diff options
Diffstat (limited to 'drivers/gpu/drm/msm/msm_gpu.h')
| -rw-r--r-- | drivers/gpu/drm/msm/msm_gpu.h | 271 |
1 files changed, 190 insertions, 81 deletions
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 58a72e6b1400..2894fc118485 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -13,17 +13,18 @@ #include <linux/interconnect.h> #include <linux/pm_opp.h> #include <linux/regulator/consumer.h> -#include <linux/reset.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_file_private; +struct msm_context; struct msm_gpu_config { const char *ioname; @@ -45,11 +46,17 @@ struct msm_gpu_config { * + z180_gpu */ struct msm_gpu_funcs { - int (*get_param)(struct msm_gpu *gpu, struct msm_file_private *ctx, + 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_file_private *ctx, + 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); @@ -73,11 +80,19 @@ struct msm_gpu_funcs { /* 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 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); + 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: */ @@ -87,6 +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; }; /** @@ -100,11 +123,15 @@ struct msm_gpu_devfreq { 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: @@ -126,8 +153,6 @@ struct msm_gpu_devfreq { /** idle_time: Time of last transition to idle: */ ktime_t idle_time; - struct devfreq_dev_status average_status; - /** * idle_work: * @@ -178,17 +203,6 @@ struct msm_gpu { refcount_t sysprof_active; /** - * cur_ctx_seqno: - * - * 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; - - /** * lock: * * General lock for serializing all the gpu things. @@ -223,7 +237,7 @@ struct msm_gpu { void __iomem *mmio; int irq; - struct msm_gem_address_space *aspace; + struct drm_gpuvm *vm; /* Power Control: */ struct regulator *gpu_reg, *gpu_cx; @@ -237,14 +251,9 @@ 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; @@ -265,16 +274,19 @@ 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; - struct thermal_cooling_device *cooling; + /** + * @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; - /* To poll for cx gdsc collapse during gpu recovery */ - struct reset_control *cx_collapse; + struct thermal_cooling_device *cooling; }; static inline struct msm_gpu *dev_to_gpu(struct device *dev) @@ -287,6 +299,17 @@ static inline struct msm_gpu *dev_to_gpu(struct device *dev) 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 @@ -327,29 +350,64 @@ 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; /** - * sysprof: + * @sysprof: * * The value of MSM_PARAM_SYSPROF set by userspace. This is * intended to be used by system profiling tools like Mesa's @@ -366,14 +424,22 @@ struct msm_file_private { */ int sysprof; - /** comm: Overridden task comm, see MSM_PARAM_COMM */ + /** + * @comm: Overridden task comm, see MSM_PARAM_COMM + * + * Accessed under msm_gpu::lock + */ char *comm; - /** cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE */ + /** + * @cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE + * + * Accessed under msm_gpu::lock + */ char *cmdline; /** - * elapsed: + * @elapsed: * * The total (cumulative) elapsed time GPU was busy with rendering * from this context in ns. @@ -381,7 +447,7 @@ struct msm_file_private { uint64_t elapsed_ns; /** - * cycles: + * @cycles: * * The total (cumulative) GPU cycles elapsed attributed to this * context. @@ -389,7 +455,7 @@ struct msm_file_private { uint64_t cycles; /** - * entities: + * @entities: * * Table of per-priority-level sched entities used by submitqueues * associated with this &drm_file. Because some userspace apps @@ -400,8 +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 * @@ -479,18 +571,22 @@ 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 mutex idr_lock; + 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]; @@ -521,26 +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; @@ -558,49 +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); -void msm_gpu_show_fdinfo(struct msm_gpu *gpu, 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_file_private *ctx); -struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx, +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); -int msm_file_private_set_sysprof(struct msm_file_private *ctx, - struct msm_gpu *gpu, int sysprof); -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; @@ -628,12 +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); @@ -671,6 +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 |