drm/etnaviv: implement per-process address spaces on MMUv2

This builds on top of the MMU contexts introduced earlier. Instead of having
one context per GPU core, each GPU client receives its own context.

On MMUv1 this still means a single shared pagetable set is used by all
clients, but on MMUv2 there is now a distinct set of pagetables for each
client. As the command fetch is also translated via the MMU on MMUv2 the
kernel command ringbuffer is mapped into each of the client pagetables.

As the MMU context switch is a bit of a heavy operation, due to the needed
cache and TLB flushing, this patch implements a lazy way of switching the
MMU context. The kernel does not have its own MMU context, but reuses the
last client context for all of its operations. This has some visible impact,
as the GPU can now only be started once a client has submitted some work and
we got the client MMU context assigned. Also the MMU context has a different
lifetime than the general client context, as the GPU might still execute the
kernel command buffer in the context of a client even after the client has
completed all GPU work and has been terminated. Only when the GPU is runtime
suspended or switches to another clients MMU context is the old context
freed up.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Guido Günther <agx@sigxcpu.org>

1 files changed, 10 insertions, 1 deletions

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
index 4438d66db6ab..c01491a6c4d8 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h
@@ -47,6 +47,8 @@ struct etnaviv_iommu_global {
 	void *bad_page_cpu;
 	dma_addr_t bad_page_dma;
 
+	u32 memory_base;
+
 	/*
 	 * This union holds members needed by either MMUv1 or MMUv2, which
 	 * can not exist at the same time.
@@ -74,6 +76,9 @@ struct etnaviv_iommu_context {
 	struct list_head mappings;
 	struct drm_mm mm;
 	unsigned int flush_seq;
+
+	/* Not part of the context, but needs to have the same lifetime */
+	struct etnaviv_vram_mapping cmdbuf_mapping;
 };
 
 int etnaviv_iommu_global_init(struct etnaviv_gpu *gpu);
@@ -98,7 +103,8 @@ size_t etnaviv_iommu_dump_size(struct etnaviv_iommu_context *ctx);
 void etnaviv_iommu_dump(struct etnaviv_iommu_context *ctx, void *buf);
 
 struct etnaviv_iommu_context *
-etnaviv_iommu_context_init(struct etnaviv_iommu_global *global);
+etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
+			   struct etnaviv_cmdbuf_suballoc *suballoc);
 static inline void etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx)
 {
 	kref_get(&ctx->refcount);
@@ -112,4 +118,7 @@ etnaviv_iommuv1_context_alloc(struct etnaviv_iommu_global *global);
 struct etnaviv_iommu_context *
 etnaviv_iommuv2_context_alloc(struct etnaviv_iommu_global *global);
 
+u32 etnaviv_iommuv2_get_mtlb_addr(struct etnaviv_iommu_context *context);
+unsigned short etnaviv_iommuv2_get_pta_id(struct etnaviv_iommu_context *context);
+
 #endif /* __ETNAVIV_MMU_H__ */