1
0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-22 11:17:19 +00:00
freebsd/sys/dev/drm
Attilio Rao 89f6b8632c Switch the vm_object mutex to be a rwlock. This will enable in the
future further optimizations where the vm_object lock will be held
in read mode most of the time the page cache resident pool of pages
are accessed for reading purposes.

The change is mostly mechanical but few notes are reported:
* The KPI changes as follow:
  - VM_OBJECT_LOCK() -> VM_OBJECT_WLOCK()
  - VM_OBJECT_TRYLOCK() -> VM_OBJECT_TRYWLOCK()
  - VM_OBJECT_UNLOCK() -> VM_OBJECT_WUNLOCK()
  - VM_OBJECT_LOCK_ASSERT(MA_OWNED) -> VM_OBJECT_ASSERT_WLOCKED()
    (in order to avoid visibility of implementation details)
  - The read-mode operations are added:
    VM_OBJECT_RLOCK(), VM_OBJECT_TRYRLOCK(), VM_OBJECT_RUNLOCK(),
    VM_OBJECT_ASSERT_RLOCKED(), VM_OBJECT_ASSERT_LOCKED()
* The vm/vm_pager.h namespace pollution avoidance (forcing requiring
  sys/mutex.h in consumers directly to cater its inlining functions
  using VM_OBJECT_LOCK()) imposes that all the vm/vm_pager.h
  consumers now must include also sys/rwlock.h.
* zfs requires a quite convoluted fix to include FreeBSD rwlocks into
  the compat layer because the name clash between FreeBSD and solaris
  versions must be avoided.
  At this purpose zfs redefines the vm_object locking functions
  directly, isolating the FreeBSD components in specific compat stubs.

The KPI results heavilly broken by this commit.  Thirdy part ports must
be updated accordingly (I can think off-hand of VirtualBox, for example).

Sponsored by:	EMC / Isilon storage division
Reviewed by:	jeff
Reviewed by:	pjd (ZFS specific review)
Discussed with:	alc
Tested by:	pho
2013-03-09 02:32:23 +00:00
..
ati_pcigart.c Now that we properly set write-combining on the pages that back the GART, 2010-04-22 18:47:30 +00:00
drm_agpsupport.c Do a sweep of the tree replacing calls to pci_find_extcap() with calls to 2011-03-23 13:10:15 +00:00
drm_atomic.h
drm_auth.c
drm_bufs.c re-write scatter gather memory allocation yet again... 2010-04-22 18:44:23 +00:00
drm_context.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
drm_dma.c
drm_drawable.c
drm_drv.c Make drm(4) build, if not work reliably, on PowerPC. 2010-11-16 03:43:06 +00:00
drm_fops.c Streamline use of cdevpriv and correct some corner cases. 2012-08-15 16:19:39 +00:00
drm_hashtab.c Address some WITNESS panics that occur when using the via driver. 2010-04-23 14:48:30 +00:00
drm_hashtab.h
drm_internal.h
drm_ioctl.c
drm_irq.c fix atomic_set_xxx misuse in drm 2010-12-11 10:18:05 +00:00
drm_linux_list.h
drm_lock.c
drm_memory.c Make drm(4) build, if not work reliably, on PowerPC. 2010-11-16 03:43:06 +00:00
drm_mm.c Address some WITNESS panics that occur when using the via driver. 2010-04-23 14:48:30 +00:00
drm_mm.h
drm_pci.c
drm_pciids.h Add support for ATI Radeon HD 4250. 2010-08-03 16:30:56 +00:00
drm_sarea.h
drm_scatter.c re-write scatter gather memory allocation yet again... 2010-04-22 18:44:23 +00:00
drm_sman.c Address some WITNESS panics that occur when using the via driver. 2010-04-23 14:48:30 +00:00
drm_sman.h
drm_sysctl.c Fix display of the drm sysctls. 2011-04-23 23:11:44 +00:00
drm_vm.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
drm.h
drmP.h Switch the vm_object mutex to be a rwlock. This will enable in the 2013-03-09 02:32:23 +00:00
i915_dma.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
i915_drm.h
i915_drv.c
i915_drv.h Do not define bool/true/false if the symbols already exist. 2011-12-12 18:43:24 +00:00
i915_irq.c
i915_mem.c
i915_reg.h Add support for Intel Pineview chips, aka IGD 2010-03-13 11:51:18 +00:00
i915_suspend.c
mach64_dma.c Fix typos - remove duplicate "the". 2011-02-21 09:01:34 +00:00
mach64_drm.h
mach64_drv.c
mach64_drv.h
mach64_irq.c
mach64_state.c
mga_dma.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
mga_drm.h
mga_drv.c
mga_drv.h Fix format string Z --> z, since the former is a deprecated and (in FreeBSD) 2011-12-16 12:42:02 +00:00
mga_irq.c
mga_state.c
mga_ucode.h
mga_warp.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
r128_cce.c re-write scatter gather memory allocation yet again... 2010-04-22 18:44:23 +00:00
r128_drm.h
r128_drv.c
r128_drv.h
r128_irq.c
r128_state.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
r300_cmdbuf.c
r300_reg.h Fix typos - remove duplicate "the". 2011-02-21 09:01:34 +00:00
r600_blit.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
r600_cp.c Now that we properly set write-combining on the pages that back the GART, 2010-04-22 18:47:30 +00:00
r600_microcode.h
radeon_cp.c re-write scatter gather memory allocation yet again... 2010-04-22 18:44:23 +00:00
radeon_cs.c Make drm(4) build, if not work reliably, on PowerPC. 2010-11-16 03:43:06 +00:00
radeon_drm.h
radeon_drv.c
radeon_drv.h
radeon_irq.c
radeon_mem.c
radeon_microcode.h
radeon_state.c In sys/dev/drm/radeon_state.c, use the correct printf length modifiers 2011-12-30 02:07:50 +00:00
savage_bci.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
savage_drm.h
savage_drv.c
savage_drv.h
savage_state.c
sis_drm.h
sis_drv.c
sis_drv.h
sis_ds.c
sis_ds.h
sis_mm.c
tdfx_drv.c
tdfx_drv.h
via_3d_reg.h
via_dma.c Cast VIA_READ to (void) where the result is unused. 2012-11-09 14:46:23 +00:00
via_dmablit.c Cast VIA_READ to (void) where the result is unused. 2012-11-09 14:46:23 +00:00
via_dmablit.h
via_drm.h
via_drv.c
via_drv.h
via_irq.c
via_map.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
via_mm.c Rework how drm maps are handled. 2010-04-22 18:21:25 +00:00
via_verifier.c
via_verifier.h
via_video.c fx->lock is used as an index, correct test case. 2010-04-28 10:33:41 +00:00