Clients like i915 need to segregate cache domains within the GTT which
can lead to small amounts of fragmentation. By allocating the uncached
buffers from the bottom and the cacheable buffers from the top, we can
reduce the amount of wasted space and also optimize allocation of the
mappable portion of the GTT to only those buffers that require CPU
access through the GTT.
For other drivers, allocating small bos from one end and large ones
from the other helps improve the quality of fragmentation.
Based on drm_mm work by Chris Wilson.
v3: Changed to use a TTM placement flag
v2: Updated kerneldoc
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Christian König <deathsimple@vodafone.de>
Signed-off-by: Lauri Kasanen <cand@gmx.com>
Signed-off-by: David Airlie <airlied@redhat.com>
Our code allows have a PPGTT that is smaller than the maximum size for
GEN6-GEN7. Though I don't think this actually ever occurs, the code may
as well work properly and more importantly look correct by using the
variable size instead of the HW max.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I'm not clear if the hardware is still subject to the same prefetching
issues that made us use a scratch page in the first place. In either
case, we're using garbage with the current code (we will end up using
offset 0).
This may be the cause of our current gem_cpu_reloc regression with
PPGTT. I cannot test it at the moment.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Linux 3.14-rc6
I need the hdmi/dvi-dual link fixes in 3.14 to avoid ugly conflicts
when merging Ville's new hdmi cloning support into my -next tree
Conflicts:
drivers/gpu/drm/i915/Makefile
drivers/gpu/drm/i915/intel_dp.c
Makefile cleanup conflicts with an acpi build fix, intel_dp.c is
trivial.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There are too many oustanding issues:
- Fence handling in the current code is broken. There's a patch series
from me, but it's blocked on and extended review (which includes
writing the testcases).
- IOMMU mapping handling is broken, we need to properly refcount it -
currently it gets destroyed when the first vma is unbound, so way
too early.
- There's a pending reset issue on snb. Since Mika's reset work and
full ppgtt have been pulled in in separate branches and ended up
intermittingly breaking each another it's unclear who's the exact
culprit here.
- We still have persistent evidince of crazy recursion bugs through
vma_unbind and ppgtt_relase, e.g.
https://bugs.freedesktop.org/show_bug.cgi?id=73383
This issue (and a few others meanwhile resolved) have blocked our
performance measuring/tuning group since 3 months.
- Secure batch dispatching is broken. This is blocking Brad Volkin's
command checker work since 3 months.
All these issues are confirmed to only happen when full ppgtt is
enabled, falling back to aliasing ppgtt resolves them. But even
aliasing ppgtt itself still has a regression:
- We currently unconditionally bind objects into the aliasing ppgtt,
which means all priviledged objects like ringbuffers are visible to
unpriviledged access again. On top of that this also breaks the
command checker for aliasing ppgtt, since it can't hide the
validated batch any more.
Furthermore topic/full-ppgtt has never been reviewed:
- Lifetime rules around vma unbinding/release are unclear, resulting
into this awesome hack called ppgtt_release. Which seems to take the
blame for most of the recursion fallout.
- Context/ring init works different on gpu reset than anywhere else.
Such differeneces have in the past always lead to really hard to
track down bugs.
- Aliasing ppgtt is treated in a bunch of places as a real address
space, but it isn't - the real address space is always the global
gtt in that case. This results in a bit a mess between contexts and
ppgtt object, further complication the context/ppgtt/vma lifetime
rules.
- We don't have any docs describing the overall concepts introduced
with full ppgtt. A short, concise overview describing vmas and some
of the strange bits around them (like the unbound vmas used by
execbuf, or the new binding rules) really is needed.
Note that a lot of the post topic/full-ppgtt merge fallout has already
been addressed, this entire list here of 10 issues really only contains
the still outstanding issues.
Finally the 3.15 merge window is approaching and I think we need to
use the remaining time to ensure that our fallback option of using
aliasing ppgtt is in solid shape. Hence I think it's time to throw the
switch. While at it demote the helper from static inline status
because really.
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the original PPGTT implementation if the number of PDPs was not a
power of two, the number of pages for the page tables would end up being
rounded up. The code actually had a bug here afaict, but this is a
theoretical bug as I don't believe this can actually occur with the
current code/HW..
With the rework of the page table allocations, there is no longer a
distinction between number of page table pages, and number of page
directory entries. To avoid confusion, kill the redundant (and newer)
struct member.
Cc: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Simply to match the GEN8 style of PPGTT initialization, split up the
allocations and mappings. Unlike GEN8, we skip a separate dma_addr_t
allocation function, as it is much simpler pre-gen8.
With this code it would be easy to make a more general PPGTT
initialization function with per GEN alloc/map/etc. or use a common
helper, similar to the ringbuffer code. I don't see a benefit to doing
this just yet, but who knows...
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This cleanup is similar to the GEN8 cleanup (though less necessary).
Having everything split will make cleaning the initialization path error
paths easier to understand.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I keep meaning to do this... by now almost the entire file has been
written by an Intel employee (including Daniel post-2010).
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This reverts commit 3a2ffb65ee.
Now that the code is fixed to use smaller allocations, it should be safe
to let the full GGTT be used on BDW.
The testcase for this is anything which uses more than half of the GTT,
thus eclipsing the old limit.
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The previous allocation mechanism would get 2 contiguous allocations,
one for the page directories, and one for the page tables. As each page
table is 1 page, and there are 512 of these per page directory, this
goes to 2MB. An unfriendly request at best. Worse still, our HW now
supports 4 page directories, and a 2MB allocation is not allowed.
In order to fix this, this patch attempts to split up each page table
allocation into a single, discrete allocation. There is nothing really
fancy about the patch itself, it just has to manage an extra pointer
indirection, and have a fancier bit of logic to free up the pages.
To accommodate some of the added complexity, two new helpers are
introduced to allocate, and free the page table pages.
NOTE: I really wanted to split the way we do allocations, and the way in
which we identify the page table/page directory being used. I found
splitting this functionality up to be too unwieldy. I apologize in
advance to the reviewer. I'd recommend looking at the result, rather
than the diff.
v2/NOTE2: This patch predated commit:
6f1cc99351
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Dec 31 15:50:31 2013 +0000
drm/i915: Avoid dereference past end of page arr
It fixed the same issue as that patch, but because of the limbo state of
PPGTT, Chris patch was merged instead. The excess churn is a result of
my using my original patch, which has my preferred naming. Primarily
act_* is changed to which_*, but it's mostly the same otherwise. I've
kept the convention Chris used for the pte wrap (I had something
slightly different, and broken - but fixable)
v3: Rename which_p[..]e to drop which_ (Chris)
Remove BUG_ON in inner loop (Chris)
Redo the pde/pdpe wrap logic (Chris)
v4: s/1MB/2MB in commit message (Imre)
Plug leaking gen8_pt_pages in both the error path, as well as general
free case (Imre)
v5: Rename leftover "which_" variables (Imre)
Add the pde = 0 wrap that was missed from v3 (Imre)
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Squash in fixup from Ben.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch converts insert_entries and clear_range, both functions which
are specific to the VM. These functions tend to encapsulate the gen
specific PTE writes. Passing absolute addresses to the insert_entries,
and clear_range will help make the logic clearer within the functions as
to what's going on. Currently, all callers simply do the appropriate
page shift, which IMO, ends up looking weird with an upcoming change for
the gen8 page table allocations.
Up until now, the PPGTT was a funky 2 level page table. GEN8 changes
this to look more like a 3 level page table, and to that extent we need
a significant amount more memory simply for the page tables. To address
this, the allocations will be split up in finer amounts.
v2: Replace size_t with uint64_t (Chris, Imre)
v3: Fix size in gen8_ppgtt_init (Ben)
Fix Size in i915_gem_suspend_gtt_mappings/restore (Imre)
Reviewed-by: Imre Deak <imre.deak@intel.com> (v2)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like cleanup in an earlier patch, the code becomes much more readable,
and easier to extend if we extract out helper functions for the various
stages of init.
Note that with this patch it becomes really simple, and tempting to begin
using the 'goto out' idiom with explicit free/fini semantics. I've
kept the error path as similar as possible to the cleanup() function to
make sure cleanup is as robust as possible
v2: Remove comment "NB:From here on, ppgtt->base.cleanup() should
function properly"
Update commit message to reflect above
v3: Rebased on top of bugfixes found in the previous patch by Imre
Moved number of pd pages assertion to the proper place (Imre)
v4:
Allocate dma address space for num_pd_pages, not num_pd_entries (Ben)
Don't use gen8_pt_dma_addr after free on error path (Imre)
With new fix from v4 of the previous patch.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Create 3 clear stages in PPGTT init. This will help with upcoming
changes be more readable. The 3 stages are, allocation, dma mapping, and
writing the P[DT]Es
One nice benefit to the patches is that it makes 2 very clear error
points, allocation, and mapping, and avoids having to do any handling
after writing PTEs (something which was likely buggy before). This
simplified error handling I suspect will be helpful when we move to
deferred/dynamic page table allocation and mapping.
The patches also attempts to break up some of the steps into more
logical reviewable chunks, particularly when we free.
v2: Don't call cleanup on the error path since that takes down the
drm_mm and list entry, which aren't setup at this point.
v3: Fixes addressing Imre's comments from:
<1392821989.19792.13.camel@intelbox>
Don't do dynamic allocation for the page table DMA addresses. I can't
remember why I did it in the first place. This addresses one of Imre's
other issues.
Fix error path leak of page tables.
v4: Fix the fix of the error path leak. Original fix still leaked page
tables. (Imre)
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
GEN8 never freed the PPGTT struct. As GEN8 doesn't use full PPGTT, the
leak is small and only found on a module reload. ie. I don't think this
needs to go to stable.
v2: The very naive, kfree in gen8 ppgtt cleanup, is subject to a double
free on PPGTT initialization failure. (Spotted by Imre). Instead this
patch pulls the ppgtt struct freeing out of the cleanup and leaves it to
the allocators/callers or the one doing the last kref_put as in standard
convention
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Anything more than just one bool parameter is just a pain to read,
symbolic constants are much better.
Split out from Chris' vma-binding rework patch.
v2: Undo the behaviour change in object_pin that Chris spotted.
v3: Split out misplaced hunk to handle set_cache_level errors,
spotted by Jani.
v4: Keep the current over-zealous binding logic in the execbuffer code
working with a quick hack while the overall binding code gets shuffled
around.
v5: Reorder the PIN_ flags for more natural patch splitup.
v6: Pull out the PIN_GLOBAL split-up again.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This will make the code more readable, and extensible which is needed
for upcoming feature work. Eventually, we'll do the same for init.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Pull drm updates from Dave Airlie:
"Been a bit busy, first week of kids school, and waiting on other trees
to go in before I could send this, so its a bit later than I'd
normally like.
Highlights:
- core:
timestamp fixes, lots of misc cleanups
- new drivers:
bochs virtual vga
- vmwgfx:
major overhaul for their nextgen virt gpu.
- i915:
runtime D3 on HSW, watermark fixes, power well work, fbc fixes,
bdw is no longer prelim.
- nouveau:
gk110/208 acceleration, more pm groundwork, old overlay support
- radeon:
dpm rework and clockgating for CIK, pci config reset, big endian
fixes
- tegra:
panel support and DSI support, build as module, prime.
- armada, omap, gma500, rcar, exynos, mgag200, cirrus, ast:
fixes
- msm:
hdmi support for mdp5"
* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (595 commits)
drm/nouveau: resume display if any later suspend bits fail
drm/nouveau: fix lock unbalance in nouveau_crtc_page_flip
drm/nouveau: implement hooks for needed for drm vblank timestamping support
drm/nouveau/disp: add a method to fetch info needed by drm vblank timestamping
drm/nv50: fill in crtc mode struct members from crtc_mode_fixup
drm/radeon/dce8: workaround for atom BlankCrtc table
drm/radeon/DCE4+: clear bios scratch dpms bit (v2)
drm/radeon: set si_notify_smc_display_change properly
drm/radeon: fix DAC interrupt handling on DCE5+
drm/radeon: clean up active vram sizing
drm/radeon: skip async dma init on r6xx
drm/radeon/runpm: don't runtime suspend non-PX cards
drm/radeon: add ring to fence trace functions
drm/radeon: add missing trace point
drm/radeon: fix VMID use tracking
drm: ast,cirrus,mgag200: use drm_can_sleep
drm/gma500: Lock struct_mutex around cursor updates
drm/i915: Fix the offset issue for the stolen GEM objects
DRM: armada: fix missing DRM_KMS_FB_HELPER select
drm/i915: Decouple GPU error reporting from ring initialisation
...
With 20+ module parameters, I think referring to them via a struct
improves clarity over just having a bunch of globals. While at it, move
the parameter initialization and definitions into a new file
i915_params.c to reduce clutter in i915_drv.c.
Apart from the ill-named i915_enable_rc6, i915_enable_fbc and
i915_enable_ppgtt parameters, for which we lose the "i915_" prefix
internally, the module parameters now look the same both on the kernel
command line and in code. For example, "i915.modeset".
The downsides of the change are losing static on a couple of variables
and not having the initialization and module_param_named() right next to
each other. On the other hand, all module parameters are now defined in
one place at i915_params.c. Plus you can do this to find all module
parameter references:
$ git grep "i915\." -- drivers/gpu/drm/i915
v2:
- move the definitions into a new file
- s/i915_params/i915/
- make i915_try_reset i915.reset, for consistency
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Because whatever.*
* This should contain a fairly long list of issues and still
unresolved resgressions, but I didn't really get a vote.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Pull PCI updates from Bjorn Helgaas:
"PCI changes for the v3.14 merge window:
Resource management
- Change pci_bus_region addresses to dma_addr_t (Bjorn Helgaas)
- Support 64-bit AGP BARs (Bjorn Helgaas, Yinghai Lu)
- Add pci_bus_address() to get bus address of a BAR (Bjorn Helgaas)
- Use pci_resource_start() for CPU address of AGP BARs (Bjorn Helgaas)
- Enforce bus address limits in resource allocation (Yinghai Lu)
- Allocate 64-bit BARs above 4G when possible (Yinghai Lu)
- Convert pcibios_resource_to_bus() to take pci_bus, not pci_dev (Yinghai Lu)
PCI device hotplug
- Major rescan/remove locking update (Rafael J. Wysocki)
- Make ioapic builtin only (not modular) (Yinghai Lu)
- Fix release/free issues (Yinghai Lu)
- Clean up pciehp (Bjorn Helgaas)
- Announce pciehp slot info during enumeration (Bjorn Helgaas)
MSI
- Add pci_msi_vec_count(), pci_msix_vec_count() (Alexander Gordeev)
- Add pci_enable_msi_range(), pci_enable_msix_range() (Alexander Gordeev)
- Deprecate "tri-state" interfaces: fail/success/fail+info (Alexander Gordeev)
- Export MSI mode using attributes, not kobjects (Greg Kroah-Hartman)
- Drop "irq" param from *_restore_msi_irqs() (DuanZhenzhong)
SR-IOV
- Clear NumVFs when disabling SR-IOV in sriov_init() (ethan.zhao)
Virtualization
- Add support for save/restore of extended capabilities (Alex Williamson)
- Add Virtual Channel to save/restore support (Alex Williamson)
- Never treat a VF as a multifunction device (Alex Williamson)
- Add pci_try_reset_function(), et al (Alex Williamson)
AER
- Ignore non-PCIe error sources (Betty Dall)
- Support ACPI HEST error sources for domains other than 0 (Betty Dall)
- Consolidate HEST error source parsers (Bjorn Helgaas)
- Add a TLP header print helper (Borislav Petkov)
Freescale i.MX6
- Remove unnecessary code (Fabio Estevam)
- Make reset-gpio optional (Marek Vasut)
- Report "link up" only after link training completes (Marek Vasut)
- Start link in Gen1 before negotiating for Gen2 mode (Marek Vasut)
- Fix PCIe startup code (Richard Zhu)
Marvell MVEBU
- Remove duplicate of_clk_get_by_name() call (Andrew Lunn)
- Drop writes to bridge Secondary Status register (Jason Gunthorpe)
- Obey bridge PCI_COMMAND_MEM and PCI_COMMAND_IO bits (Jason Gunthorpe)
- Support a bridge with no IO port window (Jason Gunthorpe)
- Use max_t() instead of max(resource_size_t,) (Jingoo Han)
- Remove redundant of_match_ptr (Sachin Kamat)
- Call pci_ioremap_io() at startup instead of dynamically (Thomas Petazzoni)
NVIDIA Tegra
- Disable Gen2 for Tegra20 and Tegra30 (Eric Brower)
Renesas R-Car
- Add runtime PM support (Valentine Barshak)
- Fix rcar_pci_probe() return value check (Wei Yongjun)
Synopsys DesignWare
- Fix crash in dw_msi_teardown_irq() (Bjørn Erik Nilsen)
- Remove redundant call to pci_write_config_word() (Bjørn Erik Nilsen)
- Fix missing MSI IRQs (Harro Haan)
- Add dw_pcie prefix before cfg_read/write (Pratyush Anand)
- Fix I/O transfers by using CPU (not realio) address (Pratyush Anand)
- Whitespace cleanup (Jingoo Han)
EISA
- Call put_device() if device_register() fails (Levente Kurusa)
- Revert EISA initialization breakage ((Bjorn Helgaas)
Miscellaneous
- Remove unused code, including PCIe 3.0 interfaces (Stephen Hemminger)
- Prevent bus conflicts while checking for bridge apertures (Bjorn Helgaas)
- Stop clearing bridge Secondary Status when setting up I/O aperture (Bjorn Helgaas)
- Use dev_is_pci() to identify PCI devices (Yijing Wang)
- Deprecate DEFINE_PCI_DEVICE_TABLE (Joe Perches)
- Update documentation 00-INDEX (Erik Ekman)"
* tag 'pci-v3.14-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (119 commits)
Revert "EISA: Initialize device before its resources"
Revert "EISA: Log device resources in dmesg"
vfio-pci: Use pci "try" reset interface
PCI: Check parent kobject in pci_destroy_dev()
xen/pcifront: Use global PCI rescan-remove locking
powerpc/eeh: Use global PCI rescan-remove locking
PCI: Fix pci_check_and_unmask_intx() comment typos
PCI: Add pci_try_reset_function(), pci_try_reset_slot(), pci_try_reset_bus()
MPT / PCI: Use pci_stop_and_remove_bus_device_locked()
platform / x86: Use global PCI rescan-remove locking
PCI: hotplug: Use global PCI rescan-remove locking
pcmcia: Use global PCI rescan-remove locking
ACPI / hotplug / PCI: Use global PCI rescan-remove locking
ACPI / PCI: Use global PCI rescan-remove locking in PCI root hotplug
PCI: Add global pci_lock_rescan_remove()
PCI: Cleanup pci.h whitespace
PCI: Reorder so actual code comes before stubs
PCI/AER: Support ACPI HEST AER error sources for PCI domains other than 0
ACPICA: Add helper macros to extract bus/segment numbers from HEST table.
PCI: Make local functions static
...
Conflicts are getting out of hand, and now we have to shuffle even
more in -next which was also shuffled in -fixes (the call for
drm_mode_config_reset needs to move yet again).
So do a proper backmerge. I wanted to wait with this for the 3.13
relaese, but alas let's just do this now.
Conflicts:
drivers/gpu/drm/i915/i915_reg.h
drivers/gpu/drm/i915/intel_ddi.c
drivers/gpu/drm/i915/intel_display.c
drivers/gpu/drm/i915/intel_pm.c
Besides the conflict around the forcewake get/put (where we chaged the
called function in -fixes and added a new parameter in -next) code all
the current conflicts are of the adjacent lines changed type.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Lauri Kasanen
Ben Widawsky
Ville Syrjälä
Daniel Vetter
Linus Torvalds
Jani Nikula