AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-20 18:56:48 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
7c6981e7ca
linux_dsm_epyc7002/drivers/gpu/drm/etnaviv/etnaviv_cmdbuf.h

47 lines
1.3 KiB
C
Raw Normal View History

drm/etnaviv: replace license text with SPDX tags This replaces the repetitive GPL-2.0 license text in code and header files with the SPDX tags. Generated hardware headers aren't changed, as any changes there need to be done in the upstream rnndb repository. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2018-05-08 21:20:54 +07:00
/* SPDX-License-Identifier: GPL-2.0 */
drm/etnaviv: move cmdbuf de-/allocation into own file This will get more complex with the following changes, so move it into its own place. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 22:09:51 +07:00
/*
* Copyright (C) 2017 Etnaviv Project
*/
#ifndef __ETNAVIV_CMDBUF_H__
#define __ETNAVIV_CMDBUF_H__
#include <linux/types.h>
drm/etnaviv: share a single cmdbuf suballoc region across all GPUs There is no need for each GPU to have it's own cmdbuf suballocation region. Only allocate a single one for the the etnaviv virtual device and share it across all GPUs. As the suballoc space is now potentially shared by more hardware jobs running in parallel, double its size to 512KB to avoid contention. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:22 +07:00
struct device;
drm/etnaviv: rework MMU handling This reworks the MMU handling to make it possible to have multiple MMU contexts. A context is basically one instance of GPU page tables. Currently we have one set of page tables per GPU, which isn't all that clever, as it has the following two consequences: 1. All GPU clients (aka processes) are sharing the same pagetables, which means there is no isolation between clients, but only between GPU assigned memory spaces and the rest of the system. Better than nothing, but also not great. 2. Clients operating on the same set of buffers with different etnaviv GPU cores, e.g. a workload using both the 2D and 3D GPU, need to map the used buffers into the pagetable sets of each used GPU. This patch reworks all the MMU handling to introduce the abstraction of the MMU context. A context can be shared across different GPU cores, as long as they have compatible MMU implementations, which is the case for all systems with Vivante GPUs seen in the wild. As MMUv1 is not able to change pagetables on the fly, without a "stop the world" operation, which stops GPU, changes pagetables via CPU interaction, restarts GPU, the implementation introduces a shared context on MMUv1, which is returned whenever there is a request for a new context. This patch assigns a MMU context to each GPU, so on MMUv2 systems there is still one set of pagetables per GPU, but due to the shared context MMUv1 systems see a change in behavior as now a single pagetable set is used across all GPU cores. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:24 +07:00
struct etnaviv_iommu_context;
drm/etnaviv: split out cmdbuf mapping into address space This allows to decouple the cmdbuf suballocator create and mapping the region into the GPU address space. Allowing multiple AS to share a single cmdbuf suballoc. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:21 +07:00
struct etnaviv_vram_mapping;
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
struct etnaviv_cmdbuf_suballoc;
drm/etnaviv: add internal representation of perfmon_request Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com> Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
2017-09-24 20:15:23 +07:00
struct etnaviv_perfmon_request;
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
drm/etnaviv: move cmdbuf de-/allocation into own file This will get more complex with the following changes, so move it into its own place. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 22:09:51 +07:00
struct etnaviv_cmdbuf {
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
/* suballocator this cmdbuf is allocated from */
struct etnaviv_cmdbuf_suballoc *suballoc;
drm/etnaviv: move cmdbuf de-/allocation into own file This will get more complex with the following changes, so move it into its own place. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 22:09:51 +07:00
/* cmdbuf properties */
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
int suballoc_offset;
drm/etnaviv: move cmdbuf de-/allocation into own file This will get more complex with the following changes, so move it into its own place. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 22:09:51 +07:00
void *vaddr;
u32 size;
u32 user_size;
};
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
struct etnaviv_cmdbuf_suballoc *
drm/etnaviv: share a single cmdbuf suballoc region across all GPUs There is no need for each GPU to have it's own cmdbuf suballocation region. Only allocate a single one for the the etnaviv virtual device and share it across all GPUs. As the suballoc space is now potentially shared by more hardware jobs running in parallel, double its size to 512KB to avoid contention. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:22 +07:00
etnaviv_cmdbuf_suballoc_new(struct device *dev);
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
void etnaviv_cmdbuf_suballoc_destroy(struct etnaviv_cmdbuf_suballoc *suballoc);
drm/etnaviv: split out cmdbuf mapping into address space This allows to decouple the cmdbuf suballocator create and mapping the region into the GPU address space. Allowing multiple AS to share a single cmdbuf suballoc. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:21 +07:00
int etnaviv_cmdbuf_suballoc_map(struct etnaviv_cmdbuf_suballoc *suballoc,
drm/etnaviv: rework MMU handling This reworks the MMU handling to make it possible to have multiple MMU contexts. A context is basically one instance of GPU page tables. Currently we have one set of page tables per GPU, which isn't all that clever, as it has the following two consequences: 1. All GPU clients (aka processes) are sharing the same pagetables, which means there is no isolation between clients, but only between GPU assigned memory spaces and the rest of the system. Better than nothing, but also not great. 2. Clients operating on the same set of buffers with different etnaviv GPU cores, e.g. a workload using both the 2D and 3D GPU, need to map the used buffers into the pagetable sets of each used GPU. This patch reworks all the MMU handling to introduce the abstraction of the MMU context. A context can be shared across different GPU cores, as long as they have compatible MMU implementations, which is the case for all systems with Vivante GPUs seen in the wild. As MMUv1 is not able to change pagetables on the fly, without a "stop the world" operation, which stops GPU, changes pagetables via CPU interaction, restarts GPU, the implementation introduces a shared context on MMUv1, which is returned whenever there is a request for a new context. This patch assigns a MMU context to each GPU, so on MMUv2 systems there is still one set of pagetables per GPU, but due to the shared context MMUv1 systems see a change in behavior as now a single pagetable set is used across all GPU cores. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:24 +07:00
struct etnaviv_iommu_context *context,
drm/etnaviv: split out cmdbuf mapping into address space This allows to decouple the cmdbuf suballocator create and mapping the region into the GPU address space. Allowing multiple AS to share a single cmdbuf suballoc. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:21 +07:00
struct etnaviv_vram_mapping *mapping,
u32 memory_base);
drm/etnaviv: rework MMU handling This reworks the MMU handling to make it possible to have multiple MMU contexts. A context is basically one instance of GPU page tables. Currently we have one set of page tables per GPU, which isn't all that clever, as it has the following two consequences: 1. All GPU clients (aka processes) are sharing the same pagetables, which means there is no isolation between clients, but only between GPU assigned memory spaces and the rest of the system. Better than nothing, but also not great. 2. Clients operating on the same set of buffers with different etnaviv GPU cores, e.g. a workload using both the 2D and 3D GPU, need to map the used buffers into the pagetable sets of each used GPU. This patch reworks all the MMU handling to introduce the abstraction of the MMU context. A context can be shared across different GPU cores, as long as they have compatible MMU implementations, which is the case for all systems with Vivante GPUs seen in the wild. As MMUv1 is not able to change pagetables on the fly, without a "stop the world" operation, which stops GPU, changes pagetables via CPU interaction, restarts GPU, the implementation introduces a shared context on MMUv1, which is returned whenever there is a request for a new context. This patch assigns a MMU context to each GPU, so on MMUv2 systems there is still one set of pagetables per GPU, but due to the shared context MMUv1 systems see a change in behavior as now a single pagetable set is used across all GPU cores. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:24 +07:00
void etnaviv_cmdbuf_suballoc_unmap(struct etnaviv_iommu_context *context,
drm/etnaviv: split out cmdbuf mapping into address space This allows to decouple the cmdbuf suballocator create and mapping the region into the GPU address space. Allowing multiple AS to share a single cmdbuf suballoc. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:21 +07:00
struct etnaviv_vram_mapping *mapping);
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
drm/etnaviv: move cmdbuf into submit object Less dynamic allocations and slims down the cmdbuf object to only the required information, as everything else is already available in the submit object. This also simplifies buffer and mappings lifetime management, as they are now exlusively attached to the submit object and not additionally to the cmdbuf. Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
2017-11-24 22:56:37 +07:00
int etnaviv_cmdbuf_init(struct etnaviv_cmdbuf_suballoc *suballoc,
struct etnaviv_cmdbuf *cmdbuf, u32 size);
drm/etnaviv: add cmdbuf suballocator There are 3 big benefits to suballocating a single big DMA buffer for command submission: 1. Avoid hammering CMA. The old way of allocating and freeing a DMA buffer for each submission was hitting some of the real slow pathes in CMA, as this allocator was not designed for a concurrent small buffers load. 2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into the GPU address space the MMU TLBs need to be flushed. By having one big buffer statically mapped to the GPU, a lot of those flushes can be avoided. 3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't reliable. To work around that we tried to lay out the cmdbufs in the GPU address space in a way to avoid this issue. This hasn't always worked if the address space is crowded. A single statically mapped buffer avoids the erratum completely. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:29:57 +07:00
void etnaviv_cmdbuf_free(struct etnaviv_cmdbuf *cmdbuf);
drm/etnaviv: split out cmdbuf mapping into address space This allows to decouple the cmdbuf suballocator create and mapping the region into the GPU address space. Allowing multiple AS to share a single cmdbuf suballoc. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> Reviewed-by: Guido Günther <agx@sigxcpu.org>
2019-07-06 00:17:21 +07:00
u32 etnaviv_cmdbuf_get_va(struct etnaviv_cmdbuf *buf,
struct etnaviv_vram_mapping *mapping);
drm/etnaviv: get cmdbuf physical address through the cmdbuf abstraction Don't allow IOMMUv2 to peek directly into the cmdbuf, but get the needed PA through a dedicated function. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 23:00:08 +07:00
dma_addr_t etnaviv_cmdbuf_get_pa(struct etnaviv_cmdbuf *buf);
drm/etnaviv: wire up iova handling in new cmdbuf abstraction Don't call the IOMMU directly, but go through the new cmdbuf abstraction. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 22:52:44 +07:00
drm/etnaviv: move cmdbuf de-/allocation into own file This will get more complex with the following changes, so move it into its own place. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
2017-01-16 22:09:51 +07:00
#endif /* __ETNAVIV_CMDBUF_H__ */
Reference in New Issue Copy Permalink