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/radeon/radeon_ttm.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 43c5ab34b634..d031b6863082 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "radeon_reg.h" #include "radeon.h" -- cgit v1.2.3 From 8d7cddcd7f9e847cec44851ca53fd3e81e846c49 Mon Sep 17 00:00:00 2001 From: Pauli Nieminen Date: Thu, 1 Apr 2010 12:44:59 +0000 Subject: drm/radeon/kms: Add ttm page pool debugfs file. ttm_page_pool file is hooked ttm_page_alloc_debugfs for pool allocator state. Signed-off-by: Pauli Nieminen Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_ttm.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 43c5ab34b634..fc787e8fa730 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -744,8 +745,8 @@ static int radeon_mm_dump_table(struct seq_file *m, void *data) static int radeon_ttm_debugfs_init(struct radeon_device *rdev) { #if defined(CONFIG_DEBUG_FS) - static struct drm_info_list radeon_mem_types_list[RADEON_DEBUGFS_MEM_TYPES]; - static char radeon_mem_types_names[RADEON_DEBUGFS_MEM_TYPES][32]; + static struct drm_info_list radeon_mem_types_list[RADEON_DEBUGFS_MEM_TYPES+1]; + static char radeon_mem_types_names[RADEON_DEBUGFS_MEM_TYPES+1][32]; unsigned i; for (i = 0; i < RADEON_DEBUGFS_MEM_TYPES; i++) { @@ -762,7 +763,13 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev) radeon_mem_types_list[i].data = &rdev->mman.bdev.man[TTM_PL_TT].manager; } - return radeon_debugfs_add_files(rdev, radeon_mem_types_list, RADEON_DEBUGFS_MEM_TYPES); + /* Add ttm page pool to debugfs */ + sprintf(radeon_mem_types_names[i], "ttm_page_pool"); + radeon_mem_types_list[i].name = radeon_mem_types_names[i]; + radeon_mem_types_list[i].show = &ttm_page_alloc_debugfs; + radeon_mem_types_list[i].driver_features = 0; + radeon_mem_types_list[i].data = NULL; + return radeon_debugfs_add_files(rdev, radeon_mem_types_list, RADEON_DEBUGFS_MEM_TYPES+1); #endif return 0; -- cgit v1.2.3 From 9d87fa2138d06ff400551800d67d522625033e35 Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Wed, 7 Apr 2010 10:21:19 +0000 Subject: drm/ttm: split no_wait argument in 2 GPU or reserve wait There is case where we want to be able to wait only for the GPU while not waiting for other buffer to be unreserved. This patch split the no_wait argument all the way down in the whole ttm path so that upper level can decide on what to wait on or not. [airlied: squashed these 4 for bisectability reasons.] drm/radeon/kms: update to TTM no_wait splitted argument drm/nouveau: update to TTM no_wait splitted argument drm/vmwgfx: update to TTM no_wait splitted argument [vmwgfx patch: Reviewed-by: Thomas Hellstrom ] Signed-off-by: Jerome Glisse Acked-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_ttm.c | 39 ++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 18 deletions(-) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 43c5ab34b634..ba4724c38ac0 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -243,9 +243,9 @@ static void radeon_move_null(struct ttm_buffer_object *bo, } static int radeon_move_blit(struct ttm_buffer_object *bo, - bool evict, int no_wait, - struct ttm_mem_reg *new_mem, - struct ttm_mem_reg *old_mem) + bool evict, int no_wait_reserve, bool no_wait_gpu, + struct ttm_mem_reg *new_mem, + struct ttm_mem_reg *old_mem) { struct radeon_device *rdev; uint64_t old_start, new_start; @@ -289,13 +289,14 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, r = radeon_copy(rdev, old_start, new_start, new_mem->num_pages, fence); /* FIXME: handle copy error */ r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL, - evict, no_wait, new_mem); + evict, no_wait_reserve, no_wait_gpu, new_mem); radeon_fence_unref(&fence); return r; } static int radeon_move_vram_ram(struct ttm_buffer_object *bo, - bool evict, bool interruptible, bool no_wait, + bool evict, bool interruptible, + bool no_wait_reserve, bool no_wait_gpu, struct ttm_mem_reg *new_mem) { struct radeon_device *rdev; @@ -316,7 +317,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo, placement.busy_placement = &placements; placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT; r = ttm_bo_mem_space(bo, &placement, &tmp_mem, - interruptible, no_wait); + interruptible, no_wait_reserve, no_wait_gpu); if (unlikely(r)) { return r; } @@ -330,11 +331,11 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo, if (unlikely(r)) { goto out_cleanup; } - r = radeon_move_blit(bo, true, no_wait, &tmp_mem, old_mem); + r = radeon_move_blit(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem, old_mem); if (unlikely(r)) { goto out_cleanup; } - r = ttm_bo_move_ttm(bo, true, no_wait, new_mem); + r = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, new_mem); out_cleanup: if (tmp_mem.mm_node) { struct ttm_bo_global *glob = rdev->mman.bdev.glob; @@ -348,7 +349,8 @@ out_cleanup: } static int radeon_move_ram_vram(struct ttm_buffer_object *bo, - bool evict, bool interruptible, bool no_wait, + bool evict, bool interruptible, + bool no_wait_reserve, bool no_wait_gpu, struct ttm_mem_reg *new_mem) { struct radeon_device *rdev; @@ -368,15 +370,15 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo, placement.num_busy_placement = 1; placement.busy_placement = &placements; placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT; - r = ttm_bo_mem_space(bo, &placement, &tmp_mem, interruptible, no_wait); + r = ttm_bo_mem_space(bo, &placement, &tmp_mem, interruptible, no_wait_reserve, no_wait_gpu); if (unlikely(r)) { return r; } - r = ttm_bo_move_ttm(bo, true, no_wait, &tmp_mem); + r = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem); if (unlikely(r)) { goto out_cleanup; } - r = radeon_move_blit(bo, true, no_wait, new_mem, old_mem); + r = radeon_move_blit(bo, true, no_wait_reserve, no_wait_gpu, new_mem, old_mem); if (unlikely(r)) { goto out_cleanup; } @@ -393,8 +395,9 @@ out_cleanup: } static int radeon_bo_move(struct ttm_buffer_object *bo, - bool evict, bool interruptible, bool no_wait, - struct ttm_mem_reg *new_mem) + bool evict, bool interruptible, + bool no_wait_reserve, bool no_wait_gpu, + struct ttm_mem_reg *new_mem) { struct radeon_device *rdev; struct ttm_mem_reg *old_mem = &bo->mem; @@ -421,18 +424,18 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, if (old_mem->mem_type == TTM_PL_VRAM && new_mem->mem_type == TTM_PL_SYSTEM) { r = radeon_move_vram_ram(bo, evict, interruptible, - no_wait, new_mem); + no_wait_reserve, no_wait_gpu, new_mem); } else if (old_mem->mem_type == TTM_PL_SYSTEM && new_mem->mem_type == TTM_PL_VRAM) { r = radeon_move_ram_vram(bo, evict, interruptible, - no_wait, new_mem); + no_wait_reserve, no_wait_gpu, new_mem); } else { - r = radeon_move_blit(bo, evict, no_wait, new_mem, old_mem); + r = radeon_move_blit(bo, evict, no_wait_reserve, no_wait_gpu, new_mem, old_mem); } if (r) { memcpy: - r = ttm_bo_move_memcpy(bo, evict, no_wait, new_mem); + r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem); } return r; -- cgit v1.2.3 From 0a2d50e3a8faaf36cde36920431586090411ea15 Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Fri, 9 Apr 2010 14:39:24 +0200 Subject: drm/radeon/kms: add support for new fault callback V7 This add the support for the new fault callback and also the infrastructure for supporting unmappable VRAM. V2 validate BO with no_wait = true V3 don't derefence bo->mem.mm_node as it's not NULL only for VRAM or GTT V4 update to splitted no_wait ttm change V5 update to new balanced io_mem_reserve/free change V6 callback is responsible for iomapping memory V7 move back iomapping to ttm Signed-off-by: Jerome Glisse Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_ttm.c | 51 ++++++++++++++++++++++++++++++++++--- 1 file changed, 47 insertions(+), 4 deletions(-) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index ba4724c38ac0..62b4b800e0a3 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -165,8 +165,7 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, man->io_size = rdev->mc.gtt_size; man->io_addr = NULL; if (!rdev->ddev->agp->cant_use_aperture) - man->flags = TTM_MEMTYPE_FLAG_NEEDS_IOREMAP | - TTM_MEMTYPE_FLAG_MAPPABLE; + man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; @@ -182,7 +181,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, /* "On-card" video ram */ man->gpu_offset = rdev->mc.vram_start; man->flags = TTM_MEMTYPE_FLAG_FIXED | - TTM_MEMTYPE_FLAG_NEEDS_IOREMAP | TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; @@ -437,10 +435,53 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, memcpy: r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem); } - return r; } +static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ + struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; + struct radeon_device *rdev = radeon_get_rdev(bdev); + + mem->bus.addr = NULL; + mem->bus.offset = 0; + mem->bus.size = mem->num_pages << PAGE_SHIFT; + mem->bus.base = 0; + mem->bus.is_iomem = false; + if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE)) + return -EINVAL; + switch (mem->mem_type) { + case TTM_PL_SYSTEM: + /* system memory */ + return 0; + case TTM_PL_TT: +#if __OS_HAS_AGP + if (rdev->flags & RADEON_IS_AGP) { + /* RADEON_IS_AGP is set only if AGP is active */ + mem->bus.offset = mem->mm_node->start << PAGE_SHIFT; + mem->bus.base = rdev->mc.agp_base; + mem->bus.is_iomem = true; + } +#endif + break; + case TTM_PL_VRAM: + mem->bus.offset = mem->mm_node->start << PAGE_SHIFT; + /* check if it's visible */ + if ((mem->bus.offset + mem->bus.size) > rdev->mc.visible_vram_size) + return -EINVAL; + mem->bus.base = rdev->mc.aper_base; + mem->bus.is_iomem = true; + break; + default: + return -EINVAL; + } + return 0; +} + +static void radeon_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ +} + static int radeon_sync_obj_wait(void *sync_obj, void *sync_arg, bool lazy, bool interruptible) { @@ -481,6 +522,8 @@ static struct ttm_bo_driver radeon_bo_driver = { .sync_obj_ref = &radeon_sync_obj_ref, .move_notify = &radeon_bo_move_notify, .fault_reserve_notify = &radeon_bo_fault_reserve_notify, + .io_mem_reserve = &radeon_ttm_io_mem_reserve, + .io_mem_free = &radeon_ttm_io_mem_free, }; int radeon_ttm_init(struct radeon_device *rdev) -- cgit v1.2.3 From 0c321c79627189204d7d0bf65ab19f5ac419abed Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Wed, 7 Apr 2010 10:21:27 +0000 Subject: drm/ttm: remove io_ field from TTM V6 All TTM driver have been converted to new io_mem_reserve/free interface which allow driver to choose and return proper io base, offset to core TTM for ioremapping if necessary. This patch remove what is now deadcode. V2 adapt to match with change in first patch of the patchset V3 update after io_mem_reserve/io_mem_free callback balancing V4 adjust to minor cleanup V5 remove the needs ioremap flag V6 keep the ioremapping facility in TTM [airlied- squashed driver removals in here also] Signed-off-by: Jerome Glisse Reviewed-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_ttm.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 62b4b800e0a3..91030eab22b0 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -161,21 +161,13 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, (unsigned)type); return -EINVAL; } - man->io_offset = rdev->mc.agp_base; - man->io_size = rdev->mc.gtt_size; - man->io_addr = NULL; if (!rdev->ddev->agp->cant_use_aperture) man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; - } else -#endif - { - man->io_offset = 0; - man->io_size = 0; - man->io_addr = NULL; } +#endif break; case TTM_PL_VRAM: /* "On-card" video ram */ @@ -184,9 +176,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; - man->io_addr = NULL; - man->io_offset = rdev->mc.aper_base; - man->io_size = rdev->mc.aper_size; break; default: DRM_ERROR("Unsupported memory type %u\n", (unsigned)type); -- cgit v1.2.3 From 5876dd249e8e47c730cac090bf6edd88e5f04327 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 26 Apr 2010 15:52:20 -0400 Subject: radeon: Unmap vram pages when reclocking Touching vram while the card is reclocking can lead to lockups. Unmap any pages that could be touched by the CPU and block any accesses to vram until the reclocking is complete. Signed-off-by: Matthew Garrett Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_ttm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index af98f45954b3..3aa3a65800ab 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -607,13 +607,17 @@ static const struct vm_operations_struct *ttm_vm_ops = NULL; static int radeon_ttm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct ttm_buffer_object *bo; + struct radeon_device *rdev; int r; - bo = (struct ttm_buffer_object *)vma->vm_private_data; + bo = (struct ttm_buffer_object *)vma->vm_private_data; if (bo == NULL) { return VM_FAULT_NOPAGE; } + rdev = radeon_get_rdev(bo->bdev); + mutex_lock(&rdev->vram_mutex); r = ttm_vm_ops->fault(vma, vmf); + mutex_unlock(&rdev->vram_mutex); return r; } -- cgit v1.2.3 From 365048ff7f977c5983d67b63c47502c5964840e9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Wed, 19 May 2010 12:46:22 +0200 Subject: drm/radeon: AGP memory is only I/O if the aperture can be mapped by the CPU. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes AGP initialization failure with Apple UniNorth bridges due to trying to ioremap() normal RAM. Signed-off-by: Michel Dänzer Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu/drm/radeon/radeon_ttm.c') diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 3aa3a65800ab..e9918d88f5b0 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -451,7 +451,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_ /* RADEON_IS_AGP is set only if AGP is active */ mem->bus.offset = mem->mm_node->start << PAGE_SHIFT; mem->bus.base = rdev->mc.agp_base; - mem->bus.is_iomem = true; + mem->bus.is_iomem = !rdev->ddev->agp->cant_use_aperture; } #endif break; -- cgit v1.2.3