diff mbox series

[RFC,16/24] drm/msm: Extend SUBMIT ioctl for VM_BIND

Message ID 20241207161651.410556-17-robdclark@gmail.com (mailing list archive)
State Not Applicable
Headers show
Series drm/msm: sparse / "VM_BIND" support | expand

Commit Message

Rob Clark Dec. 7, 2024, 4:15 p.m. UTC
From: Rob Clark <robdclark@chromium.org>

This is a bit different than the path taken by other clean-slate
drivers.  But there is a lot in similar with BO pinning in the legacy
"EXEC" path and "VM_BIND" MAP path.  Also, we want the same fence and
syncobj handling.

(Why bother with fence fd's?  Because for virtgpu nctx for, guest
syncobj's exist only as dma_fence's between the guest kernel and host.)

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_gem.h        | 10 ++---
 drivers/gpu/drm/msm/msm_gem_submit.c | 65 ++++++++++++++++++++++++----
 include/uapi/drm/msm_drm.h           | 49 ++++++++++++++++++---
 3 files changed, 103 insertions(+), 21 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 7cb720137548..8e29e36ca9c5 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -345,13 +345,13 @@  struct msm_gem_submit {
 		uint32_t nr_relocs;
 		struct drm_msm_gem_submit_reloc *relocs;
 	} *cmd;  /* array of size nr_cmds */
-	struct {
+	struct msm_gem_submit_bo {
 		uint32_t flags;
-		union {
-			struct drm_gem_object *obj;
-			uint32_t handle;
-		};
+		uint32_t handle;
+		struct drm_gem_object *obj;
 		uint64_t iova;
+		uint64_t bo_offset;
+		uint64_t range;
 	} bos[];
 };
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 79bbe552f23e..9ac74f9a139e 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -115,23 +115,37 @@  void __msm_gem_submit_destroy(struct kref *kref)
 	kfree(submit);
 }
 
+static bool invalid_alignment(uint64_t addr)
+{
+	/*
+	 * Technically this is about GPU alignment, not CPU alignment.  But
+	 * I've not seen any qcom SoC where the SMMU does not support the
+	 * CPU's smallest page size.
+	 */
+	return !PAGE_ALIGNED(addr);
+}
+
 static int submit_lookup_objects(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
-	unsigned i;
+	unsigned i, bo_stride = args->bos_stride;
 	int ret = 0;
 
+	if (!bo_stride)
+		bo_stride = sizeof(struct drm_msm_gem_submit_bo);
+
 	for (i = 0; i < args->nr_bos; i++) {
-		struct drm_msm_gem_submit_bo submit_bo;
+		struct drm_msm_gem_submit_bo_v2 submit_bo = {0};
 		void __user *userptr =
-			u64_to_user_ptr(args->bos + (i * sizeof(submit_bo)));
+			u64_to_user_ptr(args->bos + (i * bo_stride));
+		unsigned copy_sz = min(bo_stride, sizeof(submit_bo));
 
 		/* make sure we don't have garbage flags, in case we hit
 		 * error path before flags is initialized:
 		 */
 		submit->bos[i].flags = 0;
 
-		if (copy_from_user(&submit_bo, userptr, sizeof(submit_bo))) {
+		if (copy_from_user(&submit_bo, userptr, copy_sz)) {
 			ret = -EFAULT;
 			i = 0;
 			goto out;
@@ -141,14 +155,27 @@  static int submit_lookup_objects(struct msm_gem_submit *submit,
 #define MANDATORY_FLAGS (MSM_SUBMIT_BO_READ | MSM_SUBMIT_BO_WRITE)
 
 		if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) ||
-			!(submit_bo.flags & MANDATORY_FLAGS)) {
+		    !(submit_bo.flags & MANDATORY_FLAGS))
 			ret = SUBMIT_ERROR(EINVAL, submit, "invalid flags: %x\n", submit_bo.flags);
+
+		if (invalid_alignment(submit_bo.address))
+			ret = SUBMIT_ERROR(EINVAL, submit, "invalid address: %016llx\n", submit_bo.address);
+
+		if (invalid_alignment(submit_bo.bo_offset))
+			ret = SUBMIT_ERROR(EINVAL, submit, "invalid bo_offset: %016llx\n", submit_bo.bo_offset);
+
+		if (invalid_alignment(submit_bo.range))
+			ret = SUBMIT_ERROR(EINVAL, submit, "invalid range: %016llx\n", submit_bo.range);
+
+		if (ret) {
 			i = 0;
 			goto out;
 		}
 
 		submit->bos[i].handle = submit_bo.handle;
 		submit->bos[i].flags = submit_bo.flags;
+		submit->bos[i].bo_offset = submit_bo.bo_offset;
+		submit->bos[i].range = submit_bo.range;
 	}
 
 	spin_lock(&file->table_lock);
@@ -167,6 +194,15 @@  static int submit_lookup_objects(struct msm_gem_submit *submit,
 
 		drm_gem_object_get(obj);
 
+		if (submit->bos[i].bo_offset > obj->size)
+			ret = SUBMIT_ERROR(EINVAL, submit, "bo_offset to large: %016llx\n", submit->bos[i].bo_offset);
+
+		if ((submit->bos[i].bo_offset + submit->bos[i].range) > obj->size)
+			ret = SUBMIT_ERROR(EINVAL, submit, "range to large: %016llx\n", submit->bos[i].range);
+
+		if (ret)
+			goto out_unlock;
+
 		submit->bos[i].obj = obj;
 	}
 
@@ -182,6 +218,7 @@  static int submit_lookup_objects(struct msm_gem_submit *submit,
 static int submit_lookup_cmds(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
+	struct msm_context *ctx = file->driver_priv;
 	unsigned i;
 	size_t sz;
 	int ret = 0;
@@ -213,6 +250,19 @@  static int submit_lookup_cmds(struct msm_gem_submit *submit,
 			goto out;
 		}
 
+		if (msm_context_is_vmbind(ctx)) {
+			if (submit_cmd.nr_relocs) {
+				ret = SUBMIT_ERROR(EINVAL, submit, "nr_relocs must be zero");
+				goto out;
+			}
+			if (submit_cmd.submit_idx || submit_cmd.submit_offset) {
+				ret = SUBMIT_ERROR(EINVAL, submit, "submit_idx/offset must be zero");
+				goto out;
+			}
+
+			submit->cmd[i].iova = submit_cmd.iova;
+		}
+
 		submit->cmd[i].type = submit_cmd.type;
 		submit->cmd[i].size = submit_cmd.size / 4;
 		submit->cmd[i].offset = submit_cmd.submit_offset / 4;
@@ -665,9 +715,6 @@  int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (!gpu)
 		return -ENXIO;
 
-	if (args->pad)
-		return -EINVAL;
-
 	if (to_msm_vm(ctx->vm)->unusable)
 		return UERR(EPIPE, dev, "context is unusable");
 
@@ -677,7 +724,7 @@  int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (MSM_PIPE_ID(args->flags) != MSM_PIPE_3D0)
 		return UERR(EINVAL, dev, "invalid pipe");
 
-	if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_FLAGS)
+	if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_EXEC_FLAGS)
 		return UERR(EINVAL, dev, "invalid flags");
 
 	if (args->flags & MSM_SUBMIT_SUDO) {
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 072e82a80607..1a948d49c610 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -245,7 +245,10 @@  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
@@ -264,6 +267,19 @@  struct drm_msm_gem_submit_cmd {
 #define MSM_SUBMIT_BO_DUMP             0x0004
 #define MSM_SUBMIT_BO_NO_IMPLICIT      0x0008
 
+/* Map OP for for submits to a VM_BIND submitqueue:
+ *  - MAP:      map a specified range of the BO into the VM
+ *  - MAP_NULL: map a NULL page into the specified range of the VM, handle
+ *              and bo_offset MBZ.  A NULL range will return zero on reads
+ *              and discard writes
+ *              see: VkPhysicalDeviceSparseProperties::residencyNonResidentStrict
+ *  - UNMAP:    unmap a specified VM range, handle and bo_offset MBZ
+ */
+#define MSM_SUBMIT_BO_OP_MASK          0xf000
+#define MSM_SUBMIT_BO_OP_MAP           0x0000
+#define MSM_SUBMIT_BO_OP_MAP_NULL      0x1000
+#define MSM_SUBMIT_BO_OP_UNMAP         0x2000
+
 #define MSM_SUBMIT_BO_FLAGS            (MSM_SUBMIT_BO_READ | \
 					MSM_SUBMIT_BO_WRITE | \
 					MSM_SUBMIT_BO_DUMP | \
@@ -272,7 +288,16 @@  struct drm_msm_gem_submit_cmd {
 struct drm_msm_gem_submit_bo {
 	__u32 flags;          /* in, mask of MSM_SUBMIT_BO_x */
 	__u32 handle;         /* in, GEM handle */
-	__u64 presumed;       /* in/out, presumed buffer address */
+	__u64 address;        /* in/out, presumed buffer address */
+};
+
+struct drm_msm_gem_submit_bo_v2 {
+	__u32 flags;          /* in, mask of MSM_SUBMIT_BO_x */
+	__u32 handle;         /* in, GEM handle */
+	__u64 address;        /* in/out, presumed buffer address */
+	/* Remaining fields are only used with MSM_SUBMIT_OP_VM_BIND/_ASYNC: */
+	__u64 bo_offset;
+	__u64 range;
 };
 
 /* Valid submit ioctl flags: */
@@ -283,7 +308,8 @@  struct drm_msm_gem_submit_bo {
 #define MSM_SUBMIT_SYNCOBJ_IN    0x08000000 /* enable input syncobj */
 #define MSM_SUBMIT_SYNCOBJ_OUT   0x04000000 /* enable output syncobj */
 #define MSM_SUBMIT_FENCE_SN_IN   0x02000000 /* userspace passes in seqno fence */
-#define MSM_SUBMIT_FLAGS                ( \
+
+#define MSM_SUBMIT_EXEC_FLAGS            ( \
 		MSM_SUBMIT_NO_IMPLICIT   | \
 		MSM_SUBMIT_FENCE_FD_IN   | \
 		MSM_SUBMIT_FENCE_FD_OUT  | \
@@ -293,6 +319,13 @@  struct drm_msm_gem_submit_bo {
 		MSM_SUBMIT_FENCE_SN_IN   | \
 		0)
 
+#define MSM_SUBMIT_VM_BIND_FLAGS         ( \
+		MSM_SUBMIT_FENCE_FD_IN   | \
+		MSM_SUBMIT_FENCE_FD_OUT  | \
+		MSM_SUBMIT_SYNCOBJ_IN    | \
+		MSM_SUBMIT_SYNCOBJ_OUT   | \
+		0)
+
 #define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
 #define MSM_SUBMIT_SYNCOBJ_FLAGS        ( \
 		MSM_SUBMIT_SYNCOBJ_RESET | \
@@ -307,14 +340,17 @@  struct drm_msm_gem_submit_syncobj {
 /* 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.
+ *
+ * For MSM_SUBMIT_VM_BIND/_ASYNC operations, the queue must have been
+ * created with the MSM_SUBMITQUEUE_VM_BIND flag.
  */
 struct drm_msm_gem_submit {
 	__u32 flags;          /* MSM_PIPE_x | MSM_SUBMIT_x */
 	__u32 fence;          /* out (or in with MSM_SUBMIT_FENCE_SN_IN flag) */
 	__u32 nr_bos;         /* in, number of submit_bo's */
-	__u32 nr_cmds;        /* in, number of submit_cmd's */
+	__u32 nr_cmds;        /* in, number of submit_cmd's, MBZ for VM_BIND queue */
 	__u64 bos;            /* in, ptr to array of submit_bo's */
-	__u64 cmds;           /* in, ptr to array of submit_cmd's */
+	__u64 cmds;           /* in, ptr to array of submit_cmd's, MBZ for VM_BIND queue */
 	__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 */
@@ -322,8 +358,7 @@  struct drm_msm_gem_submit {
 	__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. */
-
+	__u32 bos_stride;     /* in, stride of bos array, if zero 16bytes used. */
 };
 
 #define MSM_WAIT_FENCE_BOOST	0x00000001