- 06 Dec, 2011 39 commits
-
-
Konrad Rzeszutek Wilk authored
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>
-
Jerome Glisse authored
Move the page allocation and freeing to driver callback and provide ttm code helper function for those. Most intrusive change, is the fact that we now only fully populate an object this simplify some of code designed around the page fault design. V2 Rebase on top of memory accounting overhaul V3 New rebase on top of more memory accouting changes V4 Rebase on top of no memory account changes (where/when is my delorean when i need it ?) Signed-off-by:
-
Jerome Glisse authored
ttm_backend will only exist with a ttm_tt, and ttm_tt will only be of interest when bound to a backend. Merge them to avoid code and data duplication. V2 Rebase on top of memory accounting overhaul V3 Rebase on top of more memory accounting changes V4 Rebase on top of no memory account changes (where/when is my delorean when i need it ?) V5 make sure ttm is unbound before destroying, change commit message on suggestion from Tormod Volden Signed-off-by:
-
Jerome Glisse authored
Use the ttm_tt pages array for pages allocations, move the list unwinding into the page allocation functions. Signed-off-by: -
Jerome Glisse authored
Signed-off-by:
-
Jerome Glisse authored
On failure we need to make sure the page we free has wb cache attribute. Do this pas call the proper ttm page helper function. Signed-off-by:
-
Jerome Glisse authored
This field is not use by any of the driver just drop it. Signed-off-by:
-
Jerome Glisse authored
Split btw highmem and lowmem page was rendered useless by the pool code. Remove it. Note further cleanup would change the ttm page allocation helper to actualy take an array instead of relying on list this could drasticly reduce the number of function call in the common case of allocation whole buffer. Signed-off-by:
-
Jerome Glisse authored
This was never use in none of the driver, properly using userspace page for bo would need more code (vma interaction mostly). Removing this dead code in preparation of ttm_tt & backend merge. Signed-off-by:
-
Konrad Rzeszutek Wilk authored
As a mechanism to detect whether SWIOTLB is enabled or not. We also fix the spelling - it was swioltb instead of swiotlb. CC: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> [v1: Ripped out swiotlb_enabled] Signed-off-by: -
Dave Airlie authored
Merge topic branch with some of Jesse's cleanups, the save/restore hooks were being used by GMA500 so we can't just drop them. * drm-cleanups-jbarnes: drm: remove some potentially dangerous DRM_ERRORs drm: document the drm_mode_config structure drm: document the drm_mode_group structure drm: document and cleanup drm_mode_config_funcs drm: document drm_mode_set structure drm: remove unused fields in drm_connector and document the rest drm: add drm_encoder comments drm: add comments for drm_encoder_funcs drm: fix comments for drm_crtc struct drm: remove unused connector_count field from drm_display_mode
-
Jesse Barnes authored
Each of these error messages can be caused by a broken or malicious userspace wanting to spam the dmesg with useless info. They're really not worthy of DRM_DEBUG statements either; those are generally only useful during bringup of new hardware or versions, and ought to be removed before going upstream anyway. Signed-off-by:
Jesse Barnes <jbarnes@virtuousgeek.org> Reviewed-by:
Alex Deucher <alexdeucher@gmail.com> Signed-off-by:
Dave Airlie <airlied@redhat.com>
-
Jesse Barnes authored
Including a comment about what the locks are for. Signed-off-by:
-
Jesse Barnes authored
This is actually a core structure with a big future ahead of it. Make it a little less mysterious. Signed-off-by:
-
Jesse Barnes authored
Just fix the wrapping mostly. Signed-off-by:
-
Jesse Barnes authored
This is a core mode setting structure that deserves a little verbiage. Signed-off-by:
-
Jesse Barnes authored
We never used initial_x/y or the force_encoder_id, so drop those fields and proide a basic description of the others. Really, the ELD bits belong in drm_display_info rather than directly in the connector, but that's a separate cleanup. Signed-off-by:
-
Jesse Barnes authored
Just some basic comments about the place and function of the structure and fields. Signed-off-by:
-
Jesse Barnes authored
Just basic verbiage. Signed-off-by:
-
Jesse Barnes authored
Remove stale entries and update with the latest stuff. Signed-off-by:
-
Jesse Barnes authored
Doesn't really belong here anyway. Signed-off-by:
-
Dave Airlie authored
This merges a topic branch containing patches from Alan for the GMA500 driver. * drm-gma500-alancox: gma500: Oaktrail BIOS handling gma500: Fix oaktrail probing part 1 gma500: Be smarter about layout gma500: gtt based hardware scrolling console gma500: frame buffer locking gma500: Fix backlight crash gma500: kill bogus code gma500: Convert spaces to tabs in accel_2d.c. gma500: do a pass over the FIXME tags gma500: Add VBLANK support for Poulsbo hardware gma500: Don't enable MSI on Poulsbo gma500: Only register interrupt handler for poulsbo hardware gma500: kill virtual mapping support gma500: Move the API gma500: kill off NUM_PIPE define gma500: Rename the ioctls to avoid clashing with the legacy drivers drm/gma500: begin pruning dead bits of API
-
Alan Cox authored
Now that we pull the right BIOS data out of the hat we need to use it when doing our panel setup. Signed-off-by:
Alan Cox <alan@linux.intel.com> Signed-off-by:
-
Alan Cox authored
The Oaktrail platform does not use the GCT/VBT format that is used by the Moorestowm (non PC legacy) equivalent device. It uses the BIOS tables which means an opregion and the like. The current code uses the wrong table which breaks things like the Fujitsu q550 tablets. Fix the table usage as a first step. The problem was found and diagnosed by Chia-I Wu Signed-off-by:
-
Alan Cox authored
If we can't fit a page aligned display stride then it's not the end of the world for a normal font, so try half a page and work down sizes. Signed-off-by:
-
Alan Cox authored
Add support for GTT based scrolling. Instead of pushing bits around we simply use the GTT to change the mappings. This provides us with a very fast way to scroll the display providing we have enough memory to allocate on 4K line boundaries. In practice this seems to be the case except for very big displays such as HDMI, and the usual configurations are netbooks/tablets. Signed-off-by:
-
Alan Cox authored
If we are the console then a printk can hit us with a spin lock held (and in fact the kernel will do its best to take the console printing lock). In that case we cannot politely sleep when synching after an accelerated op but must behave obnoxiously to be sure of getting the bits out. Signed-off-by:
-
Alan Cox authored
Initial changes to get backlight behaviour we want and to fix backlight crashes on suspend/resume paths. [Note: on some boxes this will now produce a warning about the backlight, this isn't a regression it's an unfixed but non harmful case I still need to nail] Signed-off-by:
-
Alan Cox authored
During the power split ups and work a chunk of code escaped into the Poulsbo code path which it isn't for. On some devices such as the Dell mini-10 this causes problems. Signed-off-by:
-
Akshay Joshi authored
Convert the spaces within the accel_2d.c file to tabs in order to comply with the coding style of the kernel. Signed-off-by:
Akshay Joshi <me@akshayjoshi.com> [Trimmed to subset relevant to current tree] Signed-off-by:
-
Alan Cox authored
Signed-off-by:
-
Patrik Jakobsson authored
Signed-off-by:
Patrik Jakobsson <patrik.r.jakobsson@gmail.com> Signed-off-by:
-
Patrik Jakobsson authored
Chipset reports MSI capabilities for Poulsbo even though it isn't really there. Signed-off-by:
-
Patrik Jakobsson authored
First step in adding proper irq handling. We'll start with poulsbo support so make sure other chips don't touch drm_irq_install(). Signed-off-by:
-
Alan Cox authored
This isn't actually usable - we simply don't have the vmap space on a 32bit system to do this stunt. Instead we will rely on the low level drivers limiting the console resolution as before. The real fix is for someone to write a page table aware version of the framebuffer console blit functions. Good university student project perhaps.. Signed-off-by:
-
Alan Cox authored
Finally move the API where it can be seen Signed-off-by:
-
Alan Cox authored
We don't want this external in case someone adds more to the hardware. We want it out of the ABI. Signed-off-by:
-
Alan Cox authored
Signed-off-by:
-
Alan Cox authored
At this point we won't add an external set of definitions. We want to get everything out before we admit to a public API beyond the standardised ones. Signed-off-by:
-
- 01 Dec, 2011 1 commit
-
-
Ville Syrjälä authored
Name the formats as DRM_FORMAT_X instead of DRM_FOURCC_X. Use consistent names, especially for the RGB formats. Component order and byte order are now strictly specified for each format. The RGB format naming follows a convention where the components names and sizes are listed from left to right, matching the order within a single pixel from most significant bit to least significant bit. The YUV format names vary more. For the 4:2:2 packed formats and 2 plane formats use the fourcc. For the three plane formats the name includes the plane order and subsampling information using the standard subsampling notation. Some of those also happen to match the official fourcc definition. The fourccs for for all the RGB formats and some of the YUV formats I invented myself. The idea was that looking at just the fourcc you get some idea what the format is about without having to decode it using some external reference. Signed-off-by:
Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by:
-
