Used by the vmwgfx driver
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
In TTM world the pages for the graphic drivers are kept in three different
pools: write combined, uncached, and cached (write-back). When the pages
are used by the graphic driver the graphic adapter via its built in MMU
(or AGP) programs these pages in. The programming requires the virtual address
(from the graphic adapter perspective) and the physical address (either System RAM
or the memory on the card) which is obtained using the pci_map_* calls (which does the
virtual to physical - or bus address translation). During the graphic application's
"life" those pages can be shuffled around, swapped out to disk, moved from the
VRAM to System RAM or vice-versa. This all works with the existing TTM pool code
- except when we want to use the software IOTLB (SWIOTLB) code to "map" the physical
addresses to the graphic adapter MMU. We end up programming the bounce buffer's
physical address instead of the TTM pool memory's and get a non-worky driver.
There are two solutions:
1) using the DMA API to allocate pages that are screened by the DMA API, or
2) using the pci_sync_* calls to copy the pages from the bounce-buffer and back.
This patch fixes the issue by allocating pages using the DMA API. The second
is a viable option - but it has performance drawbacks and potential correctness
issues - think of the write cache page being bounced (SWIOTLB->TTM), the
WC is set on the TTM page and the copy from SWIOTLB not making it to the TTM
page until the page has been recycled in the pool (and used by another application).
The bounce buffer does not get activated often - only in cases where we have
a 32-bit capable card and we want to use a page that is allocated above the
4GB limit. The bounce buffer offers the solution of copying the contents
of that 4GB page to an location below 4GB and then back when the operation has been
completed (or vice-versa). This is done by using the 'pci_sync_*' calls.
Note: If you look carefully enough in the existing TTM page pool code you will
notice the GFP_DMA32 flag is used - which should guarantee that the provided page
is under 4GB. It certainly is the case, except this gets ignored in two cases:
- If user specifies 'swiotlb=force' which bounces _every_ page.
- If user is using a Xen's PV Linux guest (which uses the SWIOTLB and the
underlaying PFN's aren't necessarily under 4GB).
To not have this extra copying done the other option is to allocate the pages
using the DMA API so that there is not need to map the page and perform the
expensive 'pci_sync_*' calls.
This DMA API capable TTM pool requires for this the 'struct device' to
properly call the DMA API. It also has to track the virtual and bus address of
the page being handed out in case it ends up being swapped out or de-allocated -
to make sure it is de-allocated using the proper's 'struct device'.
Implementation wise the code keeps two lists: one that is attached to the
'struct device' (via the dev->dma_pools list) and a global one to be used when
the 'struct device' is unavailable (think shrinker code). The global list can
iterate over all of the 'struct device' and its associated dma_pool. The list
in dev->dma_pools can only iterate the device's dma_pool.
/[struct device_pool]\
/---------------------------------------------------| dev |
/ +-------| dma_pool |
/-----+------\ / \--------------------/
|struct device| /-->[struct dma_pool for WC]</ /[struct device_pool]\
| dma_pools +----+ /-| dev |
| ... | \--->[struct dma_pool for uncached]<-/--| dma_pool |
\-----+------/ / \--------------------/
\----------------------------------------------/
[Two pools associated with the device (WC and UC), and the parallel list
containing the 'struct dev' and 'struct dma_pool' entries]
The maximum amount of dma pools a device can have is six: write-combined,
uncached, and cached; then there are the DMA32 variants which are:
write-combined dma32, uncached dma32, and cached dma32.
Currently this code only gets activated when any variant of the SWIOTLB IOMMU
code is running (Intel without VT-d, AMD without GART, IBM Calgary and Xen PV
with PCI devices).
Tested-by: Michel Dänzer <michel@daenzer.net>
[v1: Using swiotlb_nr_tbl instead of swiotlb_enabled]
[v2: Major overhaul - added 'inuse_list' to seperate used from inuse and reorder
the order of lists to get better performance.]
[v3: Added comments/and some logic based on review, Added Jerome tag]
[v4: rebase on top of ttm_tt & ttm_backend merge]
[v5: rebase on top of ttm memory accounting overhaul]
[v6: New rebase on top of more memory accouting changes]
[v7: well rebase on top of no memory accounting changes]
[v8: make sure pages list is initialized empty]
[v9: calll ttm_mem_global_free_page in unpopulate for accurate accountg]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Acked-by: Thomas Hellstrom <thellstrom@vmware.com>
Nouveau will need this on GeForce 8 and up to account for the GPU
reordering physical VRAM for some memory types.
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Acked-by: Thomas Hellström <thellstrom@vmware.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
I wrote this for the prime sharing work, but I also noticed other external
non-upstream drivers from a large company carrying a similiar patch, so I
may as well ship it in master.
Signed-off-by: Dave Airlie <airlied@redhat.com>
On AGP system we might allocate/free routinely uncached or wc memory,
changing page from cached (wb) to uc or wc is very expensive and involves
a lot of flushing. To improve performance this allocator use a pool
of uc,wc pages.
Pools are protected with spinlocks to allow multiple threads to allocate pages
simultanously. Expensive operations are done outside of spinlock to maximize
concurrency.
Pools are linked lists of pages that were recently freed. mm shrink callback
allows kernel to claim back pages when they are required for something else.
Fixes:
* set_pages_array_wb handles highmem pages so we don't have to remove them
from pool.
* Add count parameter to ttm_put_pages to avoid looping in free code.
* Change looping from _safe to normal in pool fill error path.
* Initialize sum variable and make the loop prettier in get_num_unused_pages.
* Moved pages_freed reseting inside the loop in ttm_page_pool_free.
* Add warning comment about spinlock context in ttm_page_pool_free.
Based on Jerome Glisse's and Dave Airlie's pool allocator.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Utilities to reserve, unreserve and fence a list of TTM
buffer objects in a deadlock-safe manner.
Used by the vmwgfx driver.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This is intended to be used by ttm-aware drivers to
1) Block clients to inactive masters when
they try to validate buffers for GPU use.
2) Optionally block clients to the current master when
there is thrashing due to GPU memory shortage.
Used by the vmwgfx driver.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Add objects needed for user-space to maintain reference counts on ttm objects.
This is used by the vmwgfx driver which allows user-space to maintain
map-counts on dma buffers, lock-counts on the ttm lock and ref-counts on
gpu surfaces, gpu contexts and dma buffer.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
TTM is a GPU memory manager subsystem designed for use with GPU
devices with various memory types (On-card VRAM, AGP,
PCI apertures etc.). It's essentially a helper library that assists
the DRM driver in creating and managing persistent buffer objects.
TTM manages placement of data and CPU map setup and teardown on
data movement. It can also optionally manage synchronization of
data on a per-buffer-object level.
TTM takes care to provide an always valid virtual user-space address
to a buffer object which makes user-space sub-allocation of
big buffer objects feasible.
TTM uses a fine-grained per buffer-object locking scheme, taking
care to release all relevant locks when waiting for the GPU.
Although this implies some locking overhead, it's probably a big
win for devices with multiple command submission mechanisms, since
the lock contention will be minimal.
TTM can be used with whatever user-space interface the driver
chooses, including GEM. It's used by the upcoming Radeon KMS DRM driver
and is also the GPU memory management core of various new experimental
DRM drivers.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Thomas Hellstrom