3)
 	__u32 flags;
 
 	/* Returned value of the seqno of this render job (for the
@@ -292,6 +304,7 @@ struct drm_vc4_get_hang_state {
 #define DRM_VC4_PARAM_SUPPORTS_BRANCHES		3
 #define DRM_VC4_PARAM_SUPPORTS_ETC1		4
 #define DRM_VC4_PARAM_SUPPORTS_THREADED_FS	5
+#define DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER	6
 
 struct drm_vc4_get_param {
 	__u32 param;
@@ -311,6 +324,15 @@ struct drm_vc4_set_tiling {
 	__u64 modifier;
 };
 
+/**
+ * struct drm_vc4_label_bo - Attach a name to a BO for debug purposes.
+ */
+struct drm_vc4_label_bo {
+	__u32 handle;
+	__u32 len;
+	__u64 name;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index d9dfde9aa757..0bc784f5e0db 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -297,13 +297,17 @@ union drm_vmw_surface_reference_arg {
  * @version: Allows expanding the execbuf ioctl parameters without breaking
  * backwards compatibility, since user-space will always tell the kernel
  * which version it uses.
- * @flags: Execbuf flags. None currently.
+ * @flags: Execbuf flags.
+ * @imported_fence_fd:  FD for a fence imported from another device
  *
  * Argument to the DRM_VMW_EXECBUF Ioctl.
  */
 
 #define DRM_VMW_EXECBUF_VERSION 2
 
+#define DRM_VMW_EXECBUF_FLAG_IMPORT_FENCE_FD (1 << 0)
+#define DRM_VMW_EXECBUF_FLAG_EXPORT_FENCE_FD (1 << 1)
+
 struct drm_vmw_execbuf_arg {
 	__u64 commands;
 	__u32 command_size;
@@ -312,7 +316,7 @@ struct drm_vmw_execbuf_arg {
 	__u32 version;
 	__u32 flags;
 	__u32 context_handle;
-	__u32 pad64;
+	__s32 imported_fence_fd;
 };
 
 /**
@@ -328,6 +332,7 @@ struct drm_vmw_execbuf_arg {
  * @passed_seqno: The highest seqno number processed by the hardware
  * so far. This can be used to mark user-space fence objects as signaled, and
  * to determine whether a fence seqno might be stale.
+ * @fd: FD associated with the fence, -1 if not exported
  * @error: This member should've been set to -EFAULT on submission.
  * The following actions should be take on completion:
  * error == -EFAULT: Fence communication failed. The host is synchronized.
@@ -345,7 +350,7 @@ struct drm_vmw_fence_rep {
 	__u32 mask;
 	__u32 seqno;
 	__u32 passed_seqno;
-	__u32 pad64;
+	__s32 fd;
 	__s32 error;
 };
 
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a2d4a8ac94ca..a04adbc70ddf 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -28,6 +28,7 @@
 #define __LINUX__AIO_ABI_H
 
 #include <linux/types.h>
+#include <linux/fs.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -62,14 +63,6 @@ struct io_event {
 	__s64		res2;		/* secondary result */
 };
 
-#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
-#define PADDED(x,y)	x, y
-#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
-#define PADDED(x,y)	y, x
-#else
-#error edit for your odd byteorder.
-#endif
-
 /*
  * we always use a 64bit off_t when communicating
  * with userland.  its up to libraries to do the
@@ -79,8 +72,16 @@ struct io_event {
 struct iocb {
 	/* these are internal to the kernel/libc. */
 	__u64	aio_data;	/* data to be returned in event's data */
-	__u32	PADDED(aio_key, aio_rw_flags);
-				/* the kernel sets aio_key to the req # */
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+	__u32	aio_key;	/* the kernel sets aio_key to the req # */
+	__kernel_rwf_t aio_rw_flags;	/* RWF_* flags */
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+	__kernel_rwf_t aio_rw_flags;	/* RWF_* flags */
+	__u32	aio_key;	/* the kernel sets aio_key to the req # */
+#else
+#error edit for your odd byteorder.
+#endif
 
 	/* common fields */
 	__u16	aio_lio_opcode;	/* see IOCB_CMD_ above */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index b7495d05e8de..56235dddea7d 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -358,13 +358,25 @@ struct fscrypt_key {
 #define SYNC_FILE_RANGE_WRITE		2
 #define SYNC_FILE_RANGE_WAIT_AFTER	4
 
-/* flags for preadv2/pwritev2: */
-#define RWF_HIPRI			0x00000001 /* high priority request, poll if possible */
-#define RWF_DSYNC			0x00000002 /* per-IO O_DSYNC */
-#define RWF_SYNC			0x00000004 /* per-IO O_SYNC */
-#define RWF_NOWAIT			0x00000008 /* per-IO, return -EAGAIN if operation would block */
-
-#define RWF_SUPPORTED			(RWF_HIPRI | RWF_DSYNC | RWF_SYNC |\
-					 RWF_NOWAIT)
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT)
 
 #endif /* _UAPI_LINUX_FS_H */
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index d6833426fdef..7b4567bacfc2 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -232,6 +232,35 @@ struct kfd_ioctl_wait_events_args {
 	uint32_t wait_result;		/* from KFD */
 };
 
+struct kfd_ioctl_set_scratch_backing_va_args {
+	uint64_t va_addr;	/* to KFD */
+	uint32_t gpu_id;	/* to KFD */
+	uint32_t pad;
+};
+
+struct kfd_ioctl_get_tile_config_args {
+	/* to KFD: pointer to tile array */
+	uint64_t tile_config_ptr;
+	/* to KFD: pointer to macro tile array */
+	uint64_t macro_tile_config_ptr;
+	/* to KFD: array size allocated by user mode
+	 * from KFD: array size filled by kernel
+	 */
+	uint32_t num_tile_configs;
+	/* to KFD: array size allocated by user mode
+	 * from KFD: array size filled by kernel
+	 */
+	uint32_t num_macro_tile_configs;
+
+	uint32_t gpu_id;		/* to KFD */
+	uint32_t gb_addr_config;	/* from KFD */
+	uint32_t num_banks;		/* from KFD */
+	uint32_t num_ranks;		/* from KFD */
+	/* struct size can be extended later if needed
+	 * without breaking ABI compatibility
+	 */
+};
+
 #define AMDKFD_IOCTL_BASE 'K'
 #define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
 #define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
@@ -286,7 +315,13 @@ struct kfd_ioctl_wait_events_args {
 #define AMDKFD_IOC_DBG_WAVE_CONTROL		\
 		AMDKFD_IOW(0x10, struct kfd_ioctl_dbg_wave_control_args)
 
+#define AMDKFD_IOC_SET_SCRATCH_BACKING_VA	\
+		AMDKFD_IOWR(0x11, struct kfd_ioctl_set_scratch_backing_va_args)
+
+#define AMDKFD_IOC_GET_TILE_CONFIG                                      \
+		AMDKFD_IOWR(0x12, struct kfd_ioctl_get_tile_config_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x11
+#define AMDKFD_COMMAND_END		0x13
 
 #endif
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index a3960f98679c..c8125ec1f4f2 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -22,7 +22,6 @@ enum {
 	LO_FLAGS_AUTOCLEAR	= 4,
 	LO_FLAGS_PARTSCAN	= 8,
 	LO_FLAGS_DIRECT_IO	= 16,
-	LO_FLAGS_BLOCKSIZE	= 32,
 };
 
 #include <asm/posix_types.h>	/* for __kernel_old_dev_t */
@@ -60,8 +59,6 @@ struct loop_info64 {
 	__u64		   lo_init[2];
 };
 
-#define LO_INFO_BLOCKSIZE(l) (l)->lo_init[0]
-
 /*
  * Loop filter types
  */
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index 6d3c54264d8e..3f03567631cb 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -145,43 +145,6 @@ struct nd_cmd_clear_error {
 	__u64 cleared;
 } __packed;
 
-struct nd_cmd_trans_spa {
-	__u64 spa;
-	__u32 status;
-	__u8  flags;
-	__u8  _reserved[3];
-	__u64 trans_length;
-	__u32 num_nvdimms;
-	struct nd_nvdimm_device {
-		__u32 nfit_device_handle;
-		__u32 _reserved;
-		__u64 dpa;
-	} __packed devices[0];
-
-} __packed;
-
-struct nd_cmd_ars_err_inj {
-	__u64 err_inj_spa_range_base;
-	__u64 err_inj_spa_range_length;
-	__u8  err_inj_options;
-	__u32 status;
-} __packed;
-
-struct nd_cmd_ars_err_inj_clr {
-	__u64 err_inj_clr_spa_range_base;
-	__u64 err_inj_clr_spa_range_length;
-	__u32 status;
-} __packed;
-
-struct nd_cmd_ars_err_inj_stat {
-	__u32 status;
-	__u32 inj_err_rec_count;
-	struct nd_error_stat_query_record {
-		__u64 err_inj_stat_spa_range_base;
-		__u64 err_inj_stat_spa_range_length;
-	} __packed record[0];
-} __packed;
-
 enum {
 	ND_CMD_IMPLEMENTED = 0,
 
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
new file mode 100644
index 000000000000..842792eae383
--- /dev/null
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -0,0 +1,84 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef IB_USER_IOCTL_VERBS_H
+#define IB_USER_IOCTL_VERBS_H
+
+#include <rdma/rdma_user_ioctl.h>
+
+#define UVERBS_UDATA_DRIVER_DATA_NS	1
+#define UVERBS_UDATA_DRIVER_DATA_FLAG	(1UL << UVERBS_ID_NS_SHIFT)
+
+enum uverbs_default_objects {
+	UVERBS_OBJECT_DEVICE, /* No instances of DEVICE are allowed */
+	UVERBS_OBJECT_PD,
+	UVERBS_OBJECT_COMP_CHANNEL,
+	UVERBS_OBJECT_CQ,
+	UVERBS_OBJECT_QP,
+	UVERBS_OBJECT_SRQ,
+	UVERBS_OBJECT_AH,
+	UVERBS_OBJECT_MR,
+	UVERBS_OBJECT_MW,
+	UVERBS_OBJECT_FLOW,
+	UVERBS_OBJECT_XRCD,
+	UVERBS_OBJECT_RWQ_IND_TBL,
+	UVERBS_OBJECT_WQ,
+	UVERBS_OBJECT_LAST,
+};
+
+enum {
+	UVERBS_UHW_IN = UVERBS_UDATA_DRIVER_DATA_FLAG,
+	UVERBS_UHW_OUT,
+};
+
+enum uverbs_create_cq_cmd_attr_ids {
+	CREATE_CQ_HANDLE,
+	CREATE_CQ_CQE,
+	CREATE_CQ_USER_HANDLE,
+	CREATE_CQ_COMP_CHANNEL,
+	CREATE_CQ_COMP_VECTOR,
+	CREATE_CQ_FLAGS,
+	CREATE_CQ_RESP_CQE,
+};
+
+enum uverbs_destroy_cq_cmd_attr_ids {
+	DESTROY_CQ_HANDLE,
+	DESTROY_CQ_RESP,
+};
+
+enum uverbs_actions_cq_ops {
+	UVERBS_CQ_CREATE,
+	UVERBS_CQ_DESTROY,
+};
+
+#endif
+
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 270c350bedc6..9a0b6479fe0c 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -236,6 +236,20 @@ struct ib_uverbs_rss_caps {
 	__u32 reserved;
 };
 
+struct ib_uverbs_tm_caps {
+	/* Max size of rendezvous request message */
+	__u32 max_rndv_hdr_size;
+	/* Max number of entries in tag matching list */
+	__u32 max_num_tags;
+	/* TM flags */
+	__u32 flags;
+	/* Max number of outstanding list operations */
+	__u32 max_ops;
+	/* Max number of SGE in tag matching entry */
+	__u32 max_sge;
+	__u32 reserved;
+};
+
 struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_query_device_resp base;
 	__u32 comp_mask;
@@ -247,6 +261,7 @@ struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_rss_caps rss_caps;
 	__u32  max_wq_type_rq;
 	__u32 raw_packet_caps;
+	struct ib_uverbs_tm_caps xrq_caps;
 };
 
 struct ib_uverbs_query_port {
@@ -578,7 +593,7 @@ struct ib_uverbs_ex_create_qp {
 	__u32 comp_mask;
 	__u32 create_flags;
 	__u32 rwq_ind_tbl_handle;
-	__u32  reserved1;
+	__u32  source_qpn;
 };
 
 struct ib_uverbs_open_qp {
@@ -1024,7 +1039,7 @@ struct ib_uverbs_create_xsrq {
 	__u32 max_wr;
 	__u32 max_sge;
 	__u32 srq_limit;
-	__u32 reserved;
+	__u32 max_num_tags;
 	__u32 xrcd_handle;
 	__u32 cq_handle;
 	__u64 driver_data[0];
diff --git a/include/uapi/rdma/mlx4-abi.h b/include/uapi/rdma/mlx4-abi.h
index af431752655c..c55f60e05f86 100644
--- a/include/uapi/rdma/mlx4-abi.h
+++ b/include/uapi/rdma/mlx4-abi.h
@@ -95,13 +95,63 @@ struct mlx4_ib_create_srq_resp {
 	__u32	reserved;
 };
 
+struct mlx4_ib_create_qp_rss {
+	__u64   rx_hash_fields_mask;
+	__u8    rx_hash_function;
+	__u8    reserved[7];
+	__u8    rx_hash_key[40];
+	__u32   comp_mask;
+	__u32   reserved1;
+};
+
 struct mlx4_ib_create_qp {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u8	log_sq_bb_count;
 	__u8	log_sq_stride;
 	__u8	sq_no_prefetch;
-	__u8	reserved[5];
+	__u8	reserved;
+	__u32	inl_recv_sz;
+};
+
+struct mlx4_ib_create_wq {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u8	log_range_size;
+	__u8	reserved[3];
+	__u32   comp_mask;
+};
+
+struct mlx4_ib_modify_wq {
+	__u32	comp_mask;
+	__u32	reserved;
+};
+
+struct mlx4_ib_create_rwq_ind_tbl_resp {
+	__u32	response_length;
+	__u32	reserved;
+};
+
+/* RX Hash function flags */
+enum mlx4_ib_rx_hash_function_flags {
+	MLX4_IB_RX_HASH_FUNC_TOEPLITZ	= 1 << 0,
+};
+
+/*
+ * RX Hash flags, these flags allows to set which incoming packet's field should
+ * participates in RX Hash. Each flag represent certain packet's field,
+ * when the flag is set the field that is represented by the flag will
+ * participate in RX Hash calculation.
+ */
+enum mlx4_ib_rx_hash_fields {
+	MLX4_IB_RX_HASH_SRC_IPV4	= 1 << 0,
+	MLX4_IB_RX_HASH_DST_IPV4	= 1 << 1,
+	MLX4_IB_RX_HASH_SRC_IPV6	= 1 << 2,
+	MLX4_IB_RX_HASH_DST_IPV6	= 1 << 3,
+	MLX4_IB_RX_HASH_SRC_PORT_TCP	= 1 << 4,
+	MLX4_IB_RX_HASH_DST_PORT_TCP	= 1 << 5,
+	MLX4_IB_RX_HASH_SRC_PORT_UDP	= 1 << 6,
+	MLX4_IB_RX_HASH_DST_PORT_UDP	= 1 << 7
 };
 
 #endif /* MLX4_ABI_USER_H */
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 0b3d30837a9f..1791bf123ba9 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -168,6 +168,28 @@ struct mlx5_packet_pacing_caps {
 	__u32 reserved;
 };
 
+enum mlx5_ib_mpw_caps {
+	MPW_RESERVED		= 1 << 0,
+	MLX5_IB_ALLOW_MPW	= 1 << 1,
+	MLX5_IB_SUPPORT_EMPW	= 1 << 2,
+};
+
+enum mlx5_ib_sw_parsing_offloads {
+	MLX5_IB_SW_PARSING = 1 << 0,
+	MLX5_IB_SW_PARSING_CSUM = 1 << 1,
+	MLX5_IB_SW_PARSING_LSO = 1 << 2,
+};
+
+struct mlx5_ib_sw_parsing_caps {
+	__u32 sw_parsing_offloads; /* enum mlx5_ib_sw_parsing_offloads */
+
+	/* Corresponding bit will be set if qp type from
+	 * 'enum ib_qp_type' is supported, e.g.
+	 * supported_qpts |= 1 << IB_QPT_RAW_PACKET
+	 */
+	__u32 supported_qpts;
+};
+
 struct mlx5_ib_query_device_resp {
 	__u32	comp_mask;
 	__u32	response_length;
@@ -177,6 +199,7 @@ struct mlx5_ib_query_device_resp {
 	struct	mlx5_packet_pacing_caps packet_pacing_caps;
 	__u32	mlx5_ib_support_multi_pkt_send_wqes;
 	__u32	reserved;
+	struct mlx5_ib_sw_parsing_caps sw_parsing_caps;
 };
 
 struct mlx5_ib_create_cq {
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index 75c270d839c8..54b64357ab24 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -49,6 +49,9 @@ struct qedr_alloc_ucontext_resp {
 	__u32 sges_per_recv_wr;
 	__u32 sges_per_srq_wr;
 	__u32 max_cqes;
+	__u8 dpm_enabled;
+	__u8 wids_enabled;
+	__u16 wid_count;
 };
 
 struct qedr_alloc_pd_ureq {
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 02fe8390c18f..861440a87e7c 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -8,7 +8,7 @@ enum {
 	RDMA_NL_IWCM,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
-	RDMA_NL_I40IW,
+	RDMA_NL_NLDEV,	/* RDMA device interface */
 	RDMA_NL_NUM_CLIENTS
 };
 
@@ -222,4 +222,86 @@ struct rdma_nla_ls_gid {
 	__u8		gid[16];
 };
 
+enum rdma_nldev_command {
+	RDMA_NLDEV_CMD_UNSPEC,
+
+	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
+	RDMA_NLDEV_CMD_NEW,
+	RDMA_NLDEV_CMD_DEL,
+
+	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
+	RDMA_NLDEV_CMD_PORT_SET,
+	RDMA_NLDEV_CMD_PORT_NEW,
+	RDMA_NLDEV_CMD_PORT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
+};
+
+enum rdma_nldev_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	RDMA_NLDEV_ATTR_UNSPEC,
+
+	/* Identifier for ib_device */
+	RDMA_NLDEV_ATTR_DEV_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_DEV_NAME,		/* string */
+	/*
+	 * Device index together with port index are identifiers
+	 * for port/link properties.
+	 *
+	 * For RDMA_NLDEV_CMD_GET commamnd, port index will return number
+	 * of available ports in ib_device, while for port specific operations,
+	 * it will be real port index as it appears in sysfs. Port index follows
+	 * sysfs notation and starts from 1 for the first port.
+	 */
+	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
+
+	/*
+	 * Device and port capabilities
+	 */
+	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
+
+	/*
+	 * FW version
+	 */
+	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
+
+	/*
+	 * Node GUID (in host byte order) associated with the RDMA device.
+	 */
+	RDMA_NLDEV_ATTR_NODE_GUID,			/* u64 */
+
+	/*
+	 * System image GUID (in host byte order) associated with
+	 * this RDMA device and other devices which are part of a
+	 * single system.
+	 */
+	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
+
+	/*
+	 * Subnet prefix (in host byte order)
+	 */
+	RDMA_NLDEV_ATTR_SUBNET_PREFIX,		/* u64 */
+
+	/*
+	 * Local Identifier (LID),
+	 * According to IB specification, It is 16-bit address assigned
+	 * by the Subnet Manager. Extended to be 32-bit for OmniPath users.
+	 */
+	RDMA_NLDEV_ATTR_LID,			/* u32 */
+	RDMA_NLDEV_ATTR_SM_LID,			/* u32 */
+
+	/*
+	 * LID mask control (LMC)
+	 */
+	RDMA_NLDEV_ATTR_LMC,			/* u8 */
+
+	RDMA_NLDEV_ATTR_PORT_STATE,		/* u8 */
+	RDMA_NLDEV_ATTR_PORT_PHYS_STATE,	/* u8 */
+
+	RDMA_NLDEV_ATTR_DEV_NODE_TYPE,		/* u8 */
+
+	RDMA_NLDEV_ATTR_MAX
+};
 #endif /* _UAPI_RDMA_NETLINK_H */
diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h
index 9388125ad51b..165a27e969d5 100644
--- a/include/uapi/rdma/rdma_user_ioctl.h
+++ b/include/uapi/rdma/rdma_user_ioctl.h
@@ -43,6 +43,39 @@
 /* Legacy name, for user space application which already use it */
 #define IB_IOCTL_MAGIC		RDMA_IOCTL_MAGIC
 
+#define RDMA_VERBS_IOCTL \
+	_IOWR(RDMA_IOCTL_MAGIC, 1, struct ib_uverbs_ioctl_hdr)
+
+#define UVERBS_ID_NS_MASK 0xF000
+#define UVERBS_ID_NS_SHIFT 12
+
+enum {
+	/* User input */
+	UVERBS_ATTR_F_MANDATORY = 1U << 0,
+	/*
+	 * Valid output bit should be ignored and considered set in
+	 * mandatory fields. This bit is kernel output.
+	 */
+	UVERBS_ATTR_F_VALID_OUTPUT = 1U << 1,
+};
+
+struct ib_uverbs_attr {
+	__u16 attr_id;		/* command specific type attribute */
+	__u16 len;		/* only for pointers */
+	__u16 flags;		/* combination of UVERBS_ATTR_F_XXXX */
+	__u16 reserved;
+	__u64 data;		/* ptr to command, inline data or idr/fd */
+};
+
+struct ib_uverbs_ioctl_hdr {
+	__u16 length;
+	__u16 object_id;
+	__u16 method_id;
+	__u16 num_attrs;
+	__u64 reserved;
+	struct ib_uverbs_attr  attrs[0];
+};
+
 /*
  * General blocks assignments
  * It is closed on purpose do not expose it it user space
diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h
index c8c1d2d6df4d..c6569b0032ec 100644
--- a/include/uapi/rdma/vmw_pvrdma-abi.h
+++ b/include/uapi/rdma/vmw_pvrdma-abi.h
@@ -125,7 +125,8 @@ enum pvrdma_wc_flags {
 	PVRDMA_WC_IP_CSUM_OK		= 1 << 3,
 	PVRDMA_WC_WITH_SMAC		= 1 << 4,
 	PVRDMA_WC_WITH_VLAN		= 1 << 5,
-	PVRDMA_WC_FLAGS_MAX		= PVRDMA_WC_WITH_VLAN,
+	PVRDMA_WC_WITH_NETWORK_HDR_TYPE	= 1 << 6,
+	PVRDMA_WC_FLAGS_MAX		= PVRDMA_WC_WITH_NETWORK_HDR_TYPE,
 };
 
 struct pvrdma_alloc_ucontext_resp {
@@ -283,7 +284,8 @@ struct pvrdma_cqe {
 	__u8 dlid_path_bits;
 	__u8 port_num;
 	__u8 smac[6];
-	__u8 reserved2[7]; /* Pad to next power of 2 (64). */
+	__u8 network_hdr_type;
+	__u8 reserved2[6]; /* Pad to next power of 2 (64). */
 };
 
 #endif /* __VMW_PVRDMA_ABI_H__ */