It includes code cleanups from Bhumika and Liviu, a significant shader
performance fix and additions to the cmdstream validator from Wladimir
and the addition of a cmdbuf suballocator by myself.
The suballocator improves performance on all chips by reducing the CPU
overhead of the kernel driver and side steps the GC3000 FE MMU flush
erratum, now making the workarounds in IOVA allocation we had before
unnecessary, which results in a nice cleanup of the code in that area.
* 'drm-etnaviv-next' of https://git.pengutronix.de/git/lst/linux:
drm/etnaviv: Remove duplicate header file include
Revert "drm/etnaviv: trick drm_mm into giving out a low IOVA"
drm/etnaviv: add cmdbuf suballocator
drm/etnaviv: get cmdbuf physical address through the cmdbuf abstraction
drm/etnaviv: wire up iova handling in new cmdbuf abstraction
drm/etnaviv: move cmdbuf de-/allocation into own file
drm/etnaviv: always flush MMU TLBs on map/unmap
drm/etnaviv: constify etnaviv_iommu_ops structures
drm/etnaviv: set up initial PULSE_EATER register
drm/etnaviv: add new GC3000 sensitive states
Now that commandstreams are handled through the cmdbuf suballocator
the workaround to make the IOVA games work is not needed anymore.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
There are 3 big benefits to suballocating a single big DMA buffer
for command submission:
1. Avoid hammering CMA. The old way of allocating and freeing a DMA
buffer for each submission was hitting some of the real slow
pathes in CMA, as this allocator was not designed for a concurrent
small buffers load.
2. Less TLB flushes on IOMMUv2. If a new command buffer is mapped into
the GPU address space the MMU TLBs need to be flushed. By having
one big buffer statically mapped to the GPU, a lot of those flushes
can be avoided.
3. No funky workarounds for GC3000. The FE TLB flush on GC3000 isn't
reliable. To work around that we tried to lay out the cmdbufs in
the GPU address space in a way to avoid this issue. This hasn't
always worked if the address space is crowded. A single statically
mapped buffer avoids the erratum completely.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
This will get more complex with the following changes, so move it
into its own place.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
This ensures that the GPU isn't able to write into already freed
objects, as doing this in the IOVA reaper isn't enough, as the
gem_free_object path will also cause unmaps to happen.
On MMUv2 this also ensures that stale entries, which may have
been prefetched into the TLB will be purged.
The flush is low overhead, as it gets batched up with the next
user command buffer, so this isn't incuring an overhead for
each buffer map/unmap.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Backmerge Linus master to get the connector locking revert.
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux: (645 commits)
sysctl: fix proc_doulongvec_ms_jiffies_minmax()
Revert "drm/probe-helpers: Drop locking from poll_enable"
MAINTAINERS: add Dan Streetman to zbud maintainers
MAINTAINERS: add Dan Streetman to zswap maintainers
mm: do not export ioremap_page_range symbol for external module
mn10300: fix build error of missing fpu_save()
romfs: use different way to generate fsid for BLOCK or MTD
frv: add missing atomic64 operations
mm, page_alloc: fix premature OOM when racing with cpuset mems update
mm, page_alloc: move cpuset seqcount checking to slowpath
mm, page_alloc: fix fast-path race with cpuset update or removal
mm, page_alloc: fix check for NULL preferred_zone
kernel/panic.c: add missing \n
fbdev: color map copying bounds checking
frv: add atomic64_add_unless()
mm/mempolicy.c: do not put mempolicy before using its nodemask
radix-tree: fix private list warnings
Documentation/filesystems/proc.txt: add VmPin
mm, memcg: do not retry precharge charges
proc: add a schedule point in proc_pid_readdir()
...
After rollover of the IOVA space, we want to get a low IOVA address,
otherwise the the games we play by remembering the last IOVA are
pointless. When we search for a free hole with DRM_MM_SEARCH_DEFAULT,
drm_mm will pop the next entry from the free holes stack, which will
likely be a high IOVA. By using DRM_MM_SEARCH_BELOW we can trick
drm_mm into reversing the search and provide us with a low IOVA.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Wladimir van der Laan <laanwj@gmail.com>
Compute the minimal required hole during scan and only evict those nodes
that overlap. This enables us to reduce the number of nodes we need to
evict to the bare minimum.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161222083641.2691-31-chris@chris-wilson.co.uk
The scan state occupies a large proportion of the struct drm_mm and is
rarely used and only contains temporary state. That makes it suitable to
moving to its struct and onto the stack of the callers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[danvet: Fix up etnaviv to compile, was missing a BUG_ON.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
To make sure we don't place anything there which might confuse
the FE prefetcher. This gets rid of another case of FE MMU faults
when the address space gets crowded before triggering the reaper.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
At least on the GC3000 the FE MMU is not properly flushing stale TLB
entries. Make sure to map the cmdbufs with a big enough spacing in
the IOVAs to not hit old/prefetched TLB entries when jumping to a
newly mapped cmdbuf.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
All other parts are now in place, so implement the actual translation
step and hook it up, so the driver claims support for cores with
the new MMU.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
With MMUv2 all buffers need to be mapped through the MMU once it
is enabled. Align the buffer size to 4K, as the MMU is only able to
map page aligned buffers.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
With MMUv2 the command buffers need to be mapped through the MMU.
Split out the iova search and MMU reaping logic so it can be reused
for the cmdbuf mapping, where no GEM object is involved.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
The GPU virtual address for the command buffers differs depending on
the IOMMU version. Move the calculation of the iova into etnaviv
mmu, to enable proper dispatch.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
The GPU code doesn't need to deal with the IOMMU directly, instead
it can all be hidden behind the etnaviv mmu interface. Move the
last remaining part into etnaviv mmu.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
As the comment above the code states, the linear window is only
available on MMUv1. Don't try to use it on MMUv2.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Currently, we scan the list of mappings each time we want to operate on
the vram_mapping struct. Rather than repeatedly scanning these, look
them up once in the submission path, and then use _reference and
_unreference methods as necessary to manage this object.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
This adds the etnaviv DRM driver and hooks it up in Makefiles
and Kconfig.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Dave Airlie