1 files changed, 261 insertions, 76 deletions

diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 445c6bfd4b6b..2894fc118485 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -9,18 +9,22 @@
 
 #include <linux/adreno-smmu-priv.h>
 #include <linux/clk.h>
+#include <linux/devfreq.h>
 #include <linux/interconnect.h>
 #include <linux/pm_opp.h>
 #include <linux/regulator/consumer.h>
 
 #include "msm_drv.h"
 #include "msm_fence.h"
+#include "msm_gpu_trace.h"
 #include "msm_ringbuffer.h"
 #include "msm_gem.h"
 
 struct msm_gem_submit;
+struct msm_gem_vm_log_entry;
 struct msm_gpu_perfcntr;
 struct msm_gpu_state;
+struct msm_context;
 
 struct msm_gpu_config {
 	const char *ioname;
@@ -42,8 +46,17 @@ struct msm_gpu_config {
  *    + z180_gpu
  */
 struct msm_gpu_funcs {
-	int (*get_param)(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
+	int (*get_param)(struct msm_gpu *gpu, struct msm_context *ctx,
+			 uint32_t param, uint64_t *value, uint32_t *len);
+	int (*set_param)(struct msm_gpu *gpu, struct msm_context *ctx,
+			 uint32_t param, uint64_t value, uint32_t len);
 	int (*hw_init)(struct msm_gpu *gpu);
+
+	/**
+	 * @ucode_load: Optional hook to upload fw to GEM objs
+	 */
+	int (*ucode_load)(struct msm_gpu *gpu);
+
 	int (*pm_suspend)(struct msm_gpu *gpu);
 	int (*pm_resume)(struct msm_gpu *gpu);
 	void (*submit)(struct msm_gpu *gpu, struct msm_gem_submit *submit);
@@ -59,16 +72,27 @@ struct msm_gpu_funcs {
 	/* for generation specific debugfs: */
 	void (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
-	unsigned long (*gpu_busy)(struct msm_gpu *gpu);
+	/* note: gpu_busy() can assume that we have been pm_resumed */
+	u64 (*gpu_busy)(struct msm_gpu *gpu, unsigned long *out_sample_rate);
 	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
 	int (*gpu_state_put)(struct msm_gpu_state *state);
 	unsigned long (*gpu_get_freq)(struct msm_gpu *gpu);
-	void (*gpu_set_freq)(struct msm_gpu *gpu, struct dev_pm_opp *opp);
-	struct msm_gem_address_space *(*create_address_space)
-		(struct msm_gpu *gpu, struct platform_device *pdev);
-	struct msm_gem_address_space *(*create_private_address_space)
-		(struct msm_gpu *gpu);
+	/* note: gpu_set_freq() can assume that we have been pm_resumed */
+	void (*gpu_set_freq)(struct msm_gpu *gpu, struct dev_pm_opp *opp,
+			     bool suspended);
+	struct drm_gpuvm *(*create_vm)(struct msm_gpu *gpu, struct platform_device *pdev);
+	struct drm_gpuvm *(*create_private_vm)(struct msm_gpu *gpu, bool kernel_managed);
 	uint32_t (*get_rptr)(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
+
+	/**
+	 * progress: Has the GPU made progress?
+	 *
+	 * Return true if GPU position in cmdstream has advanced (or changed)
+	 * since the last call.  To avoid false negatives, this should account
+	 * for cmdstream that is buffered in this FIFO upstream of the CP fw.
+	 */
+	bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
+	void (*sysprof_setup)(struct msm_gpu *gpu);
 };
 
 /* Additional state for iommu faults: */
@@ -78,6 +102,14 @@ struct msm_gpu_fault_info {
 	int flags;
 	const char *type;
 	const char *block;
+
+	/* Information about what we think/expect is the current SMMU state,
+	 * for example expected_ttbr0 should match smmu_info.ttbr0 which
+	 * was read back from SMMU registers.
+	 */
+	phys_addr_t pgtbl_ttbr0;
+	u64 ptes[4];
+	int asid;
 };
 
 /**
@@ -87,12 +119,19 @@ struct msm_gpu_devfreq {
 	/** devfreq: devfreq instance */
 	struct devfreq *devfreq;
 
+	/** lock: lock for "suspended", "busy_cycles", and "time" */
+	struct mutex lock;
+
 	/**
-	 * idle_constraint:
+	 * idle_freq:
 	 *
-	 * A PM QoS constraint to limit max freq while the GPU is idle.
+	 * Shadow frequency used while the GPU is idle.  From the PoV of
+	 * the devfreq governor, we are continuing to sample busyness and
+	 * adjust frequency while the GPU is idle, but we use this shadow
+	 * value as the GPU is actually clamped to minimum frequency while
+	 * it is inactive.
 	 */
-	struct dev_pm_qos_request idle_freq;
+	unsigned long idle_freq;
 
 	/**
 	 * boost_constraint:
@@ -103,11 +142,8 @@ struct msm_gpu_devfreq {
 	struct dev_pm_qos_request boost_freq;
 
 	/**
-	 * busy_cycles:
-	 *
-	 * Used by implementation of gpu->gpu_busy() to track the last
-	 * busy counter value, for calculating elapsed busy cycles since
-	 * last sampling period.
+	 * busy_cycles: Last busy counter value, for calculating elapsed busy
+	 * cycles since last sampling period.
 	 */
 	u64 busy_cycles;
 
@@ -131,6 +167,9 @@ struct msm_gpu_devfreq {
 	 * elapsed
 	 */
 	struct msm_hrtimer_work boost_work;
+
+	/** suspended: tracks if we're suspended */
+	bool suspended;
 };
 
 struct msm_gpu {
@@ -157,21 +196,11 @@ struct msm_gpu {
 	int nr_rings;
 
 	/**
-	 * cur_ctx_seqno:
+	 * sysprof_active:
 	 *
-	 * The ctx->seqno value of the last context to submit rendering,
-	 * and the one with current pgtables installed (for generations
-	 * that support per-context pgtables).  Tracked by seqno rather
-	 * than pointer value to avoid dangling pointers, and cases where
-	 * a ctx can be freed and a new one created with the same address.
-	 */
-	int cur_ctx_seqno;
-
-	/*
-	 * List of GEM active objects on this gpu.  Protected by
-	 * msm_drm_private::mm_lock
+	 * The count of contexts that have enabled system profiling.
 	 */
-	struct list_head active_list;
+	refcount_t sysprof_active;
 
 	/**
 	 * lock:
@@ -199,13 +228,16 @@ struct msm_gpu {
 	/* does gpu need hw_init? */
 	bool needs_hw_init;
 
-	/* number of GPU hangs (for all contexts) */
+	/**
+	 * global_faults: number of GPU hangs not attributed to a particular
+	 * address space
+	 */
 	int global_faults;
 
 	void __iomem *mmio;
 	int irq;
 
-	struct msm_gem_address_space *aspace;
+	struct drm_gpuvm *vm;
 
 	/* Power Control: */
 	struct regulator *gpu_reg, *gpu_cx;
@@ -219,17 +251,15 @@ struct msm_gpu {
 #define DRM_MSM_INACTIVE_PERIOD   66 /* in ms (roughly four frames) */
 
 #define DRM_MSM_HANGCHECK_DEFAULT_PERIOD 500 /* in ms */
+#define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3
 	struct timer_list hangcheck_timer;
 
-	/* Fault info for most recent iova fault: */
-	struct msm_gpu_fault_info fault_info;
-
-	/* work for handling GPU ioval faults: */
-	struct kthread_work fault_work;
-
 	/* work for handling GPU recovery: */
 	struct kthread_work recover_work;
 
+	/** retire_event: notified when submits are retired: */
+	wait_queue_head_t retire_event;
+
 	/* work for handling active-list retiring: */
 	struct kthread_work retire_work;
 
@@ -244,21 +274,42 @@ struct msm_gpu {
 
 	struct msm_gpu_state *crashstate;
 
-	/* Enable clamping to idle freq when inactive: */
-	bool clamp_to_idle;
-
 	/* True if the hardware supports expanded apriv (a650 and newer) */
 	bool hw_apriv;
 
+	/**
+	 * @allow_relocs: allow relocs in SUBMIT ioctl
+	 *
+	 * Mesa won't use relocs for driver version 1.4.0 and later.  This
+	 * switch-over happened early enough in mesa a6xx bringup that we
+	 * can disallow relocs for a6xx and newer.
+	 */
+	bool allow_relocs;
+
 	struct thermal_cooling_device *cooling;
 };
 
 static inline struct msm_gpu *dev_to_gpu(struct device *dev)
 {
 	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev);
+
+	if (!adreno_smmu)
+		return NULL;
+
 	return container_of(adreno_smmu, struct msm_gpu, adreno_smmu);
 }
 
+static inline bool
+adreno_smmu_has_prr(struct msm_gpu *gpu)
+{
+	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev);
+
+	if (!adreno_smmu)
+		return false;
+
+	return adreno_smmu && adreno_smmu->set_prr_addr;
+}
+
 /* It turns out that all targets use the same ringbuffer size */
 #define MSM_GPU_RINGBUFFER_SZ SZ_32K
 #define MSM_GPU_RINGBUFFER_BLKSIZE 32
@@ -274,7 +325,7 @@ static inline bool msm_gpu_active(struct msm_gpu *gpu)
 	for (i = 0; i < gpu->nr_rings; i++) {
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
-		if (fence_after(ring->seqno, ring->memptrs->fence))
+		if (fence_after(ring->fctx->last_fence, ring->memptrs->fence))
 			return true;
 	}
 
@@ -299,29 +350,112 @@ struct msm_gpu_perfcntr {
  * DRM_SCHED_PRIORITY_KERNEL priority level is treated specially in some
  * cases, so we don't use it (no need for kernel generated jobs).
  */
-#define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_HIGH - DRM_SCHED_PRIORITY_MIN)
+#define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_LOW - DRM_SCHED_PRIORITY_HIGH)
 
 /**
- * struct msm_file_private - per-drm_file context
- *
- * @queuelock:    synchronizes access to submitqueues list
- * @submitqueues: list of &msm_gpu_submitqueue created by userspace
- * @queueid:      counter incremented each time a submitqueue is created,
- *                used to assign &msm_gpu_submitqueue.id
- * @aspace:       the per-process GPU address-space
- * @ref:          reference count
- * @seqno:        unique per process seqno
+ * struct msm_context - per-drm_file context
  */
-struct msm_file_private {
+struct msm_context {
+	/** @queuelock: synchronizes access to submitqueues list */
 	rwlock_t queuelock;
+
+	/** @submitqueues: list of &msm_gpu_submitqueue created by userspace */
 	struct list_head submitqueues;
+
+	/**
+	 * @queueid:
+	 *
+	 * Counter incremented each time a submitqueue is created, used to
+	 * assign &msm_gpu_submitqueue.id
+	 */
 	int queueid;
-	struct msm_gem_address_space *aspace;
+
+	/**
+	 * @closed: The device file associated with this context has been closed.
+	 *
+	 * Once the device is closed, any submits that have not been written
+	 * to the ring buffer are no-op'd.
+	 */
+	bool closed;
+
+	/**
+	 * @userspace_managed_vm:
+	 *
+	 * Has userspace opted-in to userspace managed VM (ie. VM_BIND) via
+	 * MSM_PARAM_EN_VM_BIND?
+	 */
+	bool userspace_managed_vm;
+
+	/**
+	 * @vm:
+	 *
+	 * The per-process GPU address-space.  Do not access directly, use
+	 * msm_context_vm().
+	 */
+	struct drm_gpuvm *vm;
+
+	/** @kref: the reference count */
 	struct kref ref;
+
+	/**
+	 * @seqno:
+	 *
+	 * A unique per-process sequence number.  Used to detect context
+	 * switches, without relying on keeping a, potentially dangling,
+	 * pointer to the previous context.
+	 */
 	int seqno;
 
 	/**
-	 * entities:
+	 * @sysprof:
+	 *
+	 * The value of MSM_PARAM_SYSPROF set by userspace.  This is
+	 * intended to be used by system profiling tools like Mesa's
+	 * pps-producer (perfetto), and restricted to CAP_SYS_ADMIN.
+	 *
+	 * Setting a value of 1 will preserve performance counters across
+	 * context switches.  Setting a value of 2 will in addition
+	 * suppress suspend.  (Performance counters lose state across
+	 * power collapse, which is undesirable for profiling in some
+	 * cases.)
+	 *
+	 * The value automatically reverts to zero when the drm device
+	 * file is closed.
+	 */
+	int sysprof;
+
+	/**
+	 * @comm: Overridden task comm, see MSM_PARAM_COMM
+	 *
+	 * Accessed under msm_gpu::lock
+	 */
+	char *comm;
+
+	/**
+	 * @cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE
+	 *
+	 * Accessed under msm_gpu::lock
+	 */
+	char *cmdline;
+
+	/**
+	 * @elapsed:
+	 *
+	 * The total (cumulative) elapsed time GPU was busy with rendering
+	 * from this context in ns.
+	 */
+	uint64_t elapsed_ns;
+
+	/**
+	 * @cycles:
+	 *
+	 * The total (cumulative) GPU cycles elapsed attributed to this
+	 * context.
+	 */
+	uint64_t cycles;
+
+	/**
+	 * @entities:
 	 *
 	 * Table of per-priority-level sched entities used by submitqueues
 	 * associated with this &drm_file.  Because some userspace apps
@@ -332,8 +466,34 @@ struct msm_file_private {
 	 * level.
 	 */
 	struct drm_sched_entity *entities[NR_SCHED_PRIORITIES * MSM_GPU_MAX_RINGS];
+
+	/**
+	 * @ctx_mem:
+	 *
+	 * Total amount of memory of GEM buffers with handles attached for
+	 * this context.
+	 */
+	atomic64_t ctx_mem;
 };
 
+struct drm_gpuvm *msm_context_vm(struct drm_device *dev, struct msm_context *ctx);
+
+/**
+ * msm_context_is_vm_bind() - has userspace opted in to VM_BIND?
+ *
+ * @ctx: the drm_file context
+ *
+ * See MSM_PARAM_EN_VM_BIND.  If userspace is managing the VM, it can
+ * do sparse binding including having multiple, potentially partial,
+ * mappings in the VM.  Therefore certain legacy uabi (ie. GET_IOVA,
+ * SET_IOVA) are rejected because they don't have a sensible meaning.
+ */
+static inline bool
+msm_context_is_vmbind(struct msm_context *ctx)
+{
+	return ctx->userspace_managed_vm;
+}
+
 /**
  * msm_gpu_convert_priority - Map userspace priority to ring # and sched priority
  *
@@ -400,7 +560,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
  * @node:      node in the context's list of submitqueues
  * @fence_idr: maps fence-id to dma_fence for userspace visible fence
  *             seqno, protected by submitqueue lock
- * @lock:      submitqueue lock
+ * @idr_lock:  for serializing access to fence_idr
+ * @lock:      submitqueue lock for serializing submits on a queue
  * @ref:       reference count
  * @entity:    the submit job-queue
  */
@@ -410,19 +571,25 @@ struct msm_gpu_submitqueue {
 	u32 ring_nr;
 	int faults;
 	uint32_t last_fence;
-	struct msm_file_private *ctx;
+	struct msm_context *ctx;
 	struct list_head node;
 	struct idr fence_idr;
+	struct spinlock idr_lock;
 	struct mutex lock;
 	struct kref ref;
 	struct drm_sched_entity *entity;
+
+	/** @_vm_bind_entity: used for @entity pointer for VM_BIND queues */
+	struct drm_sched_entity _vm_bind_entity[0];
 };
 
 struct msm_gpu_state_bo {
 	u64 iova;
 	size_t size;
+	u32 flags;
 	void *data;
 	bool encoded;
+	char name[32];
 };
 
 struct msm_gpu_state {
@@ -450,26 +617,32 @@ struct msm_gpu_state {
 
 	struct msm_gpu_fault_info fault_info;
 
+	int nr_vm_logs;
+	struct msm_gem_vm_log_entry *vm_logs;
+
 	int nr_bos;
 	struct msm_gpu_state_bo *bos;
 };
 
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
 {
-	msm_writel(data, gpu->mmio + (reg << 2));
+	trace_msm_gpu_regaccess(reg);
+	writel(data, gpu->mmio + (reg << 2));
 }
 
 static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg)
 {
-	return msm_readl(gpu->mmio + (reg << 2));
+	trace_msm_gpu_regaccess(reg);
+	return readl(gpu->mmio + (reg << 2));
 }
 
 static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or)
 {
+	trace_msm_gpu_regaccess(reg);
 	msm_rmw(gpu->mmio + (reg << 2), mask, or);
 }
 
-static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi)
+static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg)
 {
 	u64 val;
 
@@ -487,44 +660,52 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi)
 	 * when the lo is read, so make sure to read the lo first to trigger
 	 * that
 	 */
-	val = (u64) msm_readl(gpu->mmio + (lo << 2));
-	val |= ((u64) msm_readl(gpu->mmio + (hi << 2)) << 32);
+	trace_msm_gpu_regaccess(reg);
+	val = (u64) readl(gpu->mmio + (reg << 2));
+	trace_msm_gpu_regaccess(reg+1);
+	val |= ((u64) readl(gpu->mmio + ((reg + 1) << 2)) << 32);
 
 	return val;
 }
 
-static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
+static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val)
 {
+	trace_msm_gpu_regaccess(reg);
 	/* Why not a writeq here? Read the screed above */
-	msm_writel(lower_32_bits(val), gpu->mmio + (lo << 2));
-	msm_writel(upper_32_bits(val), gpu->mmio + (hi << 2));
+	writel(lower_32_bits(val), gpu->mmio + (reg << 2));
+	trace_msm_gpu_regaccess(reg+1);
+	writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2));
 }
 
 int msm_gpu_pm_suspend(struct msm_gpu *gpu);
 int msm_gpu_pm_resume(struct msm_gpu *gpu);
 
-int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
-struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx,
+void msm_gpu_show_fdinfo(struct msm_gpu *gpu, struct msm_context *ctx,
+			 struct drm_printer *p);
+
+int msm_submitqueue_init(struct drm_device *drm, struct msm_context *ctx);
+struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_context *ctx,
 		u32 id);
 int msm_submitqueue_create(struct drm_device *drm,
-		struct msm_file_private *ctx,
+		struct msm_context *ctx,
 		u32 prio, u32 flags, u32 *id);
-int msm_submitqueue_query(struct drm_device *drm, struct msm_file_private *ctx,
+int msm_submitqueue_query(struct drm_device *drm, struct msm_context *ctx,
 		struct drm_msm_submitqueue_query *args);
-int msm_submitqueue_remove(struct msm_file_private *ctx, u32 id);
-void msm_submitqueue_close(struct msm_file_private *ctx);
+int msm_submitqueue_remove(struct msm_context *ctx, u32 id);
+void msm_submitqueue_close(struct msm_context *ctx);
 
 void msm_submitqueue_destroy(struct kref *kref);
 
-void __msm_file_private_destroy(struct kref *kref);
+int msm_context_set_sysprof(struct msm_context *ctx, struct msm_gpu *gpu, int sysprof);
+void __msm_context_destroy(struct kref *kref);
 
-static inline void msm_file_private_put(struct msm_file_private *ctx)
+static inline void msm_context_put(struct msm_context *ctx)
 {
-	kref_put(&ctx->ref, __msm_file_private_destroy);
+	kref_put(&ctx->ref, __msm_context_destroy);
 }
 
-static inline struct msm_file_private *msm_file_private_get(
-	struct msm_file_private *ctx)
+static inline struct msm_context *msm_context_get(
+	struct msm_context *ctx)
 {
 	kref_get(&ctx->ref);
 	return ctx;
@@ -552,12 +733,14 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs,
 		const char *name, struct msm_gpu_config *config);
 
-struct msm_gem_address_space *
-msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *task);
+struct drm_gpuvm *
+msm_gpu_create_private_vm(struct msm_gpu *gpu, struct task_struct *task,
+			  bool kernel_managed);
 
 void msm_gpu_cleanup(struct msm_gpu *gpu);
 
 struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
+bool adreno_has_gpu(struct device_node *node);
 void __init adreno_register(void);
 void __exit adreno_unregister(void);
 
@@ -595,6 +778,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->lock);
 }
 
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info);
+
 /*
  * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
  * support expanded privileges