linux_dsm_epyc7002/drivers/gpu/drm/etnaviv/etnaviv_mmu.c

506 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2015-2018 Etnaviv Project
*/
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
#include <linux/dma-mapping.h>
#include <linux/scatterlist.h>
#include "common.xml.h"
#include "etnaviv_cmdbuf.h"
#include "etnaviv_drv.h"
#include "etnaviv_gem.h"
#include "etnaviv_gpu.h"
#include "etnaviv_mmu.h"
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
static void etnaviv_context_unmap(struct etnaviv_iommu_context *context,
unsigned long iova, size_t size)
{
size_t unmapped_page, unmapped = 0;
size_t pgsize = SZ_4K;
if (!IS_ALIGNED(iova | size, pgsize)) {
pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%zx\n",
iova, size, pgsize);
return;
}
while (unmapped < size) {
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
unmapped_page = context->global->ops->unmap(context, iova,
pgsize);
if (!unmapped_page)
break;
iova += unmapped_page;
unmapped += unmapped_page;
}
}
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
static int etnaviv_context_map(struct etnaviv_iommu_context *context,
unsigned long iova, phys_addr_t paddr,
size_t size, int prot)
{
unsigned long orig_iova = iova;
size_t pgsize = SZ_4K;
size_t orig_size = size;
int ret = 0;
if (!IS_ALIGNED(iova | paddr | size, pgsize)) {
pr_err("unaligned: iova 0x%lx pa %pa size 0x%zx min_pagesz 0x%zx\n",
iova, &paddr, size, pgsize);
return -EINVAL;
}
while (size) {
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
ret = context->global->ops->map(context, iova, paddr, pgsize,
prot);
if (ret)
break;
iova += pgsize;
paddr += pgsize;
size -= pgsize;
}
/* unroll mapping in case something went wrong */
if (ret)
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
etnaviv_context_unmap(context, orig_iova, orig_size - size);
return ret;
}
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
static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova,
struct sg_table *sgt, unsigned len, int prot)
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 scatterlist *sg;
unsigned int da = iova;
unsigned int i, j;
int ret;
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
if (!context || !sgt)
return -EINVAL;
for_each_sg(sgt->sgl, sg, sgt->nents, i) {
u32 pa = sg_dma_address(sg) - sg->offset;
size_t bytes = sg_dma_len(sg) + sg->offset;
VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes);
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
ret = etnaviv_context_map(context, da, pa, bytes, prot);
if (ret)
goto fail;
da += bytes;
}
return 0;
fail:
da = iova;
for_each_sg(sgt->sgl, sg, i, j) {
size_t bytes = sg_dma_len(sg) + sg->offset;
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
etnaviv_context_unmap(context, da, bytes);
da += bytes;
}
return ret;
}
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
static void etnaviv_iommu_unmap(struct etnaviv_iommu_context *context, u32 iova,
struct sg_table *sgt, unsigned len)
{
struct scatterlist *sg;
unsigned int da = iova;
int i;
for_each_sg(sgt->sgl, sg, sgt->nents, i) {
size_t bytes = sg_dma_len(sg) + sg->offset;
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
etnaviv_context_unmap(context, da, bytes);
VERB("unmap[%d]: %08x(%zx)", i, iova, bytes);
BUG_ON(!PAGE_ALIGNED(bytes));
da += bytes;
}
}
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
static void etnaviv_iommu_remove_mapping(struct etnaviv_iommu_context *context,
struct etnaviv_vram_mapping *mapping)
{
struct etnaviv_gem_object *etnaviv_obj = mapping->object;
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
etnaviv_iommu_unmap(context, mapping->vram_node.start,
etnaviv_obj->sgt, etnaviv_obj->base.size);
drm_mm_remove_node(&mapping->vram_node);
}
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
static int etnaviv_iommu_find_iova(struct etnaviv_iommu_context *context,
struct drm_mm_node *node, size_t size)
{
struct etnaviv_vram_mapping *free = NULL;
drm: Improve drm_mm search (and fix topdown allocation) with rbtrees The drm_mm range manager claimed to support top-down insertion, but it was neither searching for the top-most hole that could fit the allocation request nor fitting the request to the hole correctly. In order to search the range efficiently, we create a secondary index for the holes using either their size or their address. This index allows us to find the smallest hole or the hole at the bottom or top of the range efficiently, whilst keeping the hole stack to rapidly service evictions. v2: Search for holes both high and low. Rename flags to mode. v3: Discover rb_entry_safe() and use it! v4: Kerneldoc for enum drm_mm_insert_mode. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Russell King <rmk+kernel@armlinux.org.uk> Cc: Daniel Vetter <daniel.vetter@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Sean Paul <seanpaul@chromium.org> Cc: Lucas Stach <l.stach@pengutronix.de> Cc: Christian Gmeiner <christian.gmeiner@gmail.com> Cc: Rob Clark <robdclark@gmail.com> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Alexandre Courbot <gnurou@gmail.com> Cc: Eric Anholt <eric@anholt.net> Cc: Sinclair Yeh <syeh@vmware.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com> # vmwgfx Reviewed-by: Lucas Stach <l.stach@pengutronix.de> #etnaviv Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20170202210438.28702-1-chris@chris-wilson.co.uk
2017-02-03 04:04:38 +07:00
enum drm_mm_insert_mode mode = DRM_MM_INSERT_LOW;
int ret;
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
lockdep_assert_held(&context->lock);
while (1) {
struct etnaviv_vram_mapping *m, *n;
struct drm_mm_scan scan;
struct list_head list;
bool found;
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
ret = drm_mm_insert_node_in_range(&context->mm, node,
size, 0, 0, 0, U64_MAX, mode);
if (ret != -ENOSPC)
break;
/* Try to retire some entries */
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
drm_mm_scan_init(&scan, &context->mm, size, 0, 0, mode);
found = 0;
INIT_LIST_HEAD(&list);
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
list_for_each_entry(free, &context->mappings, mmu_node) {
/* If this vram node has not been used, skip this. */
if (!free->vram_node.mm)
continue;
/*
* If the iova is pinned, then it's in-use,
* so we must keep its mapping.
*/
if (free->use)
continue;
list_add(&free->scan_node, &list);
if (drm_mm_scan_add_block(&scan, &free->vram_node)) {
found = true;
break;
}
}
if (!found) {
/* Nothing found, clean up and fail */
list_for_each_entry_safe(m, n, &list, scan_node)
BUG_ON(drm_mm_scan_remove_block(&scan, &m->vram_node));
break;
}
/*
* drm_mm does not allow any other operations while
* scanning, so we have to remove all blocks first.
* If drm_mm_scan_remove_block() returns false, we
* can leave the block pinned.
*/
list_for_each_entry_safe(m, n, &list, scan_node)
if (!drm_mm_scan_remove_block(&scan, &m->vram_node))
list_del_init(&m->scan_node);
/*
* Unmap the blocks which need to be reaped from the MMU.
* Clear the mmu pointer to prevent the mapping_get finding
* this mapping.
*/
list_for_each_entry_safe(m, n, &list, scan_node) {
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
etnaviv_iommu_remove_mapping(context, m);
m->context = NULL;
list_del_init(&m->mmu_node);
list_del_init(&m->scan_node);
}
drm: Improve drm_mm search (and fix topdown allocation) with rbtrees The drm_mm range manager claimed to support top-down insertion, but it was neither searching for the top-most hole that could fit the allocation request nor fitting the request to the hole correctly. In order to search the range efficiently, we create a secondary index for the holes using either their size or their address. This index allows us to find the smallest hole or the hole at the bottom or top of the range efficiently, whilst keeping the hole stack to rapidly service evictions. v2: Search for holes both high and low. Rename flags to mode. v3: Discover rb_entry_safe() and use it! v4: Kerneldoc for enum drm_mm_insert_mode. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: "Christian König" <christian.koenig@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Russell King <rmk+kernel@armlinux.org.uk> Cc: Daniel Vetter <daniel.vetter@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Sean Paul <seanpaul@chromium.org> Cc: Lucas Stach <l.stach@pengutronix.de> Cc: Christian Gmeiner <christian.gmeiner@gmail.com> Cc: Rob Clark <robdclark@gmail.com> Cc: Thierry Reding <thierry.reding@gmail.com> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Alexandre Courbot <gnurou@gmail.com> Cc: Eric Anholt <eric@anholt.net> Cc: Sinclair Yeh <syeh@vmware.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com> # vmwgfx Reviewed-by: Lucas Stach <l.stach@pengutronix.de> #etnaviv Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20170202210438.28702-1-chris@chris-wilson.co.uk
2017-02-03 04:04:38 +07:00
mode = DRM_MM_INSERT_EVICT;
/*
* We removed enough mappings so that the new allocation will
* succeed, retry the allocation one more time.
*/
}
return ret;
}
static int etnaviv_iommu_insert_exact(struct etnaviv_iommu_context *context,
struct drm_mm_node *node, size_t size, u64 va)
{
return drm_mm_insert_node_in_range(&context->mm, node, size, 0, 0, va,
va + size, DRM_MM_INSERT_LOWEST);
}
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
int etnaviv_iommu_map_gem(struct etnaviv_iommu_context *context,
struct etnaviv_gem_object *etnaviv_obj, u32 memory_base,
struct etnaviv_vram_mapping *mapping, u64 va)
{
struct sg_table *sgt = etnaviv_obj->sgt;
struct drm_mm_node *node;
int ret;
lockdep_assert_held(&etnaviv_obj->lock);
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
mutex_lock(&context->lock);
/* v1 MMU can optimize single entry (contiguous) scatterlists */
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
if (context->global->version == ETNAVIV_IOMMU_V1 &&
sgt->nents == 1 && !(etnaviv_obj->flags & ETNA_BO_FORCE_MMU)) {
u32 iova;
iova = sg_dma_address(sgt->sgl) - memory_base;
if (iova < 0x80000000 - sg_dma_len(sgt->sgl)) {
mapping->iova = iova;
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
list_add_tail(&mapping->mmu_node, &context->mappings);
ret = 0;
goto unlock;
}
}
node = &mapping->vram_node;
if (va)
ret = etnaviv_iommu_insert_exact(context, node,
etnaviv_obj->base.size, va);
else
ret = etnaviv_iommu_find_iova(context, node,
etnaviv_obj->base.size);
if (ret < 0)
goto unlock;
mapping->iova = node->start;
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
ret = etnaviv_iommu_map(context, node->start, sgt, etnaviv_obj->base.size,
ETNAVIV_PROT_READ | ETNAVIV_PROT_WRITE);
if (ret < 0) {
drm_mm_remove_node(node);
goto unlock;
}
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
list_add_tail(&mapping->mmu_node, &context->mappings);
context->flush_seq++;
unlock:
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
mutex_unlock(&context->lock);
return ret;
}
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_iommu_unmap_gem(struct etnaviv_iommu_context *context,
struct etnaviv_vram_mapping *mapping)
{
WARN_ON(mapping->use);
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
mutex_lock(&context->lock);
/* If the vram node is on the mm, unmap and remove the node */
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
if (mapping->vram_node.mm == &context->mm)
etnaviv_iommu_remove_mapping(context, mapping);
list_del(&mapping->mmu_node);
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
context->flush_seq++;
mutex_unlock(&context->lock);
}
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
static void etnaviv_iommu_context_free(struct kref *kref)
{
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 =
container_of(kref, struct etnaviv_iommu_context, refcount);
etnaviv_cmdbuf_suballoc_unmap(context, &context->cmdbuf_mapping);
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
context->global->ops->free(context);
}
void etnaviv_iommu_context_put(struct etnaviv_iommu_context *context)
{
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
kref_put(&context->refcount, etnaviv_iommu_context_free);
}
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 *
etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
struct etnaviv_cmdbuf_suballoc *suballoc)
{
struct etnaviv_iommu_context *ctx;
int ret;
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
if (global->version == ETNAVIV_IOMMU_V1)
ctx = etnaviv_iommuv1_context_alloc(global);
else
ctx = etnaviv_iommuv2_context_alloc(global);
if (!ctx)
return NULL;
ret = etnaviv_cmdbuf_suballoc_map(suballoc, ctx, &ctx->cmdbuf_mapping,
global->memory_base);
if (ret) {
global->ops->free(ctx);
return NULL;
}
return ctx;
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_iommu_restore(struct etnaviv_gpu *gpu,
struct etnaviv_iommu_context *context)
{
context->global->ops->restore(gpu, context);
}
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
int etnaviv_iommu_get_suballoc_va(struct etnaviv_iommu_context *context,
struct etnaviv_vram_mapping *mapping,
u32 memory_base, dma_addr_t paddr,
size_t size)
{
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
mutex_lock(&context->lock);
if (mapping->use > 0) {
mapping->use++;
mutex_unlock(&context->lock);
return 0;
}
/*
* For MMUv1 we don't add the suballoc region to the pagetables, as
* those GPUs can only work with cmdbufs accessed through the linear
* window. Instead we manufacture a mapping to make it look uniform
* to the upper layers.
*/
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
if (context->global->version == ETNAVIV_IOMMU_V1) {
mapping->iova = paddr - memory_base;
} else {
struct drm_mm_node *node = &mapping->vram_node;
int ret;
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
ret = etnaviv_iommu_find_iova(context, node, size);
if (ret < 0) {
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
mutex_unlock(&context->lock);
return ret;
}
mapping->iova = node->start;
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
ret = etnaviv_context_map(context, node->start, paddr, size,
ETNAVIV_PROT_READ);
if (ret < 0) {
drm_mm_remove_node(node);
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
mutex_unlock(&context->lock);
return ret;
}
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
context->flush_seq++;
}
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
list_add_tail(&mapping->mmu_node, &context->mappings);
mapping->use = 1;
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
mutex_unlock(&context->lock);
return 0;
}
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_iommu_put_suballoc_va(struct etnaviv_iommu_context *context,
struct etnaviv_vram_mapping *mapping)
{
struct drm_mm_node *node = &mapping->vram_node;
mutex_lock(&context->lock);
mapping->use--;
if (mapping->use > 0 || context->global->version == ETNAVIV_IOMMU_V1) {
mutex_unlock(&context->lock);
return;
}
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
etnaviv_context_unmap(context, node->start, node->size);
drm_mm_remove_node(node);
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
mutex_unlock(&context->lock);
}
size_t etnaviv_iommu_dump_size(struct etnaviv_iommu_context *context)
{
return context->global->ops->dump_size(context);
}
void etnaviv_iommu_dump(struct etnaviv_iommu_context *context, void *buf)
{
context->global->ops->dump(context, buf);
}
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
int etnaviv_iommu_global_init(struct etnaviv_gpu *gpu)
{
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
enum etnaviv_iommu_version version = ETNAVIV_IOMMU_V1;
struct etnaviv_drm_private *priv = gpu->drm->dev_private;
struct etnaviv_iommu_global *global;
struct device *dev = gpu->drm->dev;
if (gpu->identity.minor_features1 & chipMinorFeatures1_MMU_VERSION)
version = ETNAVIV_IOMMU_V2;
if (priv->mmu_global) {
if (priv->mmu_global->version != version) {
dev_err(gpu->dev,
"MMU version doesn't match global version\n");
return -ENXIO;
}
priv->mmu_global->use++;
return 0;
}
global = kzalloc(sizeof(*global), GFP_KERNEL);
if (!global)
return -ENOMEM;
global->bad_page_cpu = dma_alloc_wc(dev, SZ_4K, &global->bad_page_dma,
GFP_KERNEL);
if (!global->bad_page_cpu)
goto free_global;
memset32(global->bad_page_cpu, 0xdead55aa, SZ_4K / sizeof(u32));
if (version == ETNAVIV_IOMMU_V2) {
global->v2.pta_cpu = dma_alloc_wc(dev, ETNAVIV_PTA_SIZE,
&global->v2.pta_dma, GFP_KERNEL);
if (!global->v2.pta_cpu)
goto free_bad_page;
}
global->dev = dev;
global->version = version;
global->use = 1;
mutex_init(&global->lock);
if (version == ETNAVIV_IOMMU_V1)
global->ops = &etnaviv_iommuv1_ops;
else
global->ops = &etnaviv_iommuv2_ops;
priv->mmu_global = global;
return 0;
free_bad_page:
dma_free_wc(dev, SZ_4K, global->bad_page_cpu, global->bad_page_dma);
free_global:
kfree(global);
return -ENOMEM;
}
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_iommu_global_fini(struct etnaviv_gpu *gpu)
{
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_drm_private *priv = gpu->drm->dev_private;
struct etnaviv_iommu_global *global = priv->mmu_global;
if (--global->use > 0)
return;
if (global->v2.pta_cpu)
dma_free_wc(global->dev, ETNAVIV_PTA_SIZE,
global->v2.pta_cpu, global->v2.pta_dma);
if (global->bad_page_cpu)
dma_free_wc(global->dev, SZ_4K,
global->bad_page_cpu, global->bad_page_dma);
mutex_destroy(&global->lock);
kfree(global);
priv->mmu_global = NULL;
}