drm/vmwgfx: Use the linux DMA api to get valid device addresses of pages
The code handles three different cases: 1) physical page addresses. The ttm page array is used. 2) DMA subsystem addresses. A scatter-gather list is used. 3) Coherent pages. The ttm dma pool is used, together with the dma_ttm array os dma_addr_t Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
This commit is contained in:
Thomas Hellstrom
parent
7aeb7448d8
commit
d92d985177
|
|
@ -141,37 +141,374 @@ struct ttm_placement vmw_srf_placement = {
|
|||
};
|
||||
|
||||
struct vmw_ttm_tt {
|
||||
struct ttm_tt ttm;
|
||||
struct ttm_dma_tt dma_ttm;
|
||||
struct vmw_private *dev_priv;
|
||||
int gmr_id;
|
||||
struct sg_table sgt;
|
||||
struct vmw_sg_table vsgt;
|
||||
uint64_t sg_alloc_size;
|
||||
bool mapped;
|
||||
};
|
||||
|
||||
/**
|
||||
* Helper functions to advance a struct vmw_piter iterator.
|
||||
*
|
||||
* @viter: Pointer to the iterator.
|
||||
*
|
||||
* These functions return false if past the end of the list,
|
||||
* true otherwise. Functions are selected depending on the current
|
||||
* DMA mapping mode.
|
||||
*/
|
||||
static bool __vmw_piter_non_sg_next(struct vmw_piter *viter)
|
||||
{
|
||||
return ++(viter->i) < viter->num_pages;
|
||||
}
|
||||
|
||||
static bool __vmw_piter_sg_next(struct vmw_piter *viter)
|
||||
{
|
||||
return __sg_page_iter_next(&viter->iter);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Helper functions to return a pointer to the current page.
|
||||
*
|
||||
* @viter: Pointer to the iterator
|
||||
*
|
||||
* These functions return a pointer to the page currently
|
||||
* pointed to by @viter. Functions are selected depending on the
|
||||
* current mapping mode.
|
||||
*/
|
||||
static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter)
|
||||
{
|
||||
return viter->pages[viter->i];
|
||||
}
|
||||
|
||||
static struct page *__vmw_piter_sg_page(struct vmw_piter *viter)
|
||||
{
|
||||
return sg_page_iter_page(&viter->iter);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Helper functions to return the DMA address of the current page.
|
||||
*
|
||||
* @viter: Pointer to the iterator
|
||||
*
|
||||
* These functions return the DMA address of the page currently
|
||||
* pointed to by @viter. Functions are selected depending on the
|
||||
* current mapping mode.
|
||||
*/
|
||||
static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter)
|
||||
{
|
||||
return page_to_phys(viter->pages[viter->i]);
|
||||
}
|
||||
|
||||
static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
|
||||
{
|
||||
return viter->addrs[viter->i];
|
||||
}
|
||||
|
||||
static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter)
|
||||
{
|
||||
return sg_page_iter_dma_address(&viter->iter);
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* vmw_piter_start - Initialize a struct vmw_piter.
|
||||
*
|
||||
* @viter: Pointer to the iterator to initialize
|
||||
* @vsgt: Pointer to a struct vmw_sg_table to initialize from
|
||||
*
|
||||
* Note that we're following the convention of __sg_page_iter_start, so that
|
||||
* the iterator doesn't point to a valid page after initialization; it has
|
||||
* to be advanced one step first.
|
||||
*/
|
||||
void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
|
||||
unsigned long p_offset)
|
||||
{
|
||||
viter->i = p_offset - 1;
|
||||
viter->num_pages = vsgt->num_pages;
|
||||
switch (vsgt->mode) {
|
||||
case vmw_dma_phys:
|
||||
viter->next = &__vmw_piter_non_sg_next;
|
||||
viter->dma_address = &__vmw_piter_phys_addr;
|
||||
viter->page = &__vmw_piter_non_sg_page;
|
||||
viter->pages = vsgt->pages;
|
||||
break;
|
||||
case vmw_dma_alloc_coherent:
|
||||
viter->next = &__vmw_piter_non_sg_next;
|
||||
viter->dma_address = &__vmw_piter_dma_addr;
|
||||
viter->page = &__vmw_piter_non_sg_page;
|
||||
viter->addrs = vsgt->addrs;
|
||||
break;
|
||||
case vmw_dma_map_populate:
|
||||
case vmw_dma_map_bind:
|
||||
viter->next = &__vmw_piter_sg_next;
|
||||
viter->dma_address = &__vmw_piter_sg_addr;
|
||||
viter->page = &__vmw_piter_sg_page;
|
||||
__sg_page_iter_start(&viter->iter, vsgt->sgt->sgl,
|
||||
vsgt->sgt->orig_nents, p_offset);
|
||||
break;
|
||||
default:
|
||||
BUG();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_ttm_unmap_from_dma - unmap device addresses previsouly mapped for
|
||||
* TTM pages
|
||||
*
|
||||
* @vmw_tt: Pointer to a struct vmw_ttm_backend
|
||||
*
|
||||
* Used to free dma mappings previously mapped by vmw_ttm_map_for_dma.
|
||||
*/
|
||||
static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt)
|
||||
{
|
||||
struct device *dev = vmw_tt->dev_priv->dev->dev;
|
||||
|
||||
dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents,
|
||||
DMA_BIDIRECTIONAL);
|
||||
vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents;
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_ttm_map_for_dma - map TTM pages to get device addresses
|
||||
*
|
||||
* @vmw_tt: Pointer to a struct vmw_ttm_backend
|
||||
*
|
||||
* This function is used to get device addresses from the kernel DMA layer.
|
||||
* However, it's violating the DMA API in that when this operation has been
|
||||
* performed, it's illegal for the CPU to write to the pages without first
|
||||
* unmapping the DMA mappings, or calling dma_sync_sg_for_cpu(). It is
|
||||
* therefore only legal to call this function if we know that the function
|
||||
* dma_sync_sg_for_cpu() is a NOP, and dma_sync_sg_for_device() is at most
|
||||
* a CPU write buffer flush.
|
||||
*/
|
||||
static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt)
|
||||
{
|
||||
struct device *dev = vmw_tt->dev_priv->dev->dev;
|
||||
int ret;
|
||||
|
||||
ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents,
|
||||
DMA_BIDIRECTIONAL);
|
||||
if (unlikely(ret == 0))
|
||||
return -ENOMEM;
|
||||
|
||||
vmw_tt->sgt.nents = ret;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_ttm_map_dma - Make sure TTM pages are visible to the device
|
||||
*
|
||||
* @vmw_tt: Pointer to a struct vmw_ttm_tt
|
||||
*
|
||||
* Select the correct function for and make sure the TTM pages are
|
||||
* visible to the device. Allocate storage for the device mappings.
|
||||
* If a mapping has already been performed, indicated by the storage
|
||||
* pointer being non NULL, the function returns success.
|
||||
*/
|
||||
static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
|
||||
{
|
||||
struct vmw_private *dev_priv = vmw_tt->dev_priv;
|
||||
struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
|
||||
struct vmw_sg_table *vsgt = &vmw_tt->vsgt;
|
||||
struct vmw_piter iter;
|
||||
dma_addr_t old;
|
||||
int ret = 0;
|
||||
static size_t sgl_size;
|
||||
static size_t sgt_size;
|
||||
|
||||
if (vmw_tt->mapped)
|
||||
return 0;
|
||||
|
||||
vsgt->mode = dev_priv->map_mode;
|
||||
vsgt->pages = vmw_tt->dma_ttm.ttm.pages;
|
||||
vsgt->num_pages = vmw_tt->dma_ttm.ttm.num_pages;
|
||||
vsgt->addrs = vmw_tt->dma_ttm.dma_address;
|
||||
vsgt->sgt = &vmw_tt->sgt;
|
||||
|
||||
switch (dev_priv->map_mode) {
|
||||
case vmw_dma_map_bind:
|
||||
case vmw_dma_map_populate:
|
||||
if (unlikely(!sgl_size)) {
|
||||
sgl_size = ttm_round_pot(sizeof(struct scatterlist));
|
||||
sgt_size = ttm_round_pot(sizeof(struct sg_table));
|
||||
}
|
||||
vmw_tt->sg_alloc_size = sgt_size + sgl_size * vsgt->num_pages;
|
||||
ret = ttm_mem_global_alloc(glob, vmw_tt->sg_alloc_size, false,
|
||||
true);
|
||||
if (unlikely(ret != 0))
|
||||
return ret;
|
||||
|
||||
ret = sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
|
||||
vsgt->num_pages, 0,
|
||||
(unsigned long)
|
||||
vsgt->num_pages << PAGE_SHIFT,
|
||||
GFP_KERNEL);
|
||||
if (unlikely(ret != 0))
|
||||
goto out_sg_alloc_fail;
|
||||
|
||||
if (vsgt->num_pages > vmw_tt->sgt.nents) {
|
||||
uint64_t over_alloc =
|
||||
sgl_size * (vsgt->num_pages -
|
||||
vmw_tt->sgt.nents);
|
||||
|
||||
ttm_mem_global_free(glob, over_alloc);
|
||||
vmw_tt->sg_alloc_size -= over_alloc;
|
||||
}
|
||||
|
||||
ret = vmw_ttm_map_for_dma(vmw_tt);
|
||||
if (unlikely(ret != 0))
|
||||
goto out_map_fail;
|
||||
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
old = ~((dma_addr_t) 0);
|
||||
vmw_tt->vsgt.num_regions = 0;
|
||||
for (vmw_piter_start(&iter, vsgt, 0); vmw_piter_next(&iter);) {
|
||||
dma_addr_t cur = vmw_piter_dma_addr(&iter);
|
||||
|
||||
if (cur != old + PAGE_SIZE)
|
||||
vmw_tt->vsgt.num_regions++;
|
||||
old = cur;
|
||||
}
|
||||
|
||||
vmw_tt->mapped = true;
|
||||
return 0;
|
||||
|
||||
out_map_fail:
|
||||
sg_free_table(vmw_tt->vsgt.sgt);
|
||||
vmw_tt->vsgt.sgt = NULL;
|
||||
out_sg_alloc_fail:
|
||||
ttm_mem_global_free(glob, vmw_tt->sg_alloc_size);
|
||||
return ret;
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_ttm_unmap_dma - Tear down any TTM page device mappings
|
||||
*
|
||||
* @vmw_tt: Pointer to a struct vmw_ttm_tt
|
||||
*
|
||||
* Tear down any previously set up device DMA mappings and free
|
||||
* any storage space allocated for them. If there are no mappings set up,
|
||||
* this function is a NOP.
|
||||
*/
|
||||
static void vmw_ttm_unmap_dma(struct vmw_ttm_tt *vmw_tt)
|
||||
{
|
||||
struct vmw_private *dev_priv = vmw_tt->dev_priv;
|
||||
|
||||
if (!vmw_tt->vsgt.sgt)
|
||||
return;
|
||||
|
||||
switch (dev_priv->map_mode) {
|
||||
case vmw_dma_map_bind:
|
||||
case vmw_dma_map_populate:
|
||||
vmw_ttm_unmap_from_dma(vmw_tt);
|
||||
sg_free_table(vmw_tt->vsgt.sgt);
|
||||
vmw_tt->vsgt.sgt = NULL;
|
||||
ttm_mem_global_free(vmw_mem_glob(dev_priv),
|
||||
vmw_tt->sg_alloc_size);
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
vmw_tt->mapped = false;
|
||||
}
|
||||
|
||||
static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
|
||||
{
|
||||
struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, ttm);
|
||||
struct vmw_ttm_tt *vmw_be =
|
||||
container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
|
||||
int ret;
|
||||
|
||||
ret = vmw_ttm_map_dma(vmw_be);
|
||||
if (unlikely(ret != 0))
|
||||
return ret;
|
||||
|
||||
vmw_be->gmr_id = bo_mem->start;
|
||||
|
||||
return vmw_gmr_bind(vmw_be->dev_priv, ttm->pages,
|
||||
return vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt,
|
||||
ttm->num_pages, vmw_be->gmr_id);
|
||||
}
|
||||
|
||||
static int vmw_ttm_unbind(struct ttm_tt *ttm)
|
||||
{
|
||||
struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, ttm);
|
||||
struct vmw_ttm_tt *vmw_be =
|
||||
container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
|
||||
|
||||
vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id);
|
||||
|
||||
if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind)
|
||||
vmw_ttm_unmap_dma(vmw_be);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void vmw_ttm_destroy(struct ttm_tt *ttm)
|
||||
{
|
||||
struct vmw_ttm_tt *vmw_be = container_of(ttm, struct vmw_ttm_tt, ttm);
|
||||
struct vmw_ttm_tt *vmw_be =
|
||||
container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
|
||||
|
||||
ttm_tt_fini(ttm);
|
||||
vmw_ttm_unmap_dma(vmw_be);
|
||||
if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
|
||||
ttm_dma_tt_fini(&vmw_be->dma_ttm);
|
||||
else
|
||||
ttm_tt_fini(ttm);
|
||||
kfree(vmw_be);
|
||||
}
|
||||
|
||||
static int vmw_ttm_populate(struct ttm_tt *ttm)
|
||||
{
|
||||
struct vmw_ttm_tt *vmw_tt =
|
||||
container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
|
||||
struct vmw_private *dev_priv = vmw_tt->dev_priv;
|
||||
struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
|
||||
int ret;
|
||||
|
||||
if (ttm->state != tt_unpopulated)
|
||||
return 0;
|
||||
|
||||
if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
|
||||
size_t size =
|
||||
ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t));
|
||||
ret = ttm_mem_global_alloc(glob, size, false, true);
|
||||
if (unlikely(ret != 0))
|
||||
return ret;
|
||||
|
||||
ret = ttm_dma_populate(&vmw_tt->dma_ttm, dev_priv->dev->dev);
|
||||
if (unlikely(ret != 0))
|
||||
ttm_mem_global_free(glob, size);
|
||||
} else
|
||||
ret = ttm_pool_populate(ttm);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
static void vmw_ttm_unpopulate(struct ttm_tt *ttm)
|
||||
{
|
||||
struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
|
||||
dma_ttm.ttm);
|
||||
struct vmw_private *dev_priv = vmw_tt->dev_priv;
|
||||
struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
|
||||
|
||||
vmw_ttm_unmap_dma(vmw_tt);
|
||||
if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
|
||||
size_t size =
|
||||
ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t));
|
||||
|
||||
ttm_dma_unpopulate(&vmw_tt->dma_ttm, dev_priv->dev->dev);
|
||||
ttm_mem_global_free(glob, size);
|
||||
} else
|
||||
ttm_pool_unpopulate(ttm);
|
||||
}
|
||||
|
||||
static struct ttm_backend_func vmw_ttm_func = {
|
||||
.bind = vmw_ttm_bind,
|
||||
.unbind = vmw_ttm_unbind,
|
||||
|
|
@ -183,20 +520,28 @@ struct ttm_tt *vmw_ttm_tt_create(struct ttm_bo_device *bdev,
|
|||
struct page *dummy_read_page)
|
||||
{
|
||||
struct vmw_ttm_tt *vmw_be;
|
||||
int ret;
|
||||
|
||||
vmw_be = kmalloc(sizeof(*vmw_be), GFP_KERNEL);
|
||||
vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL);
|
||||
if (!vmw_be)
|
||||
return NULL;
|
||||
|
||||
vmw_be->ttm.func = &vmw_ttm_func;
|
||||
vmw_be->dma_ttm.ttm.func = &vmw_ttm_func;
|
||||
vmw_be->dev_priv = container_of(bdev, struct vmw_private, bdev);
|
||||
|
||||
if (ttm_tt_init(&vmw_be->ttm, bdev, size, page_flags, dummy_read_page)) {
|
||||
kfree(vmw_be);
|
||||
return NULL;
|
||||
}
|
||||
if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
|
||||
ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bdev, size, page_flags,
|
||||
dummy_read_page);
|
||||
else
|
||||
ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bdev, size, page_flags,
|
||||
dummy_read_page);
|
||||
if (unlikely(ret != 0))
|
||||
goto out_no_init;
|
||||
|
||||
return &vmw_be->ttm;
|
||||
return &vmw_be->dma_ttm.ttm;
|
||||
out_no_init:
|
||||
kfree(vmw_be);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
|
||||
|
|
@ -332,8 +677,8 @@ static int vmw_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
|
|||
|
||||
struct ttm_bo_driver vmw_bo_driver = {
|
||||
.ttm_tt_create = &vmw_ttm_tt_create,
|
||||
.ttm_tt_populate = &ttm_pool_populate,
|
||||
.ttm_tt_unpopulate = &ttm_pool_unpopulate,
|
||||
.ttm_tt_populate = &vmw_ttm_populate,
|
||||
.ttm_tt_unpopulate = &vmw_ttm_unpopulate,
|
||||
.invalidate_caches = vmw_invalidate_caches,
|
||||
.init_mem_type = vmw_init_mem_type,
|
||||
.evict_flags = vmw_evict_flags,
|
||||
|
|
|
|||
|
|
@ -32,6 +32,7 @@
|
|||
#include <drm/ttm/ttm_bo_driver.h>
|
||||
#include <drm/ttm/ttm_object.h>
|
||||
#include <drm/ttm/ttm_module.h>
|
||||
#include <linux/dma_remapping.h>
|
||||
|
||||
#define VMWGFX_DRIVER_NAME "vmwgfx"
|
||||
#define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices"
|
||||
|
|
@ -185,6 +186,9 @@ static struct pci_device_id vmw_pci_id_list[] = {
|
|||
MODULE_DEVICE_TABLE(pci, vmw_pci_id_list);
|
||||
|
||||
static int enable_fbdev = IS_ENABLED(CONFIG_DRM_VMWGFX_FBCON);
|
||||
static int vmw_force_iommu;
|
||||
static int vmw_restrict_iommu;
|
||||
static int vmw_force_coherent;
|
||||
|
||||
static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
|
||||
static void vmw_master_init(struct vmw_master *);
|
||||
|
|
@ -193,6 +197,13 @@ static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
|
|||
|
||||
MODULE_PARM_DESC(enable_fbdev, "Enable vmwgfx fbdev");
|
||||
module_param_named(enable_fbdev, enable_fbdev, int, 0600);
|
||||
MODULE_PARM_DESC(force_dma_api, "Force using the DMA API for TTM pages");
|
||||
module_param_named(force_dma_api, vmw_force_iommu, int, 0600);
|
||||
MODULE_PARM_DESC(restrict_iommu, "Try to limit IOMMU usage for TTM pages");
|
||||
module_param_named(restrict_iommu, vmw_restrict_iommu, int, 0600);
|
||||
MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages");
|
||||
module_param_named(force_coherent, vmw_force_coherent, int, 0600);
|
||||
|
||||
|
||||
static void vmw_print_capabilities(uint32_t capabilities)
|
||||
{
|
||||
|
|
@ -427,12 +438,78 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv)
|
|||
dev_priv->initial_height = height;
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_dma_select_mode - Determine how DMA mappings should be set up for this
|
||||
* system.
|
||||
*
|
||||
* @dev_priv: Pointer to a struct vmw_private
|
||||
*
|
||||
* This functions tries to determine the IOMMU setup and what actions
|
||||
* need to be taken by the driver to make system pages visible to the
|
||||
* device.
|
||||
* If this function decides that DMA is not possible, it returns -EINVAL.
|
||||
* The driver may then try to disable features of the device that require
|
||||
* DMA.
|
||||
*/
|
||||
static int vmw_dma_select_mode(struct vmw_private *dev_priv)
|
||||
{
|
||||
const struct dma_map_ops *dma_ops = get_dma_ops(dev_priv->dev->dev);
|
||||
static const char *names[vmw_dma_map_max] = {
|
||||
[vmw_dma_phys] = "Using physical TTM page addresses.",
|
||||
[vmw_dma_alloc_coherent] = "Using coherent TTM pages.",
|
||||
[vmw_dma_map_populate] = "Keeping DMA mappings.",
|
||||
[vmw_dma_map_bind] = "Giving up DMA mappings early."};
|
||||
|
||||
#ifdef CONFIG_INTEL_IOMMU
|
||||
if (intel_iommu_enabled) {
|
||||
dev_priv->map_mode = vmw_dma_map_populate;
|
||||
goto out_fixup;
|
||||
}
|
||||
#endif
|
||||
|
||||
if (!(vmw_force_iommu || vmw_force_coherent)) {
|
||||
dev_priv->map_mode = vmw_dma_phys;
|
||||
DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]);
|
||||
return 0;
|
||||
}
|
||||
|
||||
dev_priv->map_mode = vmw_dma_map_populate;
|
||||
|
||||
if (dma_ops->sync_single_for_cpu)
|
||||
dev_priv->map_mode = vmw_dma_alloc_coherent;
|
||||
#ifdef CONFIG_SWIOTLB
|
||||
if (swiotlb_nr_tbl() == 0)
|
||||
dev_priv->map_mode = vmw_dma_map_populate;
|
||||
#endif
|
||||
|
||||
out_fixup:
|
||||
if (dev_priv->map_mode == vmw_dma_map_populate &&
|
||||
vmw_restrict_iommu)
|
||||
dev_priv->map_mode = vmw_dma_map_bind;
|
||||
|
||||
if (vmw_force_coherent)
|
||||
dev_priv->map_mode = vmw_dma_alloc_coherent;
|
||||
|
||||
#if !defined(CONFIG_SWIOTLB) && !defined(CONFIG_INTEL_IOMMU)
|
||||
/*
|
||||
* No coherent page pool
|
||||
*/
|
||||
if (dev_priv->map_mode == vmw_dma_alloc_coherent)
|
||||
return -EINVAL;
|
||||
#endif
|
||||
|
||||
DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
|
||||
{
|
||||
struct vmw_private *dev_priv;
|
||||
int ret;
|
||||
uint32_t svga_id;
|
||||
enum vmw_res_type i;
|
||||
bool refuse_dma = false;
|
||||
|
||||
dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL);
|
||||
if (unlikely(dev_priv == NULL)) {
|
||||
|
|
@ -481,6 +558,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
|
|||
}
|
||||
|
||||
dev_priv->capabilities = vmw_read(dev_priv, SVGA_REG_CAPABILITIES);
|
||||
ret = vmw_dma_select_mode(dev_priv);
|
||||
if (unlikely(ret != 0)) {
|
||||
DRM_INFO("Restricting capabilities due to IOMMU setup.\n");
|
||||
refuse_dma = true;
|
||||
}
|
||||
|
||||
dev_priv->vram_size = vmw_read(dev_priv, SVGA_REG_VRAM_SIZE);
|
||||
dev_priv->mmio_size = vmw_read(dev_priv, SVGA_REG_MEM_SIZE);
|
||||
|
|
@ -558,8 +640,9 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
|
|||
}
|
||||
|
||||
dev_priv->has_gmr = true;
|
||||
if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR,
|
||||
dev_priv->max_gmr_ids) != 0) {
|
||||
if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) ||
|
||||
refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR,
|
||||
dev_priv->max_gmr_ids) != 0) {
|
||||
DRM_INFO("No GMR memory available. "
|
||||
"Graphics memory resources are very limited.\n");
|
||||
dev_priv->has_gmr = false;
|
||||
|
|
|
|||
|
|
@ -177,6 +177,58 @@ struct vmw_res_cache_entry {
|
|||
struct vmw_resource_val_node *node;
|
||||
};
|
||||
|
||||
/**
|
||||
* enum vmw_dma_map_mode - indicate how to perform TTM page dma mappings.
|
||||
*/
|
||||
enum vmw_dma_map_mode {
|
||||
vmw_dma_phys, /* Use physical page addresses */
|
||||
vmw_dma_alloc_coherent, /* Use TTM coherent pages */
|
||||
vmw_dma_map_populate, /* Unmap from DMA just after unpopulate */
|
||||
vmw_dma_map_bind, /* Unmap from DMA just before unbind */
|
||||
vmw_dma_map_max
|
||||
};
|
||||
|
||||
/**
|
||||
* struct vmw_sg_table - Scatter/gather table for binding, with additional
|
||||
* device-specific information.
|
||||
*
|
||||
* @sgt: Pointer to a struct sg_table with binding information
|
||||
* @num_regions: Number of regions with device-address contigous pages
|
||||
*/
|
||||
struct vmw_sg_table {
|
||||
enum vmw_dma_map_mode mode;
|
||||
struct page **pages;
|
||||
const dma_addr_t *addrs;
|
||||
struct sg_table *sgt;
|
||||
unsigned long num_regions;
|
||||
unsigned long num_pages;
|
||||
};
|
||||
|
||||
/**
|
||||
* struct vmw_piter - Page iterator that iterates over a list of pages
|
||||
* and DMA addresses that could be either a scatter-gather list or
|
||||
* arrays
|
||||
*
|
||||
* @pages: Array of page pointers to the pages.
|
||||
* @addrs: DMA addresses to the pages if coherent pages are used.
|
||||
* @iter: Scatter-gather page iterator. Current position in SG list.
|
||||
* @i: Current position in arrays.
|
||||
* @num_pages: Number of pages total.
|
||||
* @next: Function to advance the iterator. Returns false if past the list
|
||||
* of pages, true otherwise.
|
||||
* @dma_address: Function to return the DMA address of the current page.
|
||||
*/
|
||||
struct vmw_piter {
|
||||
struct page **pages;
|
||||
const dma_addr_t *addrs;
|
||||
struct sg_page_iter iter;
|
||||
unsigned long i;
|
||||
unsigned long num_pages;
|
||||
bool (*next)(struct vmw_piter *);
|
||||
dma_addr_t (*dma_address)(struct vmw_piter *);
|
||||
struct page *(*page)(struct vmw_piter *);
|
||||
};
|
||||
|
||||
struct vmw_sw_context{
|
||||
struct drm_open_hash res_ht;
|
||||
bool res_ht_initialized;
|
||||
|
|
@ -358,6 +410,11 @@ struct vmw_private {
|
|||
|
||||
struct list_head res_lru[vmw_res_max];
|
||||
uint32_t used_memory_size;
|
||||
|
||||
/*
|
||||
* DMA mapping stuff.
|
||||
*/
|
||||
enum vmw_dma_map_mode map_mode;
|
||||
};
|
||||
|
||||
static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res)
|
||||
|
|
@ -405,7 +462,7 @@ void vmw_3d_resource_dec(struct vmw_private *dev_priv, bool hide_svga);
|
|||
*/
|
||||
|
||||
extern int vmw_gmr_bind(struct vmw_private *dev_priv,
|
||||
struct page *pages[],
|
||||
const struct vmw_sg_table *vsgt,
|
||||
unsigned long num_pages,
|
||||
int gmr_id);
|
||||
extern void vmw_gmr_unbind(struct vmw_private *dev_priv, int gmr_id);
|
||||
|
|
@ -568,6 +625,45 @@ extern struct ttm_placement vmw_evictable_placement;
|
|||
extern struct ttm_placement vmw_srf_placement;
|
||||
extern struct ttm_bo_driver vmw_bo_driver;
|
||||
extern int vmw_dma_quiescent(struct drm_device *dev);
|
||||
extern void vmw_piter_start(struct vmw_piter *viter,
|
||||
const struct vmw_sg_table *vsgt,
|
||||
unsigned long p_offs);
|
||||
|
||||
/**
|
||||
* vmw_piter_next - Advance the iterator one page.
|
||||
*
|
||||
* @viter: Pointer to the iterator to advance.
|
||||
*
|
||||
* Returns false if past the list of pages, true otherwise.
|
||||
*/
|
||||
static inline bool vmw_piter_next(struct vmw_piter *viter)
|
||||
{
|
||||
return viter->next(viter);
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_piter_dma_addr - Return the DMA address of the current page.
|
||||
*
|
||||
* @viter: Pointer to the iterator
|
||||
*
|
||||
* Returns the DMA address of the page pointed to by @viter.
|
||||
*/
|
||||
static inline dma_addr_t vmw_piter_dma_addr(struct vmw_piter *viter)
|
||||
{
|
||||
return viter->dma_address(viter);
|
||||
}
|
||||
|
||||
/**
|
||||
* vmw_piter_page - Return a pointer to the current page.
|
||||
*
|
||||
* @viter: Pointer to the iterator
|
||||
*
|
||||
* Returns the DMA address of the page pointed to by @viter.
|
||||
*/
|
||||
static inline struct page *vmw_piter_page(struct vmw_piter *viter)
|
||||
{
|
||||
return viter->page(viter);
|
||||
}
|
||||
|
||||
/**
|
||||
* Command submission - vmwgfx_execbuf.c
|
||||
|
|
|
|||
|
|
@ -32,9 +32,11 @@
|
|||
#define VMW_PPN_SIZE (sizeof(unsigned long))
|
||||
/* A future safe maximum remap size. */
|
||||
#define VMW_PPN_PER_REMAP ((31 * 1024) / VMW_PPN_SIZE)
|
||||
#define DMA_ADDR_INVALID ((dma_addr_t) 0)
|
||||
#define DMA_PAGE_INVALID 0UL
|
||||
|
||||
static int vmw_gmr2_bind(struct vmw_private *dev_priv,
|
||||
struct page *pages[],
|
||||
struct vmw_piter *iter,
|
||||
unsigned long num_pages,
|
||||
int gmr_id)
|
||||
{
|
||||
|
|
@ -81,11 +83,13 @@ static int vmw_gmr2_bind(struct vmw_private *dev_priv,
|
|||
|
||||
for (i = 0; i < nr; ++i) {
|
||||
if (VMW_PPN_SIZE <= 4)
|
||||
*cmd = page_to_pfn(*pages++);
|
||||
*cmd = vmw_piter_dma_addr(iter) >> PAGE_SHIFT;
|
||||
else
|
||||
*((uint64_t *)cmd) = page_to_pfn(*pages++);
|
||||
*((uint64_t *)cmd) = vmw_piter_dma_addr(iter) >>
|
||||
PAGE_SHIFT;
|
||||
|
||||
cmd += VMW_PPN_SIZE / sizeof(*cmd);
|
||||
vmw_piter_next(iter);
|
||||
}
|
||||
|
||||
num_pages -= nr;
|
||||
|
|
@ -120,22 +124,54 @@ static void vmw_gmr2_unbind(struct vmw_private *dev_priv,
|
|||
vmw_fifo_commit(dev_priv, define_size);
|
||||
}
|
||||
|
||||
|
||||
static void vmw_gmr_free_descriptors(struct device *dev, dma_addr_t desc_dma,
|
||||
struct list_head *desc_pages)
|
||||
{
|
||||
struct page *page, *next;
|
||||
struct svga_guest_mem_descriptor *page_virtual;
|
||||
unsigned int desc_per_page = PAGE_SIZE /
|
||||
sizeof(struct svga_guest_mem_descriptor) - 1;
|
||||
|
||||
if (list_empty(desc_pages))
|
||||
return;
|
||||
|
||||
list_for_each_entry_safe(page, next, desc_pages, lru) {
|
||||
list_del_init(&page->lru);
|
||||
|
||||
if (likely(desc_dma != DMA_ADDR_INVALID)) {
|
||||
dma_unmap_page(dev, desc_dma, PAGE_SIZE,
|
||||
DMA_TO_DEVICE);
|
||||
}
|
||||
|
||||
page_virtual = kmap_atomic(page);
|
||||
desc_dma = page_virtual[desc_per_page].ppn << PAGE_SHIFT;
|
||||
kunmap_atomic(page_virtual);
|
||||
|
||||
__free_page(page);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* FIXME: Adjust to the ttm lowmem / highmem storage to minimize
|
||||
* the number of used descriptors.
|
||||
*
|
||||
*/
|
||||
|
||||
static int vmw_gmr_build_descriptors(struct list_head *desc_pages,
|
||||
struct page *pages[],
|
||||
unsigned long num_pages)
|
||||
static int vmw_gmr_build_descriptors(struct device *dev,
|
||||
struct list_head *desc_pages,
|
||||
struct vmw_piter *iter,
|
||||
unsigned long num_pages,
|
||||
dma_addr_t *first_dma)
|
||||
{
|
||||
struct page *page, *next;
|
||||
struct page *page;
|
||||
struct svga_guest_mem_descriptor *page_virtual = NULL;
|
||||
struct svga_guest_mem_descriptor *desc_virtual = NULL;
|
||||
unsigned int desc_per_page;
|
||||
unsigned long prev_pfn;
|
||||
unsigned long pfn;
|
||||
int ret;
|
||||
dma_addr_t desc_dma;
|
||||
|
||||
desc_per_page = PAGE_SIZE /
|
||||
sizeof(struct svga_guest_mem_descriptor) - 1;
|
||||
|
|
@ -148,23 +184,12 @@ static int vmw_gmr_build_descriptors(struct list_head *desc_pages,
|
|||
}
|
||||
|
||||
list_add_tail(&page->lru, desc_pages);
|
||||
|
||||
/*
|
||||
* Point previous page terminating descriptor to this
|
||||
* page before unmapping it.
|
||||
*/
|
||||
|
||||
if (likely(page_virtual != NULL)) {
|
||||
desc_virtual->ppn = page_to_pfn(page);
|
||||
kunmap_atomic(page_virtual);
|
||||
}
|
||||
|
||||
page_virtual = kmap_atomic(page);
|
||||
desc_virtual = page_virtual - 1;
|
||||
prev_pfn = ~(0UL);
|
||||
|
||||
while (likely(num_pages != 0)) {
|
||||
pfn = page_to_pfn(*pages);
|
||||
pfn = vmw_piter_dma_addr(iter) >> PAGE_SHIFT;
|
||||
|
||||
if (pfn != prev_pfn + 1) {
|
||||
|
||||
|
|
@ -181,104 +206,81 @@ static int vmw_gmr_build_descriptors(struct list_head *desc_pages,
|
|||
}
|
||||
prev_pfn = pfn;
|
||||
--num_pages;
|
||||
++pages;
|
||||
vmw_piter_next(iter);
|
||||
}
|
||||
|
||||
(++desc_virtual)->ppn = cpu_to_le32(0);
|
||||
(++desc_virtual)->ppn = DMA_PAGE_INVALID;
|
||||
desc_virtual->num_pages = cpu_to_le32(0);
|
||||
kunmap_atomic(page_virtual);
|
||||
}
|
||||
|
||||
if (likely(page_virtual != NULL))
|
||||
desc_dma = 0;
|
||||
list_for_each_entry_reverse(page, desc_pages, lru) {
|
||||
page_virtual = kmap_atomic(page);
|
||||
page_virtual[desc_per_page].ppn = desc_dma >> PAGE_SHIFT;
|
||||
kunmap_atomic(page_virtual);
|
||||
desc_dma = dma_map_page(dev, page, 0, PAGE_SIZE,
|
||||
DMA_TO_DEVICE);
|
||||
|
||||
if (unlikely(dma_mapping_error(dev, desc_dma)))
|
||||
goto out_err;
|
||||
}
|
||||
*first_dma = desc_dma;
|
||||
|
||||
return 0;
|
||||
out_err:
|
||||
list_for_each_entry_safe(page, next, desc_pages, lru) {
|
||||
list_del_init(&page->lru);
|
||||
__free_page(page);
|
||||
}
|
||||
vmw_gmr_free_descriptors(dev, DMA_ADDR_INVALID, desc_pages);
|
||||
return ret;
|
||||
}
|
||||
|
||||
static inline void vmw_gmr_free_descriptors(struct list_head *desc_pages)
|
||||
{
|
||||
struct page *page, *next;
|
||||
|
||||
list_for_each_entry_safe(page, next, desc_pages, lru) {
|
||||
list_del_init(&page->lru);
|
||||
__free_page(page);
|
||||
}
|
||||
}
|
||||
|
||||
static void vmw_gmr_fire_descriptors(struct vmw_private *dev_priv,
|
||||
int gmr_id, struct list_head *desc_pages)
|
||||
int gmr_id, dma_addr_t desc_dma)
|
||||
{
|
||||
struct page *page;
|
||||
|
||||
if (unlikely(list_empty(desc_pages)))
|
||||
return;
|
||||
|
||||
page = list_entry(desc_pages->next, struct page, lru);
|
||||
|
||||
mutex_lock(&dev_priv->hw_mutex);
|
||||
|
||||
vmw_write(dev_priv, SVGA_REG_GMR_ID, gmr_id);
|
||||
wmb();
|
||||
vmw_write(dev_priv, SVGA_REG_GMR_DESCRIPTOR, page_to_pfn(page));
|
||||
vmw_write(dev_priv, SVGA_REG_GMR_DESCRIPTOR, desc_dma >> PAGE_SHIFT);
|
||||
mb();
|
||||
|
||||
mutex_unlock(&dev_priv->hw_mutex);
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* FIXME: Adjust to the ttm lowmem / highmem storage to minimize
|
||||
* the number of used descriptors.
|
||||
*/
|
||||
|
||||
static unsigned long vmw_gmr_count_descriptors(struct page *pages[],
|
||||
unsigned long num_pages)
|
||||
{
|
||||
unsigned long prev_pfn = ~(0UL);
|
||||
unsigned long pfn;
|
||||
unsigned long descriptors = 0;
|
||||
|
||||
while (num_pages--) {
|
||||
pfn = page_to_pfn(*pages++);
|
||||
if (prev_pfn + 1 != pfn)
|
||||
++descriptors;
|
||||
prev_pfn = pfn;
|
||||
}
|
||||
|
||||
return descriptors;
|
||||
}
|
||||
|
||||
int vmw_gmr_bind(struct vmw_private *dev_priv,
|
||||
struct page *pages[],
|
||||
const struct vmw_sg_table *vsgt,
|
||||
unsigned long num_pages,
|
||||
int gmr_id)
|
||||
{
|
||||
struct list_head desc_pages;
|
||||
dma_addr_t desc_dma = 0;
|
||||
struct device *dev = dev_priv->dev->dev;
|
||||
struct vmw_piter data_iter;
|
||||
int ret;
|
||||
|
||||
vmw_piter_start(&data_iter, vsgt, 0);
|
||||
|
||||
if (unlikely(!vmw_piter_next(&data_iter)))
|
||||
return 0;
|
||||
|
||||
if (likely(dev_priv->capabilities & SVGA_CAP_GMR2))
|
||||
return vmw_gmr2_bind(dev_priv, pages, num_pages, gmr_id);
|
||||
return vmw_gmr2_bind(dev_priv, &data_iter, num_pages, gmr_id);
|
||||
|
||||
if (unlikely(!(dev_priv->capabilities & SVGA_CAP_GMR)))
|
||||
return -EINVAL;
|
||||
|
||||
if (vmw_gmr_count_descriptors(pages, num_pages) >
|
||||
dev_priv->max_gmr_descriptors)
|
||||
if (vsgt->num_regions > dev_priv->max_gmr_descriptors)
|
||||
return -EINVAL;
|
||||
|
||||
INIT_LIST_HEAD(&desc_pages);
|
||||
|
||||
ret = vmw_gmr_build_descriptors(&desc_pages, pages, num_pages);
|
||||
ret = vmw_gmr_build_descriptors(dev, &desc_pages, &data_iter,
|
||||
num_pages, &desc_dma);
|
||||
if (unlikely(ret != 0))
|
||||
return ret;
|
||||
|
||||
vmw_gmr_fire_descriptors(dev_priv, gmr_id, &desc_pages);
|
||||
vmw_gmr_free_descriptors(&desc_pages);
|
||||
vmw_gmr_fire_descriptors(dev_priv, gmr_id, desc_dma);
|
||||
vmw_gmr_free_descriptors(dev, desc_dma, &desc_pages);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue