Merge drm/drm-next into drm-xe-next

Bring v6.17-rc1 to propagate commits from other subsystems, particularly
PCI, which has some new functions needed for SR-IOV integration.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

3 files changed, 155 insertions, 16 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 45c4fa13499c..bdedbaccf776 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -1493,6 +1493,8 @@ struct drm_amdgpu_info_hw_ip {
 	__u32  available_rings;
 	/** version info: bits 23:16 major, 15:8 minor, 7:0 revision */
 	__u32  ip_discovery_version;
+	/* Userq available slots */
+	__u32  userq_num_slots;
 };
 
 /* GFX metadata BO sizes and alignment info (in bytes) */
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 6483f76a2165..ea91aa8afde9 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -210,6 +210,10 @@ extern "C" {
 #define DRM_FORMAT_RGBA1010102	fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */
 #define DRM_FORMAT_BGRA1010102	fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */
 
+/* 48 bpp RGB */
+#define DRM_FORMAT_RGB161616 fourcc_code('R', 'G', '4', '8') /* [47:0] R:G:B 16:16:16 little endian */
+#define DRM_FORMAT_BGR161616 fourcc_code('B', 'G', '4', '8') /* [47:0] B:G:R 16:16:16 little endian */
+
 /* 64 bpp RGB */
 #define DRM_FORMAT_XRGB16161616	fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */
 #define DRM_FORMAT_XBGR16161616	fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */
@@ -218,7 +222,7 @@ extern "C" {
 #define DRM_FORMAT_ABGR16161616	fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */
 
 /*
- * Floating point 64bpp RGB
+ * Half-Floating point - 16b/component
  * IEEE 754-2008 binary16 half-precision float
  * [15:0] sign:exponent:mantissa 1:5:10
  */
@@ -228,6 +232,20 @@ extern "C" {
 #define DRM_FORMAT_ARGB16161616F fourcc_code('A', 'R', '4', 'H') /* [63:0] A:R:G:B 16:16:16:16 little endian */
 #define DRM_FORMAT_ABGR16161616F fourcc_code('A', 'B', '4', 'H') /* [63:0] A:B:G:R 16:16:16:16 little endian */
 
+#define DRM_FORMAT_R16F          fourcc_code('R', ' ', ' ', 'H') /* [15:0] R 16 little endian */
+#define DRM_FORMAT_GR1616F       fourcc_code('G', 'R', ' ', 'H') /* [31:0] G:R 16:16 little endian */
+#define DRM_FORMAT_BGR161616F    fourcc_code('B', 'G', 'R', 'H') /* [47:0] B:G:R 16:16:16 little endian */
+
+/*
+ * Floating point - 32b/component
+ * IEEE 754-2008 binary32 float
+ * [31:0] sign:exponent:mantissa 1:8:23
+ */
+#define DRM_FORMAT_R32F          fourcc_code('R', ' ', ' ', 'F') /* [31:0] R 32 little endian */
+#define DRM_FORMAT_GR3232F       fourcc_code('G', 'R', ' ', 'F') /* [63:0] R:G 32:32 little endian */
+#define DRM_FORMAT_BGR323232F    fourcc_code('B', 'G', 'R', 'F') /* [95:0] R:G:B 32:32:32 little endian */
+#define DRM_FORMAT_ABGR32323232F fourcc_code('A', 'B', '8', 'F') /* [127:0] R:G:B:A 32:32:32:32 little endian */
+
 /*
  * RGBA format with 10-bit components packed in 64-bit per pixel, with 6 bits
  * of unused padding per component:
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 2342cb90857e..5c67294edc95 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -91,6 +91,32 @@ struct drm_msm_timespec {
 #define MSM_PARAM_UBWC_SWIZZLE 0x12 /* RO */
 #define MSM_PARAM_MACROTILE_MODE 0x13 /* RO */
 #define MSM_PARAM_UCHE_TRAP_BASE 0x14 /* RO */
+/* PRR (Partially Resident Region) is required for sparse residency: */
+#define MSM_PARAM_HAS_PRR    0x15  /* RO */
+/* MSM_PARAM_EN_VM_BIND is set to 1 to enable VM_BIND ops.
+ *
+ * With VM_BIND enabled, userspace is required to allocate iova and use the
+ * VM_BIND ops for map/unmap ioctls.  MSM_INFO_SET_IOVA and MSM_INFO_GET_IOVA
+ * will be rejected.  (The latter does not have a sensible meaning when a BO
+ * can have multiple and/or partial mappings.)
+ *
+ * With VM_BIND enabled, userspace does not include a submit_bo table in the
+ * SUBMIT ioctl (this will be rejected), the resident set is determined by
+ * the the VM_BIND ops.
+ *
+ * Enabling VM_BIND will fail on devices which do not have per-process pgtables.
+ * And it is not allowed to disable VM_BIND once it has been enabled.
+ *
+ * Enabling VM_BIND should be done (attempted) prior to allocating any BOs or
+ * submitqueues of type MSM_SUBMITQUEUE_VM_BIND.
+ *
+ * Relatedly, when VM_BIND mode is enabled, the kernel will not try to recover
+ * from GPU faults or failed async VM_BIND ops, in particular because it is
+ * difficult to communicate to userspace which op failed so that userspace
+ * could rewind and try again.  When the VM is marked unusable, the SUBMIT
+ * ioctl will throw -EPIPE.
+ */
+#define MSM_PARAM_EN_VM_BIND 0x16  /* WO, once */
 
 /* For backwards compat.  The original support for preemption was based on
  * a single ring per priority level so # of priority levels equals the #
@@ -114,6 +140,19 @@ struct drm_msm_param {
 
 #define MSM_BO_SCANOUT       0x00000001     /* scanout capable */
 #define MSM_BO_GPU_READONLY  0x00000002
+/* Private buffers do not need to be explicitly listed in the SUBMIT
+ * ioctl, unless referenced by a drm_msm_gem_submit_cmd.  Private
+ * buffers may NOT be imported/exported or used for scanout (or any
+ * other situation where buffers can be indefinitely pinned, but
+ * cases other than scanout are all kernel owned BOs which are not
+ * visible to userspace).
+ *
+ * In exchange for those constraints, all private BOs associated with
+ * a single context (drm_file) share a single dma_resv, and if there
+ * has been no eviction since the last submit, there are no per-BO
+ * bookeeping to do, significantly cutting the SUBMIT overhead.
+ */
+#define MSM_BO_NO_SHARE      0x00000004
 #define MSM_BO_CACHE_MASK    0x000f0000
 /* cache modes */
 #define MSM_BO_CACHED        0x00010000
@@ -123,6 +162,7 @@ struct drm_msm_param {
 
 #define MSM_BO_FLAGS         (MSM_BO_SCANOUT | \
                               MSM_BO_GPU_READONLY | \
+                              MSM_BO_NO_SHARE | \
                               MSM_BO_CACHE_MASK)
 
 struct drm_msm_gem_new {
@@ -180,6 +220,17 @@ struct drm_msm_gem_cpu_fini {
  * Cmdstream Submission:
  */
 
+#define MSM_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
+#define MSM_SYNCOBJ_FLAGS ( \
+		MSM_SYNCOBJ_RESET | \
+		0)
+
+struct drm_msm_syncobj {
+	__u32 handle;     /* in, syncobj handle. */
+	__u32 flags;      /* in, from MSM_SUBMIT_SYNCOBJ_FLAGS */
+	__u64 point;      /* in, timepoint for timeline syncobjs. */
+};
+
 /* The value written into the cmdstream is logically:
  *
  *   ((relocbuf->gpuaddr + reloc_offset) << shift) | or
@@ -221,7 +272,10 @@ struct drm_msm_gem_submit_cmd {
 	__u32 size;           /* in, cmdstream size */
 	__u32 pad;
 	__u32 nr_relocs;      /* in, number of submit_reloc's */
-	__u64 relocs;         /* in, ptr to array of submit_reloc's */
+	union {
+		__u64 relocs; /* in, ptr to array of submit_reloc's */
+		__u64 iova;   /* cmdstream address (for VM_BIND contexts) */
+	};
 };
 
 /* Each buffer referenced elsewhere in the cmdstream submit (ie. the
@@ -269,17 +323,6 @@ struct drm_msm_gem_submit_bo {
 		MSM_SUBMIT_FENCE_SN_IN   | \
 		0)
 
-#define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
-#define MSM_SUBMIT_SYNCOBJ_FLAGS        ( \
-		MSM_SUBMIT_SYNCOBJ_RESET | \
-		0)
-
-struct drm_msm_gem_submit_syncobj {
-	__u32 handle;     /* in, syncobj handle. */
-	__u32 flags;      /* in, from MSM_SUBMIT_SYNCOBJ_FLAGS */
-	__u64 point;      /* in, timepoint for timeline syncobjs. */
-};
-
 /* Each cmdstream submit consists of a table of buffers involved, and
  * one or more cmdstream buffers.  This allows for conditional execution
  * (context-restore), and IB buffers needed for per tile/bin draw cmds.
@@ -293,13 +336,80 @@ struct drm_msm_gem_submit {
 	__u64 cmds;           /* in, ptr to array of submit_cmd's */
 	__s32 fence_fd;       /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */
 	__u32 queueid;        /* in, submitqueue id */
-	__u64 in_syncobjs;    /* in, ptr to array of drm_msm_gem_submit_syncobj */
-	__u64 out_syncobjs;   /* in, ptr to array of drm_msm_gem_submit_syncobj */
+	__u64 in_syncobjs;    /* in, ptr to array of drm_msm_syncobj */
+	__u64 out_syncobjs;   /* in, ptr to array of drm_msm_syncobj */
 	__u32 nr_in_syncobjs; /* in, number of entries in in_syncobj */
 	__u32 nr_out_syncobjs; /* in, number of entries in out_syncobj. */
 	__u32 syncobj_stride; /* in, stride of syncobj arrays. */
 	__u32 pad;            /*in, reserved for future use, always 0. */
+};
 
+#define MSM_VM_BIND_OP_UNMAP	0
+#define MSM_VM_BIND_OP_MAP	1
+#define MSM_VM_BIND_OP_MAP_NULL	2
+
+#define MSM_VM_BIND_OP_DUMP	1
+#define MSM_VM_BIND_OP_FLAGS ( \
+		MSM_VM_BIND_OP_DUMP | \
+		0)
+
+/**
+ * struct drm_msm_vm_bind_op - bind/unbind op to run
+ */
+struct drm_msm_vm_bind_op {
+	/** @op: one of MSM_VM_BIND_OP_x */
+	__u32 op;
+	/** @handle: GEM object handle, MBZ for UNMAP or MAP_NULL */
+	__u32 handle;
+	/** @obj_offset: Offset into GEM object, MBZ for UNMAP or MAP_NULL */
+	__u64 obj_offset;
+	/** @iova: Address to operate on */
+	__u64 iova;
+	/** @range: Number of bites to to map/unmap */
+	__u64 range;
+	/** @flags: Bitmask of MSM_VM_BIND_OP_FLAG_x */
+	__u32 flags;
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+#define MSM_VM_BIND_FENCE_FD_IN		0x00000001
+#define MSM_VM_BIND_FENCE_FD_OUT	0x00000002
+#define MSM_VM_BIND_FLAGS ( \
+		MSM_VM_BIND_FENCE_FD_IN | \
+		MSM_VM_BIND_FENCE_FD_OUT | \
+		0)
+
+/**
+ * struct drm_msm_vm_bind - Input of &DRM_IOCTL_MSM_VM_BIND
+ */
+struct drm_msm_vm_bind {
+	/** @flags: in, bitmask of MSM_VM_BIND_x */
+	__u32 flags;
+	/** @nr_ops: the number of bind ops in this ioctl */
+	__u32 nr_ops;
+	/** @fence_fd: in/out fence fd (see MSM_VM_BIND_FENCE_FD_IN/OUT) */
+	__s32 fence_fd;
+	/** @queue_id: in, submitqueue id */
+	__u32 queue_id;
+	/** @in_syncobjs: in, ptr to array of drm_msm_gem_syncobj */
+	__u64 in_syncobjs;
+	/** @out_syncobjs: in, ptr to array of drm_msm_gem_syncobj */
+	__u64 out_syncobjs;
+	/** @nr_in_syncobjs: in, number of entries in in_syncobj */
+	__u32 nr_in_syncobjs;
+	/** @nr_out_syncobjs: in, number of entries in out_syncobj */
+	__u32 nr_out_syncobjs;
+	/** @syncobj_stride: in, stride of syncobj arrays */
+	__u32 syncobj_stride;
+	/** @op_stride: sizeof each struct drm_msm_vm_bind_op in @ops */
+	__u32 op_stride;
+	union {
+		/** @op: used if num_ops == 1 */
+		struct drm_msm_vm_bind_op op;
+		/** @ops: userptr to array of drm_msm_vm_bind_op if num_ops > 1 */
+		__u64 ops;
+	};
 };
 
 #define MSM_WAIT_FENCE_BOOST	0x00000001
@@ -345,12 +455,19 @@ struct drm_msm_gem_madvise {
 /*
  * Draw queues allow the user to set specific submission parameter. Command
  * submissions specify a specific submitqueue to use.  ID 0 is reserved for
- * backwards compatibility as a "default" submitqueue
+ * backwards compatibility as a "default" submitqueue.
+ *
+ * Because VM_BIND async updates happen on the CPU, they must run on a
+ * virtual queue created with the flag MSM_SUBMITQUEUE_VM_BIND.  If we had
+ * a way to do pgtable updates on the GPU, we could drop this restriction.
  */
 
 #define MSM_SUBMITQUEUE_ALLOW_PREEMPT	0x00000001
+#define MSM_SUBMITQUEUE_VM_BIND	0x00000002  /* virtual queue for VM_BIND ops */
+
 #define MSM_SUBMITQUEUE_FLAGS		    ( \
 		MSM_SUBMITQUEUE_ALLOW_PREEMPT | \
+		MSM_SUBMITQUEUE_VM_BIND | \
 		0)
 
 /*
@@ -388,6 +505,7 @@ struct drm_msm_submitqueue_query {
 #define DRM_MSM_SUBMITQUEUE_NEW        0x0A
 #define DRM_MSM_SUBMITQUEUE_CLOSE      0x0B
 #define DRM_MSM_SUBMITQUEUE_QUERY      0x0C
+#define DRM_MSM_VM_BIND                0x0D
 
 #define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
 #define DRM_IOCTL_MSM_SET_PARAM        DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SET_PARAM, struct drm_msm_param)
@@ -401,6 +519,7 @@ struct drm_msm_submitqueue_query {
 #define DRM_IOCTL_MSM_SUBMITQUEUE_NEW    DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_NEW, struct drm_msm_submitqueue)
 #define DRM_IOCTL_MSM_SUBMITQUEUE_CLOSE  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_CLOSE, __u32)
 #define DRM_IOCTL_MSM_SUBMITQUEUE_QUERY  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_QUERY, struct drm_msm_submitqueue_query)
+#define DRM_IOCTL_MSM_VM_BIND          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_VM_BIND, struct drm_msm_vm_bind)
 
 #if defined(__cplusplus)
 }