Merge tag 'drm-msm-next-2025-07-05' of https://gitlab.freedesktop.org/drm/msm into drm-next

Updates for v6.17

CI:
- uprev mesa and ci-templates
- use shallow clone to speed up build jobs
- remove sdm845/cheza jobs.  These runners are no more (RIP
  dear chezas)
- fix runner tag for i915 cml runners
- uprev igt to pull in msm test fixes

Core:
- VM_BIND support!
- single source of truth for UBWC configuration.  Adds a global soc
  driver for UBWC config which is used from display and GPU.  (And
  later vidc/camera/etc)
- Decouple ties between GPU and KMS, adding a `separate_gpu_kms`
  modparam to allow the GPU and KMS to bind to separate DRM devices.
  This should better deal with more exotic SoC configurations where
  the number of GPUs is different from number of DPUs.  The default
  behavior is to still come up as a single unified DRM device to
  avoid surprising userspace.

DP:
- major rework of the I/O accessors

DPU:
- use version checks instead of feature bits
- SM8750 support
- set min_prefill_lines for SC8180X

DSI:
- SM8750 support

GPU:
- speedbin support for X1-85
- X1-45 support

MDSS:
- SM8750 support

Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>
From: Robin Clark <robin.clark@oss.qualcomm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CACSVV0217R+kpoWQJeuYGHf6q_4aFyEJuKa=dZZKOnLQzFwppg@mail.gmail.com

5 files changed, 224 insertions, 19 deletions

diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 1a79ec3fe45c..d3a7b43e2c63 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -560,10 +560,12 @@ void drm_gem_lru_init(struct drm_gem_lru *lru, struct mutex *lock);
 void drm_gem_lru_remove(struct drm_gem_object *obj);
 void drm_gem_lru_move_tail_locked(struct drm_gem_lru *lru, struct drm_gem_object *obj);
 void drm_gem_lru_move_tail(struct drm_gem_lru *lru, struct drm_gem_object *obj);
-unsigned long drm_gem_lru_scan(struct drm_gem_lru *lru,
-			       unsigned int nr_to_scan,
-			       unsigned long *remaining,
-			       bool (*shrink)(struct drm_gem_object *obj));
+unsigned long
+drm_gem_lru_scan(struct drm_gem_lru *lru,
+		 unsigned int nr_to_scan,
+		 unsigned long *remaining,
+		 bool (*shrink)(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket),
+		 struct ww_acquire_ctx *ticket);
 
 int drm_gem_evict_locked(struct drm_gem_object *obj);
 
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index 2a9629377633..274532facfd6 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1211,6 +1211,14 @@ int drm_gpuvm_sm_map(struct drm_gpuvm *gpuvm, void *priv,
 int drm_gpuvm_sm_unmap(struct drm_gpuvm *gpuvm, void *priv,
 		       u64 addr, u64 range);
 
+int drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm,
+			  struct drm_exec *exec, unsigned int num_fences,
+			  u64 req_addr, u64 req_range,
+			  struct drm_gem_object *obj, u64 offset);
+
+int drm_gpuvm_sm_unmap_exec_lock(struct drm_gpuvm *gpuvm, struct drm_exec *exec,
+				 u64 req_addr, u64 req_range);
+
 void drm_gpuva_map(struct drm_gpuvm *gpuvm,
 		   struct drm_gpuva *va,
 		   struct drm_gpuva_op_map *op);
diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h
index d9b7bac30953..f15bcee7c928 100644
--- a/include/dt-bindings/power/qcom-rpmpd.h
+++ b/include/dt-bindings/power/qcom-rpmpd.h
@@ -240,6 +240,7 @@
 #define RPMH_REGULATOR_LEVEL_TURBO_L2		432
 #define RPMH_REGULATOR_LEVEL_TURBO_L3		448
 #define RPMH_REGULATOR_LEVEL_TURBO_L4		452
+#define RPMH_REGULATOR_LEVEL_TURBO_L5		456
 #define RPMH_REGULATOR_LEVEL_SUPER_TURBO 	464
 #define RPMH_REGULATOR_LEVEL_SUPER_TURBO_NO_CPR	480
 
diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h
new file mode 100644
index 000000000000..1ed8b1b16bc9
--- /dev/null
+++ b/include/linux/soc/qcom/ubwc.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2018, The Linux Foundation
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
+ */
+
+#ifndef __QCOM_UBWC_H__
+#define __QCOM_UBWC_H__
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+struct qcom_ubwc_cfg_data {
+	u32 ubwc_enc_version;
+	/* Can be read from MDSS_BASE + 0x58 */
+	u32 ubwc_dec_version;
+
+	/**
+	 * @ubwc_swizzle: Whether to enable level 1, 2 & 3 bank swizzling.
+	 *
+	 * UBWC 1.0 always enables all three levels.
+	 * UBWC 2.0 removes level 1 bank swizzling, leaving levels 2 & 3.
+	 * UBWC 4.0 adds the optional ability to disable levels 2 & 3.
+	 */
+	u32 ubwc_swizzle;
+#define UBWC_SWIZZLE_ENABLE_LVL1	BIT(0)
+#define UBWC_SWIZZLE_ENABLE_LVL2	BIT(1)
+#define UBWC_SWIZZLE_ENABLE_LVL3	BIT(2)
+
+	/**
+	 * @highest_bank_bit: Highest Bank Bit
+	 *
+	 * The Highest Bank Bit value represents the bit of the highest
+	 * DDR bank.  This should ideally use DRAM type detection.
+	 */
+	int highest_bank_bit;
+	bool ubwc_bank_spread;
+
+	/**
+	 * @macrotile_mode: Macrotile Mode
+	 *
+	 * Whether to use 4-channel macrotiling mode or the newer
+	 * 8-channel macrotiling mode introduced in UBWC 3.1. 0 is
+	 * 4-channel and 1 is 8-channel.
+	 */
+	bool macrotile_mode;
+};
+
+#define UBWC_1_0 0x10000000
+#define UBWC_2_0 0x20000000
+#define UBWC_3_0 0x30000000
+#define UBWC_4_0 0x40000000
+#define UBWC_4_3 0x40030000
+#define UBWC_5_0 0x50000000
+
+#if IS_ENABLED(CONFIG_QCOM_UBWC_CONFIG)
+const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void);
+#else
+static inline const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+#endif
+
+static inline bool qcom_ubwc_get_ubwc_mode(const struct qcom_ubwc_cfg_data *cfg)
+{
+	bool ret = cfg->ubwc_enc_version == UBWC_1_0;
+
+	if (ret && !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL1))
+		pr_err("UBWC config discrepancy - level 1 swizzling disabled on UBWC 1.0\n");
+
+	return ret;
+}
+
+#endif /* __QCOM_UBWC_H__ */
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)
 }