From f05dd2f09cac422c423dae8f9b8e2be13df05a8f Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Fri, 26 Feb 2010 13:32:11 -0800 Subject: drm/i915: Don't bother with the BKL for GEM ioctls. We probably don't need it for most of the other driver ioctls as well, but we explicitly did locking when doing the GEM pieces. On CPU-bound graphics tasks, the BKL was showing up as 1-2% of CPU time. Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/i915_dma.c | 46 ++++++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_dma.c') diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 8bfc0bbf13e6..a9f8589490cf 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1881,29 +1881,29 @@ struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF(DRM_I915_GET_VBLANK_PIPE, i915_vblank_pipe_get, DRM_AUTH ), DRM_IOCTL_DEF(DRM_I915_VBLANK_SWAP, i915_vblank_swap, DRM_AUTH), DRM_IOCTL_DEF(DRM_I915_HWS_ADDR, i915_set_status_page, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I915_GEM_INIT, i915_gem_init_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I915_GEM_PIN, i915_gem_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I915_GEM_UNPIN, i915_gem_unpin_ioctl, DRM_AUTH|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I915_GEM_ENTERVT, i915_gem_entervt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I915_GEM_LEAVEVT, i915_gem_leavevt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I915_GEM_CREATE, i915_gem_create_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_PREAD, i915_gem_pread_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_PWRITE, i915_gem_pwrite_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_MMAP, i915_gem_mmap_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_SET_TILING, i915_gem_set_tiling, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_GET_TILING, i915_gem_get_tiling, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id, 0), - DRM_IOCTL_DEF(DRM_I915_GEM_MADVISE, i915_gem_madvise_ioctl, 0), - DRM_IOCTL_DEF(DRM_I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image, DRM_MASTER|DRM_CONTROL_ALLOW), - DRM_IOCTL_DEF(DRM_I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW), + DRM_IOCTL_DEF(DRM_I915_GEM_INIT, i915_gem_init_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_PIN, i915_gem_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_UNPIN, i915_gem_unpin_ioctl, DRM_AUTH|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_ENTERVT, i915_gem_entervt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_LEAVEVT, i915_gem_leavevt_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_CREATE, i915_gem_create_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_SET_TILING, i915_gem_set_tiling, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_GET_TILING, i915_gem_get_tiling, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED), }; int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls); -- cgit v1.2.3 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- drivers/gpu/drm/i915/i915_dma.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu/drm/i915/i915_dma.c') diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index a9f8589490cf..2dc93939507d 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -38,6 +38,7 @@ #include #include #include +#include /* Really want an OS-independent resettable timer. Would like to have * this loop run for (eg) 3 sec, but have the timer reset every time -- cgit v1.2.3 From 20bf377e679208ba9ae0edcb8c70a8f6d33d17f9 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Wed, 21 Apr 2010 11:39:22 -0700 Subject: drm/i915: cleanup FBC buffers at unload time This keeps the memory manager from complaining when we take it down. Signed-off-by: Jesse Barnes Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/i915_dma.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'drivers/gpu/drm/i915/i915_dma.c') diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 2dc93939507d..c3cfafcbfe7d 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1357,6 +1357,8 @@ static void i915_setup_compression(struct drm_device *dev, int size) dev_priv->cfb_size = size; + dev_priv->compressed_fb = compressed_fb; + if (IS_GM45(dev)) { g4x_disable_fbc(dev); I915_WRITE(DPFC_CB_BASE, compressed_fb->start); @@ -1364,12 +1366,22 @@ static void i915_setup_compression(struct drm_device *dev, int size) i8xx_disable_fbc(dev); I915_WRITE(FBC_CFB_BASE, cfb_base); I915_WRITE(FBC_LL_BASE, ll_base); + dev_priv->compressed_llb = compressed_llb; } DRM_DEBUG("FBC base 0x%08lx, ll base 0x%08lx, size %dM\n", cfb_base, ll_base, size >> 20); } +static void i915_cleanup_compression(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + drm_mm_put_block(dev_priv->compressed_fb); + if (!IS_GM45(dev)) + drm_mm_put_block(dev_priv->compressed_llb); +} + /* true = enable decode, false = disable decoder */ static unsigned int i915_vga_set_decode(void *cookie, bool state) { @@ -1787,6 +1799,8 @@ int i915_driver_unload(struct drm_device *dev) mutex_lock(&dev->struct_mutex); i915_gem_cleanup_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); + if (I915_HAS_FBC(dev) && i915_powersave) + i915_cleanup_compression(dev); drm_mm_takedown(&dev_priv->vram); i915_gem_lastclose(dev); -- cgit v1.2.3