platform/upstream/libdrm.git
17 years agoMake the utility runnable also for normal users.
Thomas Hellstrom [Wed, 31 Jan 2007 10:41:44 +0000 (11:41 +0100)]
Make the utility runnable also for normal users.

17 years agoFix an error-path oops.
Thomas Hellstrom [Wed, 31 Jan 2007 10:03:53 +0000 (11:03 +0100)]
Fix an error-path oops.

17 years agoAdd a buffer object transfer function.
Thomas Hellstrom [Tue, 30 Jan 2007 15:20:23 +0000 (16:20 +0100)]
Add a buffer object transfer function.
Creates a placeholder for the old buffer contents
when it is transfered to / from static memory like VRAM.

17 years agoIndent according to xorg rules.
Thomas Hellstrom [Tue, 30 Jan 2007 13:42:27 +0000 (14:42 +0100)]
Indent according to xorg rules.

17 years agoAdd license header.
Thomas Hellstrom [Tue, 30 Jan 2007 13:41:02 +0000 (14:41 +0100)]
Add license header.

17 years agoAdd some relevant tests for the new buffer object interface.
Thomas Hellstrom [Tue, 30 Jan 2007 13:38:49 +0000 (14:38 +0100)]
Add some relevant tests for the new buffer object interface.

17 years agoAdd the ttmtest test utility.
Thomas Hellstrom [Tue, 30 Jan 2007 11:56:51 +0000 (12:56 +0100)]
Add the ttmtest test utility.

17 years agoClean up buffer object destruction somewhat.
Thomas Hellstrom [Tue, 30 Jan 2007 11:33:46 +0000 (12:33 +0100)]
Clean up buffer object destruction somewhat.

17 years agoUse pre-defined list_splice function.
Thomas Hellstrom [Mon, 29 Jan 2007 12:36:17 +0000 (13:36 +0100)]
Use pre-defined list_splice function.

17 years agos/buf/bo/ for consistency.
Thomas Hellstrom [Mon, 29 Jan 2007 12:19:20 +0000 (13:19 +0100)]
s/buf/bo/ for consistency.

17 years agoSome cleanup. A buffer object should only have one active memory type.
Thomas Hellstrom [Mon, 29 Jan 2007 12:11:55 +0000 (13:11 +0100)]
Some cleanup. A buffer object should only have one active memory type.

17 years agonouveau: determine chipset type at startup, instead of every time we use it.
Ben Skeggs [Sun, 28 Jan 2007 12:48:33 +0000 (23:48 +1100)]
nouveau: determine chipset type at startup, instead of every time we use it.

17 years agomake works ctx switch on nv10.
Matthieu Castet [Fri, 26 Jan 2007 20:57:44 +0000 (21:57 +0100)]
make works ctx switch on nv10.

17 years agonouveau: oops, wrong indexing in nv17 regs
Patrice Mandin [Fri, 26 Jan 2007 20:05:59 +0000 (21:05 +0100)]
nouveau: oops, wrong indexing in nv17 regs

17 years agonouveau: read gpu type once
Patrice Mandin [Fri, 26 Jan 2007 18:54:35 +0000 (19:54 +0100)]
nouveau: read gpu type once

17 years agonouveau: only save/restore nv17 regs on nv17,18 hw
Patrice Mandin [Fri, 26 Jan 2007 18:25:49 +0000 (19:25 +0100)]
nouveau: only save/restore nv17 regs on nv17,18 hw

17 years agonouveau: add extra pgraph registers
Patrice Mandin [Fri, 26 Jan 2007 18:24:34 +0000 (19:24 +0100)]
nouveau: add extra pgraph registers

17 years agonouveau: add some nv10 pgraph defines
Patrice Mandin [Fri, 26 Jan 2007 17:10:31 +0000 (18:10 +0100)]
nouveau: add some nv10 pgraph defines

17 years agonouveau: simplify and fix BIG_ENDIAN flags
Patrice Mandin [Thu, 25 Jan 2007 22:06:48 +0000 (23:06 +0100)]
nouveau: simplify and fix BIG_ENDIAN flags

17 years agoRemove a scary error printed when we were leaking memory caches.
Thomas Hellstrom [Thu, 25 Jan 2007 13:26:58 +0000 (14:26 +0100)]
Remove a scary error printed when we were leaking memory caches.

We don't use memory caches anymore...

Fix memory accounting initialization to only use low or DMA32 memory.

17 years agonouveau: nv4c default context
Ben Skeggs [Thu, 25 Jan 2007 00:11:01 +0000 (11:11 +1100)]
nouveau: nv4c default context

17 years agonouveau: always print nsource/nstatus regs on PGRAPH errors
Ben Skeggs [Wed, 24 Jan 2007 21:16:23 +0000 (08:16 +1100)]
nouveau: always print nsource/nstatus regs on PGRAPH errors

17 years agovblank interrupt fix
Zou Nan hai [Wed, 24 Jan 2007 08:33:21 +0000 (16:33 +0800)]
vblank interrupt fix

17 years agonouveau: fix getparam from 32-bit client on 64-bit kernel
Ben Skeggs [Fri, 19 Jan 2007 04:41:51 +0000 (15:41 +1100)]
nouveau: fix getparam from 32-bit client on 64-bit kernel

17 years agonouveau: re-add 6150 Go pciid (0x0244)
Ben Skeggs [Sat, 13 Jan 2007 23:42:58 +0000 (10:42 +1100)]
nouveau: re-add 6150 Go pciid (0x0244)

17 years agonouveau: cleanup nv30_graph.c
Jeremy Kolb [Fri, 19 Jan 2007 02:39:36 +0000 (21:39 -0500)]
nouveau: cleanup nv30_graph.c

17 years agonouveau: Remove write to CTX_SIZE. This gives us proper nv3x PGRAPH switching.
Jeremy Kolb [Fri, 19 Jan 2007 02:39:09 +0000 (21:39 -0500)]
nouveau: Remove write to CTX_SIZE. This gives us proper nv3x PGRAPH switching.

17 years agoadd missing quadro id
Dave Jones [Thu, 18 Jan 2007 06:28:49 +0000 (01:28 -0500)]
add missing quadro id

17 years agonouveau: Try to get nv35 pgraph switching working. Doesn't quite yet.
Jeremy Kolb [Wed, 17 Jan 2007 13:46:59 +0000 (08:46 -0500)]
nouveau: Try to get nv35 pgraph switching working. Doesn't quite yet.

Hook into nv20 pgraph switching functions (they're identical for nv3x).
Actually call nv30_pgraph_context_init so the ctx_table is allocated.

Thanks to Carlos Martin for the help.

17 years agonouveau: opps nv20 ctx ramin size was wrong
Matthieu Castet [Sun, 14 Jan 2007 19:04:20 +0000 (20:04 +0100)]
nouveau: opps nv20 ctx ramin size was wrong

17 years agonouveau: opps restored the wrong channel
Matthieu Castet [Sat, 13 Jan 2007 22:30:43 +0000 (23:30 +0100)]
nouveau: opps restored the wrong channel

17 years agonouveau: nv20 graph ctx switch.
Matthieu Castet [Sat, 13 Jan 2007 22:19:41 +0000 (23:19 +0100)]
nouveau: nv20 graph ctx switch.

Untested...

17 years agonouveau: first step to make graph ctx works
Matthieu Castet [Sat, 13 Jan 2007 20:43:47 +0000 (21:43 +0100)]
nouveau: first step to make graph ctx works

It is still not working, but now we could use some 3D commands
without needed to run nvidia blob before.

17 years agonouveau: add and indent pgraph regs
Matthieu Castet [Sat, 13 Jan 2007 20:41:33 +0000 (21:41 +0100)]
nouveau: add and indent pgraph regs

17 years agonouveau: Oops, fix the nv04 RAMFC_DMA_FETCH value.
Stephane Marchesin [Sat, 13 Jan 2007 11:32:45 +0000 (12:32 +0100)]
nouveau: Oops, fix the nv04 RAMFC_DMA_FETCH value.

17 years agonouveau: add missing symlink
Dave Airlie [Fri, 12 Jan 2007 21:43:15 +0000 (08:43 +1100)]
nouveau: add missing symlink

17 years agonouveau : remove useless init : we clear RAMIN before
Matthieu Castet [Fri, 12 Jan 2007 19:30:14 +0000 (20:30 +0100)]
nouveau : remove useless init : we clear RAMIN before

17 years agoDelay for a usec while spinning waiting for ring buffer space.
Haihao Xiang [Fri, 12 Jan 2007 19:24:14 +0000 (11:24 -0800)]
Delay for a usec while spinning waiting for ring buffer space.

This means the loop will wait up to ~10ms for ring buffer space to become
available, rather than just however long it takes to check the space 10000
times.  This matches other drivers' behavior when waiting for ring buffer/fifo
space.

17 years agonouveau: get nv30 context switching to work.
Jeremy Kolb [Fri, 12 Jan 2007 05:13:05 +0000 (00:13 -0500)]
nouveau: get nv30 context switching to work.

* Pulled in some registers from nv10reg.h.  Needed for context switching.
* Filled in nv30 graphics context (based on nv40_graph.c).
* Figure out nv30 context table, set up on context creation.  Allows the cards automatic switching to work.

17 years agoradeon: Fix u32 overflows when determining AGP base address in card space.
Michel Dänzer [Thu, 11 Jan 2007 08:02:07 +0000 (09:02 +0100)]
radeon: Fix u32 overflows when determining AGP base address in card space.

The overflows could lead to the AGP aperture overlapping the framebuffer area
in the card's address space when the latter is located at the very end of the
32 bit address space, which would result in a freeze on X server startup,
probably because the card read commands from the framebuffer instead of from
AGP.

See http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=392915 .

17 years agoRevert "nouveau: Fill in context_init for nv10-nv3x."
Dave Airlie [Wed, 10 Jan 2007 04:19:47 +0000 (15:19 +1100)]
Revert "nouveau: Fill in context_init for nv10-nv3x."

This reverts ac076cb9aff976e8fae567cfa82a898bfc2712e8 commit.

Well it didn't do anything interesting...

17 years agonouveau: Fill in context_init for nv10-nv3x.
Jeremy Kolb jkolb@brandeis.edu [Wed, 10 Jan 2007 04:12:37 +0000 (23:12 -0500)]
nouveau: Fill in context_init for nv10-nv3x.

Fill in the context with the values from PFIFO_CACH1. This should work from nv10 through the nv30 series.

17 years agonouveau: Don't use DRIVER_USE_MTRR, we already setup our own mtrr over vram.
Stephane Marchesin [Wed, 10 Jan 2007 03:42:09 +0000 (04:42 +0100)]
nouveau: Don't use DRIVER_USE_MTRR, we already setup our own mtrr over vram.

17 years agottm: make ttm alloc/free into alloc_pages/free_pages
Dave Airlie [Tue, 9 Jan 2007 04:51:29 +0000 (15:51 +1100)]
ttm: make ttm alloc/free into alloc_pages/free_pages

Add a vmalloc flag to the page flags

17 years agonovueau: try resource 3 if resource 2 is 0 length
Dave Airlie [Tue, 9 Jan 2007 02:38:36 +0000 (13:38 +1100)]
novueau: try resource 3 if resource 2 is 0 length

This happens on my NV43 PPC

17 years agonouveau: fix nv4a context size.
Stephane Marchesin [Mon, 8 Jan 2007 19:55:57 +0000 (20:55 +0100)]
nouveau: fix nv4a context size.

17 years agoadd export symbol for memory manager
Dave Airlie [Mon, 8 Jan 2007 11:26:35 +0000 (22:26 +1100)]
add export symbol for memory manager

17 years agonouveau: nv4a context support.
Stephane Marchesin [Mon, 8 Jan 2007 04:02:40 +0000 (05:02 +0100)]
nouveau: nv4a context support.

17 years agoMerge branch 'master' of git+ssh://marcheu@git.freedesktop.org/git/mesa/drm
Stephane Marchesin [Mon, 8 Jan 2007 02:50:34 +0000 (03:50 +0100)]
Merge branch 'master' of git+ssh://marcheu@git.freedesktop.org/git/mesa/drm

17 years agoi830: complete fix for i830 maps
Dave Airlie [Mon, 8 Jan 2007 02:09:12 +0000 (13:09 +1100)]
i830: complete fix for i830 maps

17 years agonouveau: oops
Ben Skeggs [Mon, 8 Jan 2007 01:50:44 +0000 (12:50 +1100)]
nouveau: oops

17 years agonouveau: nv43 context stuff
Ben Skeggs [Mon, 8 Jan 2007 01:47:22 +0000 (12:47 +1100)]
nouveau: nv43 context stuff

17 years agodrm: remove drm_follow_page, and drm_ioremap and ioremapfree
Christoph Hellwig [Sun, 7 Jan 2007 23:55:49 +0000 (10:55 +1100)]
drm: remove drm_follow_page, and drm_ioremap and ioremapfree

This comes from the Re: [patch] paravirt: isolate module ops on lkml
It needs some testing, please report any regressions caused.

Signed-off-by: Dave Airlie <airlied@linux.ie>
17 years agofixup i810/i830 to use drm_core_ioremap instead of drm_ioremap
Dave Airlie [Mon, 8 Jan 2007 11:27:11 +0000 (22:27 +1100)]
fixup i810/i830 to use drm_core_ioremap instead of drm_ioremap

17 years agonouveau: fix a stupid bug from me.
Stephane Marchesin [Sun, 7 Jan 2007 23:11:39 +0000 (00:11 +0100)]
nouveau: fix a stupid bug from me.

17 years agonouveau: avoid allocating vram that's used as instance memory.
Ben Skeggs [Sun, 7 Jan 2007 13:37:39 +0000 (00:37 +1100)]
nouveau: avoid allocating vram that's used as instance memory.

17 years agonouveau: map pci resource 2 on >=nv40
Ben Skeggs [Sun, 7 Jan 2007 12:56:45 +0000 (23:56 +1100)]
nouveau: map pci resource 2 on >=nv40

17 years agoRevert i915 drm driver name to i915; miniglx doesn't work otherwise
Keith Packard [Sun, 7 Jan 2007 01:40:50 +0000 (17:40 -0800)]
Revert i915 drm driver name to i915; miniglx doesn't work otherwise

Yes, this driver supports the new memory manager, that is indicated by the
version number being >= 1.7.

17 years agoBump i915 minor for ARB_OC ioctl
Wang Zhenyu [Mon, 4 Dec 2006 07:48:04 +0000 (15:48 +0800)]
Bump i915 minor for ARB_OC ioctl

17 years agoi915: ARB_Occlusion_query(MMIO ioctl) support.
Zou Nan hai [Mon, 4 Dec 2006 07:48:04 +0000 (15:48 +0800)]
i915: ARB_Occlusion_query(MMIO ioctl) support.

This adds a new ioctl for passing counter information from the chip back to
applications, these counters include the data needed to perform OC.

17 years agonouveau: get c51 doing glxgears without the binary driver's help.
Ben Skeggs [Sat, 6 Jan 2007 07:05:21 +0000 (18:05 +1100)]
nouveau: get c51 doing glxgears without the binary driver's help.

17 years agonouveau: Use PMC_BOOT_0 to determine which ctx_voodoo to load.
Ben Skeggs [Sat, 6 Jan 2007 06:50:00 +0000 (17:50 +1100)]
nouveau: Use PMC_BOOT_0 to determine which ctx_voodoo to load.

17 years agonouveau: oops, we don't need OS_HAS_MTRR actually.
Stephane Marchesin [Fri, 5 Jan 2007 19:59:45 +0000 (20:59 +0100)]
nouveau: oops, we don't need OS_HAS_MTRR actually.

17 years agoMerge branch 'master' of git+ssh://marcheu@git.freedesktop.org/git/mesa/drm
Stephane Marchesin [Fri, 5 Jan 2007 19:50:46 +0000 (20:50 +0100)]
Merge branch 'master' of git+ssh://marcheu@git.freedesktop.org/git/mesa/drm

17 years agonouveau: Add an mtrr over the whole FB
Stephane Marchesin [Fri, 5 Jan 2007 19:49:34 +0000 (20:49 +0100)]
nouveau: Add an mtrr over the whole FB

17 years agoMerge branch 'master' of git+ssh://matc@git.freedesktop.org/git/mesa/drm/
Matthieu Castet [Fri, 5 Jan 2007 18:41:12 +0000 (19:41 +0100)]
Merge branch 'master' of git+ssh://matc@git.freedesktop.org/git/mesa/drm/

17 years agoAdd basic pgraph context for nv10.
Matthieu Castet [Fri, 5 Jan 2007 18:40:11 +0000 (19:40 +0100)]
Add basic pgraph context for nv10.
It only fake a context switch : pgraph state are not save/restored.

17 years agoCleanup the nv04 fifo code a bit.
Stephane Marchesin [Fri, 5 Jan 2007 18:37:06 +0000 (19:37 +0100)]
Cleanup the nv04 fifo code a bit.

17 years agoi915: Fix a DRM_ERROR that should be DRM_DEBUG.
Michel Dänzer [Tue, 2 Jan 2007 09:05:48 +0000 (10:05 +0100)]
i915: Fix a DRM_ERROR that should be DRM_DEBUG.

It would clutter up the kernel output in a situation which is legitimate before
X.org 7.2 and handled correctly by the 3D driver.

17 years agoMake git ignore Emacs style backup files and cscope files.
Michel Dänzer [Tue, 2 Jan 2007 09:03:56 +0000 (10:03 +0100)]
Make git ignore Emacs style backup files and cscope files.

17 years agolinux-core: Make git ignore generated module symbol version files.
Michel Dänzer [Tue, 2 Jan 2007 09:02:44 +0000 (10:02 +0100)]
linux-core: Make git ignore generated module symbol version files.

17 years agonouveau: oops, forgot to free RAMIN..
Ben Skeggs [Tue, 2 Jan 2007 05:35:00 +0000 (16:35 +1100)]
nouveau: oops, forgot to free RAMIN..

17 years agonouveau: Hookup nv40_graph_init.
Ben Skeggs [Tue, 2 Jan 2007 04:56:10 +0000 (15:56 +1100)]
nouveau: Hookup nv40_graph_init.

Now I can get 3D + working grctx switching on my NV40 without
the binary driver initialising the card first.  However, this
change also breaks 3D on my C51 even *with* the binary driver's
help.  So, it's likely that the weird voodoo is card-specific.

17 years agonouveau: Hook up grctx code for NV4x.
Ben Skeggs [Tue, 2 Jan 2007 04:08:04 +0000 (15:08 +1100)]
nouveau: Hook up grctx code for NV4x.

This is enough to get grctx switching going on my NV40 and C51 after
the binary driver has initialised the card first.

Bumping the drm patchlevel because the ddx needs some modifications to
have NV4x work at all with these changes.

17 years agonouveau: Add nv40-specific PGRAPH code, not hooked up yet.
Ben Skeggs [Tue, 2 Jan 2007 03:52:43 +0000 (14:52 +1100)]
nouveau: Add nv40-specific PGRAPH code, not hooked up yet.

17 years agonouveau: Only clobber PFIFO if no channels are already alloc'd
Ben Skeggs [Tue, 2 Jan 2007 03:41:34 +0000 (14:41 +1100)]
nouveau: Only clobber PFIFO if no channels are already alloc'd

With this change the GPU is responsible for doing the channel switch
itself.  This is needed for the upcoming NV4x PGRAPH context work as
we don't yet know enough to manually swap PGRAPH contexts.

17 years agomake build against 2.6.20 hopefully
Dave Airlie [Mon, 1 Jan 2007 00:30:38 +0000 (11:30 +1100)]
make build against 2.6.20 hopefully

17 years agofixup permission along line of kernel
Dave Airlie [Mon, 1 Jan 2007 00:22:35 +0000 (11:22 +1100)]
fixup permission along line of kernel

17 years agoAdd some new via chipsets.
Thomas Hellstrom [Thu, 28 Dec 2006 21:17:08 +0000 (22:17 +0100)]
Add some new via chipsets.
Disable 3D functionality and AGP DMA for chipsets with the DX9 3D engine.

17 years agoLeftover from previous commit.
Thomas Hellstrom [Wed, 27 Dec 2006 18:46:46 +0000 (19:46 +0100)]
Leftover from previous commit.

17 years agoAllow for non-power-of-two texture pitch alignment.
Thomas Hellstrom [Wed, 27 Dec 2006 18:38:33 +0000 (19:38 +0100)]
Allow for non-power-of-two texture pitch alignment.

17 years agoProper allocation of AGP pages for ttms.
Thomas Hellstrom [Wed, 27 Dec 2006 14:32:09 +0000 (15:32 +0100)]
Proper allocation of AGP pages for ttms.

17 years agonouveau: return the *actual* type of memory alloc'd to userspace
Ben Skeggs [Tue, 26 Dec 2006 14:58:57 +0000 (01:58 +1100)]
nouveau: return the *actual* type of memory alloc'd to userspace

17 years agonouveau: Alloc cmdbuf for each channel individually
Ben Skeggs [Tue, 26 Dec 2006 12:30:26 +0000 (23:30 +1100)]
nouveau: Alloc cmdbuf for each channel individually

17 years agoBug #9120.
Thomas Hellstrom [Thu, 21 Dec 2006 11:05:49 +0000 (12:05 +0100)]
Bug #9120.
Require at least agpgart version 0.102 for the AGP TTM backend.
This should hopefully avoid crashes when the wrong agpgart
driver is installed.

17 years agoImprove memory manager accounting printout formatting.
Thomas Hellstrom [Thu, 21 Dec 2006 09:40:25 +0000 (10:40 +0100)]
Improve memory manager accounting printout formatting.

17 years agoFix buggy aligned allocations.
Thomas Hellstrom [Thu, 21 Dec 2006 09:32:13 +0000 (10:32 +0100)]
Fix buggy aligned allocations.

17 years agonouveau: save/restore endianness flag on FIFO switch
Ben Skeggs [Thu, 21 Dec 2006 06:43:48 +0000 (17:43 +1100)]
nouveau: save/restore endianness flag on FIFO switch

This makes my G5 survive glxinfo and nouveau_demo - airlied

17 years agoRemove the stupid root_node field from the core memory manager.
Thomas Hellstrom [Wed, 20 Dec 2006 18:33:50 +0000 (19:33 +0100)]
Remove the stupid root_node field from the core memory manager.

17 years agoReplace vmalloc_32.
Thomas Hellstrom [Wed, 20 Dec 2006 13:40:36 +0000 (14:40 +0100)]
Replace vmalloc_32.

The vmalloc_32 function together with the memset to clear
the new pages are replaced with a vmalloc_user.

A pre-2.6.18 compat vmalloc_user is added.

Please replace any breakage on machines with > 1GB of memory.

17 years agoSome via PCI posting flushes.
Thomas Hellstrom [Wed, 20 Dec 2006 12:04:21 +0000 (13:04 +0100)]
Some via PCI posting flushes.

17 years agoMerge branch 'nouveau-1'
Dave Airlie [Tue, 19 Dec 2006 23:30:16 +0000 (10:30 +1100)]
Merge branch 'nouveau-1'

17 years agofixup symlinks via Makefile
Dave Airlie [Tue, 19 Dec 2006 23:29:43 +0000 (10:29 +1100)]
fixup symlinks via Makefile

17 years agoadd nouveau symlinks via git
Dave Airlie [Tue, 19 Dec 2006 23:28:55 +0000 (10:28 +1100)]
add nouveau symlinks via git

17 years agoremove unused via/sis files from lk build
Dave Airlie [Tue, 19 Dec 2006 23:22:43 +0000 (10:22 +1100)]
remove unused via/sis files from lk build

17 years agoSecurity fix. Zero pages before they are handed to user space.
Thomas Hellstrom [Tue, 19 Dec 2006 22:45:59 +0000 (23:45 +0100)]
Security fix. Zero pages before they are handed to user space.

TTM pages were not cleared when allocated and handed to user space.
Sensitive information may leak.

17 years agoSecurity fix. Zero pages before they are handed to user space.
Thomas Hellstrom [Tue, 19 Dec 2006 22:23:17 +0000 (23:23 +0100)]
Security fix. Zero pages before they are handed to user space.

Shared memory areas were not cleared when they are allocated and
handed to user space. Sensitive information may leak.

17 years agoReclaim buffers locked fixup.
Thomas Hellstrom [Tue, 19 Dec 2006 22:14:11 +0000 (23:14 +0100)]
Reclaim buffers locked fixup.

Avoid calling reclaim_buffers_locked if we don't have a
hardware lock.

Improve reclaim_buffers_locked deadlock error formatting.

17 years agoadd kcalloc compat for before 2.6.10
Dave Airlie [Tue, 19 Dec 2006 11:10:34 +0000 (22:10 +1100)]
add kcalloc compat for before 2.6.10

17 years agoremove do munmap 4 args
Dave Airlie [Tue, 19 Dec 2006 10:51:30 +0000 (21:51 +1100)]
remove do munmap 4 args